专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20220284185A1 STORAGE MEDIUM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE 有权
公开(公告)号：US20220284185A1
公开(公告)日：2022-09-08
申请号：US17824039
申请日：2022-05-25
申请人： FUJITSU LIMITED
发明人： Masahiro Kataoka , Shinji HORI , Ryo Matsumura , Nobuyuki Takebe
IPC分类号： G06F40/232 , G06F40/247 , G06F40/268
摘要： A non-transitory computer-readable storage medium storing an information processing program that causes at least one computer to execute a process includes extracting first sentence vectors of a plurality of first sentences included in a first text; specifying a second sentence of which a tendency of a vector is different from the plurality of first sentences from among a plurality of second sentences included in a second text based on the extracted first sentence vectors and second sentence vectors of the plurality of second sentences; extracting a word that matches a homophone or a conjunction stored in a storage device from among words included in the specified second sentence; and generating a third sentence of which a tendency of a vector is the same as or similar to the plurality of first sentences by converting the extracted word into a word associated with the homophone or the conjunction.

2. 发明申请

US20220215168A1 INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND PROGRAM 有权
公开(公告)号：US20220215168A1
公开(公告)日：2022-07-07
申请号：US17612522
申请日：2020-04-01
申请人： SONY GROUP CORPORATION
发明人： RYOSUKE MITANI
IPC分类号： G06F40/268 , G06F40/242 , G06F40/216
摘要： The occurrence cost of unknown words that are not registered in a morphological analysis dictionary is calculated by applying an occurrence cost regression model, which is a learning model. An information processing device includes a notation feature amount extraction unit that extracts a notation feature amount of a character string, a part-of-speech feature amount extraction unit that extracts a part-of-speech feature amount of the character string, and an occurrence cost estimation unit that receives the notation feature amount and the part-of-speech feature amount and calculates an occurrence cost of the character string by applying an occurrence cost regression model. The occurrence cost regression model is a learning model that estimates the occurrence cost from the notation feature amount and the part-of speech feature amount of a character string, generated by a learning process using registration data of an existing morphological analysis dictionary as teacher data.

3. 发明申请

US20220207237A1 INFORMATION PROVISION SYSTEM AND INFORMATION PROVISION METHOD 有权
公开(公告)号：US20220207237A1
公开(公告)日：2022-06-30
申请号：US17594365
申请日：2020-03-30
申请人： Universal Entertainment Corporation
发明人： Takuo HENMI , Junichi SATO
IPC分类号： G06F40/268 , G06F16/332 , G06F40/279
摘要： An object of the present invention is to provide an information provision system and an information provision method by which a user is able to easily acquire desired knowledge data. In an information provision system 1, a suggestion server 400 stores question text strings associated with response contents in advance, receives an input text string input by a user 10 by using a user terminal 100, performs morphological analysis for the input text string and each of the question text strings, calculates a score indicating to what extent each of the question text strings is related to the input text string based on results of the morphological analysis for the question text strings and a result of the morphological analysis for the input text string, and causes the user terminal 100 to display at least one of the question text strings. The score of the at least one of the question text strings satisfies a predetermined condition.

4. 发明申请

US20220114202A1 SUMMARY GENERATION APPARATUS, CONTROL METHOD, AND SYSTEM 有权
公开(公告)号：US20220114202A1
公开(公告)日：2022-04-14
申请号：US17473341
申请日：2021-09-13
申请人： KONICA MINOLTA, INC.
发明人： Takashi KUWABARA
IPC分类号： G06F16/34 , G06F16/33 , G06F16/35 , G06F40/268
摘要： A summary generation apparatus generates a summary from language data, and includes a hardware processor that: classifies a word included in the language data and generates a plurality of word clusters in such a manner that words having a possibility of being related to one topic belong to an identical word cluster; selects a representative word cluster including words related to a topic representing description content of the language data from the plurality of word clusters; and generates a summary from the language data on the basis of the representative word cluster.

5. 发明授权

US11289070B2 System and method for identifying a speaker's community of origin from a sound sample 有权
公开(公告)号：US11289070B2
公开(公告)日：2022-03-29
申请号：US16362215
申请日：2019-03-22
申请人： John Rankin
发明人： John Rankin
IPC分类号： G06F40/268 , G10L15/00 , G10L15/02 , G10L15/22 , G10L15/26 , G10L15/30
摘要： A system and method for determining a target speaker's community of origin from a sound sample of the target speaker is provided. An indexed database of morpheme data from speakers from various communities of origin is provided. Indexed morphemes from a target speaker are extracted. The extracted indexed morphemes from the target speaker are compared against the morpheme data in the indexed database to determine the target speaker's community of origin.

6. 发明授权

US11275887B2 Non-transitory computer-readable recording medium, evaluation method, and information processing device 有权
公开(公告)号：US11275887B2
公开(公告)日：2022-03-15
申请号：US17166463
申请日：2021-02-03
申请人： FUJITSU LIMITED
发明人： Yuki Matoba , Masahiro Kataoka , Yasunari Tateiwa
IPC分类号： G06F17/00 , G06F40/12 , G06F40/30 , G06F40/268 , H04L51/02
摘要： The information processing device receives question information, converts words contained in the received question information into word vectors including a plurality of element values respectively associated with a plurality of elements. The information processing device refers to the memory that stores, in association with the elements, specific information specifying the strength of specific meanings contained within the element values associated with the elements and acquires, using the specific information, a plurality of semantic information items indicating the strength of the specific meanings respectively contained within the plurality of element values included in the word vectors. The information processing device performs an evaluation relating to the received question information on the basis of the acquired plurality of semantic information items.

7. 发明申请

US20220067298A1 SYSTEMS AND METHODS FOR UNSUPERVISED PARAPHRASE MINING 有权
公开(公告)号：US20220067298A1
公开(公告)日：2022-03-03
申请号：US17008563
申请日：2020-08-31
申请人： Recruit Co., Ltd.,
发明人： Behzad GOLSHAN , Chen CHEN , Wang-Chiew TAN , Danni MA
IPC分类号： G06F40/35 , G06F40/284 , G06F40/268 , G06K9/62
摘要： Disclosed embodiments relate to aligning pairs of sentences. Techniques can include receiving a plurality of sentences; generating a graph for each of at least two sentences of the plurality of sentences, wherein generating a graph for each sentence of the at least two sentences comprises: identifying one or more tokens for the sentence; and connecting via edges the one or more tokens; generating a combined graph for the at least two sentences wherein generating a combined graph comprises: aligning the identified tokens of the at least two sentences of the plurality of sentences; identifying matching and non-matching tokens between the at least two sentences based on the alignment; and merging matching tokens into a combined graph node.

8. 发明授权

US11265271B2 Electronic message composition support method and apparatus 有权
公开(公告)号：US11265271B2
公开(公告)日：2022-03-01
申请号：US16258783
申请日：2019-01-28
申请人： VERIZON MEDIA INC.
发明人： Joel Tetreault , Aasish Pappu , Edo Liberty , Liangliang Cao , Meizhu Liu , Ellie Pavlick , Gilad Tsur , Yoelle Maarek
IPC分类号： H04L12/58 , G06F40/169 , H04L51/046 , H04L51/02 , G06F40/232 , G06F40/253 , G06F40/268 , H04L67/02
摘要： An electronic message composition support system, method and architecture including machine learning and natural language processing techniques for extending message composition capability and support and to provide feedback to a user regarding an error, condition, etc., detected in the user's message before the user sends the message, e.g., while the user is composing the message using a messaging application's user interface.

9. 发明授权

US11250842B2 Multi-dimensional parsing method and system for natural language processing 有权
公开(公告)号：US11250842B2
公开(公告)日：2022-02-15
申请号：US16773270
申请日：2020-01-27
申请人： Min Ku Kim
发明人： Min Ku Kim
IPC分类号： G10L15/19 , G06F16/33 , G10L15/22 , G10L15/18 , G10L13/00 , G06F40/30 , G06F40/211 , G06F40/45 , G06F40/268 , G06F40/58 , G06F40/284
摘要： A method for translating a text written or otherwise communicated in a source natural language into a text written or otherwise communicable in target natural language, in reliance upon a multidimensional model, relies on determining the core concept in the sentences of the source text, and leverages the determined core concepts to create the target language translation. The method includes processing the source natural language text into sentences, then parsing the sentences, including assigning codes and/or directional operators to realize parsed sentences according to the model. The sentence models are then processed effect the actual translation to the target natural language text, and communicated.

10. 发明申请

US20220012437A1 TRANSLATING METHOD USING VISUALLY REPRESENTED ELEMENTS, AND DEVICE THEREFOR 有权
公开(公告)号：US20220012437A1
公开(公告)日：2022-01-13
申请号：US17484990
申请日：2021-09-24
申请人： Hyun Jin KIM
发明人： Hyun Jin KIM
IPC分类号： G06F40/58 , G06F40/268
摘要： A translating method using visually represented elements, and device therefor is provided. According to an embodiment, a translation method performed by a computing device, may include acquiring data of a first sentence in a first language, the first sentence including a first morpheme of a first type and a second morpheme of a second type different from the first type, generating a first graph representing the first sentence, a first node of the first graph corresponding to the first morpheme of the first type of the first sentence, a first edge of the first graph corresponding to the second morpheme of the second type of the first sentence, and each node and each edge of the first graph being concatenated to each other so that the first sentence is completed when representations corresponding to each node and each edge of the first graph are concatenated while traversing the first graph in a first order, replacing the representations of the first language corresponding to each node and each edge of the first graph with representations of a second language, acquiring a second sentence of the second language by concatenating the representations of the second language corresponding to each node and each edge of the first graph while traversing the first graph in a second order at least in part different from the first order, and outputting the second sentence as a translation result of the first sentence into the second language.

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