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

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.)

2. 发明专利

AU6648101A Method and system for information extraction 未知
公开(公告)号：AU6648101A
公开(公告)日：2002-01-02
申请号：AU6648101
申请日：2001-06-20
申请人： HAPAX INFORMATION SYSTEMS AB
发明人： EJERHED EVA , BRAROE PETER A
IPC分类号： G06F17/30 , G06F40/00 , G06F40/20 , G06F40/211 , G06F40/253 , G06F40/268 , G06F40/30 , G06F17/27
摘要： A method, a system and a computer program for extracting information from a natural language text corpus based on a natural language query are disclosed. The natural language text corpus is indexed and stored. A natural language query is analyzed with respect to phrases, phrase types, syntactic roles, word tokens of phrases, and lexical meaning of word tokens. One or more surface variants are created for at least one phrase of the natural language query. The one or more surface variants each have the same phrase type as the at least one phrase of the natural language query, and each comprise a word token which is a lexical head and has the same lexical meaning as a word token which is a lexical head of the at least one phrase of the natural language query. The one or more surface variants and the at least one phrase of the natural language query are compared with the indexed and stored natural language text corpus. Portions of text are extracted from the indexed and stored natural language text corpus, which portions comprise a string of word tokens that matches any one of said surface variants or said at least one phrase of the natural language query.

3. 发明专利

CA2889463C SENTENCE PARSING CORRECTION SYSTEM 未知
公开(公告)号：CA2889463C
公开(公告)日：2021-08-31
申请号：CA2889463
申请日：2013-10-24
申请人： WALKER READING TECH INC
发明人： WALKER RANDALL C
IPC分类号： G06F40/205 , G06F40/253 , G06F40/289
摘要： A system provides on a computer display screen, a graphical image of an initial parsing as generated by a computerized algorithm. Individual clauses are encased in expandable containers that a user can shift and resize on the screen using a mouse or other cursor control device to thereby improve the initial parsing.

4. 发明专利

DE102019217595A1 DOMÄNENSPEZIFISCHE VORHERSAGE DER PROZESSSCHWIERIGKEIT 未知
公开(公告)号：DE102019217595A1
公开(公告)日：2020-05-14
申请号：DE102019217595
申请日：2019-11-14
申请人： BOSCH GMBH ROBERT
发明人： HAETTY ANNA CONSTANZE , WANG BINGQING
IPC分类号： G06F40/253 , G06F16/35 , G06N3/02
摘要： Ein Verfahren zum Bestimmen einer operativen Schwierigkeit eines Prozesses, der in einem Dokument beschrieben ist, das Text enthält, beinhaltet das Erzeugen von Textdaten, die dem Text des Dokuments entsprechen, und das Erzeugen einer Wortvektorausgabe durch Verarbeiten der Textdaten durch eine Vielzahl von Wortvektoren, wobei die Vielzahl von Wortvektoren auf einer domänenspezifischen Textsammlung und einer allgemeinsprachlichen Textsammlung basiert. Das Verfahren beinhaltet ferner das Erzeugen einer statistischen Informationsausgabe durch Verarbeiten der Textdaten durch eine Vielzahl statistischer Informationsvektoren, wobei die Vielzahl von statistischen Informationsvektoren auf der domänenspezifischen Textsammlung und der allgemeinsprachlichen Textsammlung basiert, und das Erzeugen einer Ausgabe der gattergesteuerten wiederkehrenden Einheit (Gated Recurring Unit, GRU) durch Verarbeiten (i) der Wortvektorausgabe, (ii) der statistischen Informationsausgabe, (iii) der Daten auf Wortebene basierend auf den Textdaten, (iv) der Daten auf Satzebene basierend auf den Textdaten und (v) der Daten auf Absatzebene basierend auf den Textdaten durch mindestens eine GRU.

5. 发明专利

IL284748D0 Anti-cyberbullying systems and methods 未知
公开(公告)号：IL284748D0
公开(公告)日：2021-08-31
申请号：IL28474821
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.)

6. 发明专利

IL279651D0 Systems and methods for translating natural language sentences into database queries 未知
公开(公告)号：IL279651D0
公开(公告)日：2021-03-01
申请号：IL27965120
申请日：2020-12-21
申请人： BITDEFENDER IPR MAN LTD
IPC分类号： G06F16/242 , G06F16/2452 , G06F40/146 , G06F40/211 , G06F40/253 , G06F40/42 , G06F40/51
摘要： Described systems and methods allow an automatic translation from a natural language (e.g., English) into an artificial language such as a structured query language (SQL). In some embodiments, a translator module includes an encoder component and a decoder component, both components comprising recurrent neural networks. Training the translator module comprises two stages. A first stage trains the translator module to produce artificial language (AL) output when presented with an AL input. For instance, the translator is first trained to reproduce an AL input. A second stage of training comprises training the translator to produce AL output when presented with a natural language (NL) input.

7. 发明专利

IL274250D0 Computer implemented method and system for detecting a set of relevant communities 未知
公开(公告)号：IL274250D0
公开(公告)日：2020-06-30
申请号：IL27425020
申请日：2020-04-26
申请人： AIRBUS DEFENCE & SPACE SAS
IPC分类号： G06F16/335 , G06F16/38 , G06F16/901 , G06F40/253 , G06F40/284 , G06F40/30 , G06F40/35 , G06Q30/02 , G06Q50/00 , H04L12/58
摘要： Computer implemented method for detecting a set of relevant communities of accounts, said accounts being connected by at least one communication platform, said method comprising the following steps: - Collecting data from a stream of messages circulating on at least one communication platform; - Extracting interaction data and shared objects, said shared objects being shared among the accounts; - Processing each collected message in order to obtain content metadata; - Processing collected data in order to obtain an account profile of each account; - From collected data building shared objects graphs and interaction graphs; - Building a resulting graph; - Applying a community detection method to the resulting graph to obtain a set of communities of accounts; - Computing quality indicators of the set of communities to obtain at least one score for each community said score enabling the selection of at least a relevant community.

8. 实用新型

CN219202338U 一种翻译机有权
公开(公告)号：CN219202338U
公开(公告)日：2023-06-16
申请号：CN202320174023.9
申请日：2023-01-31
申请人：深圳市泰为软件开发有限公司
发明人：许宁涛 , 邝毅勋
IPC分类号： G06F16/33 , G06F40/253 , G06F40/42 , G10L15/00 , G10L15/02
摘要：本实用新型涉及翻译机的技术领域，公开了一种翻译机，包括：采集单元、第一识别单元、第二识别单元、语法修正单元、翻译单元；本实用新型中设置了第一识别单元和第二识别单元，分别对外部音频数据进行语言特征识别和方言特征识别，以判断外部音频数据属于何种语言的何种方言，再对外部音频数据激进型翻译，以确保翻译准确，本实用新型中还设置有语法修正单元，语法修正单元能够对外部音频数据进行语法修正，避免口语表达中的语法错误导致翻译错误，解决了现有技术中难以准确翻译出其他语言的方言的问题。

9. 发明专利

DE112020003661T5 ANPASSEN EINES GESPRÄCHSFLUSSES AUF GRUNDLAGE DES VERHALTENS IN EINERKOGNITIVEN MENSCH-MASCHINE-INTERAKTION 未知
公开(公告)号：DE112020003661T5
公开(公告)日：2022-04-21
申请号：DE112020003661
申请日：2020-07-29
申请人： IBM
发明人： PEREZ GONZALEZ IGNACIO , PEDRAZZOLI FERNANDO , DELGADO SANCHEZ ALEJANDRO , GARCIA GUERRERO ANA PATRICIA , ALVAREZ FERNANDEZ MARIA JOSE
IPC分类号： G06F40/35 , G06F3/01 , G06F40/253 , G06Q10/10
摘要： Es werden ein Verfahren und System zum Anpassen eines Gesprächsflusses auf Grundlage eines Benutzerverhaltens in einer kognitiven Mensch-Maschine-Interaktion bereitgestellt, die an einem Gateway zu einem kognitiven Interaktionsdienstes durchgeführt wird. Das Verfahren umfasst: Empfangen einer Reihe kognitiver Mensch-Maschine-Interaktionen während eines Gesprächsflusses; Feststellen, dass ein Verhaltensmuster der menschlichen kognitiven Interaktionen einem definierten Verhaltensmuster entspricht; Feststellen, dass eine Mehrzahl von Maschinenantworten einem definierten Schwellenwert einer maximalen Wiederholung von Antworten auf das definierte Verhaltensmuster entspricht; und Anweisen des kognitiven Interaktionsdienstes, eine Art einer nachfolgenden Antwort gemäß einer definierten Aktion für das definierte Verhaltensmuster anzupassen.

10. 发明专利

AU2020103810A4 A METHOD FOR DETECTING FAKE NEWS USING GRAMMATIC TRANSFORMATION ON NEURAL NETWORK COMPUTER READABLE MEDIUM 未知
公开(公告)号：AU2020103810A4
公开(公告)日：2021-02-11
申请号：AU2020103810
申请日：2020-12-01
申请人： AGARWAL BASANT , GOEL SUBHASH CHAND DR , HARJULE PRIYANKA , KANUNGO SONAL , KUMAR RAJENDER MR
发明人： KUMAR RAJENDER , GOEL DR SUBHASH CHAND , AGARWAL BASANT , HARJULE PRIYANKA , KANUNGO SONAL
IPC分类号： G06N3/08 , G06F40/253
摘要： A method for detecting fake news using grammatic transformation on neural network computer readable medium Present invention discloses a method for searching fake news using grammar 5 transformation on a neural network, and a recording medium and apparatus for performing the same. The fake news search method using grammar transformation on a neural network is the step of embedding a proposition sentence, which is determined to be true or false by a news sentence, as a word vector, and inputting the word vector into a predetermined natural language processing neural network (context) generating a vector, 10 generating a candidate sentence that is a sentence having the same meaning as the proposition sentence but different grammar by inputting the context vector into a predetermined natural language processing neural network, and comparing the candidate sentence with the news sentence And determining whether the proposition sentence is true or false and searching whether the news sentence corresponds to fake news. Application Number: Page 1 of 2 Word Context Embedding Generating Matching Reasoning Unit Unit Unit Unit 10 30 50 70 FIG. 1 is a block diagram of an apparatus for searching fake news using grammar modification on a neural network

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