# Generated by ShowAPI OpenAPI generator # source: market/2561 # generated-at: 2026-09-05T12:50:56.038Z openapi: 3.0.3 info: title: 百度云-语言与知识 description: 提供全面、领先的NLP基础模块能力,涵盖词、短语、句子等不同粒度的底层能力,您可将其应用于多种技术和业务方向。 termsOfService: https://www.showapi.com/helpcenter/view#/4019/2 version: 1.0.0 servers: - url: https://route.showapi.com paths: /2561-14: x-pointCode: 14 x-mode: mapping x-read-timeout: 51 x-connect-timeout: 50 post: summary: 文本审核 description: 自动创作、辅助创作、多模态创作。 自动创作:可通过接入数据、配置专属写作模板,快速实现批量和自动生成文章的能力。原接口订购地址:https://cloud.baidu.com/product/textcensoring responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: ret_code: type: number data: type: array items: type: object properties: hits: type: array items: type: object properties: words: type: array items: type: string description: 违规文本关键字 datasetName: type: string description: 违规项目所属数据集名称 probability: type: number description: 不合规项置信度 description: 命中关键词信息 subType: type: number description: |- 审核子类型,此字段需参照type主类型字段决定其含义: 当type=11时subType取值含义: 0:百度官方默认违禁词库 当type=12时subType取值含义: 0:低质灌水、1:暴恐违禁、2:文本色情、3:政治敏感、4:恶意推广、5:低俗辱骂 6:恶意推广-联系方式、7:恶意推广-软文推广、8:广告法审核 当type=13时subType取值含义: 0:自定义文本黑名单 当type=14时subType取值含义: 0:自定义文本白名单 conclusion: type: string description: 审核结果,可取值:合规、不合规、疑似、审核失败 type: type: number description: 审核主类型,11:百度官方违禁词库、12:文本反作弊、13:自定义文本黑名单、14:自定义文本白名单 msg: type: string description: 不合规项描述信息 conclusionType: type: number description: 审核结果类型,可取值1.合规,2.不合规,3.疑似,4.审核失败 description: 不合规/疑似/命中白名单项详细信息。响应成功并且conclusion为疑似或不合规或命中白名单时才返回,响应失败或conclusion为合规且未命中白名单时不返回 conclusion: type: string description: 审核结果,可取值:合规、不合规、疑似、审核失败 conclusionType: type: number description: 审核结果类型,可取值1.合规,2.不合规,3.疑似,4.审核失败 log_id: type: number description: 业务返回体 operationId: 2561_14_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 待审核文本,UTF-8,不可为空,不超过20000字节 required: - ds_id /2561-13: x-pointCode: 13 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 地址识别 description: 针对快递、电商行业中客户在线提交的大量非结构化地址单据,该接口可以帮助精准提取快递填单文本中的姓名、电话、地址信息,通过自然语言处理辅助地址识别做自动补充和纠正,生成标准规范的结构化信息,大幅提升企业处理单据的效率。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number description: | 请求唯一标识码 text: type: string description: | 输入的对话文本内容 items: type: array items: type: object properties: "0": type: object properties: prob: type: number description: | 情绪一级分类标签对应的概率 label: type: string description: | 情绪一级分类标签;pessimistic(负向情绪)、neutral(中性情绪)、optimistic(正向情绪) subitems: type: array items: type: object properties: "0": type: object properties: prob: type: number description: | 情绪二级分类标签对应的概率 label: type: string description: 情绪二级分类标签;客服模型正向(thankful感谢、happy愉快)、客服模型负向(complaining抱怨、angry愤怒);闲聊模型正向(like喜爱、happy愉快)、闲聊模型负向(angry愤怒、disgusting厌恶、fearful恐惧、sad悲伤) replies: type: array items: type: string description: 参考回复话术,中性情绪下该项为空 description: | 二级分析结果数组 description: | 分析结果数组 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_13_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 待识别的文本内容,不超过1000字节 confidence: type: number description: 不设置时默认为-1 required: - ds_id - text /2561-12: x-pointCode: 12 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 文章标签 description: 文本标签服务对文章的标题和内容进行深度分析,输出能够反映文章关键信息的主题、话题、实体等多维度标签以及对应的置信度,该技术在个性化推荐、文章聚合、内容检索等场景具有广泛的应用价值。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: ret_code: type: number items: type: array items: type: object properties: tag: type: string description: 内容标签 score: type: number description: 权重值,取值范围[0,1] description: 分析结果数组 log_id: type: number description: 业务返回体 operationId: 2561_12_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 title: type: string description: 文章标题,最大80字节 content: type: string description: 文章内容,最大65535字节 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - title - content - charset /2561-11: x-pointCode: 11 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 依存句法分析 description: 自动分析文本中的依存句法结构信息,实现对自然语言的精准理解。原接口订购地址:https://cloud.baidu.com/product/nlp_basic responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number description: 随机数,本次请求的唯一标识码 text: type: string description: 原始文本 items: type: array items: type: object properties: "0": type: object properties: id: type: string description: 词的ID word: type: string description: 分好的词 postag: type: string description: 词性 取值范围参考帮助文档 head: type: string description: 词的父节点ID deprel: type: string description: 词与父节点的依存关系 取值范围参考帮助文档 "1": type: object properties: id: type: string word: type: string postag: type: string head: type: string deprel: type: string "2": type: object properties: id: type: string word: type: string postag: type: string head: type: string deprel: type: string ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_11_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 待分析文本,长度不超过256字节 charset: type: string description: "body整体文本内容可以支持GBK和UTF-8两种格式的编码。\t" required: - ds_id - text - charset /2561-10: x-pointCode: 10 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 评论观点抽取 description: 自动抽取和分析评论观点,帮助您实现舆情分析、用户理解,支持产品优化和营销决策。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: items: type: array items: type: object properties: "0": type: object properties: prop: type: string description: 匹配上的属性词 adj: type: string description: 匹配上的描述词 sentiment: type: number description: | 该情感搭配的极性(0表示消极,1表示中性,2表示积极) begin_pos: type: number description: 该情感搭配在句子中的开始位置 end_pos: type: number description: 该情感搭配在句子中的结束位置 abstract: type: string description: 对应于该情感搭配的短句摘要 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_10_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 评论内容,最大10240字节 type: type: number description: 评论行业类型,默认为4(餐饮美食) charset: type: string description: "body整体文本内容可以支持GBK和UTF-8两种格式的编码。\t" required: - ds_id - text - type - charset /2561-9: x-pointCode: 9 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 60 post: summary: 词向量表示 description: 本接口已于2017年5月25日升级,仅支持词向量查询。如果希望查询两个词的相似度,可使用词义相似度。原接口订购地址:https://cloud.baidu.com/product/nlp_basic responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: word: type: string description: 查询词 vec: type: array items: type: string description: 词向量结果表示 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_9_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 word: type: string description: 文本内容,最大64字节 dem: type: number description: 词向量维度。默认值为0(对应1024维),目前仅支持dem=0 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - word - charset /2561-8: x-pointCode: 8 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 情感倾向分析 description: 对包含主观信息的文本进行情感倾向性判断,为口碑分析、话题监控、舆情分析等应用提供帮助。还可使用EasyDL定制训练平台,结合业务场景深度定制高精度情感倾向分析服务。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: text: type: string items: type: array items: type: object properties: "0": type: object properties: sentiment: type: number description: 表示情感极性分类结果,0:负向,1:中性,2:正向 confidence: type: number description: 表示分类的置信度,取值范围[0,1] positive_prob: type: number description: 表示属于积极类别的概率 ,取值范围[0,1] negative_prob: type: number description: 表示属于消极类别的概率,取值范围[0,1] ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_8_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 文本内容,最大2048字节 charset: type: string description: "body整体文本内容可以支持GBK和UTF-8两种格式的编码。\t" required: - ds_id - text - charset /2561-7: x-pointCode: 7 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 文本纠错 description: 识别文本中有错误的片段,进行错误提示并给出正确的建议文本内容。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number description: 请求唯一标识码 item: type: object properties: vec_fragment: type: array items: type: object properties: "0": type: object properties: ori_frag: type: string description: 原片段 begin_pos: type: number description: 起始(长度单位) correct_frag: type: string description: 替换片段 end_pos: type: number description: 结尾(长度单位) description: 替换候选片段信息 score: type: number description: 模型置信度打分 correct_query: type: string description: 纠错后的文本 description: 分析结果 text: type: string ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_7_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 待纠错文本,输入限制511字节 charset: type: string description: "body整体文本内容可以支持GBK和UTF-8两种格式的编码。\t" required: - ds_id - text - charset /2561-6: x-pointCode: 6 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 词法分析 description: 基于大数据和用户行为的分词、词性标注、命名实体识别,定位基本语言元素,消除歧义,支撑自然语言的准确理解。原接口订购地址:https://cloud.baidu.com/product/nlp_basic responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: text: type: string description: | 原始单条请求文本 items: type: array items: type: object properties: "0": type: object properties: byte_length: type: number description: | 字节级length byte_offset: type: number description: | 在text中的字节级offset formal: type: string description: | 词汇的标准化表达,主要针对时间、数字单位,没有归一化表达的,此项为空串 item: type: string description: | 词汇的字符串 ne: type: string description: 命名实体类型,命名实体识别算法使用。词性标注算法中,此项为空串 pos: type: string description: 词性,词性标注算法使用。命名实体识别算法中,此项为空串 uri: type: string description: 链指到知识库的URI,只对命名实体有效。对于非命名实体和链接不到知识库的命名实体,此项为空串 loc_details: type: array items: type: string description: 地址成分,非必需,仅对地址型命名实体有效,没有地址成分的,此项为空数组。 basic_words: type: array items: type: string description: 基本词成分 "1": type: object properties: byte_length: type: number byte_offset: type: number formal: type: string item: type: string ne: type: string pos: type: string uri: type: string loc_details: type: array items: type: string basic_words: type: array items: type: string "2": type: object properties: byte_length: type: number byte_offset: type: number formal: type: string item: type: string ne: type: string pos: type: string uri: type: string loc_details: type: array items: type: string basic_words: type: array items: type: string "3": type: object properties: byte_length: type: number byte_offset: type: number formal: type: string item: type: string ne: type: string pos: type: string uri: type: string loc_details: type: array items: type: string basic_words: type: array items: type: string "4": type: object properties: byte_length: type: number byte_offset: type: number formal: type: string item: type: string ne: type: string pos: type: string uri: type: string loc_details: type: array items: type: string basic_words: type: array items: type: string description: | 词汇数组,每个元素对应结果中的一个词 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_6_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 暂无 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - text - charset /2561-5: x-pointCode: 5 x-mode: mapping x-read-timeout: 5 x-connect-timeout: 5 post: summary: 新闻摘要 description: 基于深度语义分析模型,自动抽取新闻文本中的关键信息并生成指定长度的新闻摘要。可用于热点新闻聚合、新闻推荐、语音播报、APP消息Push等场景。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: summary: type: string description: 摘要结果 ret_code: type: number log_id: type: number description: 请求唯一标识码 description: 业务返回体 operationId: 2561_5_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 title: type: string description: 字符串(限200字符数)字符串仅支持gbk编码,长度需小于200字符数(即400字节),请输入前确认字符数没有超限,若字符数超长会返回错误。标题在算法中具有重要的作用,若文章确无标题,不必输入此参数 content: type: string description: 字符串(限3000字符数以内)字符串仅支持gbk编码,长度需小于3000字符数(即6000字节),请输入前确认字符数没有超限,若字符数超长会返回错误。正文中如果包含段落信息,请使用"\n"分隔,段落信息算法中有重要的作用,请尽量保留 max_summary_len: type: number description: 此数值将作为摘要结果的最大长度。例如:原文长度1000字,本参数设置为150,则摘要结果的最大长度是150字;推荐最优区间:200-500字 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - title - content - max_summary_len /2561-4: x-pointCode: 4 x-mode: mapping x-read-timeout: 20 x-connect-timeout: 20 post: summary: DNN语言模型 description: 依托全网海量优质数据和深度神经网络技术,判断一句话是否符合语言表达习惯,帮助您实现文本分析、纠错、对话等多种语义应用。原接口订购地址:https://cloud.baidu.com/product/nlp_basic responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: text: type: string items: type: array items: type: object properties: "0": type: object properties: word: type: string description: | 句子的切词结果 prob: type: number description: 该词在句子中的概率值,取值范围[0,1] "1": type: object properties: word: type: string prob: type: number "2": type: object properties: word: type: string prob: type: number "3": type: object properties: word: type: string prob: type: number description: 结果集合 ppl: type: number description: | 描述句子通顺的值:数值越低,句子越通顺 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_4_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 文本内容,最大256字节,不需要切词 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - charset /2561-3: x-pointCode: 3 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 对话情绪识别 description: 自动检测用户日常对话文本中蕴含的情绪特征,帮助企业更全面的把握产品体验、监控客户服务质量。原接口订购地址:https://cloud.baidu.com/product/nlp_apply responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number description: | 请求唯一标识码 text: type: string description: | 输入的对话文本内容 items: type: array items: type: object properties: "0": type: object properties: prob: type: number description: | 情绪一级分类标签对应的概率 label: type: string description: | 情绪一级分类标签;pessimistic(负向情绪)、neutral(中性情绪)、optimistic(正向情绪) subitems: type: array items: type: object properties: "0": type: object properties: prob: type: number description: | 情绪二级分类标签对应的概率 label: type: string description: 情绪二级分类标签;客服模型正向(thankful感谢、happy愉快)、客服模型负向(complaining抱怨、angry愤怒);闲聊模型正向(like喜爱、happy愉快)、闲聊模型负向(angry愤怒、disgusting厌恶、fearful恐惧、sad悲伤) replies: type: array items: type: string description: 参考回复话术,中性情绪下该项为空 description: | 二级分析结果数组 description: | 分析结果数组 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_3_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text: type: string description: 待识别情感文本,输入限制512字节 scene: type: string description: default(默认项-不区分场景),talk(闲聊对话-如度秘聊天等),task(任务型对话-如导航对话等),customer_service(客服对话-如电信/银行客服等) charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - text - scene - charset /2561-2: x-pointCode: 2 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 短文本相似度 description: 依托全网海量优质数据和深度神经网络技术,为您提供高精度的短文本相似度服务,帮助快速实现推荐、检索、排序等应用。原接口订购地址:https://cloud.baidu.com/product/nlp_basic responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number description: 随机数,请求唯一标识码 texts: type: object properties: text_1: type: string text_2: type: string score: type: number description: 似度结果取值(0,1],分数越高说明相似度越高 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_2_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 text_1: type: string description: 待比较文本1,最大512字节 text_2: type: string description: 待比较文本2,最大512字节 model: type: string description: 默认为"ERNIE" charset: type: string description: "body整体文本内容可以支持GBK和UTF-8两种格式的编码。\t" required: - ds_id - text_1 - text_2 /2561-1: x-pointCode: 1 x-mode: mapping x-read-timeout: 50 x-connect-timeout: 50 post: summary: 文章分类 description: |- 原接口订购地址:https://cloud.baidu.com/product/nlp_apply。对文章按照内容类型进行自动分类,首批支持娱乐、体育、科技等26个主流内容类型,为文章聚类、文本内容分析等应用提供基础技术支持。 目前支持的一级粗粒度分类类目如下:1、国际 2、体育 3、娱乐 4、社会 5、财经 6、时事 7、科技 8、情感 9、汽车 10、教育 11、时尚 12、游戏 13、军事 14、旅游 15、美食 16、文化 17、健康养生 18、搞笑 19、家居 20、动漫 21、宠物 22、母婴育儿 23、星座运势 24、历史 25、音乐 26、综合。 responses: "200": description: 成功响应 content: application/json: schema: allOf: - $ref: "#/components/schemas/ShowapiResEnvelope" - type: object properties: showapi_res_body: type: object properties: log_id: type: number item: type: object properties: lv2_tag_list: type: array items: type: object properties: "0": type: object properties: score: type: number description: 类别标签对应得分,范围0-1 tag: type: string description: 类别标签 "1": type: object properties: score: type: number tag: type: string "2": type: object properties: score: type: number tag: type: string description: 二级分类结果 lv1_tag_list: type: array items: type: object properties: "0": type: object properties: score: type: number tag: type: string description: 一级分类结果(唯一) description: 分析结果数组 ret_code: type: number description: showapi的调用标识,并非数据源返回字段,调用失败时无该字段 description: 业务返回体 operationId: 2561_1_POST parameters: [] requestBody: content: application/x-www-form-urlencoded: schema: type: object properties: ds_id: type: string description: 数据源 title: type: string description: 文章标题,最大80字节 content: type: string description: 文章内容,最大65535字节 charset: type: string description: body整体文本内容可以支持GBK和UTF-8两种格式的编码。 required: - ds_id - title - content components: securitySchemes: AppKeyAuth: type: apiKey in: query name: appKey description: 从 ShowAPI 控制台获取的 appKey,管理地址:https://www.showapi.com/console#/myApp schemas: ShowapiResEnvelope: type: object description: ShowAPI 统一返回包裹(业务数据位于 showapi_res_body) properties: showapi_res_code: type: integer description: API 返回的状态码 showapi_res_error: type: string description: API 返回的错误信息 showapi_res_id: type: string description: API 请求的唯一标识 showapi_fee_num: type: integer description: API 调用计费次数 security: - AppKeyAuth: [] externalDocs: url: https://www.showapi.com/apiGateway/view/2561?tab=book x-apiCode: "2561" x-is-own: false x-is-op: false