GENERATING NEW CONTENT FROM EXISTING PRODUCTIVITY APPLICATION CONTENT USING A LARGE LANGUAGE MODEL

    公开(公告)号:US20240289360A1

    公开(公告)日:2024-08-29

    申请号:US18174740

    申请日:2023-02-27

    Inventor: Isaac CHEPKWONY

    CPC classification number: G06F16/3328 G06F40/40 G06T11/60

    Abstract: Systems and methods for generating new content from a machine-learning model. A content generator extracts string content from existing slides of a slide presentation document and generates a text query using the existing slide content as context. The query is directed to a large language model. Additionally, prompt input from a user is received and combined with the context in the query. A response from the large language model is parsed and text output is separated into prospective slides to add to the slide presentation document. Upon selection of one or more prospective slides, the prospective slides are generated and added as new slides to the slide presentation document.

    METHODS AND SYSTEMS FOR GENERATION OF TEXT USING LARGE LANGUAGE MODEL WITH INDICATIONS OF UNSUBSTANTIATED INFORMATION

    公开(公告)号:US20240256764A1

    公开(公告)日:2024-08-01

    申请号:US18180518

    申请日:2023-03-08

    Applicant: Shopify Inc.

    CPC classification number: G06F40/169 G06F16/3328 G06F40/205 G06F40/40

    Abstract: Methods and systems for prompting a large language model (LLM) to generate a description of an object with indications of any unsubstantiated information are disclosed. A prompt is generated to a LLM to generate a description of an object, where the prompt includes one or more object attributes to include in the generated description. The prompt also includes an instruction for the LLM to annotate any portions of the generated description that are, involve, and/or include unsubstantiated information according to a defined format. The prompt is provided to the LLM and the generated description is received. The generated description is parsed to identify, based on the defined format, one or more annotated portions indicating unsubstantiated information. The generated description is presented for display via a user device.

    SYSTEM AND METHOD FOR ADAPTIVE SEARCH RESPONSES

    公开(公告)号:US20240220518A1

    公开(公告)日:2024-07-04

    申请号:US18093206

    申请日:2023-01-04

    CPC classification number: G06F16/3328 G06F16/3347

    Abstract: Systems, methods, and other embodiments associated with an adaptive search system are described. In one embodiment, user actions are monitored on a search results list in a graphical user interface, wherein the search results list is obtained based on a query vector representing a search query. The query vector is dynamically modified in response to the user actions on a selected result document by shifting the query vector away from the selected result document in a vector space in response to the user rejecting the selected result document. A revised search results list is then generated without the user changing the search query by executing the modified query vector in a search.

    Non-tabular datasource connector
    88.
    发明授权

    公开(公告)号:US11966426B2

    公开(公告)日:2024-04-23

    申请号:US17161016

    申请日:2021-01-28

    Applicant: Splunk Inc.

    Abstract: Systems and methods for querying and obtaining results from an external data source that operates with a different querying language is provided. The system activates a datasource connector of the system. The system receives attributes of a query in a native language of the system, and the datasource connector formats the attributes of the query into a query language statement in a native language of the external source. The datasource connector then makes an application programming interface (API) call to the external source. The API call includes a transmission of the query language statement to the external source, which causes the external source to perform a query using the query language statement. The datasource connector receives results of the query performed at the external source, whereby the results are in a non-tabular format. The datasource connector then reformats the results into a tabular format.

Patent Agency Ranking