专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明授权

US12141535B2 Techniques for maintaining rhetorical flow 有权
公开(公告)号：US12141535B2
公开(公告)日：2024-11-12
申请号：US17725496
申请日：2022-04-20
申请人： Oracle International Corporation
发明人： Boris Galitsky
IPC分类号： G06F40/30 , G06F16/31 , G06F16/332 , G06F18/22 , G06F40/211 , G06F40/35 , G06F40/44 , G06F40/51 , G06F40/55 , G06N3/08
CPC分类号： G06F40/35 , G06F16/322 , G06F16/3329 , G06F18/22 , G06F40/211 , G06F40/44 , G06F40/51 , G06F40/55 , G06N3/08
摘要： Disclosed systems, devices, and methods improve dialogue management through the use of dialogue discourse trees (DDTs). To determine whether a candidate response (CR) is appropriate in the dialogue, the CR can be added to other utterances that have been previously provided in a dialogue between two parties and a dialogue discourse tree (DDT) can be generated from the result. The DDT includes nodes corresponding to elementary discourse units (EDUs) representing text fragments of the utterances and the CR. The DDT may include nodes that indicate rhetorical relationships between EDUs. In some embodiments, the DDT comprises a node representing at least one dialogue-specific rhetorical relationship between two utterances. The DDT for the CR can be provided to a machine-learning model that has been trained to identify whether the rhetorical flow is maintained between the utterances of the DDT. If so, the CR can be provided in response to the request.

72. 发明授权

US12135950B2 Automated document adaptation based on topic classification 有权
公开(公告)号：US12135950B2
公开(公告)日：2024-11-05
申请号：US17408715
申请日：2021-08-23
申请人： International Business Machines Corporation
发明人： Micah Forster , Sai Krishna Reddy Gudimetla , Aaron K. Baughman
IPC分类号： G06F40/44 , G06F17/18 , G06F40/247 , G06F40/30 , G06N3/045
CPC分类号： G06F40/44 , G06F17/18 , G06F40/247 , G06F40/30 , G06N3/045
摘要： Using a logistic regression classification model executing on a processor, a topic is classified into an interaction type in a set of predefined interaction types. A set of documents corresponding to the topic is extracted from a document repository. Using a generative adversarial model executing on a processor, a sentiment corresponding to a reaction to a previous presentation is scored, the scoring resulting in a scored sentiment. Using a trained attention layer model, the interaction type, the set of documents, and the scored sentiment are weighted, the weighting generating a weighted interaction type, a weighted set of documents, and a weighted scored sentiment. Using a natural language generation transformer model executing on the processor, a document in the weighted set of documents is weighted according to the weighted interaction type and the weighted scored sentiment.

73. 发明公开

US20240338533A1 METHOD, APPARATUS AND ELECTRONIC DEVICE FOR INFORMATION PROCESSING 审中-公开
公开(公告)号：US20240338533A1
公开(公告)日：2024-10-10
申请号：US18565685
申请日：2022-07-20
申请人： Beijing Youzhuju Network Technology Co., Ltd.
发明人： Jun Cao , Qingnan Jiang , Chengqi Zhao , Mingxuan Wang , Lei Li , Xiaohui Wang
IPC分类号： G06F40/44 , G06F40/58
CPC分类号： G06F40/44 , G06F40/58
摘要： A method, apparatus and electronic device for information processing. The method includes: obtaining a first hidden state vector obtained by inputting information to be translated that is expressed in a source language into a pre-trained first translation model, and a first probability distribution that the first hidden state vector is predicted as respective words in a predetermined vocabulary; obtaining, from a vector index library of a target language, at least one of target index term that satisfies a predetermined condition with the first hidden state vector; determining a second probability distribution that the second hidden state vector is predicted as the respective words in the predetermined vocabulary; determining a second probability distribution of the second hidden state vector; fusing the first and second probability distribution to obtain a fusion probability distribution; and determining a translation result with the fusion probability distribution.

74. 发明授权

US12099806B2 Place recognition method based on knowledge graph inference 有权
公开(公告)号：US12099806B2
公开(公告)日：2024-09-24
申请号：US17701137
申请日：2022-03-22
申请人： SOUTHEAST UNIVERSITY
发明人： Xinde Li , Pei Li , Changyin Sun
IPC分类号： G06F40/30 , G06F40/268 , G06F40/44 , G06N5/02 , G06N5/04
CPC分类号： G06F40/30 , G06F40/268 , G06F40/44 , G06N5/02 , G06N5/04
摘要： The present disclosure discloses a place recognition method based on knowledge graph inference; and provides, on the basis of giving a knowledge graph construction method in the place field, a recognition method of general places that is based on knowledge graph inference and can integrate various heterogeneous environmental information, including the following steps: (1) extracting main clues such as the main items that make up the place, the produced events, and the spatial structure from various heterogeneous information, and describing these clues in natural language text; (2) screening the foregoing descriptions by using natural language processing methods, to form place description entities; (3) constructing a knowledge graph in the place field according to the occurrence frequencies of the description entities in an actual environment; and (4) implementing inference and classification based on the knowledge graph by using a Deep Neural Network (DNN), to give a final recognition result. The present disclosure improves the place recognition accuracy by means of knowledge graph inference, and greatly improves semantic interpretability in the place recognition process.

75. 发明授权

US12094464B2 Utterance analysis device, utterance analysis method, and computer program 有权
公开(公告)号：US12094464B2
公开(公告)日：2024-09-17
申请号：US17554248
申请日：2021-12-17
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： Natsuki Saeki
IPC分类号： G10L15/22 , G06F16/35 , G06F40/295 , G06F40/35 , G06F40/44 , G10L15/18 , G10L15/26
CPC分类号： G10L15/22 , G06F16/353 , G06F40/295 , G06F40/35 , G06F40/44 , G10L15/18 , G10L15/26
摘要： An utterance analysis device including: a storage that stores a plurality of pieces of related information each relating to one of a plurality of categories; a control circuit that receives utterance data of an utterer in order of time series, and analyzes content of the utterance data by using a plurality of first likelihoods, which are each values for identifying a possibility that the utterance data acquired by the acquire corresponds to each category; and a display processor that displays, under control of the control circuit, display data including link information indicating an association for displaying related information relating to the category of the utterance data from the storage.

76. 发明授权

US12067369B2 System and method for language translation 有权
公开(公告)号：US12067369B2
公开(公告)日：2024-08-20
申请号：US18228842
申请日：2023-08-01
申请人： 7299362 Canada Inc.
发明人： Renxian Zhang , Jinnan Lu , Zhanxuan Ding , Jie Ma , Syed Salman Ali , Jason Cox , Xun Li
IPC分类号： G06F40/47 , G06F40/211 , G06F40/42 , G06F40/44 , G06F40/51 , G06F40/55 , G06N3/04 , G06N3/044 , G06N3/082 , G06N3/086 , G06N5/025 , G06N7/01 , G06N20/00 , G06F40/20
CPC分类号： G06F40/47 , G06F40/211 , G06F40/42 , G06F40/44 , G06F40/51 , G06F40/55 , G06N3/04 , G06N3/044 , G06N3/082 , G06N3/086 , G06N5/025 , G06N7/01 , G06N20/00 , G06F40/20
摘要： Provided are computer implemented systems and methods for providing improved language translation, including translation of input text to an output translated text Selement. This may include providing for rule-based language translation. This may further include a plurality of machine translation models adapted to different translation domains. A machine translation selector is described that selects an in-domain machine translator from the plurality of machine translation models based on an input text element. The selected in-domain machine translator may generate a first translated text element from the input text element. A post-editor module may generate a second translated text element by predicting a post-edit to the first translated text element. The first translated text element and the second translated text element are evaluated by a quality evaluation model that determines a first metric associated with the first translated text element and a second metric associated with the second text element.

77. 发明授权

US12061872B2 Non-lexicalized features for language identity classification using subword tokenization 有权
公开(公告)号：US12061872B2
公开(公告)日：2024-08-13
申请号：US17237961
申请日：2021-04-22
申请人： Oracle International Corporation
发明人： Philip Ogren
IPC分类号： G06F40/263 , G06F18/2431 , G06F40/44 , G06N20/00
CPC分类号： G06F40/263 , G06F18/2431 , G06F40/44 , G06N20/00
摘要： A natural language identity classifier system is described, which employs a supervised machine learning (ML) model to perform language identity classification on input text. The ML model takes, as input, non-lexicalized features of target text derived from subword tokenization of the text. Specifically, these non-lexicalized features are generated based on statistics determined for tokens identified for the input text. According to an embodiment, at least some of the non-lexicalized features are based on natural language-specific summary statistics that indicate how often tokens were found within a corpus for each natural language. Use of such summary statistics allows for generation of natural language specific conditional probability-based features. Because of the inherent interpretability of a trained non-lexicalized ML model as described herein, it is possible to modify behavior of the trained ML model by adjusting summary statistics maintained for natural language tokens and/or by adjusting data for the subword tokenizers.

78. 发明授权

US12019992B2 Code enrichment for training language models relating to computer programming 有权
公开(公告)号：US12019992B2
公开(公告)日：2024-06-25
申请号：US17657530
申请日：2022-03-31
申请人： FUJITSU LIMITED
发明人： Mehdi Bahrami , Wei-Peng Chen
IPC分类号： G06F8/60 , G06F8/30 , G06F8/36 , G06F8/41 , G06F8/65 , G06F8/73 , G06F11/36 , G06F16/951 , G06F18/20 , G06F18/22 , G06F18/23213 , G06F40/166 , G06F40/211 , G06F40/216 , G06F40/242 , G06F40/30 , G06F40/40 , G06F40/44 , G06N3/04 , G06N3/08
CPC分类号： G06F40/30 , G06F8/30 , G06F8/36 , G06F8/42 , G06F8/436 , G06F8/65 , G06F8/73 , G06F11/3624 , G06F16/951 , G06F18/22 , G06F18/23213 , G06F18/285 , G06F40/166 , G06F40/211 , G06F40/216 , G06F40/242 , G06F40/40 , G06F40/44 , G06N3/04 , G06N3/08
摘要： According to an aspect of an embodiment, operations for code enrichment for training language models on tasks related to computer programming are provided. The operations include receiving source code data including a computer-executable code and a natural language (NL) text. The operations further include determining blocks of code from the computer-executable code. The operations further include extracting a set of features related to components of the source code data from the blocks of code. The extraction is performed by parsing the blocks of code using Abstract Syntax Tree (AST) data of the blocks of code. The operations further include revising the AST data. The operations further include updating the source code data based on the revised AST data and generating a dataset of NL and abstracted code features as training data based on the updated source code data and further training a language model on a sequence-to-sequence generation task.

79. 发明公开

US20240184997A1 MULTI-MODEL JOINT DENOISING TRAINING 审中-公开
公开(公告)号：US20240184997A1
公开(公告)日：2024-06-06
申请号：US18278364
申请日：2022-03-08
申请人： Microsoft Technology Licensing, LLC
发明人： Linjun SHOU , Ming GONG , Xuanyu BAI , Xuguang WANG , Daxin JIANG
IPC分类号： G06F40/44 , G06F40/284
CPC分类号： G06F40/44 , G06F40/284
摘要： The present disclosure proposes a method and apparatus for multi-model joint denoising training. Multiple models may be obtained. A set of training samples may be denoised through the multiple models. The multiple models may be trained with the set of denoised training samples.

80. 发明公开

US20240160860A1 ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE 审中-公开
公开(公告)号：US20240160860A1
公开(公告)日：2024-05-16
申请号：US18410613
申请日：2024-01-11
申请人： SAMSUNG ELECTRONICS CO., LTD.
发明人： Sungjun LIM
IPC分类号： G06F40/44 , G06F40/47 , G06F40/51
CPC分类号： G06F40/44 , G06F40/47 , G06F40/51
摘要： An electronic device and a controlling method of the electronic device are disclosed. In particular, the electronic device according to the disclosure includes a communicator, a memory configured to store information on an encoder and learning data for learning of the encoder, and a processor configured to, based on acquiring information on an original text of a first language, input the information on the original text into the encoder, and acquire a first encoding vector indicating semantic information included in the original text, input the first encoding vector into a discriminator, and acquire a probability value indicating a probability that the first encoding vector would correspond to a normal translation, based on the probability value being greater than or equal to a predetermined first threshold value, control the communicator to transmit the first encoding vector to an external device including a decoder for acquiring a translation text of a second language corresponding to the original text, and based on the probability value being smaller than the first threshold value, identify a second encoding vector having the highest similarity value indicating similarity to the first encoding vector among encoding vectors included in the learning data, and control the communicator to transmit the identified second encoding vector to the external device.

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