METHOD FOR KNOWLEDGE EXTRACTION THROUGH DATA MINING
    61.
    发明申请
    METHOD FOR KNOWLEDGE EXTRACTION THROUGH DATA MINING 审中-公开
    数据挖掘中提取知识的方法

    公开(公告)号:WO2015021404A3

    公开(公告)日:2015-11-12

    申请号:PCT/US2014050381

    申请日:2014-08-08

    Applicant: SYSTAMEDIC INC

    Abstract: The disclosed embodiments relate to data mining methods for determining economically valuable cause effect relationships between objects and properties associated with objects using co-occurrence frequency measurements of semantic terms characterizing observations of properties., effects or behaviors of objects in different environments and using these measurements as object descriptors in calculations determining object similarities. Specifically, these methods may be used to identify new indications of medicines, identify biomarkers associated with disease, identify biomarkers associated with drug effects, quantify disease diagnosis, identify novel drug targets, identify pharmacologic equivalencies of medicines, identify pharmacologic equivalencies between medicines and traditional medicines, identify pharmacologic equivalencies between medicines and Natural products, identify equivalencies between alternate medical procedures, identify risk benefit profiles of medicine combinations, identify targets for antibodies, identify synergies between medicines, identify Side effects of medicines, identify risks of experimental medicines, identify functions of biological networks.

    Abstract translation: 所公开的实施例涉及用于使用语义术语的共现频率测量来确定对象和与对象相关联的属性之间的经济上有价值的因果效应关系的数据挖掘方法,所述语义术语表征对属性的观察,不同环境中的对象的效果或行为并且使用这些测量作为 计算中的对象描述符确定对象的相似性。 具体而言,这些方法可用于鉴别药物的新适应症,鉴定与疾病相关的生物标志物,鉴定与药物作用相关的生物标志物,量化疾病诊断,确定新的药物靶点,确定药物的药理等效性,确定药物与传统药物之间的药理等效性 ,确定药物与天然产品之间的药理学等同性,确定替代医疗程序之间的等效性,确定药物组合的风险效益概况,确定抗体的目标,确定药物之间的协同作用,确定药物的副作用,确定实验药物的风险, 生物网络。

    LEARNING MULTIMEDIA SEMANTICS FROM LARGE-SCALE UNSTRUCTURED DATA
    62.
    发明申请
    LEARNING MULTIMEDIA SEMANTICS FROM LARGE-SCALE UNSTRUCTURED DATA 审中-公开
    从大规模的非结构化数据学习多媒体语义

    公开(公告)号:WO2015167942A1

    公开(公告)日:2015-11-05

    申请号:PCT/US2015/027408

    申请日:2015-04-24

    CPC classification number: G06F17/30705 G06F17/30675 G06F17/30864 G06N99/005

    Abstract: Systems and methods for learning topic models from unstructured data and applying the learned topic models to recognize semantics for new data items are described herein. In at least one embodiment, a corpus of multimedia data items associated with a set of labels may be processed to generate a refined corpus of multimedia data items associated with the set of labels. Such processing may include arranging the multimedia data items in clusters based on similarities of extracted multimedia features and generating intra-cluster and inter-cluster features. The intra-cluster and the inter-cluster features may be used for removing multimedia data items from the corpus to generate the refined corpus. The refined corpus may be used for training topic models for identifying labels. The resulting models may be stored and subsequently used for identifying semantics of a multimedia data item input by a user.

    Abstract translation: 本文描述了用于从非结构化数据学习主题模型并应用所学习的主题模型以识别新数据项的语义的系统和方法。 在至少一个实施例中,可以处理与一组标签相关联的多媒体数据项的语料库,以生成与该组标签相关联的多媒体数据项的精简语料库。 这种处理可以包括基于提取的多媒体特征的相似性来排列多媒体数据项,并且生成集群内和集群间特征。 集群内和集群间特征可用于从语料库中移除多媒体数据项以产生精细语料库。 精致的语料库可用于训练用于识别标签的主题模型。 所得到的模型可以被存储并随后用于识别由用户输入的多媒体数据项的语义。

    METHOD AND SYSTEM FOR GENERATING A DEFINITION OF A WORD FROM MULTIPLE SOURCES
    63.
    发明申请
    METHOD AND SYSTEM FOR GENERATING A DEFINITION OF A WORD FROM MULTIPLE SOURCES 审中-公开
    用于生成来自多个来源的词的定义的方法和系统

    公开(公告)号:WO2015162464A1

    公开(公告)日:2015-10-29

    申请号:PCT/IB2014/065542

    申请日:2014-10-22

    Abstract: There is provided a method of performing an on-line definition of a first word, the first word received from a user of an electronic device via a communication network. The method can be executed at a server. The method comprises: obtaining a first definition set from a first source, the first definition set being based on the first word; obtaining a second definition set from a second source, the second definition set being based on the first word; parsing the first definition set to obtain individual first set words; parsing the second definition set to obtain individual second set words; organizing the individual first set words into at least one definition cluster; causing the electronic device to display to the user at least the first cluster.

    Abstract translation: 提供了一种通过通信网络从电子设备的用户接收的第一个字执行第一个字的在线定义的方法。 该方法可以在服务器上执行。 该方法包括:从第一源获得第一定义集,所述第一定义集合基于所述第一字; 从第二源获得第二定义集合,所述第二定义集合基于所述第一字; 解析第一个定义集以获得单个的第一个集合的单词; 解析第二定义集以获得单独的第二集合词; 将至少一个定义集群中的个体第一集合单词组织起来; 使得所述电子设备至少向所述用户显示所述第一群集。

    DETERMINING PREFERRED COMMUNICATION EXPLANATIONS USING RECORD-RELEVANCY TIERS
    64.
    发明申请
    DETERMINING PREFERRED COMMUNICATION EXPLANATIONS USING RECORD-RELEVANCY TIERS 审中-公开
    使用记录相关性来确定优选的通信解释

    公开(公告)号:WO2015094158A1

    公开(公告)日:2015-06-25

    申请号:PCT/US2013/075344

    申请日:2013-12-16

    Abstract: In one example of the disclosure, data indicative of a word or phrase communicated during a meeting including a plurality of participants is obtained. For each participant, records electronically accessible to the participant are identified, and each record is associated with a tier from a hierarchy of record-relevancy tiers. A set of explanations for the communication and associated scores is identified, including for each participant, beginning with a most relevant tier, searching the records accessible to the participant tier by tier until an explanation is identified, and assigning a score to the explanation according to the tier associated with the record in which the explanation is found. A preferred explanation for the communication is determined based upon the scores, and a display of the preferred explanation is caused.

    Abstract translation: 在本公开的一个示例中,获得指示在包括多个参与者的会议期间传送的单词或短语的数据。 对于每个参与者,识别参与者可电子访问的记录,并且每个记录与记录相关层级别的层相关联。 确定一组关于通信和相关分数的解释,包括对于每个参与者,从最相关的层次开始,按层次搜索参与者层次可访问的记录,直到识别出解释,并且根据 与找到解释的记录相关联的层。 基于分数确定通信的优选说明,并且引起优选说明的显示。

    METHOD AND APPARATUS FOR SEARCH
    65.
    发明申请
    METHOD AND APPARATUS FOR SEARCH 审中-公开
    搜索方法和设备

    公开(公告)号:WO2015078273A1

    公开(公告)日:2015-06-04

    申请号:PCT/CN2014/090370

    申请日:2014-11-05

    Inventor: LIU, Xiaojun

    CPC classification number: G06F17/30622 G06F17/30675 G06F17/30864

    Abstract: Methods and apparatuses for search are provided and related to the field of search technology. A method may include: performing term segmentation for grabbed documents to count a term frequency of each term, the term frequency of the term representing a number of the grabbed documents containing the term; generating a high frequency term inverted index and a low frequency term inverted index respectively, wherein the high frequency term inverted index contains terms having a term frequency higher than a predefined threshold, and the low frequency term inverted index contains terms having a term frequency not higher than the predefined threshold; and loading the high frequency term inverted index and the low frequency term inverted index respectively to different retrieval modules, the different retrieval modules respectively corresponding to mutually independent storage devices.

    Abstract translation: 提供搜索方法和设备,并与搜索技术领域相关。 一种方法可以包括:对被抓取的文档执行术语分段以对每个术语的术语频率进行计数,该术语的术语频率表示包含术语的被抓取文档的数量; 分别产生高频项反转索引和低频项反转索引,其中高频项反向索引包含具有高于预定义阈值的项频率的项,低频项反向索引包含术语频率不高的项 超过预定阈值; 并将高频项倒置指数和低频项倒置指数分别加载到不同的检索模块,不同的检索模块分别对应于相互独立的存储设备。

    NATURAL LANGUAGE SEARCH RESULTS FOR INTENT QUERIES
    66.
    发明申请
    NATURAL LANGUAGE SEARCH RESULTS FOR INTENT QUERIES 审中-公开
    自然语言搜索结果的INTETIC QUERIES

    公开(公告)号:WO2014197227A1

    公开(公告)日:2014-12-11

    申请号:PCT/US2014/039354

    申请日:2014-05-23

    Applicant: GOOGLE INC.

    Abstract: Systems and methods provide natural language search results to clearintent queries. To provide the natural language search results, a system may parse a document from an authoritative source to generate at least one headingtext pair, the text appearing under the heading in the document. The system may assign a topic and a question category to the heading-text pair and store the heading-text pair in a data store keyed by the topic and the question category. The system determines that a query corresponds to the topic and the question category, and provides the heading-text pair as a natural language search result for the query. In some implementations, the text portion of the heading-text pair may be a paragraph or a list of items and the natural language search result may be provided with conventional snippet-based search results in response to the query.

    Abstract translation: 系统和方法提供自然语言搜索结果以清除任意查询。 为了提供自然语言搜索结果,系统可以从权威来源解析文档以生成至少一个标题文本对,该文本出现在文档中的标题下。 该系统可以向标题文本对分配主题和问题类别,并将标题文本对存储在由主题和问题类别键入的数据存储中。 系统确定查询对应于主题和问题类别,并将标题文本对作为查询的自然语言搜索结果。 在一些实现中,标题文本对的文本部分可以是项目的段落或列表,并且响应于查询可以向自然语言搜索结果提供常规的基于片段的搜索结果。

    METHOD OF CALCULATING A SCORE OF A MEDICAL SUGGESTION AS A SUPPORT IN MEDICAL DECISION MAKING
    67.
    发明申请
    METHOD OF CALCULATING A SCORE OF A MEDICAL SUGGESTION AS A SUPPORT IN MEDICAL DECISION MAKING 审中-公开
    计算医疗建议评分作为医疗决策支持的方法

    公开(公告)号:WO2014135699A3

    公开(公告)日:2014-11-06

    申请号:PCT/EP2014054502

    申请日:2014-03-07

    Applicant: MEDESSO GMBH

    CPC classification number: G06F19/345 G06F17/3064 G06F17/30675 G16H50/20

    Abstract: A method for generating a medical suggestion useful for supporting a process of medical decision making is presented. A database with a particular, advantageous structure and content allows for the efficient evaluation of received known medical facts based on a set based processing and calculation. Thus, a digital, automatic, and holistic method generating a medical suggestion is provided, which increases the reliability of the selected medical suggestion which is provided to the user as most probable. The structure of the herein provided database provides for maintenance advantages of the database as the complexity is reduced and single structures of the database are manageable and easily understandable. A corresponding medical decision support system is presented as well.

    Abstract translation: 提出了一种生成有助于支持医学决策过程的医学建议的方法。 具有特定的,有利的结构和内容的数据库允许基于基于集合的处理和计算来有效地评估所接收的已知医疗事实。 因此,提供了产生医学建议的数字,自动和全面的方法,这增加了以最可能的方式提供给用户的所选医疗建议的可靠性。 本文提供的数据库的结构提供了数据库的维护优势,因为复杂性降低,数据库的单个结构可以管理和易于理解。 还提出了相应的医疗决策支持系统。

    SKILLS ENDORSEMENTS
    68.
    发明申请
    SKILLS ENDORSEMENTS 审中-公开
    技能支持

    公开(公告)号:WO2014074607A3

    公开(公告)日:2014-07-03

    申请号:PCT/US2013068763

    申请日:2013-11-06

    Applicant: LINKEDIN CORP

    Abstract: Disclosed in some examples is a method comprising determining a first set of high ranking skills, the first set containing skills possessed by a member of the social networking service based upon the member's user profile; determining a second set of high ranking skills, the second set containing skills for a second member of the social networking service based on the second member's user profile; determining a third set of high ranking skills, the third set being the intersection between the first and second set of high ranking skills; and suggesting one or more of the skills in the third set of high ranking skills to the member for endorsement of the second member with respect to that skill.

    Abstract translation: 在一些示例中公开了一种方法,包括:确定第一组高级技能,第一组包含社交网络服务的成员基于成员的用户简档拥有的技能; 确定第二组高级技能,所述第二组包含基于所述第二成员的用户简档的所述社交网络服务的第二成员的技能; 确定第三组高排位技能,第三组是高排技能的第一和第二组之间的交集; 并向成员提出第三组高级技能中的一项或多项技能,以便对第二名成员进行相关技能的认可。

    实时检索信息获取方法、装置及服务器

    公开(公告)号:WO2014067298A1

    公开(公告)日:2014-05-08

    申请号:PCT/CN2013/080071

    申请日:2013-07-25

    Inventor: 李梦凡

    CPC classification number: G06F17/30675 G06F17/30

    Abstract: 本发明提供了一种实时检索信息获取方法,所述方法包括:获取实时检索请求中的检索关键词以及检索目标时间;通过数据倒排索引中的时间跳表获取与所述检索目标时间对应的倒排块;根据所述检索关键词在与所述检索目标时间对应的倒排块中进行检索,得到所述实时检索请求的检索结果。本发明还提供了一种实时检索装置以及服务器。采用本发明,实现快速的实时数据检索,进而可以实现有限成本下的数据分布趋势图的实时获取。

    フォレンジックシステムおよびフォレンジック方法並びにフォレンジックプログラム
    70.
    发明申请
    フォレンジックシステムおよびフォレンジック方法並びにフォレンジックプログラム 审中-公开
    威廉制度,威尔逊法和威尔逊计划

    公开(公告)号:WO2014057964A1

    公开(公告)日:2014-04-17

    申请号:PCT/JP2013/077442

    申请日:2013-10-09

    Abstract: レビュワーのレビューの負荷を軽減することを可能とする。 デジタル情報に含まれる文書データから抽出された、所定数の文書を含む文書群に対して利用者が、訴訟との関連性について判断した結果である結果情報を受け付ける結果情報受付部と、結果情報ごとに文書群に共通して出現する要素の特徴から該要素の評価値を算出し、該評価値に基づいて、要素を選定する要素選定部と、文書データの各文書に含まれる選定された要素および選定された要素の評価値から文書データの各文書のスコアを算出するスコア算出部と、スコアに基づいて、訴訟との関連性の判断に関する再現率を算出する再現率算出部とを備える。

    Abstract translation: 本发明能够缓解评审者的审查负担。 本发明提供有:结果信息接收单元,其接收作为用户确定关于包含从包含在数字信息中的文本数据提取的预定数量的文本的文本组的诉讼的相关性的结果的结果信息; 元素选择单元,根据针对每个结果信息单元显示为文档组的共同点的元素的特征,计算元素的评估值,并且基于评估值选择元素; 分数计算单元,其从文本数据的每个文本中包含的所选元素和所选择的元素的评估值中计算文本数据的每个文本的分数; 以及回忆因子计算单元,其基于所述得分计算与所述诉讼的相关性的确定有关的召回因子。

Patent Agency Ranking