专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明专利

DE112017006785B4 Datenanalysator und Datenanalyseverfahren 未知
公开(公告)号：DE112017006785B4
公开(公告)日：2023-01-19
申请号：DE112017006785
申请日：2017-02-14
申请人： MITSUBISHI ELECTRIC CORP
发明人： AIKAWA TAKEYUKI , ITSUI HIROYASU
IPC分类号： G06F40/40 , G06F16/34 , G06F16/36
摘要： Eine Einheit (103) zum Sammeln ähnlicher Ausdrücke sammelt aus verteilten Darstellungen von Wörterdaten ein Wort/eine Phrase eines Ausdrucks, der einem Analysegesichtspunkt-Wort/einer Analysegesichtspunktverbindung ähnlich ist, und eine Worteinbettung, die dem Wort/der Phrase entspricht. Eine Dimensionsauswahleinheit (104) wählt in Abhängigkeit von dem Analysegesichtspunkt-Wort/der Analysegesichtspunktphrase eine Dimension einer Worteinbettung aus und komprimiert eine Worteinbettung, die dem Wort/der Phrase, das bzw. die durch die Einheit (103) zum Sammeln ähnlicher Ausdrücke gesammelt worden ist, entspricht, in der ausgewählten Dimension.

32. 发明专利

GB2603057A Text string summarization 未知
公开(公告)号：GB2603057A
公开(公告)日：2022-07-27
申请号：GB202203098
申请日：2021-07-26
申请人： NVIDIA CORP
发明人： NEILESH CHORAKHALIKAR , MANAS JOSHI , ARUNACHALAM ARUNACHALAM , BABER M SHAIKH
IPC分类号： G06F16/34 , G06F40/247 , G06F40/30 , G06F40/40 , G06N3/02
摘要： Apparatuses, systems, and techniques to summarize a plurality of text strings. In at least one embodiment, one or more machine learning structures are used to generate a summary of a plurality of text strings based, at least in part, on an association between one or more words in a text string and one or more words with similar meaning.

33. 发明专利

AU2017246135B2 Systems and methods for providing a visualizable results list 未知
公开(公告)号：AU2017246135B2
公开(公告)日：2022-06-16
申请号：AU2017246135
申请日：2017-03-28
申请人： LEXISNEXIS DIVISION OF REED ELSEVIER INC
发明人： MILLER RICHARD D , MYERS JACOB AARON , FRASCONE TODD J , MEHRA GAURAV , HAINES RONALD C , WITTMER PHILIP , LI YANGGUANG
IPC分类号： G06F16/248 , G06F16/31 , G06F16/335 , G06F16/34
摘要： Systems and methods for displaying a visualizable results list in response to an electronic search request are disclosed. A method includes accessing metadata for each of a plurality of search results that result from a search query, annotating one or more locations in each search result with first and second indicators for each of one or more grouped search terms in first and second units based on the metadata, and displaying a visualizable results list that includes the plurality of search results and a corresponding hit pattern for each search result. The hit pattern includes the first indicator and the second indicator.

34. 发明专利

AU2018226398B2 AUTOMATED HIGHLIGHTING OF KEY POINTS IN CONTENT USING MACHINE LEARNING TO IMPROVE DOCUMENT COMPREHENSION. USING EASY TO COLLECT HUMAN FEEDBACK TO IMPROVE THE ALGORITHM 未知
公开(公告)号：AU2018226398B2
公开(公告)日：2021-11-11
申请号：AU2018226398
申请日：2018-09-04
申请人： ADOBE INC
发明人： THEVENET FREDERIC , CHANG WALTER , FITZGERALD SEAN , MALANGULLY RAGUNANDAN RAO , WATERS JASON , BYRUM LAURIE , DOCKHORN CARL
IPC分类号： G06F16/34 , G06F40/00 , G06F40/103 , G06F40/106 , G06F40/30 , G06F40/47
摘要： Highlighting key portions of text within a document is described. A document having text is obtained, and key portions of the document are determined using summarization techniques. Key portion data indicative of the key portions is generated and maintained for output to generate a highlighted document in which highlight overlays are displayed over or proximate the determined key portions of the text within the document. In one or more implementations, reader interactions with the highlighted document are monitored to generate reader feedback data. The reader feedback data may then be combined with the output of the summarization techniques in order to adjust the determined key portions. In some cases, the reader feedback data may also be used to improve the summarization techniques. DOCUMENT Document Highlighting 100 System 102 l - Key Portion FD Recognizer 104 I -OItil.OI MIM SummariZation - Model 116 N Adjustment Mdl / ~~ 122Moue Documents 112 Key Portion '- 118 Data 114 Network Reader 110 Feedback Data 124 NN -12 120 Client Devices 106 / 66. Reader/ Application 108 LHighlighted\ Douent 120

35. 发明专利

CA3150836A1 TRANSFORMING A DATA STREAM INTO STRUCTURED DATA 未知
公开(公告)号：CA3150836A1
公开(公告)日：2021-02-18
申请号：CA3150836
申请日：2020-05-14
申请人： DATADOG INC
发明人： MASSON CHARLES-PHILIPPE , KAPPEL STEPHEN PAUL
IPC分类号： G06F16/34 , G06F16/35
摘要： A method for processing a data stream to identify a structure of the data stream includes receiving the data stream a sequence of characters, retrieving a set of rules for encoding characters into at least one token, and parsing the data stream. Parsing includes generating a plurality of tokens according to the set of rules. Each token represents a corresponding portion of the sequence of characters. Parsing includes forming a sequence of tokens from the plurality of tokens and assigning at least one attribute value describing the corresponding portion of the sequence of characters of the corresponding token to which the attribute value is assigned. The sequence of tokens are assigned to a cluster by determining that the sequence of tokens matches a pattern by which the cluster is characterized. The sequence of tokens is merged with the cluster. A representation of the cluster is output.

36. 发明专利

SG11202012049SA VISUALIZATION CUSTOMIZATION 未知
公开(公告)号：SG11202012049SA
公开(公告)日：2021-01-28
申请号：SG11202012049S
申请日：2019-06-28
申请人： LUCID SOFTWARE INC
发明人： DILTS BENJAMIN , MORELLI ANTHONY , HART JAMES , DAVIS TYLER , MCKENNA SEAN , STRINGHAM RYAN , DRAPER PAUL , LUTTMER LAURA
IPC分类号： G06F16/28 , G06F16/25 , G06F16/34 , G06F16/904
摘要： In an example, a method may include generating a semantic layout of a visualization based on a contract associated with a visualization type. The method may also include receiving input effective to alter a set of one or more graphical objects to display for each of some but not all data objects of a data source from a default set of one or more graphical objects to a custom set of one or more graphical objects. The method may also include generating a concrete layout of the visualization that specifies the set of one or more graphical objects to display for each of the data objects, including the default set for a first data object and the custom set for a second data object. The method also includes displaying the visualization based on the contract, the semantic layout, and the concrete layout, the visualization having the visualization type.

37. 发明专利

SG11202011481QA METHOD AND DEVICE FOR RENDERING LYRICS 未知
公开(公告)号：SG11202011481QA
公开(公告)日：2020-12-30
申请号：SG11202011481Q
申请日：2018-11-21
申请人： TENCENT MUSIC ENTERTAINMENT TECHNOLOGY SHENZHEN CO LTD
发明人： FENG SUIYU
IPC分类号： G06F16/34
摘要： The present application relates to the technical field of computers and provides a method and device for rendering lyrics. The method comprises: obtaining the pronunciation of a polysyllabic word to be rendered in the target lyrics, and obtaining playback time information of the pronunciation in the process of rendering the target lyrics (201); determining a first number of pseudo-names comprised in the pronunciation (202); and performing, according to the first number and the playback time information of the pronunciation of the polysyllabic word to be rendered, word-for-word rendering on the polysyllabic word to be rendered and each pseudo-name in the pronunciation of the polysyllabic word to be rendered simultaneously (203), wherein the pronunciation of the polysyllabic word to be rendered is adjacent to and parallel to the polysyllabic word to be rendered. By means of the method, the lyrics rendering is more reasonable.

38. 发明专利

GB2558400B Generating presentation slides with distilled content 未知
公开(公告)号：GB2558400B
公开(公告)日：2020-11-04
申请号：GB201718646
申请日：2017-11-10
申请人： GOOGLE LLC
发明人： VISHNU SIVAJI , STEVEN JOSEPH SAVIANO , ANDREA DULKO
IPC分类号： G06F16/34 , G06F40/20

39. 发明专利

GB2573189A Generating a topic-based summary of textual content 未知
公开(公告)号：GB2573189A
公开(公告)日：2019-10-30
申请号：GB201901522
申请日：2019-02-04
申请人： ADOBE INC
发明人： KUNDAN KRISHNA , BALAJI VASAN SRINIVASAN
IPC分类号： G06F16/34 , G06F40/00
摘要： A method for generating a summary of textual content tuned to a specific topic involves using a topic-aware encoding model to encode 804 the text using a topic label (e.g. a one-hot vector) to generate topic-aware encoded text. A word generation model selects a next word 808 for the summary from the encoded text. The word generation model is trained using machine learning and training data including documents with corresponding summaries, each having an associated topic. The selected next word is provided as feedback 810 to the word generation model. Also disclosed is a method for training the encoding word generation models by obtaining an intermediate dataset comprising documents, and a summary of each document with an associated topic. Training data is generated by merging the text of first and second documents to make a new document which is associated with the summary and topic of the first document, merging their text again and associating the resulting new document with the summary and topic of the second document. The original documents are discarded. This process is repeated until the intermediate training set is exhausted. The training data is then used to train the encoding and word generation models.

40. 发明专利

GB2571811A Abstractive summarization of long documents using deep learning 未知
公开(公告)号：GB2571811A
公开(公告)日：2019-09-11
申请号：GB201819509
申请日：2018-11-30
申请人： ADOBE INC
发明人： ARMAN COHAN , WALTER-WEI-TUH CHANG , TRUNG HUU BUI , FRANCK DEMONCOURT , DOO SOON KIM
IPC分类号： G06F16/34
摘要： Disclosed is an abstractive summarization method for summarizing documents, including long documents. The method for generating a summarization of a structured document having a plurality of sections comprises: processing each word in a plurality of words in a section using a respective first recurrent neural network to generate a word-level representation; processing each word-level representation by a second recurrent neural network to generate a section-level representation; generating a context vector by performing a neural attention process on one or more hidden states of said first recurrent neural network and one or more hidden stats of said second recurrent neural network; and then generating a next predicted word in said summarization based upon a previously predicted work and said context vector. The method is used for example to generate a document S from scratch by using words and phrases that are not exactly from the original document D. This robust abstractive summarization is a generally more natural way to summarize a document as humans also tend to write abstractive summaries in their own words rather than copying exact sentences from a source document. This method is particularly useful for summarizing long complex documents.

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