专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明专利

DE112019006203T5 Verfahren zur Klassifizierung von Inhalten und Verfahren zur Erzeugung eines Klassifizierungsmodells 未知
公开(公告)号：DE112019006203T5
公开(公告)日：2021-09-02
申请号：DE112019006203
申请日：2019-12-03
申请人： SEMICONDUCTOR ENERGY LAB
发明人： MOMO JUNPEI , FUKUTOME TAKAHIRO
IPC分类号： G06F16/906 , G06F3/048 , G06N20/00
摘要： Ein Klassifizierungsmodell, das Inhalte klassifiziert, wird bereitgestellt. Lerninhalte und Inhalte sind enthalten. Die Lerninhalte sind mit einem ersten Merkmal und einem Lernlabel versehen, und die Inhalte sind mit einem zweiten Merkmal versehen. Das Verfahren zur Klassifizierung von Inhalten umfasst einen Schritt zur Erzeugung einer Vielzahl von ersten Klassifizierungsmodellen durch maschinelles Lernen unter Verwendung der Vielzahl von Lerninhalten, einen Schritt zur Erzeugung eines zweiten Klassifizierungsmodells unter Verwendung der Vielzahl von ersten Klassifizierungsmodellen und einen Schritt zur Bereitstellung von Beurteilungsdaten für die Vielzahl von Inhalten unter Verwendung des zweiten Klassifizierungsmodells und zur Anzeige auf einer GUI. Die Beurteilungsdaten umfassen ein Klassifizierungslabel oder einen Score. Die GUI kann einen bestimmten numerischen Bereich des Scores bestimmen und einen entsprechenden Inhalt in Form einer Liste anzeigen. Es sei angemerkt, dass Merkmale, die für die Inhalte bereitgestellt werden, Verwaltungsparameter (Metadaten) sind.

22. 发明专利

CA3104730A1 APPARATUS FOR FAST CLUSTERING OF MASSIVE DATA BASED ON VARIATE-SPECIFIC POPULATION STRATA 未知
公开(公告)号：CA3104730A1
公开(公告)日：2021-06-30
申请号：CA3104730
申请日：2020-12-31
申请人： AFFINIO INC
发明人： HANKINSON STEPHEN , BESHAI MAGED
IPC分类号： G06Q30/02 , G06F16/906
摘要： ABSTRACT An apparatus for fast clustering of massive data is disclosed. A set of variates characterizes a population of objects with the domain of each variate segmented into a variate-specific number of population strata. The set of variates and the variate-specific population strata define boundaries of a number of cluster zones. Each object of the population of objects is allocated to a cluster corresponding to a respective cluster zone according to the boundaries of the cluster zones and object vectors individually characterizing the population of objects. Upon receiving a specific object vector of a model object, a specific cluster compatible with the model object is determined according to the specific object vector and the boundaries of the cluster zones. Date Recue/Date Received 2021-01-17

23. 发明专利

CA3083461A1 USER INTERFACE SYSTEM INCORPORATING ANALYSIS OF USER INTERACTION CLASSIFICATION 未知
公开(公告)号：CA3083461A1
公开(公告)日：2021-03-27
申请号：CA3083461
申请日：2020-06-12
申请人： TORONTO DOMINION BANK
发明人： JUDY RICHARD DOUGLAS , DEVABHAKTUNI RAJESH BADU , BLOMBERG AARON ANDREW , POLASANI SHRUTHI , HOOPER ADRIAN ALAN
IPC分类号： G06F16/906 , G06F3/048
摘要： A classification system includes a processor and a memory that stores an initial dataset, an analyzed dataset, a model rules database, and instructions. The instructions, in response to receiving first interaction data corresponding to a first interaction, store the first interaction data in the initial dataset as a first entry. The instructions include, at a predetermined time, selecting a set of entries from the initial dataset including the first entry and obtaining a set of analysis rules from the model rules database. The instructions include, for each selected set of entries, calculating an additional parameter based on the obtained set of analysis rules and generating a first analyzed dataset corresponding to the obtained set of analysis rules. The instructions include storing the first analyzed dataset and providing the first analyzed dataset to determine a recommendation using the first analyzed dataset and displaying the recommendation on a user interface.

24. 发明专利

GB2586718A Methods and systems for simplified graphical depictions of bipartite graphs 未知
公开(公告)号：GB2586718A
公开(公告)日：2021-03-03
申请号：GB202015111
申请日：2019-04-04
申请人： BOSCH GMBH ROBERT
发明人： YEUK-YIN CHAN , LIU REN , PANPAN XU
IPC分类号： G06F16/901 , G06F16/904 , G06F16/906
摘要： A method for generating a graphical display of a bipartite graph includes receiving bipartite graph data, generating, a first meta-node including at least two nodes in the first set of nodes in the bipartite graph data and a second meta-node including at least two nodes in a second set of nodes in the bipartite graph data based on the bipartite graph data using a minimum description length (MDL) optimization process to generate the first meta-node and the second meta-node. The method further includes generating a first graphical depiction of the first meta-node and the second meta-node, the graphical depiction including a single edge connecting the first meta-node and the second meta-node to provide a summarized display of the bipartite graph data.

25. 发明专利

CA3086388A1 DOCUMENT MANAGEMENT SYSTEM HAVING CONTEXT-BASED ACCESS CONTROL AND RELATED METHODS 未知
公开(公告)号：CA3086388A1
公开(公告)日：2021-01-11
申请号：CA3086388
申请日：2020-07-10
申请人： BLACKBERRY LTD
发明人： MALTON ANDREW JAMES , WALENSTEIN ANDREW ERIC , QUINTAL KYLE JEFFREY OWEN , KANTARCI MELIKE EROL , KANTARCI BURAK
IPC分类号： G06F16/93 , G06F16/906
摘要： Abstract A document management system having context-based access control and related methods are provided. The document management system determines whether to perform user authentication based on derived context-information comprising one or a combination of derived user-context parameters and document-context parameters that provide additional context to document access requests. Date Recue/Date Received 2020-07-10

26. 发明专利

DE112019000972T5 Verfahren und Systeme für vereinfachte grafische Abbildungen von bipartiten Graphen 未知
公开(公告)号：DE112019000972T5
公开(公告)日：2020-11-12
申请号：DE112019000972
申请日：2019-04-04
申请人： BOSCH GMBH ROBERT
发明人： REN LIU , XU PANPAN , CHAN YEUK-YIN
IPC分类号： G06F16/901 , G06F16/904 , G06F16/906
摘要： Ein Verfahren zum Generieren einer grafischen Darstellung eines bipartiten Graphen beinhaltet, bipartite Graphendaten zu empfangen, einen ersten Metaknoten, der wenigstens zwei Knoten im ersten Satz von Knoten in den bipartiten Graphendaten enthält, und einen zweiten Metaknoten, der wenigstens zwei Knoten in einem zweiten Satz von Knoten in den bipartiten Graphendaten enthält, auf Basis der bipartiten Graphendaten unter Verwendung eines Minimum Description Length- (MDL-) Optimierungsprozesses zu generieren, um den ersten Metaknoten und den zweiten Metaknoten zu generieren. Das Verfahren beinhaltet des Weiteren, eine erste grafische Abbildung des ersten Metaknotens und des zweiten Metaknotens zu generieren, wobei die grafische Abbildung eine einzelne Kante enthält, die den ersten Metaknoten und den zweiten Metaknoten verbindet, um eine verdichtete Darstellung der bipartiten Graphendaten bereitzustellen.

27. 发明专利

GB2582665A Feature dataset classification 未知
公开(公告)号：GB2582665A
公开(公告)日：2020-09-30
申请号：GB201904481
申请日：2019-03-29
申请人： ADVANCED RISC MACH LTD
发明人： EMRE ÖZER , GAVIN BROWN , CHARLES EDWARD MICHAEL REYNOLDS , JEDRZEJ KUFEL , JOHN PHILIP BIGGS
IPC分类号： G06F16/906
摘要： Multiple feature data values, represented by a set of bits are used to indicate a set of features, so that class retrieval circuitry can retrieve class indications for each feature data value. The class indications are predetermined for each permutation of the set of bits for each feature. This enables determination of a classification, which may use a Bayes classifier, such as a Gausssian naïve Bayes classifier, in the training phase as a best indication, and may be based on a single distribution type or heterogeneous types. The class indications may have a look-up table format, and retrieved in parallel for each feature data value. The classification may be determined by a vote, and indications may be weighted. This may be used in a wearable plastic device with feature datasets coupled to sensors.

28. 发明专利

CA3081043A1 METHOD OF AND SYSTEM FOR TRAINING MACHINE LEARNING ALGORITHM FOR OBJECT CLASSIFICATION 未知
公开(公告)号：CA3081043A1
公开(公告)日：2020-08-13
申请号：CA3081043
申请日：2020-05-21
申请人： ELEMENT AI INC
发明人： ZHANG XIANG , DROUIN ALEXANDRE
IPC分类号： G06N20/00 , G06F16/906
摘要： A method and a system for training a machine learning algorithm (MLA) for object classification. The machine learning algorithm includes an embedding layer and a classification layer. A set of embedding indices representing a reference object is received. The set of embedding indices has been generated based on a byte representation of the reference object. A label associated with the reference object indicative of a reference class the objects belongs to is received. The MLA is iteratively trained to classify objects by embedding the set of embedding indices to obtain an input vector and by predicting an estimated class based on the input vector, and updating a parameter of at least one of the embedding layer and the updated embedding layer. The set of embedding indices is generated by parsing the byte representation to obtain byte n-grams and by applying a hash function on the byte n-grams.

29. 发明专利

CA3087635A1 UNIFIED KNOWLEDGE GRAPHS 未知
公开(公告)号：CA3087635A1
公开(公告)日：2020-08-08
申请号：CA3087635
申请日：2019-07-29
申请人： INTUIT INC
发明人： SRUNIVAS SUDHIR , GERAGHTY KEVIN
IPC分类号： G06F17/00 , G06F16/901 , G06F16/906
摘要： Certain aspects of the present disclosure provide techniques for generating a unified knowledge graph. In one example, a method includes receiving entity data from a data source comprising a plurality of entities; forming a plurality of type-specific groups of entity data based on the received entity data; for each respective type-specific group of entity data of the plurality of type-specific groups of entity data: disambiguating the entity data within the respective type-specific group of entity data; creating a plurality of entity relationships based on the disambiguated entity data; and exporting the plurality of entity relationships to a type-specific subgraph; and forming a unified knowledge graph based on a plurality of type-specific subgraphs, wherein each type-specific subgraph of the plurality of type-specific subgraphs is associated with a single type-specific group of entity data of the plurality of type-specific groups of entity data.

30. 发明专利

CA2845743C RESOLVING SIMILAR ENTITIES FROM A TRANSACTION DATABASE 未知
公开(公告)号：CA2845743C
公开(公告)日：2020-03-31
申请号：CA2845743
申请日：2014-03-12
申请人： PALANTIR TECHNOLOGIES INC
发明人： ERENRICH DANIEL
IPC分类号： G06F16/90 , G06F16/906 , G06N20/00 , G06Q20/00
摘要： A technique for identifying related transaction records from a database storing transaction records for multiple entities includes grouping transaction records with a common attribute value into transaction record sets, receiving a selection of an exemplar record set and determining the probability the transaction record set stores transaction records associated with a first entity. Other operations include resolving the transaction record set as storing transaction records associated with the first entity. This improves the process of identifying related transaction records because related transaction records missed by string comparisons transaction record attributes are detected.

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