{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "chinese-medical-dialogue-data",
  "name": "Chinese-medical-dialogue-data（Toyhom）",
  "summary": {
    "zh": "许可证声明：宽松（MIT）；本站处理：只链接原出处。许可证宽松，但有来源风险：来源未说明，无法判断来源版权；只链接原出处。",
    "en": "License: permissive (MIT); Mdexa hosting: link-only. License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Department-specific consultation QA",
    "zh": "分科问诊问答"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "792,099条：内科220,606、妇产科183,751、外科115,991、儿科101,602、男科94,596、肿瘤科75,553",
    "measures": [
      {
        "value": 792099,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "total"
      },
      {
        "value": 220606,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "internal medicine"
      },
      {
        "value": 183751,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "obstetrics and gynecology"
      },
      {
        "value": 115991,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "surgery"
      },
      {
        "value": 101602,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "pediatrics"
      },
      {
        "value": 94596,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "andrology"
      },
      {
        "value": 75553,
        "unit": "qa-pairs",
        "qualifier": "exact",
        "scope": "oncology"
      }
    ]
  },
  "publisher": "Toyhom",
  "year": {
    "value": null,
    "raw": "未标明"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "MIT",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "MIT LICENSE file in a repository that holds only data (snapshot s03: root contains Data_数据, LICENSE, README.md and a sample CSV)",
      "zh": "只存放数据的仓库里的 MIT LICENSE 文件（快照 s03：根目录只有 Data_数据、LICENSE、README.md 与样例 CSV）"
    },
    "evidence": [
      {
        "location": "repo-sidebar",
        "location_detail": {
          "en": "GitHub repository sidebar: MIT; no terms of use on the page",
          "zh": "GitHub 仓库侧栏：MIT；页面无使用条款"
        },
        "excerpt": "MIT License\nCopyright (c) 2019 Toyhom",
        "spdx": "MIT",
        "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证宽松，但有来源风险：来源未说明，无法判断来源版权；只链接原出处。",
    "en": "License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only."
  },
  "signoff": null,
  "repo_license": {
    "spdx": "MIT",
    "source": "license-file",
    "verified": true,
    "snapshot_id": "s02",
    "url": "https://github.com/Toyhom/Chinese-medical-dialogue-data",
    "data_only": true,
    "data_only_snapshot": "s03"
  },
  "risk_flags": [
    "unknown-provenance"
  ],
  "provenance": {
    "source_description": {
      "en": "The page does not state the data source",
      "zh": "页面未写数据来源"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Data source not stated; whether the MIT license can cover the original QA content cannot be judged",
      "zh": "数据来源未写，MIT 许可证是否有权覆盖原始问答内容无法判断"
    },
    {
      "en": "Other projects (the BianQue corpus) cite it as an open QA collection",
      "zh": "其他项目（扁鹊语料）将其作为开源问答集合引用"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/Toyhom/Chinese-medical-dialogue-data"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified-no-license-statement",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "data_format",
      "value": "csv",
      "basis": "author-stated",
      "excerpt": "### 每个文件夹下有一个csv文件，其中的数据格式为:",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "author-stated",
      "excerpt": "在ChatGLM-6B上微调的结果，随机选择了1/30的数据进行微调，下表为评估结果。",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "Single-turn QA pairs.",
        "zh": "单轮问答对"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-size",
      "note": {
        "zh": "覆盖内科、妇产科、外科、儿科、男科、肿瘤科六个科室",
        "en": "Six departments"
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Recorded the code repository license separately; it is not treated as a data license statement.",
        "zh": "单独记录代码仓库许可证，不视为数据许可声明。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status changed from unstated to permissive: LICENSE file in a data-only repository counts as a data license statement; added unknown-provenance (README does not state the data source).",
        "zh": "许可状态由未声明改为宽松：只存放数据的仓库里的 LICENSE 文件算数据许可声明；新增 unknown-provenance（README 未写数据来源）。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 4 (2 stated by the authors with excerpts, 2 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 4 个（作者声明 2 个，附逐字摘录；据内容推断 2 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: multi-specialty(inferred).",
        "zh": "新增专科标签：multi-specialty(inferred)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "github",
    "repo_id": "Toyhom/Chinese-medical-dialogue-data",
    "source": {
      "api_url": "https://api.github.com/repos/Toyhom/Chinese-medical-dialogue-data",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/Toyhom/Chinese-medical-dialogue-data",
        "evidence": {
          "excerpt": "git clone https://github.com/YOUR-USERNAME/YOUR-REPOSITORY",
          "doc": "github-clone",
          "url": "https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": null,
      "last_modified": "2023-08-18T05:34:28Z",
      "default_branch": "master"
    },
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": [
      "the platform publishes no checksum for these files; none was computed (we do not download data files)"
    ]
  },
  "_links": {
    "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：ChatMed_Consult_Dataset (https://mdexa.com/zh/datasets/chatmed-consult-dataset/)；DISC-Med-SFT (https://mdexa.com/zh/datasets/disc-med-sft/)；Huatuo-26M (https://mdexa.com/zh/datasets/huatuo-26m/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "ChatMed_Consult_Dataset",
        "url": "https://mdexa.com/zh/datasets/chatmed-consult-dataset/",
        "json": "https://mdexa.com/zh/datasets/chatmed-consult-dataset.json"
      },
      {
        "name": "DISC-Med-SFT",
        "url": "https://mdexa.com/zh/datasets/disc-med-sft/",
        "json": "https://mdexa.com/zh/datasets/disc-med-sft.json"
      },
      {
        "name": "Huatuo-26M",
        "url": "https://mdexa.com/zh/datasets/huatuo-26m/",
        "json": "https://mdexa.com/zh/datasets/huatuo-26m.json"
      }
    ]
  }
}