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. 发明专利

IL286519D0 System and method for the generation and editing of text content in website building systems 未知
公开(公告)号：IL286519D0
公开(公告)日：2021-10-31
申请号：IL28651921
申请日：2021-09-19
申请人： WIX COM LTD
IPC分类号： G06F3/0482 , G06F16/9532 , G06F16/958 , G06F40/131 , G06F40/137 , G06F40/166 , G06F40/186 , G06F40/216 , G06F40/30 , G06N5/00 , G06N5/04 , G06N20/00
摘要： A text content generation (TCG) system to generate text for a text field for a website building system (WBS). The TCG system includes a data gatherer to gather text samples from sources internal and external to the WBS; an analysis engine to analyze the text samples and to identify common text structures, substructures and website contexts; an HDS creator to receive the output of the analysis engine and to create a hierarchical data structure (HDS) definition for each text sample accordingly, the HDS creator to also create associated rules for handling the application and behavior for each HDS, where each HDS describes a text element alternative for a given field role and a content management system (CMS) to store the HDS definitions and the text samples.

2. 发明专利

IL274565A System and method for the generation and editing of text content in website building systems 未知
公开(公告)号：IL274565A
公开(公告)日：2021-09-30
申请号：IL27456520
申请日：2020-05-10
申请人： WIX COM LTD
IPC分类号： G06F3/0482 , G06F16/9532 , G06F16/958 , G06F40/131 , G06F40/137 , G06F40/14 , G06F40/166 , G06F40/186 , G06F40/20 , G06F40/216 , G06F40/30 , G06N5/00 , G06N5/04 , G06N20/00
摘要： A text content generation (TCG) system to generate text for a text field for a website building system (WBS). The TCG system includes a data gatherer to gather text samples from sources internal and external to the WBS; an analysis engine to analyze the text samples and to identify common text structures, substructures and website contexts; an HDS creator to receive the output of the analysis engine and to create a hierarchical data structure (HDS) definition for each text sample accordingly, the HDS creator to also create associated rules for handling the application and behavior for each HDS, where each HDS describes a text element alternative for a given field role and a content management system (CMS) to store the HDS definitions and the text samples.

3. 发明专利

IL284751D0 Parental control systems and methods for detecting an exposure of confidential information 未知
公开(公告)号：IL284751D0
公开(公告)日：2021-08-31
申请号：IL28475121
申请日：2021-07-11
申请人： BITDEFENDER IPR MAN LTD
IPC分类号： G06F21/55 , G06F21/62 , G06F40/216 , G06F40/253 , G06F40/30 , G06N3/04 , G06N3/08 , G06Q10/10 , H04L12/58 , H04L29/06 , H04W4/12 , H04W4/21 , H04W12/02
摘要： Some embodiments use text and/or image processing methods to determine whether a user of an electronic messaging platform is subject to an online threat such as cyberbullying, sexual grooming, and identity theft, among others. In some embodiments, a text content of electronic messages is automatically harvested and aggregated into conversations. Conversation data are then analyzed to extract various threat indicators. A result of a text analysis may be combined with a result of an analysis of an image transmitted as part of the respective conversation. When a threat is detected, some embodiments automatically send a notification to a third party (e.g., parent, teacher, etc.)

4. 发明专利

IL252457A Methods for understanding incomplete natural language query 未知
公开(公告)号：IL252457A
公开(公告)日：2021-06-30
申请号：IL25245717
申请日：2017-05-23
申请人： MICROSOFT TECHNOLOGY LICENSING LLC
IPC分类号： G06F40/216 , G06F40/274 , G06F40/279 , G06N20/00 , G10L15/18 , G10L15/26
摘要： Analysis of incomplete natural language expressions using n-gram analysis and contextual information allows one or more domains to be predicted. For each domain, intent a likely intent of the user is determined using n-gram analysis and contextual information. Intent may correspond to functions of a domain application. In such a case, information required for the functions to execute the application may be populated using n-gram analysis and/or contextual information. The application may then be presented to the user for confirmation of intent. Confirmation of intent along with the incomplete natural language expression and contextual information may then be used to train one or more models used to predict user intent based on incomplete natural language expressions.

5. 发明专利

AU2021103476A4 Method and System for Recommending Products based on Feature Intentions 未知
公开(公告)号：AU2021103476A4
公开(公告)日：2022-05-26
申请号：AU2021103476
申请日：2021-06-19
申请人： CHIRANJEEVI PANDI , RAVI KUMAR K C , SANTOSH D TEJA
发明人： SANTOSH D TEJA , RAVI KUMAR K C , CHIRANJEEVI PANDI
IPC分类号： G06Q30/06 , G06F40/216 , G06F40/237 , G06F40/284 , G06Q30/02 , G10L15/18
摘要： The present invention generally relates to a system and method for feature level intentions-based product recommendations with case-based reasoning. The system comprises a pre-processing unit for performing tokenization, stopwords removal and Part-of-Speech (PoS) tagging from collected online product reviews from e-commerce sites; a product features extraction module for extracting frequent features, relevant features, implicit features and infrequent features, wherein WordNet is utilized to finalize the extracted features as a dictionary word; an opinion analysis module for extracting opinion words and determining opinion orientations and thereafter evaluating feature intentions and feature sentiments; and a prediction module for obtaining sentiment of the product features and intentions on the product features and thereby determining similar products based on intentions and recommending similar products to customers. Ii~ :11 ]I~~Z 7i~ ~ I

6. 发明专利

GB2584239B Dynamically constructing and configuring a conversational agent learning model 未知
公开(公告)号：GB2584239B
公开(公告)日：2022-03-02
申请号：GB202012150
申请日：2019-01-21
申请人： IBM
发明人： GIUSEPPE CIANO , LUIGI PICHETTI , PIETRO MARELLA , LEONARDO MODEO
IPC分类号： G06F40/35 , G06F40/216 , G06F40/56 , G06N3/10 , G06N5/02 , G06N20/00 , H04L51/02
摘要： An approach is described with respect to dynamically constructing and configuring a conversational agent learning model. Various aspects of the conversational agent learning model may be constructed and updated without continuous intervention of a domain administrator. A method pertaining to such approach may include retrieving a corpus of information. The corpus of information may include records from a set of repositories and external data, including data from social networks or applications. The method further may include configuring the conversational agent learning model based upon the retrieved corpus of information. The method further may include deploying the conversational agent learning model by facilitating interaction between the conversational agent learning model and a plurality of clients. The method further may include updating the conversational agent learning model to address any modification to the corpus of information.

7. 发明专利

AU2018226420B2 VOICE ASSISTED INTELLIGENT SEARCHING IN MOBILE DOCUMENTS 未知
公开(公告)号：AU2018226420B2
公开(公告)日：2021-07-22
申请号：AU2018226420
申请日：2018-09-04
申请人： ADOBE INC
发明人： PATEL TIRTH , VENKATA RAVI TEJA AILAVARAPU , SINGAL DHRUV , MUKHERJEE ARGHYA , NATARAJAN ANANDHAVELU
IPC分类号： G06F16/33 , G06F40/216 , G06F40/284 , G10L15/08
摘要： Systems and techniques for searching within a document include receiving a query by way of a user interface of an application, and in conjunction with identification of the at least one document. A feature value characterizing a relevance of each grammatical unit of the document to the query may be extracted. The grammatical units may be ranked, based on each feature value of each grammatical unit. At least one selected grammatical unit of the plurality of grammatical units may then be displayed, based on the ranking. Receive a query, by way of a user interface of an application, in conjunction with identification of the at least one document, the at least one document stored using a computer memory Identify a plurality of grammatical units within the at least one document Extract a value for at least one feature for each grammatical unit with respect to the query, the at least one feature value characterizing a relevance of each grammatical unit to the query Rank the grammatical units, based on each feature value of each grammatical unit Display, by way of the user interface and in conjunction with the at least one document, at least one selected grammatical unit of the plurality of grammatical units, based on the ranking

8. 发明专利

AU2021101958A4 TAMIL TEXT CATEGORIZATION USING FEATURE WEIGHT LEARNING OF K-NEAREST NEIGHBOUR ALGORITHMS 未知
公开(公告)号：AU2021101958A4
公开(公告)日：2021-06-03
申请号：AU2021101958
申请日：2021-04-15
申请人： KAPILA DHIRAJ , P SAGAYA AURELIA , RAJAMANI VETRIVEERAN , RAMA PARVATHY L , SENTHIL KUMAR M DR , SHARMA MADHU
发明人： SENTHIL KUMAR M , RAMA PARVATHY L , P SAGAYA AURELIA , RAJAMANI VETRIVEERAN , SHARMA MADHU , KAPILA DHIRAJ
IPC分类号： G06F16/35 , G06F40/216 , G06K9/62 , G06N20/00
摘要： TAMIL TEXT CATEGORIZATION USING FEATURE WEIGHT LEARNING OF K-NEAREST NEIGHBOUR ALGORITHMS Text classification is the assignment of choosing whether a report has a place with a bunch of prespecified classes of documents. Programmed order plans can significantly encourage the interaction of classification. Arrangement of reports is trying, as the quantity of segregating words can be huge. Many existing calculations just would not work with these many highlights. The k-closest neighbour arrangement is a case-based learning calculation that has demonstrated to be viable for an assortment of issue spaces including archives. The key component of this plan is the accessibility of a comparability measure that is fit for recognizing neighbours of a particular record. A significant downside of the comparability measure utilized in k-nearest neighbour is that it utilizes all highlights in registering distances. In many archive informational indexes, just a more modest number of absolute vocabulary might be helpful in classifying reports. A potential way to deal with conquer this issue is to learn loads for various highlights. TAMIL TEXT CATEGORIZATION USING FEATURE WEIGHT LEARNING OF K-NEAREST NEIGHBOUR ALGORITHMS TEXT DOCUMENTS PRE-PROCESSING CLASSIFICATION TEXT DOCUMENT CLASSIFIED INTO FIGURE 1: BASIC TEXT CLASSIFICATION PROCESS

9. 发明专利

AU2019240606B2 Linguistic analysis 未知
公开(公告)号：AU2019240606B2
公开(公告)日：2021-04-15
申请号：AU2019240606
申请日：2019-10-02
申请人： THINKING SOLUTIONS PTY LTD
发明人： BALL JOHN
IPC分类号： G06F40/30 , G06F40/216 , G06F40/42 , G06F40/55 , G06F40/56
摘要： The invention concerns linguistic analysis. In particular the invention involves a method of operating a computer to perform linguistic analysis. In another aspect the invention is a computer system which implements the method, and in a further aspect the invention is software for programming a computer to perform the method. The method comprising the steps of: Splitting an input text into words and sentences. For each sentence, comparing phrases in the sentence with known phrases stored in a database, as follows: For each word in the sentence, comparing its value and the values of the words following it with the values of the words of stored phrases, starting with the longest stored phrase that starts with that word, and working from longest to shortest. In the event a match is found for two or more consecutive words, and considering the words around the phrase, labelling the matched phrase with an overphrase that describes the grammar use of the matched phrase. After the penultimate word has been compared, recasting the sentence by replacing the matched phrases by their respective overphrases. Then repeating the comparison process with the recast sentence until there is no further recasting.

10. 发明专利

NZ762972A Method for chinese concept embedding generation based on wikipedia link structure 未知
公开(公告)号：NZ762972A
公开(公告)日：2022-08-26
申请号：NZ76297218
申请日：2018-10-26
申请人： UNIV QILU TECHNOLOGY
发明人： LU WENPENG
IPC分类号： G06F16/81 , G06F16/955 , G06F40/134 , G06F40/216 , G06F40/53 , G06N3/06 , G06N20/00
摘要： The present invention discloses a method and a device for Chinese concept embedding generation based on Wikipedia link structure. The method includes: Step (1): According to the title concepts and/or link concepts in Chinese Wikipedia pages, a link information database is constructed; Step (2): For the title concepts, according to their link relationships with link concepts in the link information database, the positive and negative training instances are constructed respectively, which constitute the training dataset; Step (3): A concept embedding model is built, including an input layer, an embedding layer, a computational operation layer, and an output layer; Step (4): The concept embedding model is trained with the training dataset, then, the Chinese concept embedding is extracted/generated from the concept embedding model. The present invention can accurately distinguish different concepts and overcome the problem of polysemy that troubles the traditional embedding methods, which is beneficial to generate more accurate concept embedding representation.

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