SAVING PRODUCTION RUNS OF A FUNCTION AS UNIT TEST AND AUTOMATIC OUTPUT REGENERATION

    公开(公告)号:US20240403634A1

    公开(公告)日:2024-12-05

    申请号:US18676339

    申请日:2024-05-28

    Abstract: An artificial intelligence system can be used to respond to natural language inputs. The AI System may, for example, receive a first user input for a LLM, generate a first prompt based on the first user input, transmit the first prompt to an LLM, receive an output from the LLM, and evaluate the output from the LLM with reference to one or more validation tests. Responsive to determining that the output from the LLM is not validated, generate a second prompt for the LLM, where the second prompt indicates at least an aspect of the output that caused the output to not be evaluated (e.g., a portion of the output that may need to be updated or corrected), transmit the second prompt to the LLM, and receive an updated output from the LLM. The AI system can include an application for testing functions that utilize interactions with language models.

    GRAPHICAL REPRESENTATION OF A COMPLEX TASK

    公开(公告)号:US20220138870A1

    公开(公告)日:2022-05-05

    申请号:US17578224

    申请日:2022-01-18

    Abstract: Systems and methods are provided for storing data representing respective sub-elements of a complex task. Data representing one or more links between two or more sub-elements is stored, the links indicating a dependency between said sub-elements. A work order is calculated based on the identified links. A graphical representation of the calculated work order which indicates said sub-elements and their dependencies is provided. The links may indicate a temporal dependency of a second sub-element on a first sub-element and in which the provided graphical representation presents the temporal relationship of the sub-elements. Historical data may be received for association with one or more selected links or sub-elements, the historical data related to a prior event and which affects the temporal relationship between the sub-elements. An updated work order modified by the historical data may be calculated. An updated graphical representation of the work order may be provided.

    Presentation and analysis of user interaction data

    公开(公告)号:US09785317B2

    公开(公告)日:2017-10-10

    申请号:US14228109

    申请日:2014-03-27

    CPC classification number: G06F3/0484 G06Q10/00

    Abstract: An interactive, graph-based user interaction data analysis system is disclosed. The system is configured to provide analysis and graphical visualizations of user interaction data to a system operator. In various embodiments, interactive visualizations and analyzes provided by the system may be based on user interaction data aggregated across particular groups of users, across particular time frames, and/or from particular computer-based platforms and/or applications. According to various embodiments, the system may enable insights into, for example, user interaction patterns and/or ways to optimize for desired user interactions, among others. In an embodiment, the system allows an operator to analyze and investigate user interactions with content provided via one or more computer-based platforms, software applications, and/or software application editions.

    Graphical representation of an output

    公开(公告)号:US09652139B1

    公开(公告)日:2017-05-16

    申请号:US15216476

    申请日:2016-07-21

    CPC classification number: G06F3/04847 G06F3/0482 G06T11/206

    Abstract: Aspects of the present disclosure relate to graphical representation of an output. A server provides for presentation, at a display device, of a first graphical representation of an output for a class. The server receives a selection of a time range for the class. The server determines, based on the output for the class during the selected time range, a baseline output. The server provides for presentation, in response to the selection of the time range, of a second graphical representation of the output, during the time range, for a family from the class, the second graphical representation indicating a difference between the output for the family and an output value for the family predicted based on the baseline output.

Patent Agency Ranking