diff --git a/prototypes/arc1_prototype/server.py b/prototypes/arc1_prototype/server.py index d8ab52a..89d5cf9 100644 --- a/prototypes/arc1_prototype/server.py +++ b/prototypes/arc1_prototype/server.py @@ -41,3 +41,38 @@ def getFromChatGPTSingle(value: str) -> dict: def get_greeting(name: str) -> str: """Get a personalized greeting""" return f"Hello, {name}!" + +""" Example prompt: Get data from spacy and exxeta and merge them. Validate if Core+ is a valid RISIKOPROFIL. """ +@mcp.tool() +def validate_entity(entity: str, label: str) -> dict: + """Returns if the entity is valid based on hardcoded rules.""" + valid_risiko = {"core", "core+", "value-added", "opportunistisch"} + normalized = entity.lower().replace(" ", "").replace("-", "") + + if label.lower() == "risikoprofil" and normalized in valid_risiko: + return {"status": "valid", "entity": entity} + return {"status": "invalid", "entity": entity} + +""" Example prompt: Get spacy and exxeta results and merge them. Then validate if "Core/Core+" is a valid Risikoprofil. """ +@mcp.tool() +def merge_spacy_exxeta(spacy_result: list[dict], exxeta_result: list[dict]) -> list[dict]: + """Merge two results, mark as validated if label/entity/page match.""" + def norm(e): return e["entity"].lower().replace(" ", "") + + merged = [] + seen = set() + + for s in spacy_result: + s_norm = norm(s) + s_page = s["page"] + match = next((e for e in exxeta_result if e["label"] == s["label"] and norm(e) == s_norm and e["page"] == s_page), None) + if match: + merged.append({**s, "status": "validated"}) + seen.add((match["entity"], match["page"])) + else: + merged.append({**s, "status": "spacy_only"}) + + for e in exxeta_result: + if (e["entity"], e["page"]) not in seen: + merged.append({**e, "status": "exxeta_only"}) + return merged \ No newline at end of file diff --git a/prototypes/arc2_prototype/app.py b/prototypes/arc2_prototype/app.py index 97466d8..0f73b37 100644 --- a/prototypes/arc2_prototype/app.py +++ b/prototypes/arc2_prototype/app.py @@ -37,7 +37,7 @@ def upload(): extract_with_spacy(pitchbook_pages) # Step 3: Merge and validate results - merge_and_validate_entities() + merge_and_validate_entities(filter_label="RISIKOPROFIL") except Exception as e: return jsonify({"error": str(e)}), 500 diff --git a/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json b/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json index 53a163e..b67c44c 100644 --- a/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json +++ b/prototypes/arc2_prototype/exxeta_service/output/exxeta-results.json @@ -6,7 +6,7 @@ }, { "label": "RISIKOPROFIL", - "entity": "core, core+, value-added", + "entity": "Core, core+, value-added", "page": 7 }, { @@ -49,16 +49,6 @@ "entity": "Core", "page": 14 }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14 - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14 - }, { "label": "RISIKOPROFIL", "entity": "Core", @@ -81,12 +71,7 @@ }, { "label": "RISIKOPROFIL", - "entity": "Core", - "page": 15 - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", + "entity": "Core/Core+", "page": 19 }, { @@ -109,6 +94,11 @@ "entity": "Core", "page": 26 }, + { + "label": "RISIKOPROFIL", + "entity": "Value-added", + "page": 26 + }, { "label": "RISIKOPROFIL", "entity": "Core Offices, Core + assets", @@ -119,16 +109,6 @@ "entity": "Core, Core+", "page": 33 }, - { - "label": "RISIKOPROFIL", - "entity": "Core, Core+", - "page": 33 - }, - { - "label": "RISIKOPROFIL", - "entity": "Value-added", - "page": 33 - }, { "label": "RISIKOPROFIL", "entity": "Core", diff --git a/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json b/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json index eb4f254..cab4095 100644 --- a/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json +++ b/prototypes/arc2_prototype/merge_validate_service/output/merged-results.json @@ -1,16 +1,79 @@ [ + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 1, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core and Core+", "page": 4, "status": "validated" }, + { + "label": "RISIKOPROFIL", + "entity": "CITIES", + "page": 6, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "closed-end and open-ended", + "page": 6, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 6, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 7, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 7, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "core, core+, value-added", "page": 7, "status": "validated" }, + { + "label": "RISIKOPROFIL", + "entity": "Each", + "page": 8, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Land", + "page": 8, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "C", + "page": 8, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core", @@ -18,6 +81,13 @@ "status": "single-source", "source": "exxeta" }, + { + "label": "RISIKOPROFIL", + "entity": "Fund\nFund Objective", + "page": 10, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core/Core+", @@ -38,11 +108,39 @@ }, { "label": "RISIKOPROFIL", - "entity": "UK, DE, BE, NL, LU,", + "entity": "CH", "page": 10, "status": "single-source", "source": "spacy" }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 10, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "June", + "page": 11, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Lock", + "page": 11, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "before", + "page": 11, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core / Core +", @@ -57,7 +155,7 @@ }, { "label": "RISIKOPROFIL", - "entity": "core\n", + "entity": "Long", "page": 12, "status": "single-source", "source": "spacy" @@ -69,6 +167,20 @@ "status": "single-source", "source": "spacy" }, + { + "label": "RISIKOPROFIL", + "entity": "Hold", + "page": 12, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 12, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "core/core+", @@ -77,56 +189,32 @@ }, { "label": "RISIKOPROFIL", - "entity": "6,4 6,4", + "entity": "Fund\nSees has", "page": 13, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Country /", + "entity": "Core", "page": 14, - "status": "single-source", - "source": "spacy" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core Excellent", + "entity": "Core", "page": 14, - "status": "single-source", - "source": "spacy" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core 40", + "entity": "Core", "page": 14, - "status": "single-source", - "source": "spacy" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core 400m", - "page": 14, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core 99m-102", - "page": 14, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core 85m-90m", - "page": 14, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core 50", + "entity": "Good New", "page": 14, "status": "single-source", "source": "spacy" @@ -135,89 +223,38 @@ "label": "RISIKOPROFIL", "entity": "Core", "page": 14, + "status": "validated" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core 85m-90", + "page": 14, "status": "single-source", - "source": "exxeta" + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "June\n", + "page": 14, + "status": "single-source", + "source": "spacy" }, { "label": "RISIKOPROFIL", "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" + "page": 15, + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 14, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Country /", + "entity": "Good New", "page": 15, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Core Good New", - "page": 15, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core 44m-46m", - "page": 15, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core Good New", - "page": 15, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core CBD New", - "page": 15, - "status": "single-source", - "source": "spacy" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core Good New", + "entity": "Good", "page": 15, "status": "single-source", "source": "spacy" @@ -226,47 +263,58 @@ "label": "RISIKOPROFIL", "entity": "Core", "page": 15, - "status": "single-source", - "source": "exxeta" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core", + "entity": "Leed Platinium", "page": 15, "status": "single-source", - "source": "exxeta" + "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Core", + "entity": "City", "page": 15, "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 15, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "Core", - "page": 15, - "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "countries, giving", - "page": 18, - "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", "entity": "Core", + "page": 15, + "status": "validated" + }, + { + "label": "RISIKOPROFIL", + "entity": "Good New", + "page": 15, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core CBD", + "page": 15, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 15, + "status": "validated" + }, + { + "label": "RISIKOPROFIL", + "entity": "Good New", + "page": 15, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core/Core+", "page": 19, "status": "single-source", "source": "exxeta" @@ -285,14 +333,49 @@ }, { "label": "RISIKOPROFIL", - "entity": "D, and", + "entity": "C.", "page": 21, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "UK, DE, BE, NL, LU,", + "entity": "Fund", + "page": 22, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Sarl", + "page": 22, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Look", + "page": 26, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "High", + "page": 26, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Tier", + "page": 26, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "CH", "page": 26, "status": "single-source", "source": "spacy" @@ -306,7 +389,21 @@ }, { "label": "RISIKOPROFIL", - "entity": "core or", + "entity": "Value-added", + "page": 26, + "status": "single-source", + "source": "exxeta" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 27, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "core", "page": 27, "status": "single-source", "source": "spacy" @@ -318,6 +415,13 @@ "status": "single-source", "source": "spacy" }, + { + "label": "RISIKOPROFIL", + "entity": "Each", + "page": 27, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core Offices, Core + assets", @@ -334,24 +438,38 @@ }, { "label": "RISIKOPROFIL", - "entity": "kgCO,e", + "entity": "kgCO,e/m?.an", "page": 30, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "C,\n", + "entity": "C", + "page": 31, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "CARBONE\nC,\n", "page": 32, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Core, Core+", + "entity": "Fund\n", "page": 33, "status": "single-source", - "source": "exxeta" + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "semi-annually", + "page": 33, + "status": "single-source", + "source": "spacy" }, { "label": "RISIKOPROFIL", @@ -362,21 +480,42 @@ }, { "label": "RISIKOPROFIL", - "entity": "Value-added", - "page": 33, + "entity": "Core", + "page": 34, "status": "single-source", - "source": "exxeta" + "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "KfW, Dwp", + "entity": "CoC", + "page": 34, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 34, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "CoC", + "page": 34, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "CoC", "page": 35, "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Bank,", + "entity": "Core Parking", "page": 35, "status": "single-source", "source": "spacy" @@ -395,37 +534,49 @@ "status": "single-source", "source": "exxeta" }, + { + "label": "RISIKOPROFIL", + "entity": "3/5", + "page": 36, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 36, + "status": "single-source", + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 36, + "status": "single-source", + "source": "spacy" + }, { "label": "RISIKOPROFIL", "entity": "Core Parking", "page": 36, - "status": "single-source", - "source": "exxeta" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core Parking", + "entity": "Cash-on-cash", "page": 36, "status": "single-source", - "source": "exxeta" - }, - { - "label": "RISIKOPROFIL", - "entity": "HSBC, RTE", - "page": 37, - "status": "single-source", "source": "spacy" }, { "label": "RISIKOPROFIL", - "entity": "Core WALB (", + "entity": "Core", "page": 37, - "status": "single-source", - "source": "spacy" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core WALB (", + "entity": "Cash-on-cash", "page": 37, "status": "single-source", "source": "spacy" @@ -434,28 +585,46 @@ "label": "RISIKOPROFIL", "entity": "Core", "page": 37, - "status": "single-source", - "source": "exxeta" + "status": "validated" }, { "label": "RISIKOPROFIL", - "entity": "Core", + "entity": "Cash-on-cash", "page": 37, "status": "single-source", - "source": "exxeta" + "source": "spacy" + }, + { + "label": "RISIKOPROFIL", + "entity": "5/5", + "page": 38, + "status": "single-source", + "source": "spacy" }, { "label": "RISIKOPROFIL", "entity": "Core", "page": 38, + "status": "validated" + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 38, "status": "single-source", - "source": "exxeta" + "source": "spacy" }, { "label": "RISIKOPROFIL", "entity": "Core", "page": 38, + "status": "validated" + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 38, "status": "single-source", - "source": "exxeta" + "source": "spacy" } ] \ No newline at end of file diff --git a/prototypes/arc2_prototype/merge_validate_service/validator.py b/prototypes/arc2_prototype/merge_validate_service/validator.py index e194021..f5045e4 100644 --- a/prototypes/arc2_prototype/merge_validate_service/validator.py +++ b/prototypes/arc2_prototype/merge_validate_service/validator.py @@ -8,7 +8,7 @@ def load_json(path: Path): with path.open("r", encoding="utf-8") as f: return json.load(f) -def merge_and_validate_entities(): +def merge_and_validate_entities(filter_label=None): base = Path(__file__).resolve().parent.parent spacy_path = base / "spacy_service/output/spacy-results.json" exxeta_path = base / "exxeta_service/output/exxeta-results.json" @@ -43,7 +43,10 @@ def merge_and_validate_entities(): merged.append({**e, "status": "single-source", "source": "exxeta"}) merged.sort(key=lambda x: (x.get("page", 0), x.get("label", ""))) + + if filter_label: + merged = [m for m in merged if m.get("label") == filter_label] + with output_path.open("w", encoding="utf-8") as f: json.dump(merged, f, indent=2) - - return merged \ No newline at end of file + return merged diff --git a/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf b/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf index ffcd519..f694f52 100644 Binary files a/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf and b/prototypes/arc2_prototype/ocr_pdf_service/output/pitchbook-OCR.pdf differ diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json b/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json index daabc76..477e900 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json +++ b/prototypes/arc2_prototype/spacy_service/models/model-best/meta.json @@ -2,13 +2,13 @@ "lang":"de", "name":"pipeline", "version":"0.0.0", - "spacy_version":">=3.7.2,<3.8.0", + "spacy_version":">=3.8.5,<3.9.0", "description":"", "author":"", "email":"", "url":"", "license":"", - "spacy_git_version":"a89eae928", + "spacy_git_version":"d0c705c", "vectors":{ "width":0, "vectors":0, @@ -21,7 +21,11 @@ ], "ner":[ - "RISIKOPROFIL" + "AUSSCH\u00dcTTUNGSRENDITE", + "Aussch\u00fcttungsrendite", + "Laufzeit", + "RISIKOPROFIL", + "Risikoprofil" ] }, "pipeline":[ @@ -36,17 +40,37 @@ ], "performance":{ - "ents_f":1.0, - "ents_p":1.0, - "ents_r":1.0, + "ents_f":0.9007633588, + "ents_p":0.8309859155, + "ents_r":0.9833333333, "ents_per_type":{ "RISIKOPROFIL":{ "p":1.0, "r":1.0, "f":1.0 + }, + "AUSSCH\u00dcTTUNGSRENDITE":{ + "p":0.5925925926, + "r":0.9411764706, + "f":0.7272727273 + }, + "Aussch\u00fcttungsrendite":{ + "p":0.6666666667, + "r":1.0, + "f":0.8 + }, + "Laufzeit":{ + "p":1.0, + "r":1.0, + "f":1.0 + }, + "Risikoprofil":{ + "p":1.0, + "r":1.0, + "f":1.0 } }, - "tok2vec_loss":0.000000029, - "ner_loss":0.0000000614 + "tok2vec_loss":128.6722957797, + "ner_loss":1581.2761230469 } } \ No newline at end of file diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model index 8a0c5ae..4bdcbcf 100644 Binary files a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model and b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/model differ diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves index e72ba15..b293ca8 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves +++ b/prototypes/arc2_prototype/spacy_service/models/model-best/ner/moves @@ -1 +1 @@ -movesx{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}cfgneg_key \ No newline at end of file +moves{"0":{},"1":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"2":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"3":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"4":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5,"":1},"5":{"":1}}cfgneg_key \ No newline at end of file diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model index 1cfa6a5..3c788ee 100644 Binary files a/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model and b/prototypes/arc2_prototype/spacy_service/models/model-best/tok2vec/model differ diff --git a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json index 7569f1d..dff255e 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json +++ b/prototypes/arc2_prototype/spacy_service/models/model-best/vocab/strings.json @@ -6,6 +6,7 @@ "\"", "$", "%", + "&", "'", "''", "'-(", @@ -50,6 +51,12 @@ "*", "+", ",", + ",00", + ",12", + ",25", + ",40", + ",80", + ",91", "-", "-((", "-))", @@ -103,41 +110,82 @@ ".w.", ".\u00e4.", "/", + "/2,12", "/3", "/Core+", + "/FK", + "/XX", "/Xxxx+", "/core+", "/d", + "/d,dd", + "/fk", + "/xx", "/xxxx+", "0", "0%+", + "0,1", + "0,80", "0.0", "0.o", + "000", + "018", "022", + "023", "032", "034", "0_0", "0_o", "1", + "1,40", "1.", "10", + "100", "12", + "14", "2", "2.", "20", + "200", + "200.000", + "2018", "2022", "2032", "2034", + "24", + "25", "250", "3", + "3,8", "3.", + "31.12.2023", "33", "333", "35", + "4", + "4,0", + "4,5", + "4,6", + "4,7", + "4,8", + "4,9", + "4,91", + "40", "5", + "5,0", + "5,00", + "5,25", + "5,3", + "5,7", "50", + "5Mio.\u20ac", + "5mio.\u20ac", + "6", + "60", "7", + "7,5", "7,50%+", + "75", "8", "8)", "8-", @@ -243,6 +291,7 @@ ">:o", ">:x", "><(((*>", + "?", "@", "@_@", "A", @@ -250,6 +299,9 @@ "A.C.", "A.D.", "A.G.", + "AIN", + "AUSSCH\u00dcTTUNGSRENDITE", + "Ab", "Abb", "Abb.", "Abbildung", @@ -262,34 +314,62 @@ "Abt.", "Abteilung", "Add", + "Aktive", "Aktueller", + "AlF", "Allgemeine", "Amsterdam", + "Angestrebter", + "Ankauf", + "Ankaufs-", + "Ankaufsphase", + "Anlagebedingungen", "Anlagestrategien", + "Anlagesusschuss", "Anlagevehikels", + "Annahmen", "Ansprechpartners", "Antagevehikels", + "Anteilseigner", "Apr", "Apr.", "April", + "Area", "Art", + "Artikel", "Assets", "Aufl\u00f6sung", + "Aufnahme", + "Auftakt", "Aufwertung", "Aug", "Aug.", "August", + "Auschittungsrendite", + "Auschu\u0308ttungsrendite", + "Ausschu\u0308ttung", + "Ausschu\u0308ttungsintervalle", + "Ausschu\u0308ttungsrandite", + "Ausschu\u0308ttungsrendite", + "Aussch\u00fcttungsintervalle", + "Aussch\u00fcttungsrandite", + "Aussch\u00fcttungsrendite", + "Aussch\u00fcttungsrendites", "B", "B.", "B.A.", "B.Sc", "B.Sc.", + "BELGIUM", "Bahnhof", "Band", + "Baumanagementgebahr", "Bd", "Bd.", "Beispiel", + "Benefits", "Berlin", + "Bestandsentwicklung", "Bestandsentwicklungen", "Betr", "Betr.", @@ -300,11 +380,13 @@ "Bhf.", "Biol", "Biol.", + "Brussels", "Bsp", "Bsp.", "C", "C++", "C.", + "CBD", "CDU", "CDU/CSU", "CSU", @@ -313,15 +395,20 @@ "Cie", "Cie.", "Cities", + "Closed", "Closings", "Co", "Co.", + "Considering", "Core", "Core+", "Core+/Value", + "Country", "D", "D.", "D.C.", + "Darlehen", + "Deutsche", "Deutschland", "Deutschlands", "Dez", @@ -329,28 +416,40 @@ "Dezember", "Di", "Di.", + "Die", "Dienstag", "Different", "Dipl", "Dipl.", "Dipl.-Ing", "Dipl.-Ing.", + "Dis", "Do", "Do.", "Donnerstag", "Dr", "Dr.", + "Drawbacks", "D\u00e4nemark", "E", "E-Mail", "E.", + "ERD", + "ESG-", + "EUR", + "Eigenkapital", + "Einmalige", "Einw", + "Einwohner", + "Estate", "Europe", "European", "Exit", "F", "F.", + "FDR", "FIL", + "FRANCE", "Fa", "Fa.", "Fam", @@ -359,13 +458,18 @@ "Feb", "Feb.", "Februar", + "Finanzierung", + "Finanzierungskonditionen", "Firma", "Fond", "Fonds", "Fr", "Fr.", + "France", "Frankreich", "Frau", + "Fremdkapital", + "French", "Frl", "Frl.", "Fr\u00e4ulein", @@ -374,13 +478,19 @@ "G.", "G.m.b", "G.m.b.H.", + "GEDis", + "GERD", + "GRRE", "Gateway", "Gebr", "Gebr.", + "Gebu\u0308hren", + "Geb\u00fchren", "Geplantes", "Gesamtrendite", "H", "H.", + "Haltedauer", "Halten", "Halten-Strategie", "Hauptbahnhof", @@ -390,6 +500,8 @@ "Herrn", "Hg", "Hg.", + "Hotel", + "Hotels", "Hr", "Hr.", "Hrn", @@ -402,10 +514,14 @@ "II.", "III", "III.", + "INK", "INREV", "IRR", + "ITE", + "IUM", "IV", "IV.", + "Im", "Immobilien", "Immobilien-Spezialfonds", "Inc", @@ -413,7 +529,14 @@ "Informationen", "Ing", "Ing.", + "Invastitionsfokus", + "Investftionsvolumen", + "Investitionen", + "Investitions-annahmen", "Investmentmanagers", + "Investmentzeitraum", + "Investtionszeltraum", + "It", "J", "Jahr", "Jahre", @@ -436,15 +559,25 @@ "K", "K.", "K.O.", + "Kapitalzusagen", "Kaufen", + "Keine", "Key", + "Klassifizierung", + "Kosten", "L", "L'", "L.A.", + "LT", "LTV", "LTY", "Laufzeit", + "Levallois", + "Limited", + "Lisbon", + "Logistics", "London", + "Lux-based", "L\u00e4nderallokation", "L\u2019", "M", @@ -452,19 +585,27 @@ "M.A.", "M.Sc", "M.Sc.", + "MGallery", + "Madrid", + "Manage", "Manager", "Maximaler", "Mehrwertsteuer", + "Metropolregianen", "Metropolregionen", "Mi", "Mi.", "Milliarde", "Million", + "Mindestanlage", + "Mindestens", "Mio", "Mio.", + "Mitgliedschaft", "Mittwoch", "Mo", "Mo.", + "Monate", "Montag", "Mr", "Mr.", @@ -480,8 +621,12 @@ "N", "N.Y.", "N.Y.C.", + "NCE", + "NDS", + "NETHERLANDS", "Nachvermietungsstrategie", "Name", + "Navigate", "Niederlande", "Nov", "Nov.", @@ -489,15 +634,21 @@ "Nr", "Nr.", "Nummer", + "Nuremberg", "O", "O.", "O.K.", "O.O", "O.o", + "OPCI", "O_O", "O_o", + "Objekt", + "Objekten", + "Of", "Offen", "Offener", + "Offices", "Okt", "Okt.", "Oktober", @@ -507,13 +658,20 @@ "Original", "P", "P.S.", + "PCI", + "Parformanceabh\u00e4ngige", "Paris", "Pkt", "Pkt.", + "Prime", "Prof", "Prof.", "Professor", + "Prognostizierte", "Punkt", + "Q", + "Qin", + "Quote", "R", "R.", "R.I.P.", @@ -521,19 +679,33 @@ "REV", "RISIKOPROFIL", "ROOT", + "RRE", + "Real", "Rechtsform", "Red", "Red.", "Redaktion", + "Regionen", + "Rendite-", + "Renovierungen", + "Rents", + "Residential", + "Retail", "Risikoprofil", "Risk", + "Rotterdam", "S", "S'", + "SFDR", + "SG-", + "SPAIN", + "SRI", "Sa", "Sa.", "Samstag", "Sc.", "Schweden", + "Sector", "Sep", "Sep.", "Sept", @@ -544,28 +716,38 @@ "So", "So.", "Sonntag", + "Spezial-AlF", "St", "St.", + "Stabilisierung", "Standortaufwertungsstrategie", "Standorte", "Std", "Std.", + "Steuern", "Stil", "Str", "Str.", "Strategie", "Stra\u00dfe", "Struktur", + "Strukturierungsgebu\u0308hr", + "Strukturierungsgeb\u00fchr", "Stunde", + "St\u00e4dten", "S\u2019", "T", "T.", + "Tag", "Tausend", + "Teflimmobilfe)-", "Tel", "Tel.", "Telefon", "Telefonnummer", + "Tenant", "The", + "There", "Tr", "Tr.", "Tsd", @@ -575,6 +757,7 @@ "U.S.", "U.S.A.", "U.S.S.", + "USt", "Univ", "Univ.", "Universit\u00e4t", @@ -583,10 +766,16 @@ "V.V", "V_V", "Value", + "Verbesserungen", + "Vergu\u0308tung", + "Verg\u00fctung", + "Verkaufs", + "Verkaufs-", "Vol", "Vol.", "W", "Wertstabile", + "Why", "Wohnimmobilien", "X'", "X++", @@ -605,9 +794,13 @@ "XX", "XX.", "XXX", + "XXX-", "XXX.", "XXX/XXX", "XXXX", + "XXXxx", + "XXx", + "XXxxxx", "X_X", "X_x", "Xx", @@ -615,18 +808,27 @@ "XxXx", "XxXx.", "Xxx", + "Xxx-xxxx", "Xxx.", "Xxxx", "Xxxx+", "Xxxx+/Xxxxx", + "Xxxx-", "Xxxx-XXX", "Xxxx-Xxxxx-XXX", "Xxxx.", "Xxxx.-Xxx", "Xxxx.-Xxx.", "Xxxxx", + "Xxxxx)-", "Xxxxx)/Xxxx", + "Xxxxx-", + "Xxxxx-XxX", "Xxxxx-Xxxxx", + "Xxxxx-xxxx", + "Xxxxx\u0308xx", + "Xxxxx\u0308xxxx", + "Xxxx\u0308xxxx", "Xx\u0308xxxx", "X\u2019", "Z", @@ -634,10 +836,15 @@ "Ziel-LTY", "Ziel-Netto-IRR", "Zielanlagestrategie", + "Zielm\u00e4rkte", + "Zielobjektgr\u00f6\u00dfe", "Zielregionfen)/Jand", + "Zielrendite", "Zielsektoren", "Zielvolumen", "Ziirraiaein", + "Zins-", + "Zinss\u00e4tze", "Zt", "Zt.", "[", @@ -676,6 +883,7 @@ "a.g.", "a.m.", "a.z.", + "ab", "abb", "abb.", "abk", @@ -688,56 +896,114 @@ "abzgl.", "abz\u00fcglich", "ace", + "ach", + "act", + "active", "add", "adv", "adv.", + "aft", + "age", + "aha", "ahr", "ail", "aiming", + "ain", + "ake", + "akt", + "aktive", "aktueller", "al", "al.", + "ald", + "alf", + "all", "allg", "allg.", "allgemein", "allgemeine", + "also", "am.", "ame", "amsterdam", + "an", "an.", "and", + "angestrebt", + "angestrebter", + "ankauf", + "ankaufs-", + "ankaufsphase", + "anlagebedingungen", "anlagestrategien", + "anlagesusschuss", "anlagevehikels", + "annahmen", + "ans", "ansprechpartners", + "ant", "antagevehikels", + "anteilseigner", "apr", "apr.", + "are", + "area", "ark", + "ars", "art", + "artikel", + "as", + "ase", "asset", + "assetor", "assets", "at", "at.", + "ate", "ath", + "attractive", "auf", "aufl\u00f6sung", + "aufnahme", + "auftakt", "aufwertung", "auf\u2019m", "aug", "aug.", + "aum", + "auschittungsrendite", + "auschu\u0308ttungsrendite", "ausgew\u00e4hlte", + "ausschlie\u00dflich", + "ausschu\u0308ttung", + "ausschu\u0308ttungsintervalle", + "ausschu\u0308ttungsrandite", + "ausschu\u0308ttungsrendite", + "aussch\u00fcttungsintervalle", + "aussch\u00fcttungsrandite", + "aussch\u00fcttungsrendite", + "aussch\u00fcttungsrendites", + "ave", "ax.", "b", "b.", "b.a.", "b.sc", "b.sc.", + "balanced", + "basis", + "baumanagementgebahr", "bb.", "bd", "bd.", + "be", + "bei", "beispielsweise", + "belgium", + "benefits", "ber", "berlin", + "bestandsentwicklung", "bestandsentwicklungen", "betr", "betr.", @@ -749,14 +1015,20 @@ "bhf.", "biol", "biol.", + "bis", "bk.", + "bon", "br.", + "brussels", "bs.", "bsp", "bsp.", "bspw", "bspw.", "bt.", + "build", + "buildings", + "but", "bzgl", "bzgl.", "bzw", @@ -768,27 +1040,49 @@ "ca", "ca.", "cal", + "can", + "capital", + "cbd", "cdu", "cdu/csu", "ce>", + "ced", + "ces", + "cey", + "characteristic", + "che", "chr", "chr.", "cht", "cie", "cie.", "cities", + "city", + "cks", "cl.", + "closed", "closings", "co", "co.", + "collective", + "combines", + "competition", + "considered", + "considering", "core", "core+", "core+/value", + "could", + "country", + "creation", "csu", "cts", + "current", "d", "d'", "d)", + "d,d", + "d,dd", "d,dd%+", "d-", "d-)", @@ -800,19 +1094,26 @@ "d.h.", "d.x", "dX", + "dXxx.\u20ac", "d_d", "d_x", "dam", + "darlehen", "dd", + "dd.dd.dddd", "ddd", + "ddd.ddd", "dddd", "de", "ded", + "deep", + "defined", "dem", "den", "der", "dergleichen", "des", + "deutsche", "deutschland", "deutschlands", "development", @@ -822,22 +1123,30 @@ "dgl.", "di", "di.", + "die", "different", "dipl", "dipl.", "dipl.-ing", "dipl.-ing.", + "dis", + "diversification", + "diversity", + "dividend", "do", "do.", "don", "dr", "dr.", + "drawbacks", "du", "du\u2019s", "dv.", + "dxxx.\u20ac", "d\u00e4nemark", "d\u2019", "e", + "e)-", "e-mail", "e.", "e.V.", @@ -845,17 +1154,23 @@ "e.g", "e.g.", "e.v.", + "eal", "ean", "eb.", "ebd", "ebd.", "ebenda", "ebr", + "ebt", + "economic", "ed.", + "eep", "egr", + "egt", "egy", "ehem", "ehem.", + "eigenkapital", "eigentlich", "eigtl", "eigtl.", @@ -863,34 +1178,56 @@ "eine", "einem", "einen", + "einer", + "einmalige", + "eins", "einw", + "einwohner", + "einzeln", "eit", + "ekt", "el.", + "eld", + "eln", "els", "em.", "en.", + "end", + "ended", "engl", "engl.", "englisch", "enhancing", + "ens", "ent", "entspr", "entspr.", + "eons", "ep.", "ept", "er", "er.", + "erd", + "ere", + "erfolgten", + "erg", "erm", "erm.", + "ern", "err", "ers", "ersten", + "ery", "er\u2019s", "es", + "esg-", + "ess", + "estate", "etc", "etc.", "etr", "ets", + "eur", "europe", "european", "ev", @@ -899,8 +1236,11 @@ "evtl", "evtl.", "exit", + "experienced", "expertise", "exposure", + "externe", + "extract", "ez.", "e\u2019s", "f", @@ -909,24 +1249,38 @@ "fa.", "fam", "fam.", + "fdr", "feb", "feb.", "fen", + "festen", + "festgelegt", "festgelegter", + "fierce", "fil", + "finanzierung", + "finanzierungskonditionen", + "flagship", "fond", "fonds", + "for", + "form", "fr", "fr.", + "france", "frankreich", "franz\u00f6sisch", + "fremdkapital", + "french", "frl", "frl.", "frz", "frz.", + "fs-", "fs.", "fund", "fu\u0308hrende", + "f\u00fcr", "f\u2019m", "g", "g.", @@ -937,6 +1291,10 @@ "geb.", "gebr", "gebr.", + "gebu\u0308hren", + "geb\u00fchren", + "ged", + "gedis", "gegebenenfalls", "gegen\u00fcber", "gegr", @@ -945,8 +1303,11 @@ "gem", "gem.", "gen", + "geographies", "geplantes", + "gepr\u00fcft", "ger", + "gerd", "gesamtrendite", "gf.", "gfs", @@ -956,29 +1317,41 @@ "ggfs.", "gg\u00fc", "gg\u00fc.", + "ght", "gie", "gl.", "good", "gr.", + "grre", "gtl", + "guarantee", "g\u00fc.", "h", "h.", "h.c", "h.c.", + "haltedauer", "halten", "halten-strategie", + "have", "hbf", "hbf.", "hd.", "hed", "hem", + "hen", + "here", "hf.", "hg", "hg.", + "high", "hil", "hinter", "hinter\u2019m", + "hip", + "his", + "hme", + "hotel", "hotels", "hr", "hr.", @@ -1005,12 +1378,18 @@ "i.o.", "i.tr.", "i.v.", + "ial", + "ice", "ich", "ich\u2019s", + "ics", + "ide", "ie.", "ien", "ies", "ig.", + "ige", + "igh", "ihr", "ihr\u2019s", "ii", @@ -1018,11 +1397,14 @@ "iii", "iii.", "il.", + "ild", "ile", "illustration", + "im", "ime", "immobilien", "immobilien-spezialfonds", + "improve", "in", "in.", "inc", @@ -1035,38 +1417,54 @@ "ing", "ing.", "initiatives", + "ink", "inkl", "inkl.", "inklusive", "inrev", + "ins", "insb", "insb.", "insbesondere", + "interesting", + "invastitionsfokus", + "investftionsvolumen", + "investitionen", + "investitions-annahmen", + "investment", "investmentmanagers", "investments", + "investmentzeitraum", + "investor", + "investtionszeltraum", "inw", "io.", "iol", "ion", "ipl", + "ird", "irr", "is", "ise", "isk", "iss", + "it", "ite", "ith", + "its", "ity", "itz", "ium", "iv", "iv.", + "ive", "j", "j.", "jahr", "jahre", "jan", "jan.", + "jedes", "jh", "jh.", "jhd", @@ -1079,17 +1477,26 @@ "jun.", "jur", "jur.", + "j\u00e4hrlich", + "j\u00e4hrliche", "k", "k.", "k.o.", + "kapitalzusagen", "kath", "kath.", "katholisch", "kaufen", + "keine", + "kel", "ket", "key", "kl.", + "klassifizierung", + "kosten", "kt.", + "kte", + "kus", "l", "l'", "l.", @@ -1100,21 +1507,38 @@ "laufzeit", "laut", "le.g", + "leave", "ler", + "less", + "levallois", "level", + "leverage", + "leveraged", + "leveraging", "lg.", + "limited", "lin", "lio", + "liquid", + "liquidity", + "lisbon", + "listed", + "lle", "llg", + "lls", "llt", "llv", + "logistics", "london", + "low", + "lso", "lt", "lt.", "lte", "ltv", "lty", "lue", + "lux-based", "lv.", "l\u00e4nderallokation", "l\u2019", @@ -1128,32 +1552,44 @@ "m.m.", "m.sc", "m.sc.", + "madrid", + "main", + "make", "mal", + "manage", "management", "manager", "market", + "markets", "max", "max.", "maximal", "maximaler", + "means", "men", "mer", + "metropolregianen", "metropolregionen", + "mgallery", "mi", "mi.", + "mic", "million", "min", "min.", "mind", "mind.", + "mindestanlage", "mindestens", "minimal", "minor", "mio", "mio.", "mit", + "mitgliedschaft", "mo", "mo.", + "monate", "monatlich", "mr", "mr.", @@ -1163,6 +1599,7 @@ "mrz.", "mtl", "mtl.", + "must", "mwst", "mwst.", "m\u00e4r", @@ -1174,32 +1611,45 @@ "n.r", "n.y.", "n.y.c.", + "nach", + "nachhaltig", "nachvermietungsstrategie", "name", "nat", "nat.", + "navigate", "nc.", + "nce", + "nch", "ncl", "nd.", "nde", "nds", "ne", + "ned", "nem", "nen", "ner", + "nes", + "netherlands", + "neu", "ng.", "ngl", "ngs", "niederlande", "niv", "nkl", + "no", "nor", "nov", "nov.", "nr", "nr.", + "ns-", "nsb", + "nse", "nts", + "nuremberg", "o", "o.", "o.0", @@ -1213,27 +1663,52 @@ "o.o", "o.\u00e4", "o.\u00e4.", + "o.\u20ac", "o_0", "o_O", "o_o", + "objectives", + "objekt", + "objekten", "of", "of.", + "ofQin", "offen", "offener", + "offers", + "office", + "offices", + "ofqin", "og.", + "ois", "okt", "okt.", "ol.", + "ome", + "on", "ond", + "ons", "ood", + "oom", + "opci", "opco", "ope", + "open", + "open-ended", + "operators", + "opportunities", + "or", + "order", "ore", "orig", "orig.", "original", "orm", + "ors", + "ote", + "outside", "ov.", + "ove", "over", "p", "p.", @@ -1242,51 +1717,92 @@ "p.s", "p.s.", "pCo", + "pan-European", + "pan-european", + "parformanceabh\u00e4ngige", "paris", + "pci", "pco", + "pen", "pers", "pers.", "phil", "phil.", + "pid", "pkt", "pkt.", "pl.", "portfolio", + "potential", "pr.", "premium", + "preservation", + "pricey", + "prime", "prof", "prof.", "profile", + "prognostizierte", + "program", "projects", + "providing", "pt.", "pw.", "q", "q.", "q.e.d", "q.e.d.", + "qin", "quality", + "quote", "r", "r.", "r.i.p.", + "ram", + "rapid", + "rce", + "rd", "rd.", "re", "re+", + "rea", + "real", + "recent", "rechtsform", + "recovery", "red", "red.", + "region", + "regionen", + "remains", "ren", + "rendite-", + "renovierungen", + "rent", + "rents", "rer", "rer.", + "residential", + "respective", + "retail", "rev", + "reversion", + "rid", "rig", + "right", "ris", "risikoprofil", "risk", "rl.", "rm.", + "rms", "rn.", + "rne", "rof", + "room", + "rotterdam", "rr.", + "rre", "rs.", "rsg", "rte", @@ -1307,67 +1823,107 @@ "sb.", "schweden", "sd.", + "sector", + "sectors", + "sed", + "segment", "sen", "sen.", + "sense", "sep", "sep.", "sept", "sept.", "set", "sf.", + "sfdr", + "sg-", "sg.", + "sich", "sie", "sie\u2019s", + "sis", "sitz", "skandinavien", + "small", "so", "so.", + "sobald", "sog", "sog.", + "some", "sp.", "space", + "spain", + "spezial-alf", "spr", "spw", + "sri", "ss.", "st", "st.", + "stabilisieren", + "stabilisierung", "standortaufwertungsstrategie", "standorte", "std", "std.", "stellv", "stellv.", + "steuern", "stil", "str", "str.", "strategie", + "strategies", "strategy", "struktur", + "strukturierungsgebu\u0308hr", + "strukturierungsgeb\u00fchr", + "st\u00e4dten", "sw.", "s\u2019", "t", "t.", "tactical", + "tag", + "tal", + "targeting", + "targets", "tc.", "td.", + "te-", + "ted", + "tee", + "teflimmobilfe)-", "tel", "tel.", "telefonnummer", "ten", + "tenant", "ter", + "terms", "tes", "th.", "the", + "there", + "this", + "through", + "tic", "tig", "til", "time", "tl.", "to", + "top", + "tor", "tr", "tr.", + "try", "tsd", "tsd.", "tur", + "tze", "t\u00e4gl", "t\u00e4gl.", "t\u00e4glich", @@ -1384,23 +1940,36 @@ "u.u.", "u.v.m", "u.v.m.", + "uer", + "ufs", "ug.", + "ugh", + "uid", "ul.", + "uld", + "umliegende", "un.", "und", + "under", + "undertaking", "ung", "univ", "univ.", + "unless", "unter", + "unterstellt", "unter\u2019m", "ur.", "ure", "usf", "usf.", + "uss", + "ust", "usw", "usw.", "uvm", "uvm.", + "u\u0308ber", "u\u2019s", "v", "v.", @@ -1415,9 +1984,16 @@ "v_v", "value", "value-added", + "var", "vel", "ver", + "verbesserungen", "vergleiche", + "vergu\u0308tung", + "verg\u00fctung", + "verkaufs", + "verkaufs-", + "very", "ves", "vgl", "vgl.", @@ -1430,6 +2006,7 @@ "vol", "vol.", "vom", + "von", "vor", "vor\u2019m", "vs", @@ -1438,10 +2015,14 @@ "w", "w.", "wSt", + "walls", "way", "well-established", + "werden", "wertstabile", + "why", "wir", + "wird", "wir\u2019s", "wiss", "wiss.", @@ -1477,24 +2058,35 @@ "xx", "xx.", "xx.x", + "xxXxx", "xxx", + "xxx-", + "xxx-Xxxxx", + "xxx-xxxx", "xxx.", "xxxx", + "xxxx)-", "xxxx)/xxxx", "xxxx+", "xxxx+/xxxx", + "xxxx-", "xxxx-xxx", "xxxx-xxxx", "xxxx-xxxx-xxx", "xxxx.", + "xxxx\u0308xx", + "xxxx\u0308xxxx", "xxxx\u2019x", "xxx\u2019x", "xx\u0308xxxx", "xx\u2019x", + "x\u0308xxx", "x\u2019", "x\ufe35x", "y", "y.", + "years", + "yield", "z", "z.", "z.B.", @@ -1512,14 +2104,23 @@ "ziel-lty", "ziel-netto-irr", "zielanlagestrategie", + "zielm\u00e4rkte", + "zielobjektgr\u00f6\u00dfe", "zielregionfen)/jand", + "zielrendite", "zielsektoren", "zielvolumen", "ziirraiaein", + "zins-", + "zinss\u00e4tze", "zt", + "zu", + "zum", "zw.", + "zwischen", "zzgl", "zzgl.", + "{", "|", "}", "\u00a0", @@ -1549,11 +2150,15 @@ "\u00f6sterr", "\u00f6sterr.", "\u00f6sterreichisch", + "\u00f6\u00dfe", "\u00fc", "\u00fc.", "\u00fcber", "\u00fcbersicht", "\u00fcber\u2019m", + "\u00fcft", + "\u00fchr", + "\u0308hr", "\u0ca0", "\u0ca0_\u0ca0", "\u0ca0\ufe35\u0ca0", @@ -1574,6 +2179,8 @@ "\u2019xxx", "\u2019\u2019", "\u201a", + "\u201c", + "\u201d", "\u20ac", "\u2501", "\u253b", diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json b/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json index daabc76..477e900 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json +++ b/prototypes/arc2_prototype/spacy_service/models/model-last/meta.json @@ -2,13 +2,13 @@ "lang":"de", "name":"pipeline", "version":"0.0.0", - "spacy_version":">=3.7.2,<3.8.0", + "spacy_version":">=3.8.5,<3.9.0", "description":"", "author":"", "email":"", "url":"", "license":"", - "spacy_git_version":"a89eae928", + "spacy_git_version":"d0c705c", "vectors":{ "width":0, "vectors":0, @@ -21,7 +21,11 @@ ], "ner":[ - "RISIKOPROFIL" + "AUSSCH\u00dcTTUNGSRENDITE", + "Aussch\u00fcttungsrendite", + "Laufzeit", + "RISIKOPROFIL", + "Risikoprofil" ] }, "pipeline":[ @@ -36,17 +40,37 @@ ], "performance":{ - "ents_f":1.0, - "ents_p":1.0, - "ents_r":1.0, + "ents_f":0.9007633588, + "ents_p":0.8309859155, + "ents_r":0.9833333333, "ents_per_type":{ "RISIKOPROFIL":{ "p":1.0, "r":1.0, "f":1.0 + }, + "AUSSCH\u00dcTTUNGSRENDITE":{ + "p":0.5925925926, + "r":0.9411764706, + "f":0.7272727273 + }, + "Aussch\u00fcttungsrendite":{ + "p":0.6666666667, + "r":1.0, + "f":0.8 + }, + "Laufzeit":{ + "p":1.0, + "r":1.0, + "f":1.0 + }, + "Risikoprofil":{ + "p":1.0, + "r":1.0, + "f":1.0 } }, - "tok2vec_loss":0.000000029, - "ner_loss":0.0000000614 + "tok2vec_loss":128.6722957797, + "ner_loss":1581.2761230469 } } \ No newline at end of file diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model index 8a0c5ae..4bdcbcf 100644 Binary files a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model and b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/model differ diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves index e72ba15..b293ca8 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves +++ b/prototypes/arc2_prototype/spacy_service/models/model-last/ner/moves @@ -1 +1 @@ -movesx{"0":{},"1":{"RISIKOPROFIL":45},"2":{"RISIKOPROFIL":45},"3":{"RISIKOPROFIL":45},"4":{"RISIKOPROFIL":45,"":1},"5":{"":1}}cfgneg_key \ No newline at end of file +moves{"0":{},"1":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"2":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"3":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5},"4":{"RISIKOPROFIL":91,"AUSSCH\u00dcTTUNGSRENDITE":40,"Laufzeit":21,"Aussch\u00fcttungsrendite":8,"Risikoprofil":5,"":1},"5":{"":1}}cfgneg_key \ No newline at end of file diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model index 1cfa6a5..3c788ee 100644 Binary files a/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model and b/prototypes/arc2_prototype/spacy_service/models/model-last/tok2vec/model differ diff --git a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json index 7569f1d..dff255e 100644 --- a/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json +++ b/prototypes/arc2_prototype/spacy_service/models/model-last/vocab/strings.json @@ -6,6 +6,7 @@ "\"", "$", "%", + "&", "'", "''", "'-(", @@ -50,6 +51,12 @@ "*", "+", ",", + ",00", + ",12", + ",25", + ",40", + ",80", + ",91", "-", "-((", "-))", @@ -103,41 +110,82 @@ ".w.", ".\u00e4.", "/", + "/2,12", "/3", "/Core+", + "/FK", + "/XX", "/Xxxx+", "/core+", "/d", + "/d,dd", + "/fk", + "/xx", "/xxxx+", "0", "0%+", + "0,1", + "0,80", "0.0", "0.o", + "000", + "018", "022", + "023", "032", "034", "0_0", "0_o", "1", + "1,40", "1.", "10", + "100", "12", + "14", "2", "2.", "20", + "200", + "200.000", + "2018", "2022", "2032", "2034", + "24", + "25", "250", "3", + "3,8", "3.", + "31.12.2023", "33", "333", "35", + "4", + "4,0", + "4,5", + "4,6", + "4,7", + "4,8", + "4,9", + "4,91", + "40", "5", + "5,0", + "5,00", + "5,25", + "5,3", + "5,7", "50", + "5Mio.\u20ac", + "5mio.\u20ac", + "6", + "60", "7", + "7,5", "7,50%+", + "75", "8", "8)", "8-", @@ -243,6 +291,7 @@ ">:o", ">:x", "><(((*>", + "?", "@", "@_@", "A", @@ -250,6 +299,9 @@ "A.C.", "A.D.", "A.G.", + "AIN", + "AUSSCH\u00dcTTUNGSRENDITE", + "Ab", "Abb", "Abb.", "Abbildung", @@ -262,34 +314,62 @@ "Abt.", "Abteilung", "Add", + "Aktive", "Aktueller", + "AlF", "Allgemeine", "Amsterdam", + "Angestrebter", + "Ankauf", + "Ankaufs-", + "Ankaufsphase", + "Anlagebedingungen", "Anlagestrategien", + "Anlagesusschuss", "Anlagevehikels", + "Annahmen", "Ansprechpartners", "Antagevehikels", + "Anteilseigner", "Apr", "Apr.", "April", + "Area", "Art", + "Artikel", "Assets", "Aufl\u00f6sung", + "Aufnahme", + "Auftakt", "Aufwertung", "Aug", "Aug.", "August", + "Auschittungsrendite", + "Auschu\u0308ttungsrendite", + "Ausschu\u0308ttung", + "Ausschu\u0308ttungsintervalle", + "Ausschu\u0308ttungsrandite", + "Ausschu\u0308ttungsrendite", + "Aussch\u00fcttungsintervalle", + "Aussch\u00fcttungsrandite", + "Aussch\u00fcttungsrendite", + "Aussch\u00fcttungsrendites", "B", "B.", "B.A.", "B.Sc", "B.Sc.", + "BELGIUM", "Bahnhof", "Band", + "Baumanagementgebahr", "Bd", "Bd.", "Beispiel", + "Benefits", "Berlin", + "Bestandsentwicklung", "Bestandsentwicklungen", "Betr", "Betr.", @@ -300,11 +380,13 @@ "Bhf.", "Biol", "Biol.", + "Brussels", "Bsp", "Bsp.", "C", "C++", "C.", + "CBD", "CDU", "CDU/CSU", "CSU", @@ -313,15 +395,20 @@ "Cie", "Cie.", "Cities", + "Closed", "Closings", "Co", "Co.", + "Considering", "Core", "Core+", "Core+/Value", + "Country", "D", "D.", "D.C.", + "Darlehen", + "Deutsche", "Deutschland", "Deutschlands", "Dez", @@ -329,28 +416,40 @@ "Dezember", "Di", "Di.", + "Die", "Dienstag", "Different", "Dipl", "Dipl.", "Dipl.-Ing", "Dipl.-Ing.", + "Dis", "Do", "Do.", "Donnerstag", "Dr", "Dr.", + "Drawbacks", "D\u00e4nemark", "E", "E-Mail", "E.", + "ERD", + "ESG-", + "EUR", + "Eigenkapital", + "Einmalige", "Einw", + "Einwohner", + "Estate", "Europe", "European", "Exit", "F", "F.", + "FDR", "FIL", + "FRANCE", "Fa", "Fa.", "Fam", @@ -359,13 +458,18 @@ "Feb", "Feb.", "Februar", + "Finanzierung", + "Finanzierungskonditionen", "Firma", "Fond", "Fonds", "Fr", "Fr.", + "France", "Frankreich", "Frau", + "Fremdkapital", + "French", "Frl", "Frl.", "Fr\u00e4ulein", @@ -374,13 +478,19 @@ "G.", "G.m.b", "G.m.b.H.", + "GEDis", + "GERD", + "GRRE", "Gateway", "Gebr", "Gebr.", + "Gebu\u0308hren", + "Geb\u00fchren", "Geplantes", "Gesamtrendite", "H", "H.", + "Haltedauer", "Halten", "Halten-Strategie", "Hauptbahnhof", @@ -390,6 +500,8 @@ "Herrn", "Hg", "Hg.", + "Hotel", + "Hotels", "Hr", "Hr.", "Hrn", @@ -402,10 +514,14 @@ "II.", "III", "III.", + "INK", "INREV", "IRR", + "ITE", + "IUM", "IV", "IV.", + "Im", "Immobilien", "Immobilien-Spezialfonds", "Inc", @@ -413,7 +529,14 @@ "Informationen", "Ing", "Ing.", + "Invastitionsfokus", + "Investftionsvolumen", + "Investitionen", + "Investitions-annahmen", "Investmentmanagers", + "Investmentzeitraum", + "Investtionszeltraum", + "It", "J", "Jahr", "Jahre", @@ -436,15 +559,25 @@ "K", "K.", "K.O.", + "Kapitalzusagen", "Kaufen", + "Keine", "Key", + "Klassifizierung", + "Kosten", "L", "L'", "L.A.", + "LT", "LTV", "LTY", "Laufzeit", + "Levallois", + "Limited", + "Lisbon", + "Logistics", "London", + "Lux-based", "L\u00e4nderallokation", "L\u2019", "M", @@ -452,19 +585,27 @@ "M.A.", "M.Sc", "M.Sc.", + "MGallery", + "Madrid", + "Manage", "Manager", "Maximaler", "Mehrwertsteuer", + "Metropolregianen", "Metropolregionen", "Mi", "Mi.", "Milliarde", "Million", + "Mindestanlage", + "Mindestens", "Mio", "Mio.", + "Mitgliedschaft", "Mittwoch", "Mo", "Mo.", + "Monate", "Montag", "Mr", "Mr.", @@ -480,8 +621,12 @@ "N", "N.Y.", "N.Y.C.", + "NCE", + "NDS", + "NETHERLANDS", "Nachvermietungsstrategie", "Name", + "Navigate", "Niederlande", "Nov", "Nov.", @@ -489,15 +634,21 @@ "Nr", "Nr.", "Nummer", + "Nuremberg", "O", "O.", "O.K.", "O.O", "O.o", + "OPCI", "O_O", "O_o", + "Objekt", + "Objekten", + "Of", "Offen", "Offener", + "Offices", "Okt", "Okt.", "Oktober", @@ -507,13 +658,20 @@ "Original", "P", "P.S.", + "PCI", + "Parformanceabh\u00e4ngige", "Paris", "Pkt", "Pkt.", + "Prime", "Prof", "Prof.", "Professor", + "Prognostizierte", "Punkt", + "Q", + "Qin", + "Quote", "R", "R.", "R.I.P.", @@ -521,19 +679,33 @@ "REV", "RISIKOPROFIL", "ROOT", + "RRE", + "Real", "Rechtsform", "Red", "Red.", "Redaktion", + "Regionen", + "Rendite-", + "Renovierungen", + "Rents", + "Residential", + "Retail", "Risikoprofil", "Risk", + "Rotterdam", "S", "S'", + "SFDR", + "SG-", + "SPAIN", + "SRI", "Sa", "Sa.", "Samstag", "Sc.", "Schweden", + "Sector", "Sep", "Sep.", "Sept", @@ -544,28 +716,38 @@ "So", "So.", "Sonntag", + "Spezial-AlF", "St", "St.", + "Stabilisierung", "Standortaufwertungsstrategie", "Standorte", "Std", "Std.", + "Steuern", "Stil", "Str", "Str.", "Strategie", "Stra\u00dfe", "Struktur", + "Strukturierungsgebu\u0308hr", + "Strukturierungsgeb\u00fchr", "Stunde", + "St\u00e4dten", "S\u2019", "T", "T.", + "Tag", "Tausend", + "Teflimmobilfe)-", "Tel", "Tel.", "Telefon", "Telefonnummer", + "Tenant", "The", + "There", "Tr", "Tr.", "Tsd", @@ -575,6 +757,7 @@ "U.S.", "U.S.A.", "U.S.S.", + "USt", "Univ", "Univ.", "Universit\u00e4t", @@ -583,10 +766,16 @@ "V.V", "V_V", "Value", + "Verbesserungen", + "Vergu\u0308tung", + "Verg\u00fctung", + "Verkaufs", + "Verkaufs-", "Vol", "Vol.", "W", "Wertstabile", + "Why", "Wohnimmobilien", "X'", "X++", @@ -605,9 +794,13 @@ "XX", "XX.", "XXX", + "XXX-", "XXX.", "XXX/XXX", "XXXX", + "XXXxx", + "XXx", + "XXxxxx", "X_X", "X_x", "Xx", @@ -615,18 +808,27 @@ "XxXx", "XxXx.", "Xxx", + "Xxx-xxxx", "Xxx.", "Xxxx", "Xxxx+", "Xxxx+/Xxxxx", + "Xxxx-", "Xxxx-XXX", "Xxxx-Xxxxx-XXX", "Xxxx.", "Xxxx.-Xxx", "Xxxx.-Xxx.", "Xxxxx", + "Xxxxx)-", "Xxxxx)/Xxxx", + "Xxxxx-", + "Xxxxx-XxX", "Xxxxx-Xxxxx", + "Xxxxx-xxxx", + "Xxxxx\u0308xx", + "Xxxxx\u0308xxxx", + "Xxxx\u0308xxxx", "Xx\u0308xxxx", "X\u2019", "Z", @@ -634,10 +836,15 @@ "Ziel-LTY", "Ziel-Netto-IRR", "Zielanlagestrategie", + "Zielm\u00e4rkte", + "Zielobjektgr\u00f6\u00dfe", "Zielregionfen)/Jand", + "Zielrendite", "Zielsektoren", "Zielvolumen", "Ziirraiaein", + "Zins-", + "Zinss\u00e4tze", "Zt", "Zt.", "[", @@ -676,6 +883,7 @@ "a.g.", "a.m.", "a.z.", + "ab", "abb", "abb.", "abk", @@ -688,56 +896,114 @@ "abzgl.", "abz\u00fcglich", "ace", + "ach", + "act", + "active", "add", "adv", "adv.", + "aft", + "age", + "aha", "ahr", "ail", "aiming", + "ain", + "ake", + "akt", + "aktive", "aktueller", "al", "al.", + "ald", + "alf", + "all", "allg", "allg.", "allgemein", "allgemeine", + "also", "am.", "ame", "amsterdam", + "an", "an.", "and", + "angestrebt", + "angestrebter", + "ankauf", + "ankaufs-", + "ankaufsphase", + "anlagebedingungen", "anlagestrategien", + "anlagesusschuss", "anlagevehikels", + "annahmen", + "ans", "ansprechpartners", + "ant", "antagevehikels", + "anteilseigner", "apr", "apr.", + "are", + "area", "ark", + "ars", "art", + "artikel", + "as", + "ase", "asset", + "assetor", "assets", "at", "at.", + "ate", "ath", + "attractive", "auf", "aufl\u00f6sung", + "aufnahme", + "auftakt", "aufwertung", "auf\u2019m", "aug", "aug.", + "aum", + "auschittungsrendite", + "auschu\u0308ttungsrendite", "ausgew\u00e4hlte", + "ausschlie\u00dflich", + "ausschu\u0308ttung", + "ausschu\u0308ttungsintervalle", + "ausschu\u0308ttungsrandite", + "ausschu\u0308ttungsrendite", + "aussch\u00fcttungsintervalle", + "aussch\u00fcttungsrandite", + "aussch\u00fcttungsrendite", + "aussch\u00fcttungsrendites", + "ave", "ax.", "b", "b.", "b.a.", "b.sc", "b.sc.", + "balanced", + "basis", + "baumanagementgebahr", "bb.", "bd", "bd.", + "be", + "bei", "beispielsweise", + "belgium", + "benefits", "ber", "berlin", + "bestandsentwicklung", "bestandsentwicklungen", "betr", "betr.", @@ -749,14 +1015,20 @@ "bhf.", "biol", "biol.", + "bis", "bk.", + "bon", "br.", + "brussels", "bs.", "bsp", "bsp.", "bspw", "bspw.", "bt.", + "build", + "buildings", + "but", "bzgl", "bzgl.", "bzw", @@ -768,27 +1040,49 @@ "ca", "ca.", "cal", + "can", + "capital", + "cbd", "cdu", "cdu/csu", "ce>", + "ced", + "ces", + "cey", + "characteristic", + "che", "chr", "chr.", "cht", "cie", "cie.", "cities", + "city", + "cks", "cl.", + "closed", "closings", "co", "co.", + "collective", + "combines", + "competition", + "considered", + "considering", "core", "core+", "core+/value", + "could", + "country", + "creation", "csu", "cts", + "current", "d", "d'", "d)", + "d,d", + "d,dd", "d,dd%+", "d-", "d-)", @@ -800,19 +1094,26 @@ "d.h.", "d.x", "dX", + "dXxx.\u20ac", "d_d", "d_x", "dam", + "darlehen", "dd", + "dd.dd.dddd", "ddd", + "ddd.ddd", "dddd", "de", "ded", + "deep", + "defined", "dem", "den", "der", "dergleichen", "des", + "deutsche", "deutschland", "deutschlands", "development", @@ -822,22 +1123,30 @@ "dgl.", "di", "di.", + "die", "different", "dipl", "dipl.", "dipl.-ing", "dipl.-ing.", + "dis", + "diversification", + "diversity", + "dividend", "do", "do.", "don", "dr", "dr.", + "drawbacks", "du", "du\u2019s", "dv.", + "dxxx.\u20ac", "d\u00e4nemark", "d\u2019", "e", + "e)-", "e-mail", "e.", "e.V.", @@ -845,17 +1154,23 @@ "e.g", "e.g.", "e.v.", + "eal", "ean", "eb.", "ebd", "ebd.", "ebenda", "ebr", + "ebt", + "economic", "ed.", + "eep", "egr", + "egt", "egy", "ehem", "ehem.", + "eigenkapital", "eigentlich", "eigtl", "eigtl.", @@ -863,34 +1178,56 @@ "eine", "einem", "einen", + "einer", + "einmalige", + "eins", "einw", + "einwohner", + "einzeln", "eit", + "ekt", "el.", + "eld", + "eln", "els", "em.", "en.", + "end", + "ended", "engl", "engl.", "englisch", "enhancing", + "ens", "ent", "entspr", "entspr.", + "eons", "ep.", "ept", "er", "er.", + "erd", + "ere", + "erfolgten", + "erg", "erm", "erm.", + "ern", "err", "ers", "ersten", + "ery", "er\u2019s", "es", + "esg-", + "ess", + "estate", "etc", "etc.", "etr", "ets", + "eur", "europe", "european", "ev", @@ -899,8 +1236,11 @@ "evtl", "evtl.", "exit", + "experienced", "expertise", "exposure", + "externe", + "extract", "ez.", "e\u2019s", "f", @@ -909,24 +1249,38 @@ "fa.", "fam", "fam.", + "fdr", "feb", "feb.", "fen", + "festen", + "festgelegt", "festgelegter", + "fierce", "fil", + "finanzierung", + "finanzierungskonditionen", + "flagship", "fond", "fonds", + "for", + "form", "fr", "fr.", + "france", "frankreich", "franz\u00f6sisch", + "fremdkapital", + "french", "frl", "frl.", "frz", "frz.", + "fs-", "fs.", "fund", "fu\u0308hrende", + "f\u00fcr", "f\u2019m", "g", "g.", @@ -937,6 +1291,10 @@ "geb.", "gebr", "gebr.", + "gebu\u0308hren", + "geb\u00fchren", + "ged", + "gedis", "gegebenenfalls", "gegen\u00fcber", "gegr", @@ -945,8 +1303,11 @@ "gem", "gem.", "gen", + "geographies", "geplantes", + "gepr\u00fcft", "ger", + "gerd", "gesamtrendite", "gf.", "gfs", @@ -956,29 +1317,41 @@ "ggfs.", "gg\u00fc", "gg\u00fc.", + "ght", "gie", "gl.", "good", "gr.", + "grre", "gtl", + "guarantee", "g\u00fc.", "h", "h.", "h.c", "h.c.", + "haltedauer", "halten", "halten-strategie", + "have", "hbf", "hbf.", "hd.", "hed", "hem", + "hen", + "here", "hf.", "hg", "hg.", + "high", "hil", "hinter", "hinter\u2019m", + "hip", + "his", + "hme", + "hotel", "hotels", "hr", "hr.", @@ -1005,12 +1378,18 @@ "i.o.", "i.tr.", "i.v.", + "ial", + "ice", "ich", "ich\u2019s", + "ics", + "ide", "ie.", "ien", "ies", "ig.", + "ige", + "igh", "ihr", "ihr\u2019s", "ii", @@ -1018,11 +1397,14 @@ "iii", "iii.", "il.", + "ild", "ile", "illustration", + "im", "ime", "immobilien", "immobilien-spezialfonds", + "improve", "in", "in.", "inc", @@ -1035,38 +1417,54 @@ "ing", "ing.", "initiatives", + "ink", "inkl", "inkl.", "inklusive", "inrev", + "ins", "insb", "insb.", "insbesondere", + "interesting", + "invastitionsfokus", + "investftionsvolumen", + "investitionen", + "investitions-annahmen", + "investment", "investmentmanagers", "investments", + "investmentzeitraum", + "investor", + "investtionszeltraum", "inw", "io.", "iol", "ion", "ipl", + "ird", "irr", "is", "ise", "isk", "iss", + "it", "ite", "ith", + "its", "ity", "itz", "ium", "iv", "iv.", + "ive", "j", "j.", "jahr", "jahre", "jan", "jan.", + "jedes", "jh", "jh.", "jhd", @@ -1079,17 +1477,26 @@ "jun.", "jur", "jur.", + "j\u00e4hrlich", + "j\u00e4hrliche", "k", "k.", "k.o.", + "kapitalzusagen", "kath", "kath.", "katholisch", "kaufen", + "keine", + "kel", "ket", "key", "kl.", + "klassifizierung", + "kosten", "kt.", + "kte", + "kus", "l", "l'", "l.", @@ -1100,21 +1507,38 @@ "laufzeit", "laut", "le.g", + "leave", "ler", + "less", + "levallois", "level", + "leverage", + "leveraged", + "leveraging", "lg.", + "limited", "lin", "lio", + "liquid", + "liquidity", + "lisbon", + "listed", + "lle", "llg", + "lls", "llt", "llv", + "logistics", "london", + "low", + "lso", "lt", "lt.", "lte", "ltv", "lty", "lue", + "lux-based", "lv.", "l\u00e4nderallokation", "l\u2019", @@ -1128,32 +1552,44 @@ "m.m.", "m.sc", "m.sc.", + "madrid", + "main", + "make", "mal", + "manage", "management", "manager", "market", + "markets", "max", "max.", "maximal", "maximaler", + "means", "men", "mer", + "metropolregianen", "metropolregionen", + "mgallery", "mi", "mi.", + "mic", "million", "min", "min.", "mind", "mind.", + "mindestanlage", "mindestens", "minimal", "minor", "mio", "mio.", "mit", + "mitgliedschaft", "mo", "mo.", + "monate", "monatlich", "mr", "mr.", @@ -1163,6 +1599,7 @@ "mrz.", "mtl", "mtl.", + "must", "mwst", "mwst.", "m\u00e4r", @@ -1174,32 +1611,45 @@ "n.r", "n.y.", "n.y.c.", + "nach", + "nachhaltig", "nachvermietungsstrategie", "name", "nat", "nat.", + "navigate", "nc.", + "nce", + "nch", "ncl", "nd.", "nde", "nds", "ne", + "ned", "nem", "nen", "ner", + "nes", + "netherlands", + "neu", "ng.", "ngl", "ngs", "niederlande", "niv", "nkl", + "no", "nor", "nov", "nov.", "nr", "nr.", + "ns-", "nsb", + "nse", "nts", + "nuremberg", "o", "o.", "o.0", @@ -1213,27 +1663,52 @@ "o.o", "o.\u00e4", "o.\u00e4.", + "o.\u20ac", "o_0", "o_O", "o_o", + "objectives", + "objekt", + "objekten", "of", "of.", + "ofQin", "offen", "offener", + "offers", + "office", + "offices", + "ofqin", "og.", + "ois", "okt", "okt.", "ol.", + "ome", + "on", "ond", + "ons", "ood", + "oom", + "opci", "opco", "ope", + "open", + "open-ended", + "operators", + "opportunities", + "or", + "order", "ore", "orig", "orig.", "original", "orm", + "ors", + "ote", + "outside", "ov.", + "ove", "over", "p", "p.", @@ -1242,51 +1717,92 @@ "p.s", "p.s.", "pCo", + "pan-European", + "pan-european", + "parformanceabh\u00e4ngige", "paris", + "pci", "pco", + "pen", "pers", "pers.", "phil", "phil.", + "pid", "pkt", "pkt.", "pl.", "portfolio", + "potential", "pr.", "premium", + "preservation", + "pricey", + "prime", "prof", "prof.", "profile", + "prognostizierte", + "program", "projects", + "providing", "pt.", "pw.", "q", "q.", "q.e.d", "q.e.d.", + "qin", "quality", + "quote", "r", "r.", "r.i.p.", + "ram", + "rapid", + "rce", + "rd", "rd.", "re", "re+", + "rea", + "real", + "recent", "rechtsform", + "recovery", "red", "red.", + "region", + "regionen", + "remains", "ren", + "rendite-", + "renovierungen", + "rent", + "rents", "rer", "rer.", + "residential", + "respective", + "retail", "rev", + "reversion", + "rid", "rig", + "right", "ris", "risikoprofil", "risk", "rl.", "rm.", + "rms", "rn.", + "rne", "rof", + "room", + "rotterdam", "rr.", + "rre", "rs.", "rsg", "rte", @@ -1307,67 +1823,107 @@ "sb.", "schweden", "sd.", + "sector", + "sectors", + "sed", + "segment", "sen", "sen.", + "sense", "sep", "sep.", "sept", "sept.", "set", "sf.", + "sfdr", + "sg-", "sg.", + "sich", "sie", "sie\u2019s", + "sis", "sitz", "skandinavien", + "small", "so", "so.", + "sobald", "sog", "sog.", + "some", "sp.", "space", + "spain", + "spezial-alf", "spr", "spw", + "sri", "ss.", "st", "st.", + "stabilisieren", + "stabilisierung", "standortaufwertungsstrategie", "standorte", "std", "std.", "stellv", "stellv.", + "steuern", "stil", "str", "str.", "strategie", + "strategies", "strategy", "struktur", + "strukturierungsgebu\u0308hr", + "strukturierungsgeb\u00fchr", + "st\u00e4dten", "sw.", "s\u2019", "t", "t.", "tactical", + "tag", + "tal", + "targeting", + "targets", "tc.", "td.", + "te-", + "ted", + "tee", + "teflimmobilfe)-", "tel", "tel.", "telefonnummer", "ten", + "tenant", "ter", + "terms", "tes", "th.", "the", + "there", + "this", + "through", + "tic", "tig", "til", "time", "tl.", "to", + "top", + "tor", "tr", "tr.", + "try", "tsd", "tsd.", "tur", + "tze", "t\u00e4gl", "t\u00e4gl.", "t\u00e4glich", @@ -1384,23 +1940,36 @@ "u.u.", "u.v.m", "u.v.m.", + "uer", + "ufs", "ug.", + "ugh", + "uid", "ul.", + "uld", + "umliegende", "un.", "und", + "under", + "undertaking", "ung", "univ", "univ.", + "unless", "unter", + "unterstellt", "unter\u2019m", "ur.", "ure", "usf", "usf.", + "uss", + "ust", "usw", "usw.", "uvm", "uvm.", + "u\u0308ber", "u\u2019s", "v", "v.", @@ -1415,9 +1984,16 @@ "v_v", "value", "value-added", + "var", "vel", "ver", + "verbesserungen", "vergleiche", + "vergu\u0308tung", + "verg\u00fctung", + "verkaufs", + "verkaufs-", + "very", "ves", "vgl", "vgl.", @@ -1430,6 +2006,7 @@ "vol", "vol.", "vom", + "von", "vor", "vor\u2019m", "vs", @@ -1438,10 +2015,14 @@ "w", "w.", "wSt", + "walls", "way", "well-established", + "werden", "wertstabile", + "why", "wir", + "wird", "wir\u2019s", "wiss", "wiss.", @@ -1477,24 +2058,35 @@ "xx", "xx.", "xx.x", + "xxXxx", "xxx", + "xxx-", + "xxx-Xxxxx", + "xxx-xxxx", "xxx.", "xxxx", + "xxxx)-", "xxxx)/xxxx", "xxxx+", "xxxx+/xxxx", + "xxxx-", "xxxx-xxx", "xxxx-xxxx", "xxxx-xxxx-xxx", "xxxx.", + "xxxx\u0308xx", + "xxxx\u0308xxxx", "xxxx\u2019x", "xxx\u2019x", "xx\u0308xxxx", "xx\u2019x", + "x\u0308xxx", "x\u2019", "x\ufe35x", "y", "y.", + "years", + "yield", "z", "z.", "z.B.", @@ -1512,14 +2104,23 @@ "ziel-lty", "ziel-netto-irr", "zielanlagestrategie", + "zielm\u00e4rkte", + "zielobjektgr\u00f6\u00dfe", "zielregionfen)/jand", + "zielrendite", "zielsektoren", "zielvolumen", "ziirraiaein", + "zins-", + "zinss\u00e4tze", "zt", + "zu", + "zum", "zw.", + "zwischen", "zzgl", "zzgl.", + "{", "|", "}", "\u00a0", @@ -1549,11 +2150,15 @@ "\u00f6sterr", "\u00f6sterr.", "\u00f6sterreichisch", + "\u00f6\u00dfe", "\u00fc", "\u00fc.", "\u00fcber", "\u00fcbersicht", "\u00fcber\u2019m", + "\u00fcft", + "\u00fchr", + "\u0308hr", "\u0ca0", "\u0ca0_\u0ca0", "\u0ca0\ufe35\u0ca0", @@ -1574,6 +2179,8 @@ "\u2019xxx", "\u2019\u2019", "\u201a", + "\u201c", + "\u201d", "\u20ac", "\u2501", "\u253b", diff --git a/prototypes/arc2_prototype/spacy_service/output/spacy-results.json b/prototypes/arc2_prototype/spacy_service/output/spacy-results.json index d68242e..2017868 100644 --- a/prototypes/arc2_prototype/spacy_service/output/spacy-results.json +++ b/prototypes/arc2_prototype/spacy_service/output/spacy-results.json @@ -1,14 +1,89 @@ [ + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 1 + }, { "label": "RISIKOPROFIL", "entity": "Core and Core+", "page": 4 }, + { + "label": "RISIKOPROFIL", + "entity": "CITIES", + "page": 6 + }, + { + "label": "RISIKOPROFIL", + "entity": "closed-end and open-ended", + "page": 6 + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 6 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,3%", + "page": 6 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "1,0%", + "page": 6 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,9%", + "page": 6 + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 7 + }, + { + "label": "RISIKOPROFIL", + "entity": "Club", + "page": 7 + }, { "label": "RISIKOPROFIL", "entity": "core, core+, value-added", "page": 7 }, + { + "label": "RISIKOPROFIL", + "entity": "Each", + "page": 8 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "57 86 100\neach asset: the BREEAM In Use Part 1 international referential is fully Pollution\n59%", + "page": 8 + }, + { + "label": "RISIKOPROFIL", + "entity": "Land", + "page": 8 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "51%", + "page": 8 + }, + { + "label": "RISIKOPROFIL", + "entity": "C", + "page": 8 + }, + { + "label": "RISIKOPROFIL", + "entity": "Fund\nFund Objective", + "page": 10 + }, { "label": "RISIKOPROFIL", "entity": "Core/Core+", @@ -25,10 +100,50 @@ "page": 10 }, { - "label": "RISIKOPROFIL", - "entity": "UK, DE, BE, NL, LU,", + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "45%", "page": 10 }, + { + "label": "RISIKOPROFIL", + "entity": "CH", + "page": 10 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 10 + }, + { + "label": "Risikoprofil", + "entity": "Cash on Cash: 4% - 5%\nSt\n10 GE: :: Estate Prime Europe", + "page": 10 + }, + { + "label": "RISIKOPROFIL", + "entity": "June", + "page": 11 + }, + { + "label": "RISIKOPROFIL", + "entity": "Lock", + "page": 11 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "55-", + "page": 11 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5-10; 10-50; 50+ ME). Fee only payable on investment called.\nFees For investors committing before 31/", + "page": 11 + }, + { + "label": "RISIKOPROFIL", + "entity": "before", + "page": 11 + }, { "label": "RISIKOPROFIL", "entity": "Core / Core +", @@ -41,7 +156,7 @@ }, { "label": "RISIKOPROFIL", - "entity": "core\n", + "entity": "Long", "page": 12 }, { @@ -49,6 +164,16 @@ "entity": "Term / core+", "page": 12 }, + { + "label": "RISIKOPROFIL", + "entity": "Hold", + "page": 12 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 12 + }, { "label": "RISIKOPROFIL", "entity": "core/core+", @@ -56,78 +181,168 @@ }, { "label": "RISIKOPROFIL", - "entity": "6,4 6,4", + "entity": "Fund\nSees has", + "page": 13 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5,3 16,1", + "page": 13 + }, + { + "label": "Laufzeit", + "entity": "13,6 8,9 12,8 8,0", + "page": 13 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "58,9 58,2 59,8 0,0", + "page": 13 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5th 5th", + "page": 13 + }, + { + "label": "Ausschüttungsrendite", + "entity": "10th 5th\n", + "page": 13 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5,3\n", + "page": 13 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "45%", "page": 13 }, { "label": "RISIKOPROFIL", - "entity": "Country /", + "entity": "Core", + "page": 14 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,17%", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core Excellent", + "entity": "Core", + "page": 14 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "400m Good Very", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core 40", + "entity": "Core", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core 400m", + "entity": "Good New", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core 99m-102", + "entity": "Core", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core 85m-90m", + "entity": "Core 85m-90", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Core 50", + "entity": "June\n", + "page": 14 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "55m", "page": 14 }, { "label": "RISIKOPROFIL", - "entity": "Country /", + "entity": "Core", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "Core Good New", + "entity": "Good New", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "Core 44m-46m", + "entity": "Good", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "Core Good New", + "entity": "Core", + "page": 15 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "59 parking", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "Core CBD New", + "entity": "Leed Platinium", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "Core Good New", + "entity": "City", + "page": 15 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,50%", "page": 15 }, { "label": "RISIKOPROFIL", - "entity": "countries, giving", - "page": 18 + "entity": "Core", + "page": 15 + }, + { + "label": "RISIKOPROFIL", + "entity": "Good New", + "page": 15 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,50%", + "page": 15 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core CBD", + "page": 15 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 15 + }, + { + "label": "RISIKOPROFIL", + "entity": "Good New", + "page": 15 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "52 assets 55 assets", + "page": 17 }, { "label": "RISIKOPROFIL", @@ -139,19 +354,104 @@ "entity": "core/core+", "page": 20 }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "472 1,636", + "page": 20 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3,214 4,846", + "page": 20 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "52 71 62 =RE-=)Seti\nassets Be — Be\nEr \\ ie ‘ulgarie\nRE Leverage 0% 234% 296% 307%", + "page": 20 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "358%", + "page": 20 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "378%", + "page": 20 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "347%", + "page": 20 + }, { "label": "RISIKOPROFIL", - "entity": "D, and", + "entity": "C.", "page": 21 }, { "label": "RISIKOPROFIL", - "entity": "UK, DE, BE, NL, LU,", + "entity": "Fund", + "page": 22 + }, + { + "label": "RISIKOPROFIL", + "entity": "Sarl", + "page": 22 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "| 5%", + "page": 24 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4%", + "page": 24 + }, + { + "label": "Ausschüttungsrendite", + "entity": "| 3%", + "page": 24 + }, + { + "label": "Laufzeit", + "entity": "19\n(4\nma3", + "page": 25 + }, + { + "label": "Risikoprofil", + "entity": "This context of rarity, if it benefits “In white”\nparameters\nlaunches, it exerts upward pressure on facial rents.\nSource!\n30 GE: :: Estate Prime Europe", + "page": 25 + }, + { + "label": "RISIKOPROFIL", + "entity": "Look", "page": 26 }, { "label": "RISIKOPROFIL", - "entity": "core or", + "entity": "High", + "page": 26 + }, + { + "label": "RISIKOPROFIL", + "entity": "Tier", + "page": 26 + }, + { + "label": "RISIKOPROFIL", + "entity": "CH", + "page": 26 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 27 + }, + { + "label": "RISIKOPROFIL", + "entity": "core", "page": 27 }, { @@ -161,37 +461,257 @@ }, { "label": "RISIKOPROFIL", - "entity": "kgCO,e", + "entity": "Each", + "page": 27 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "59%", + "page": 29 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "52%", + "page": 29 + }, + { + "label": "RISIKOPROFIL", + "entity": "kgCO,e/m?.an", "page": 30 }, { "label": "RISIKOPROFIL", - "entity": "C,\n", + "entity": "C", + "page": 31 + }, + { + "label": "Ausschüttungsrendite", + "entity": "3\ncriteria are considered to build this grade:\n- The geolocation of the asset and the resulting predictive scenarios of the climate change ;\n- The devices and characteristics of the asset allowing it to resist to these risks ;\n- The immediate environment of the asset that may include aggravating factors.\nre\n36 |", + "page": 31 + }, + { + "label": "RISIKOPROFIL", + "entity": "CARBONE\nC,\n", "page": 32 }, { "label": "RISIKOPROFIL", - "entity": "KfW, Dwp", + "entity": "Fund\n", + "page": 33 + }, + { + "label": "RISIKOPROFIL", + "entity": "semi-annually", + "page": 33 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5)", + "page": 34 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.02%", + "page": 34 + }, + { + "label": "RISIKOPROFIL", + "entity": "CoC", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.14%", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.40%", + "page": 34 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.31%", + "page": 34 + }, + { + "label": "RISIKOPROFIL", + "entity": "CoC", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.31%", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.26%", + "page": 34 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5) Our sourcing capabilities make us a specialist of European assets’ origination and asset management\nroJmoe\nEnjoy Area: Office 16,970 sqm Forward sale deal,\nParis development to be\nCore Parking", + "page": 35 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "Co-investment between", "page": 35 }, { "label": "RISIKOPROFIL", - "entity": "Bank,", + "entity": "CoC", + "page": 35 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.30%", "page": 35 }, { "label": "RISIKOPROFIL", - "entity": "HSBC, RTE", + "entity": "Core Parking", + "page": 35 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.25%", + "page": 35 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.60%", + "page": 35 + }, + { + "label": "RISIKOPROFIL", + "entity": "3/5", + "page": 36 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 36 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.45%", + "page": 36 + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 36 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.48%", + "page": 36 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "3.22%", + "page": 36 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core Parking", + "page": 36 + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 36 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4/5)", "page": 37 }, { "label": "RISIKOPROFIL", - "entity": "Core WALB (", + "entity": "Core", + "page": 37 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4,78%", "page": 37 }, { "label": "RISIKOPROFIL", - "entity": "Core WALB (", + "entity": "Cash-on-cash", "page": 37 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5.59%", + "page": 37 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 37 + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 37 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5.8%", + "page": 37 + }, + { + "label": "RISIKOPROFIL", + "entity": "5/5", + "page": 38 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 38 + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 38 + }, + { + "label": "RISIKOPROFIL", + "entity": "Core", + "page": 38 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.24%", + "page": 38 + }, + { + "label": "RISIKOPROFIL", + "entity": "Cash-on-cash", + "page": 38 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "4.78%", + "page": 38 + }, + { + "label": "AUSSCHÜTTUNGSRENDITE", + "entity": "5.56%", + "page": 38 } ] \ No newline at end of file