专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20230034344A1 SYSTEMS AND METHODS FOR PROACTIVELY EXTRACTING DATA FROM COMPLEX DOCUMENTS 有权
公开(公告)号：US20230034344A1
公开(公告)日：2023-02-02
申请号：US17443642
申请日：2021-07-27
申请人： Capital One Services, LLC
发明人： Indu Jain
IPC分类号： G06F40/186 , G06F40/30 , G06F40/216 , G06F21/60 , G06N3/04
摘要： A system for proactively extracting data from complex documents is disclosed. The system may include one or more processors, an NLP device, a trained machine learning device, and a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to, receive one or more documents from a client device, extract one or more extractable data entries from the one or more data entries, generate, one or more normalized data entries, and proactively generate and add one or more completed data entries in place of one or more placeholders in a first document template. The system may receive a natural language prompt from a user device and determine a machine-readable semantic representation. The system may identify sensitive data entries and generate a graphical user interface identifying completed data entries and associated confidence intervals.

12. 发明授权

US11562090B2 Enforcing sensitive data protection in security systems 有权
公开(公告)号：US11562090B2
公开(公告)日：2023-01-24
申请号：US16424022
申请日：2019-05-28
申请人： International Business Machines Corporation
发明人： Dmitri Dodor , Peter A. Maniatis , Leonid Rodniansky
IPC分类号： G06F17/00 , G06F21/62 , G06F40/211 , G06F40/216 , G06F40/284
摘要： A security system that monitors requests to a protected resource is configured to determine that a syntactically-invalid language statement in a request is one that should be treated as a “security high risk” statement (SHRS) because it has a probability of containing sensitive data. A machine language that defines the structure and syntax of the language statements used by a client-server application may have multiple SHRSs. SHRSs are identified in advance by syntactical analysis of the language statements that comprise the machine language. The security system stores (or can otherwise obtain) a representation of each of the set of these high risk statements. In response to detecting that a request has a syntactically-invalid language statement, the system determines whether the invalid language statement has a measure of similarity sufficiently close to any of statement in the SHRS set. Upon a positive determination, an appropriate security action is taken to ensure sensitive data is not exposed.

13. 发明授权

US11507745B2 System and method for detecting undesirable and potentially harmful online behavior 有权
公开(公告)号：US11507745B2
公开(公告)日：2022-11-22
申请号：US17478328
申请日：2021-09-17
申请人： Samurai Labs sp. z o.o.
发明人： Michal Wroczynski , Gniewosz Leliwa
IPC分类号： G06F40/253 , G06N3/08 , H04L51/046 , G06N20/00 , G06F40/211 , G06F40/216 , G06F40/279
摘要： Embodiments include computer-implemented methods and systems for detecting undesirable and potentially harmful online behavior. The embodiments described and claimed could also be applied to detecting any other type of online behavior to be detected, but the descriptions focuses on detecting online violence. More particularly, the embodiments disclosed relate to detecting online violence using symbolic methods of natural language processing (NLP) that utilize and govern the usage of: 1) syntactic parser for analyzing grammatical context of the input text data, 2) unsupervised learning methods for improving selected aspects of the system and adjusting the system to new data sources and guidelines, and 3) statistical classifiers for resolving specific well-defined sub-tasks, in which statistical approaches surpass the symbolic methods.

14. 发明申请

US20220358291A1 DEPENDENCY PATH REASONING FOR MEASUREMENT EXTRACTION 有权
公开(公告)号：US20220358291A1
公开(公告)日：2022-11-10
申请号：US17237878
申请日：2021-04-22
申请人： Adobe Inc.
发明人： Amir Pouran Ben Veyseh , Franck Dernoncourt
IPC分类号： G06F40/295 , G06F40/216
摘要： The present disclosure provides systems and methods for relationship extraction. Embodiments of the present disclosure provide a relationship extraction network trained to identify relationships among entities in an input text. The relationship extraction network is used to generate a dependency path between entities in an input phrase. The dependency path includes a set of words that connect the entities, and is used to predict a relationship between the entities. In some cases, the dependency path is related to a syntax tree, but it may include additional words, and omit some words from a path extracted based on a syntax tree.

15. 发明授权

US11481552B2 Generative-discriminative language modeling for controllable text generation 有权
公开(公告)号：US11481552B2
公开(公告)日：2022-10-25
申请号：US17011939
申请日：2020-09-03
申请人： salesforce.com, inc.
发明人： Ben Krause , Akhilesh Deepak Gotmare
IPC分类号： G06F40/274 , G06F40/284 , G10L15/183 , G06F40/216
摘要： The embodiments describe a generative-discriminative (GeDi) language modeling for determining a next token in a text sequence. A class conditional language model and a positive control code determine a first class conditional probability for each token candidate. The class conditional language model and a negative control code determine a second class conditional probability for the each token candidate. A logarithmic probability difference between the first class conditional probability and the second class conditional probability is determined for each token candidate. An unconditional language model determines an unconditional probability for each token candidate. A combined probability is determined by combining the unconditional probability and the logarithmic probability difference for each token candidate. The next token is selected from the token candidates based on the combined probabilities of the token candidates.

16. 发明授权

US11481461B2 Concept networks and systems and methods for the creation, update and use of same to select images, including the selection of images corresponding to destinations in artificial intelligence systems 有权
公开(公告)号：US11481461B2
公开(公告)日：2022-10-25
申请号：US17097895
申请日：2020-11-13
申请人： REALPAGE, INC.
发明人： Chao Pan , Melanie Tosik
IPC分类号： G06F16/50 , G06F16/9535 , G06N20/00 , G06F16/901 , G06F16/9038 , G06F40/216 , G06F40/295
摘要： Systems and methods for concept based searching or recommendation are disclosed. More particularly, embodiments of a concept based approach to the search and analysis of data, including the creation, update or use of concept networks in searching and analyzing data are disclosed, including embodiments of the usage of such concept networks in artificial intelligence systems that are capable of utilizing concepts expressed by users to return or evaluate associated images.

17. 发明授权

US11481415B1 Corpus temporal analysis and maintenance 有权
公开(公告)号：US11481415B1
公开(公告)日：2022-10-25
申请号：US17217871
申请日：2021-03-30
申请人： International Business Machines Corporation
发明人： Gandhi Sivakumar , Rodolfo Lopez , Louie A. Dickens
IPC分类号： G06F16/332 , G06F16/338 , G06F16/901 , G06F40/216 , G06F16/33
摘要： An approach to determining if a corpus is obsolete for the selected purpose. The approach can receive a corpus and a context from a user. The approach can extract terms from the corpus based on the context. The approach can generate a temporal context mapping of the terms. The approach can analyze the terms based on the temporal context mapping. The approach can determine if a further analysis of the temporal context mapping by a subject matter expert (SME) is necessary and if so, employ an SME for the analysis. The approach can determine if the corpus is obsolete for the selected purpose based on the temporal context mapping. The approach can delete the corpus from the repository and send the user an obsolete notice if the corpus is obsolete or can generate a corpus report and send the user the corpus report if the corpus is not obsolete.

18. 发明授权

US11468233B2 Intention identification method, intention identification apparatus, and computer-readable recording medium 有权
公开(公告)号：US11468233B2
公开(公告)日：2022-10-11
申请号：US16750182
申请日：2020-01-23
申请人： Liang Liang , Lei Ding , Bin Dong , Shanshan Jiang , Yixuan Tong
发明人： Liang Liang , Lei Ding , Bin Dong , Shanshan Jiang , Yixuan Tong
IPC分类号： G06F40/216 , G06F40/30 , G06F16/242 , G06F40/56 , G06F40/211
摘要： An intention identification method includes generating a heterogeneous text network based on a language material sample; using a graph embedding algorithm to perform learning with respect to the heterogeneous text network and obtain a vector representation of the language material sample and a word, and determining keywords of the language material sample based on a similarity in terms of a vector between the language material sample and the word in the language material sample; training an intention identification model until a predetermined training termination condition is satisfied, by using the keywords of the language material samples, and obtaining the trained intention identification model; and receiving a language material query, and using the trained intention identification model to identify an intention of the language material query.

19. 发明授权

US11468232B1 Detecting machine text 有权
公开(公告)号：US11468232B1
公开(公告)日：2022-10-11
申请号：US16674581
申请日：2019-11-05
申请人： SupportLogic, Inc.
发明人： Poonam Rath
IPC分类号： G06F40/216 , G06K9/62 , G06F40/40 , G06F40/284 , G06N20/00
摘要： System receives historical text block, creates historical features for historical text block's historical text lines. System trains machine-learning model to cluster historical features into historical features clusters based on their similarities. System identifies historical features cluster as historical human text cluster. System classifies each historical text line for historical human text cluster as human text, and each historical text line for other historical features clusters as machine text. System receives text block, creates features for text block's text lines. System applies trained machine-learning model to cluster features into features clusters based on their similarities. System identifies features cluster as human text cluster. System classifies each text line for human text cluster as human text, and each text line for other features clusters as machine text. System applies human text analysis to each text line classified as human text and machine text analysis to each text line classified as machine text.

20. 发明授权

US11449678B2 Deep learning based dialog method, apparatus, and device 有权
公开(公告)号：US11449678B2
公开(公告)日：2022-09-20
申请号：US16369579
申请日：2019-03-29
申请人： HUAWEI TECHNOLOGIES CO., LTD.
发明人： Zhengdong Lu , Shan He , Qiang Jiang
IPC分类号： G06F40/30 , G06F16/00 , G06N99/00 , G06F40/35 , G06F40/56 , G06F40/216 , G06F16/2455 , G06N3/08
摘要： A deep learning based dialog method, apparatus, and device are provided and belong to the field of artificial intelligence. The method includes: obtaining a to-be-replied statement, encoding the to-be-replied statement to obtain a first vector , where the first vector is a representation of the to-be-replied statement; obtaining dialog history information corresponding to the to-be-replied statement, and the attention vector is used to represent search intent; making each dialog statement interact with the attention vector, so as to extract information related to the search intent from the dialog statement to obtain a plurality of result vectors, generating a to-be-decoded vector based on the plurality of result vectors, and decoding the to-be-decoded vector to obtain a next word in the reply statement. In the method, the reply statement refers to a dialog history.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式