METHOD OF PROPOSING SOLUTION, BASED ON SURVEY

    公开(公告)号:US20240362242A1

    公开(公告)日:2024-10-31

    申请号:US18645746

    申请日:2024-04-25

    发明人: Ju Won LIM

    IPC分类号: G06F16/248 G06F16/25

    CPC分类号: G06F16/248 G06F16/258

    摘要: Provided are a method and apparatus for proposing a solution, based on a survey. The method includes storing indicators in a data format in a database, wherein each of the indicators is transformed from a pattern of responses of respondents related to an issue, transforming a response of a user to the survey to a patterned response, the patterned response in the data format, selecting an indicator to be compared with the patterned response among the indicators, the indicators and the patterned response are being in the same data format, determining one or more issues, based on a comparison of the patterned response and the selected indicator, determining a proposal solution set, based on the one or more issues, and displaying the one or more issues and the proposal solution set on a device of the user.

    TECHNIQUES FOR SEARCHING USING TARGET APPLICATIONS

    公开(公告)号:US20240362239A1

    公开(公告)日:2024-10-31

    申请号:US18768302

    申请日:2024-07-10

    摘要: A user device includes a processing unit that executes a search application. Executing the search application causes the processing unit to receive a user search query, send the user search query to a plurality of target applications, and receive a set of search results from each of the target applications. Each search result includes application state access data configured to access an application state of the target application associated with the search result. Executing the search application causes the processing unit to rank the search results, display the ranked search results, and detect user selection of one of the displayed search results. Additionally, executing the search application causes the processing unit to send the application state access data associated with the selected search result to the target application associated with the selected search result and display the application state accessed using the application state access data.

    System and method for a natural language understanding system based on iterative intent detection and slot filling neural layers

    公开(公告)号:US12125478B2

    公开(公告)日:2024-10-22

    申请号:US17409239

    申请日:2021-08-23

    申请人: Robert Bosch GmbH

    发明人: Zhengyu Zhou

    CPC分类号: G10L15/1815 G10L15/16

    摘要: A computer-implemented method includes receiving one or more word embedding vectors in response to data indicative of one or more words. The method also includes utilizing a first recurrent neural network, outputting one or more intent representation vectors utilizing the one or more word embedding vectors; utilizing a second recurrent neural network, outputting one or more slot representation vectors utilizing the one or more intent representation vectors and the one or more word embedding vectors; and utilizing at least an additional third recurrent neural network and a fourth recurrent neural network, outputting a sentence intent and a slot label based on the one or more word embedding vectors, the one or more intent representation vectors, or the one or more slot representation vectors from either the first or second recurrent neural network.

    Digital content query-aware sequential search

    公开(公告)号:US12124439B2

    公开(公告)日:2024-10-22

    申请号:US17513127

    申请日:2021-10-28

    申请人: Adobe Inc.

    摘要: Digital content search techniques are described that overcome the challenges found in conventional sequence-based techniques through use of a query-aware sequential search. In one example, a search query is received and sequence input data is obtained based on the search query. The sequence input data describes a sequence of digital content and respective search queries. Embedding data is generated based on the sequence input data using an embedding module of a machine-learning model. The embedding module includes a query-aware embedding layer that generates embeddings of the sequence of digital content and respective search queries. A search result is generated referencing at least one item of digital content by processing the embedding data using at least one layer of the machine-learning model.