公开(公告)号：US12100418B2

公开(公告)日：2024-09-24

申请号：US17472511

申请日：2021-09-10

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Jianhua Tao ,  Zheng Lian ,  Bin Liu ,  Xuefei Liu

IPC分类号： G10L25/63 ,  G06F18/25 ,  G06F40/166 ,  G06F40/211 ,  G06F40/216 ,  G06F40/284 ,  G06F40/289 ,  G06F40/30 ,  G06N20/00 ,  G06N20/20 ,  G06V20/40 ,  G06V40/16 ,  G10L15/02 ,  G10L15/26 ,  G10L25/30

CPC分类号： G10L25/63 ,  G06F18/253 ,  G06F40/166 ,  G06F40/211 ,  G06F40/216 ,  G06F40/284 ,  G06F40/289 ,  G06F40/30 ,  G06N20/00 ,  G06N20/20 ,  G06V20/41 ,  G06V40/166 ,  G06V40/168 ,  G10L15/02 ,  G10L15/26 ,  G10L25/30

摘要： Disclosed is a dialogue emotion correction method based on a graph neural network, including: extracting acoustic features, text features, and image features from a video file to fuse them into multi-modal features; obtaining an emotion prediction result of each sentence of a dialogue in the video file by using the multi-modal features; fusing the emotion prediction result of each sentence with interaction information between talkers in the video file to obtain interaction information fused emotion features; combining, on the basis of the interaction information fused emotion features, with context-dependence relationship in the dialogue to obtain time-series information fused emotion features; correcting, by using the time-series information fused emotion features, the emotion prediction result of each sentence that is obtained previously as to obtain a more accurate emotion recognition result.

公开(公告)号：US12099811B2

公开(公告)日：2024-09-24

申请号：US18088583

申请日：2022-12-25

申请人： UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

发明人： William Tunstall-Pedoe ,  Finlay Curran ,  Harry Roscoe ,  Robert Heywood

IPC分类号： G06F40/35 ,  G06F16/242 ,  G06F16/31 ,  G06F16/332 ,  G06F16/951 ,  G06F16/955 ,  G06F40/123 ,  G06F40/126 ,  G06F40/20 ,  G06F40/205 ,  G06F40/211 ,  G06F40/216 ,  G06F40/226 ,  G06F40/242 ,  G06F40/279 ,  G06F40/289 ,  G06F40/30 ,  G06F40/44 ,  G06F40/45 ,  G06F40/47 ,  G06F40/58 ,  G06N3/0442 ,  G06N3/0455 ,  G06N3/0499 ,  G06N3/08 ,  G06N5/02 ,  G06N5/04 ,  G06N20/00 ,  G06Q10/1053 ,  G06Q30/0251 ,  G06Q30/0601 ,  G10L15/16 ,  G10L15/18 ,  G10L15/22 ,  G10L15/26 ,  G10L25/63 ,  G16H10/60 ,  H04L51/02 ,  G06N3/091 ,  G10L15/08

CPC分类号： G06F40/35 ,  G06F16/243 ,  G06F16/322 ,  G06F16/3329 ,  G06F16/951 ,  G06F40/123 ,  G06F40/126 ,  G06F40/20 ,  G06F40/205 ,  G06F40/211 ,  G06F40/226 ,  G06F40/242 ,  G06F40/279 ,  G06F40/30 ,  G06F40/45 ,  G06F40/47 ,  G06F40/58 ,  G06N3/0442 ,  G06N3/0455 ,  G06N3/0499 ,  G06N3/08 ,  G06N5/02 ,  G06Q10/1053 ,  G06Q30/0255 ,  G06Q30/0257 ,  G06Q30/0631 ,  G10L15/16 ,  G10L15/1815 ,  G10L15/22 ,  G10L15/26 ,  G10L25/63 ,  G16H10/60 ,  H04L51/02 ,  G06N3/091 ,  G10L2015/088

摘要： There is provided a computer implemented method for the automated analysis or use of data, to answer questions, comprising the steps of: (a) storing in a non-transitory storage medium a structured, machine-readable representation of data that conforms to a machine-readable language, in which the machine-readable language uses a shared syntax across factual statements, queries and reasoning, and uses nesting of nodes and passages, as an unambiguous syntax; where the data relates to parts of documents stored in a document store; (b) automatically processing the structured, machine-readable representation of data to answer questions, in which a user's query is automatically translated into the machine-readable language and a system responds to the user's query by utilising the machine-readable language translation of the query.

公开(公告)号：US20240303433A1

公开(公告)日：2024-09-12

申请号：US18269177

申请日：2021-10-08

申请人： NEC Platforms, Ltd.

发明人： Kazuki Nakajima

IPC分类号： G06F40/216

CPC分类号： G06F40/216

摘要： An information processing apparatus includes: an input unit configured to input a menu name of a restaurant; an output unit configured to output a category name; a storage unit configured to store the menu name and the category name corresponding to the menu name so as to be associated with each other; a morphological analysis unit configured to execute morphological analysis to divide the inputted menu name into words and determine parts of speech; and a specification unit configured to generate, in a case where no category name corresponding to the inputted menu name is stored, a feature amount vector characterizing whether each of the words is included in the menu name or not as a result of the morphological analysis, and specify a category name corresponding to the inputted menu name based on a result of learning the menu name and the category name.

公开(公告)号：US12080091B2

公开(公告)日：2024-09-03

申请号：US18331990

申请日：2023-06-09

申请人： Open Text SA ULC

发明人： Matthias Theodor Middendorf ,  Gisela Barbara Cäcilie Hammann ,  Carsten Peust

IPC分类号： G06F17/00 ,  G06F16/22 ,  G06F16/25 ,  G06F16/93 ,  G06F18/21 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/216 ,  G06F40/274 ,  G06N20/00 ,  G06V30/19 ,  G06V30/412 ,  G06V30/414 ,  G06V30/416

CPC分类号： G06V30/416 ,  G06F16/2282 ,  G06F16/258 ,  G06F16/93 ,  G06F18/217 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/216 ,  G06F40/274 ,  G06N20/00 ,  G06V30/1916 ,  G06V30/412 ,  G06V30/414

摘要： A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as one negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.

公开(公告)号：US20240265054A1

公开(公告)日：2024-08-08

申请号：US18626067

申请日：2024-04-03

申请人： Insight Direct USA, Inc.

发明人： Cathy Snell ,  Dhairya Kothari

IPC分类号： G06F16/9538 ,  G06F16/954 ,  G06F40/216

CPC分类号： G06F16/9538 ,  G06F16/954 ,  G06F40/216

摘要： A clustered metasearch system receives a search query from a user. The system uses Natural Language Processing to identify an object of the search query and descriptors of the search query. The system sorts the search into an applicable realm based on the object of the search query. The system then conducts the search across a variety of search engines and collects root domains from the search results. Root domains within the same realm as the search query are prioritized and additional factors such as the presence of descriptors in the result, the recency of the result, the search engine rank of the result, and the distance from the center of the realm are used to determine the final ranking of the results. The results are then displayed to a user.

公开(公告)号：US12056592B2

公开(公告)日：2024-08-06

申请号：US16993724

申请日：2020-08-14

申请人： Eightfold AI Inc.

发明人： Sanjeet Hajarnis ,  Varun Kacholia ,  Tushar Makkar ,  Xingjian Wang ,  Yi Ding

IPC分类号： G06N3/04 ,  G06F18/21 ,  G06F18/2113 ,  G06F18/214 ,  G06F40/216 ,  G06N3/044 ,  G06N3/045 ,  G06T1/20

CPC分类号： G06N3/044 ,  G06F18/2113 ,  G06F18/2155 ,  G06F40/216 ,  G06N3/045 ,  G06T1/20

摘要： A system and method include one or more processing devices to implement a sequence of transformer neural networks, first and second sequence-to-sequence layers that each comprises a sequence of nodes, and an output layer to provide the first set and second set of score vectors to a downstream application of a natural language processing (NLP) task.

公开(公告)号：US20240232533A9

公开(公告)日：2024-07-11

申请号：US18048064

申请日：2022-10-20

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Zhaoqi Wu ,  Yi Fang Chen ,  Zhi Wang ,  Yi Qun Zhang ,  Yan Du ,  Li Na Yuan

IPC分类号： G06F40/295 ,  G06F40/216 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06F40/295 ,  G06F40/216 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08

摘要： A method of this disclosure may include performing a named entity recognition on text information related to requirements for a wireframe by a first artificial intelligence (AI) model, so as to extract entities and relations of the entities from the text information. The method may further comprise inputting the extracted entities and relations to a second AI model to generate the wireframe, wherein the second AI model is trained so that a difference between resultant relations of the entities of the generated wireframe and the extracted relations of the entities from the first AI model is decreased.

公开(公告)号：US20240220544A1

公开(公告)日：2024-07-04

申请号：US18603024

申请日：2024-03-12

申请人： Prodigo Solutions Inc.

发明人： Dermot Pope ,  Aaron Manuel

IPC分类号： G06F16/903 ,  G06F12/0875 ,  G06F17/18 ,  G06F40/216

CPC分类号： G06F16/90344 ,  G06F12/0875 ,  G06F17/18 ,  G06F40/216 ,  G06F2212/45

摘要： Methods of and systems for searching a catalog include parsing the items of the catalog into tokens, determining the frequency with which each token appears in the catalog, and storing the frequencies in a cache. Queries to the catalog are likewise parsed into tokens, and the tokens of the query string are compared to frequency values in the cache to identify a smaller search space within the catalog.

公开(公告)号：US12026469B2

公开(公告)日：2024-07-02

申请号：US17529947

申请日：2021-11-18

申请人： Proofpoint, Inc.

发明人： Hung-Jen Chang ,  Gaurav Mitesh Dalal ,  Ali Mesdaq

IPC分类号： G06F40/30 ,  G06F40/216 ,  G06N20/20

CPC分类号： G06F40/30 ,  G06F40/216 ,  G06N20/20

摘要： Aspects of the disclosure relate to detecting random and/or algorithmically-generated character sequences in domain names. A computing platform may train a machine learning model based on a set of semantically-meaningful words. Subsequently, the computing platform may receive a seed string and a set of domains to be analyzed in connection with the seed string. Based on the machine learning model, the computing platform may apply a classification algorithm to the seed string and the set of domains, where applying the classification algorithm to the seed string and the set of domains produces a classification result. Thereafter, the computing platform may store the classification result.

公开(公告)号：US12026462B2

公开(公告)日：2024-07-02

申请号：US16204486

申请日：2018-11-29

申请人： International Business Machines Corporation

发明人： Thomas Conti ,  Rajesh Bordawekar ,  Stephen Warren ,  Christopher Harding ,  Jose Neves

IPC分类号： G06F40/216 ,  G06F11/36 ,  G06F18/23213 ,  G06F18/24 ,  G06F40/20 ,  G06N3/088 ,  G06N5/04 ,  G06N20/10

CPC分类号： G06F40/216 ,  G06F11/3672 ,  G06F18/23213 ,  G06F18/24 ,  G06F40/20 ,  G06N3/088 ,  G06N5/04 ,  G06N20/10

摘要： Methods, systems and computer program products for determining recommended parameters for use in generating a word embedding model are provided. Aspects include storing a plurality of meaningful test cases. Each meaningful test case includes a test data profile and one or more test model parameters used to create a word embedding model that has been classified as yielding meaningful results. Aspects include receiving a production data set to be used in generating a new word embedding model. The production data set includes data stored in a relational database having a plurality of columns and a plurality of rows. Aspects include generating a data profile associated with the production data set. Aspects include generating a recommendation for one or more production model parameters for use in building a word embedding model based on the data profile associated with the production data set and the plurality of meaningful test cases.