公开(公告)号：WO2020234673A1

公开(公告)日：2020-11-26

申请号：PCT/IB2020/054007

申请日：2020-04-28

Applicant: THOMSON REUTERS ENTERPRISE CENTRE GMBH ,  EKMEKCI, Berk

Inventor： EKMEKCI, Berk ,  HAGERMAN, Eleanor ,  HOWALD, Blake

IPC: G06F16/738 ,  G06F16/953 ,  G06F40/10 ,  G06F40/20 ,  G06F40/295 ,  G06Q50/10 ,  G06Q50/26

Abstract: In some aspects, a method includes extracting sentences from data corresponding to documents. Each extracted sentence includes at least one matched pair (a keyword from a first or second keyword set and an entity from an entity set). The method includes ordering the plurality of extracted sentences based on a distance between a respective keyword and a respective entity in each extracted sentence. The method includes identifying a first type and a second type of extracted sentences from the ordered plurality of extracted sentences. Sentences having the first type include keywords of the first keyword set. Sentences having the second type include keywords of the second keyword set. The method includes generating an extracted summary including at least one sentence having the first type and at least one sentence having the second type, intermixed based on a predetermined order rule set. The method includes outputting the extracted summary.

公开(公告)号：WO2020233364A1

公开(公告)日：2020-11-26

申请号：PCT/CN2020/087479

申请日：2020-04-28

Applicant: 深圳壹账通智能科技有限公司

Inventor： 余瑾 ,  肖敏 ,  郁国荣 ,  胡庆瑜

IPC: H04L29/08 ,  G06F16/953

Abstract: 本申请揭示了一种资源处理平台的确认方法、装置、电子设备和介质。该方法包括：接收资源处理请求，所述资源处理请求具有选择条件关键词；获取多个资源处理平台的标签；确定所述多个资源处理平台中标签与所述选择条件关键词匹配的资源处理平台，作为候选资源处理平台；根据与资源处理平台对应的处理成功计数器的计数值以及处理失败计数器的计数值，确定各候选资源处理平台的历史处理成功率；根据所述历史处理成功率，从所述多个候选资源处理平台中确定目标资源处理平台；将所述资源处理请求分配到该目标资源处理平台。本申请实施例在多资源处理平台系统中优化了对资源处理平台的选择。

公开(公告)号：WO2020147259A1

公开(公告)日：2020-07-23

申请号：PCT/CN2019/091529

申请日：2019-06-17

Applicant: 平安科技(深圳)有限公司

Inventor： 杨晟 ,  陈爽 ,  陈源

IPC: G06F16/951 ,  G06F16/953 ,  G06K9/62

Abstract: 本申请属于计算机技术领域，尤其涉及一种用户画像方法、装置、计算机可读存储介质及终端设备。所述方法获取用户在各个评估维度上的特征信息，并根据所述特征信息构造所述用户的特征向量；从预设的历史用户信息数据库中选取N个训练样本，并组成训练样本集合；将预设的分类器集合中的各个分类器的各种排列顺序进行遍历，根据所述用户的特征向量和所述训练样本集合分别计算各种排列顺序的样本平均距离；从各种排列顺序中选取样本平均距离最小的一种排列顺序作为优选路径，并根据所述用户在所述优选路径中经各个分类器处理得到的标签值构造所述用户的标签向量。在前的分类器的结果会参与到在后的分类器的处理之中，大大提升了用户画像的准确率。

公开(公告)号：WO2020143314A1

公开(公告)日：2020-07-16

申请号：PCT/CN2019/118080

申请日：2019-11-13

Applicant: 平安科技(深圳)有限公司

Inventor： 杨坤 ,  许开河 ,  王少军

IPC: G06F16/953 ,  G06F16/95

Abstract: 一种基于搜索引擎的问答方法、装置、存储介质及计算机设备，该方法包括：获取用户输入的目标问题（S102）；确定目标问题的关键词（S104）；根据关键词从搜索引擎中搜索到多个搜索结果（S106）；计算多个搜索结果中每个搜索结果与关键词的匹配度（S108）；将匹配度大于或等于预设值的搜索结果作为候选答案（S110）；判断候选答案的类型是否是文献类型（S112）；如果候选答案的类型是文献类型，则根据预设算法解析候选答案，得到目标问题的答案（S114）；如果候选答案的类型不是文献类型，则确定候选答案为目标问题的答案（S116）。所述方法解决了聊天机器人应答能力差的问题。

公开(公告)号：WO2020024908A1

公开(公告)日：2020-02-06

申请号：PCT/CN2019/098194

申请日：2019-07-29

Applicant: 上海点融信息科技有限责任公司

Inventor： 肖诗源

IPC: G06F16/953 ,  G06F21/60

Abstract: 本发明内容公开了一种用于在区块链即服务平台上搜索数据的方法，该方法包括：A.经由超文本传输协议接口接收搜索请求；B.在与所述区块链即服务平台通信连接的数据库中搜索与所述搜索请求相匹配的索引，其中，所述数据库中存储的索引包括根据区块链数据所创建的索引；C.基于搜索到的索引中的统一资源定位地址生成搜索结果网页；D.返回与所述搜索请求相关联的搜索结果网页。利用本发明内容的方法既能够满足区块链组织者向其他用户共享有效值信息的需求，也能够满足用户对区块链中的数据进行有效搜索的需求。

公开(公告)号：WO2020014350A1

公开(公告)日：2020-01-16

申请号：PCT/US2019/041189

申请日：2019-07-10

Applicant: HOME DEPOT INTERNATIONAL, INC.

Inventor： LARCHEV, Gregory ,  MOORE, Jared ,  ZHAO, Rongkai ,  CASTRILLON, Felipe ,  WANG, Chao

IPC: G06F16/93 ,  G06F16/953 ,  G06F16/9532 ,  G06F16/24 ,  G06F16/242 ,  G06F16/245 ,  G06F16/2453

Abstract: Systems and methods for providing suggestions responsive to search queries for a search engine are disclosed. Such suggestions may include one or more related search queries and/or a spell correction. Related search queries may be provided by converting the search query into a document vector space, determining documents that are similar to the query in the vector space, and determining prior search queries to which those similar documents are responsive. Spell corrections may be provided by comparing n-tuple word combinations in the search query to a library of correct n-tuple word combinations and making appropriate corrections.

公开(公告)号：WO2019235791A1

公开(公告)日：2019-12-12

申请号：PCT/KR2019/006655

申请日：2019-06-03

Applicant: 삼성전자 주식회사

Inventor： 슈드후리마이낙 ,  샤르마아비셱

IPC: G06F16/953 ,  G06F16/9032 ,  G06F16/2457

Abstract: 정보 처리 디바이스가 IoT(the internet of Things) 디바이스를 이용하여 정보를 처리하는 방법에 있어서, 사용자로부터 웹 검색 쿼리를 수신하는 단계, 웹 검색 쿼리와 관련된 적어도 하나의 IoT 디바이스의 컨텍스트 정보를 불러오는 단계, 웹 검색 쿼리 및 적어도 하나의 IoT 디바이스의 컨텍스트 정보를 포함하는 합성 웹 검색 쿼리를 자동으로 생성하는 단계 및 합성 웹 검색 쿼리에 대한 검색 결과를 이용하여 적어도 하나의 IoT 디바이스에 대하여 적용할 제어를 결정하는 단계를 포함하는 정보 처리 방법이 제공된다.

公开(公告)号：WO2023081607A1

公开(公告)日：2023-05-11

申请号：PCT/US2022/078915

申请日：2022-10-28

Applicant: VIDEOXRM INC.

Inventor： BAKER, David N.

IPC: G06F16/45 ,  G06F16/9536 ,  G06F16/953 ,  G06N20/00

Abstract: This document presents methods, systems, and apparatuses for self-building hierarchically indexed multimedia databases and product and service-hierarchy databases that include multiple branches and multiple trees of nodes. The databases hierarchically organize video, audio, and documents per node. The documents can be architectural plans, investor presentations, technical specifications, product or service guides, market research reports), news, messages, industry information, regulatory status, licensing, blogs, etc. in some embodiments, the databases disclosed organize and track company market performance and stock investment information for issuers and inventors based on the products and services produced and offered by each competitor. The databases also organize and track podcasts-by-node, messages-by-node, text, voice messages-by-node, and voice calls-by-node.

公开(公告)号：WO2023040230A1

公开(公告)日：2023-03-23

申请号：PCT/CN2022/082281

申请日：2022-03-22

Applicant: 北京百度网讯科技有限公司

Inventor： 余文利 ,  杨国强 ,  刘伟 ,  张博

IPC: G06F16/953 ,  G06F16/951 ,  G06F16/958

Abstract: 公开了数据评估方法、评估模型的训练方法、装置、电子设备以及存储介质，涉及计算机技术领域，尤其涉及智能搜索、深度学习技术领域。具体实现方案为：响应于用于识别待识别索引数据的质量的请求，获取与待识别索引数据相对应的目标网页的目标关联数据（S210），其中，目标网页为未知网页内容的网页，目标关联数据表征与待识别索引数据相对应的目标网页的质量；以及基于目标关联数据，得到针对待识别索引数据的质量评估结果（S220）。

公开(公告)号：WO2022268808A1

公开(公告)日：2022-12-29

申请号：PCT/EP2022/066874

申请日：2022-06-21

Applicant: METACLUSTER LT, UAB

Inventor： JURAVICIUS, Martynas ,  KUKSTA, Andrius

IPC: G06F16/35 ,  G06F16/951 ,  G06V10/82 ,  G06F16/953 ,  G06F18/2178 ,  G06F18/24155 ,  G06N20/00 ,  G06N20/10 ,  G06N20/20 ,  G06N3/08 ,  G06N5/01 ,  G06N7/01 ,  G06V10/464

Abstract: Advanced response processing in web data collection discloses processor-implemented apparatuses, methods, and systems of processing unstructured raw HTML responses collected in the context of a data collection service, the method comprising, in one embodiment, receiving raw unstructured HTML documents and extracting text data with associated meta information that may comprise style and formatting information. In some embodiments data field tags and values may be assigned to the text blocks extracted, classifying the data based on the processing of Machine Learning algorithms. Additionally, blocks of extracted data may be grouped and re-grouped together and presented as a single data point. In another embodiment the system may aggregate and present the text data with the associated meta information in a structured format. In certain embodiments the Machine Learning model may be a model trained on a pre-created training data set labeled manually or in an automatic fashion.