中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

64 records (took 0.026 seconds)

    PRESENTATION AND ANALYSIS OF USER INTERACTION DATA
    41.
    发明申请
    PRESENTATION AND ANALYSIS OF USER INTERACTION DATA 审中-公开

    公开(公告)号：US20200326823A1

    公开(公告)日：2020-10-15

    申请号：US16911791

    申请日：2020-06-25

    Applicant: Palantir Technologies Inc.

    Inventor： Ben Duffield ,  Geoff Stowe ,  Ankit Shankar

    IPC: 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 analyses 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.

    Database system for time series data storage, processing, and analysis
    42.
    发明授权
    Database system for time series data storage, processing, and analysis 有权

    公开(公告)号：US10216695B1

    公开(公告)日：2019-02-26

    申请号：US15922752

    申请日：2018-03-15

    Applicant: Palantir Technologies Inc.

    Inventor： Ankit Shankar ,  Kirat Singh ,  Kayo Teramoto ,  Lucas Lemanowicz ,  Thomas Hasner

    IPC: G06F7/00 ,  G06F17/30 ,  H04W4/38 ,  G06F9/451 ,  G06F17/18

    Abstract: A system includes a communications interface configured to receive a plurality of data series captured by a plurality of sensors. A first database includes at least a first data series of the plurality of data series. A second database includes metadata related to the first data series. One or more processors are configured to receive an instruction including an indication of a computation to perform and metadata filter criteria, query the second database to determine at least a portion of the first data series that satisfies the metadata filter criteria by reference to at least the metadata related to the first data series, access, from the first database and based on results of the query of the second database, the portion of the first data series, and perform the computation on the portion of first data series accessed from the first database.

    PRESENTATION AND ANALYSIS OF USER INTERACTION DATA
    45.
    发明申请
    PRESENTATION AND ANALYSIS OF USER INTERACTION DATA 审中-公开

    公开(公告)号：US20170364227A1

    公开(公告)日：2017-12-21

    申请号：US15697808

    申请日：2017-09-07

    Applicant: Palantir Technologies Inc.

    Inventor： Ben Duffield ,  Geoff Stowe ,  Ankit Shankar

    IPC: 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 analyses 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.

    SYSTEMS AND USER INTERFACES FOR DYNAMIC AND INTERACTIVE SIMULTANEOUS QUERYING OF MULTIPLE DATA STORES
    48.
    发明申请
    SYSTEMS AND USER INTERFACES FOR DYNAMIC AND INTERACTIVE SIMULTANEOUS QUERYING OF MULTIPLE DATA STORES 有权
    多个数据存储区的动态和交互式同时查询的系统和用户界面

    公开(公告)号：US20150112998A1

    公开(公告)日：2015-04-23

    申请号：US14504103

    申请日：2014-10-01

    Applicant: Palantir Technologies Inc.

    Inventor： Ankit Shankar ,  Andrew Ash ,  Geoff Stowe ,  Thomas Petracca ,  Benjamin Duffield

    IPC: G06F17/30

    CPC classification number: G06F17/3056 ,  G06F17/30312 ,  G06F17/30389 ,  G06F17/30395 ,  G06F17/30427 ,  G06F17/30477 ,  G06F17/30545 ,  G06F17/30554 ,  G06F17/30566 ,  G06F17/30625 ,  G06F17/30958

    Abstract: Embodiments of the present disclosure relate to a computer system and interactive user interfaces configured to enable efficient and rapid access to multiple different data sources simultaneously, and by an unskilled user. The unskilled user may provide simple and intuitive search terms to the system, and the system may thereby automatically query multiple related data sources of different types and present results to the user. Data sources in the system may be efficiently interrelated with one another by way of a mathematical graph in which nodes represent data sources and/or portions of data sources (for example, database tables), and edges represent relationships among the data sources and/or portions of data sources. For example, edges may indicate relationships between particular rows and/or columns of various tables. The table graph enables a compact and memory efficient storage of relationships among various disparate data sources.

    Abstract translation: 本公开的实施例涉及被配置为能够同时有效且快速地访问多个不同数据源的计算机系统和交互式用户界面，以及非熟练用户。 不熟练的用户可以向系统提供简单和直观的搜索项，并且系统可以自动地查询不同类型的多个相关数据源并将结果呈现给用户。 系统中的数据源可以通过数学图形来有效地相互关联，其中节点表示数据源和/或数据源（例如，数据库表）的部分，边缘表示数据源和/或 部分资料来源。 例如，边缘可以指示各种表的特定行和/或列之间的关系。 表格可以实现对各种不同数据源之间关系的紧凑和高效的存储。

    LARGE LANGUAGE MODEL RESPONSE OPTIMIZATION USING CUSTOM COMPUTER LANGUAGES
    49.
    发明申请
    LARGE LANGUAGE MODEL RESPONSE OPTIMIZATION USING CUSTOM COMPUTER LANGUAGES 有权

    公开(公告)号：US20240403290A1

    公开(公告)日：2024-12-05

    申请号：US18674672

    申请日：2024-05-24

    Applicant: Palantir Technologies Inc.

    Inventor： Matthew Hawes ,  Ankit Shankar ,  Matthew Bayer

    IPC: G06F16/242

    Abstract: A system may receive a natural language query and receive an indication of a format of a first computer language as well as an indication of one or more computer-based tools stored in and/or accessible by the system. The system can transmit a prompt to a large language model (“LLM”). The prompt may include the natural language query, the indication of the format, and the indication of the one or more computer-based tools. The system can receive, from the LLM, a response to the prompt in the format of the first computer language. The system can parse the response in the first computer language to identify at least: a computer-based tool of the one or more computer-based tools. The system can generate a second query in a second computer language and provide the second query in the second computer language to the computer-based tool.

    STRUCTURING AND RICH DEBUGGING OF INPUTS AND OUTPUTS TO LARGE LANGUAGE MODELS
    50.
    发明申请
    STRUCTURING AND RICH DEBUGGING OF INPUTS AND OUTPUTS TO LARGE LANGUAGE MODELS 有权

    公开(公告)号：US20240403194A1

    公开(公告)日：2024-12-05

    申请号：US18676141

    申请日：2024-05-28

    Applicant: Palantir Technologies Inc.

    Inventor： Matthew Hawes ,  Ankit Shankar ,  Morten Telling ,  Jack Dobson ,  Adil Majid

    IPC: G06F11/36

    Abstract: The disclosure is directed to methods and systems for improving interactions with a Large Language Model (LLM). An artificial intelligence system (AIS) can receive user inputs via a graphical user interface indicating a task to be performed by the LLM, one or more tools which may be accessed by the AIS in response to tool calls from the LLM, and an output schema for structuring a format of a response from the LLM. The AIS can generate a prompt for the LLM based on the user input. The prompt can include indications of the one or more tools, one or more example tool operations, the task to be performed, and an indication of the output schema. The AIS can include a debugging application or module enabling rich debugging of language model interactions in a single view.

Patent Agency Ranking