知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

3215 records (took 0.033 seconds)

    CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS
    1.
    发明申请
    CONTRASTIVE IN-CONTEXT LEARNING FOR LARGE LANGUAGE MODELS 有权

    公开(公告)号：US20250139445A1

    公开(公告)日：2025-05-01

    申请号：US18498988

    申请日：2023-10-31

    Applicant: INTUIT INC.

    Inventor： Xiang GAO ,  Kamalika DAS

    IPC: G06N3/088 ,  G06F40/40 ,  G06N3/0455

    Abstract: A contrastive in-context learning protocol for large language models. The protocol includes inputting positive and negative examples to a large language model. Additionally, the large language model may be instructed to analyze the reasons behind the positive examples being positive and the negative examples being negative. The large language model with such contrastive in-context learning can generate specific responses/answers based on user preferences, generally not possible using conventional models.

    Deep learning based context embedding approach for detecting data entry errors
    2.
    发明授权
    Deep learning based context embedding approach for detecting data entry errors 有权

    公开(公告)号：US12288159B2

    公开(公告)日：2025-04-29

    申请号：US18122633

    申请日：2023-03-16

    Applicant: Intuit, Inc.

    Inventor： Arkadeep Banerjee ,  Vignesh T. Subrahmaniam

    IPC: G06N3/08

    Abstract: Certain aspects of the present disclosure provide techniques for detecting data entry errors. A method generally includes receiving a string value as user input for a data field, selecting a plurality of reference values previously entered into the data field within a time period, processing, with an embedding model configured to classify an input string value as a valid or invalid entry, the string value and the reference values and thereby generating a first vector as output, computing one or more statistics for the reference values and the string value, creating a second vector based on the one or more statistics, generating a concatenated vector by concatenating the first vector and the second vector, processing, with a classifier model configured to classify the string value as valid or invalid, the concatenated vector and thereby generating a classification output, and taking action based on the classification output.

    Intelligent data repair for moving source
    3.
    发明授权
    Intelligent data repair for moving source 有权

    公开(公告)号：US12282465B1

    公开(公告)日：2025-04-22

    申请号：US18775077

    申请日：2024-07-17

    Applicant: Intuit Inc.

    Inventor： Saikiran Sri Thunuguntla ,  Vishal Reddy Baddam ,  Pradeep Srinivas Krishna ,  Thatchinamoorthy Kallipatti Arumugam

    IPC: G06F16/20 ,  G06F16/215 ,  G06F16/23 ,  G06F16/2458 ,  G06F16/18 ,  G06F16/21 ,  G06F16/25

    Abstract: Systems and methods for intelligently repairing data are disclosed. An example method is performed by one or more processors of a data quality management (DQM) system and includes receiving a transmission over a communications network from a computing device associated with the DQM system, the transmission including an indication that source data stored in a source database was ingested and stored as target data in a target database at a time of ingestion, comparing, using an advanced DQM algorithm, the target data with the source data, the advanced DQM algorithm including generating a first set of parity results based on changes occurring before the time of ingestion, generating a second set of parity results based on changes occurring after the time of ingestion, and generating differential results based on the first and the second set of parity results, and selectively repairing ones of the changes based on the differential results.

    Efficient real time serving of ensemble models
    4.
    发明授权
    Efficient real time serving of ensemble models 有权

    公开(公告)号：US12277485B2

    公开(公告)日：2025-04-15

    申请号：US18102075

    申请日：2023-01-26

    Applicant: Intuit Inc.

    Inventor： Aviv Ben Arie ,  Omer Zalmanson

    IPC: G06N20/20

    Abstract: A method implements efficient real time serving of ensemble models. The method includes receiving an input and processing the input with an abridged model to generate a set of component scores and an abridged score. The method further includes processing the set of component scores with a deviation threshold to select one of the abridged score and an ensemble score as an output and presenting the output.

    Computer prediction of relevant data from multiple disparate sources
    5.
    发明授权
    Computer prediction of relevant data from multiple disparate sources 有权

    公开(公告)号：US12271827B2

    公开(公告)日：2025-04-08

    申请号：US17086317

    申请日：2020-10-30

    Applicant: Intuit Inc.

    Inventor： Yair Horesh ,  Alexander Zhicharevich ,  Shlomi Medalion ,  Natalie Bar Eliyahu

    IPC: G06N5/022 ,  G06F18/214 ,  G06F40/30 ,  G06N5/045 ,  G06N20/00

    Abstract: A method including extracting data from disparate data sources. The data includes data pairs including a corresponding data point and a corresponding time associated with the corresponding data point. The method also includes extracting insights from the data at least by identifying a trend in the data pairs. The method also includes forming a model vector including the insights and an additional attribute to the insights. The additional attribute characterizes the insights. The additional attribute includes at least user feedback including a user ranking of a ranked subset of the insights from a user. The method also includes inputting the model vector into a trained insight machine learning model to obtain a predicted ranking of the insights. The method also includes selecting, based on the predicted user ranking, a pre-determined number of insights to form predicted relevant insights. The method also includes reporting the predicted relevant insights.

    DYNAMICALLY TARGETED NETWORK INVITATIONS
    6.
    发明申请
    DYNAMICALLY TARGETED NETWORK INVITATIONS 有权

    公开(公告)号：US20250111397A1

    公开(公告)日：2025-04-03

    申请号：US18480308

    申请日：2023-10-03

    Applicant: INTUIT INC.

    Inventor： Hadar LACKRITZ ,  Natalie BAR ELIYAHU ,  Omer WOSNER

    IPC: H04L41/142 ,  H04L41/0893 ,  H04L43/0876

    Abstract: The present disclosure relates to dynamic targeting of network invitations. Embodiments include clustering, based on network usage data, a plurality of in-network entities into active network users and passive network users. Embodiments include generating, for each active in-network entity, a vector representation based on connections between the active in-network entity and one or more other entities. Embodiments include generating, for each out-of-network entity, a corresponding vector representation based on connections between the out-of-network entity and one or more in-network entities. Embodiments include determining, for each out-of-network, a probability that the out-of-network entity will join the network based on comparing the corresponding vector representation of the out-of-network entity to a vector that is determined based on the vector representation of each active in-network entity. Embodiments include selecting an out-of-network entity to invite to the network based on the probability that the out-of-network entity will join the network.

    IDENTIFICATION AND ALERT GENERATION FOR MISCATEGORIZATIONS IN CATEGORIZATION PROBLEMS
    7.
    发明申请
    IDENTIFICATION AND ALERT GENERATION FOR MISCATEGORIZATIONS IN CATEGORIZATION PROBLEMS 有权

    公开(公告)号：US20250111154A1

    公开(公告)日：2025-04-03

    申请号：US18375775

    申请日：2023-10-02

    Applicant: Intuit Inc.

    Inventor： Natalie BAR ELIYAHU ,  Omer WOSNER

    IPC: G06F40/284 ,  G06F40/40

    Abstract: Systems and methods are disclosed for managing categorization problem solutions and identifying miscategorizations. The identification of a miscategorization of an object is based on the object's first embedding being different than the first embeddings of other objects in a cluster. The objects in the cluster are clustered together based on second embeddings of the objects, with the first embedding generated based on a first description associated with an object and the second embedding generated based on a second description associated with the object. As such, while the clustering of second embeddings may initially indicate that the objects in the cluster are similar, the comparison between first embeddings of the objects in the cluster (such as calculating a distance between a first embedding and a center of the cluster based on the first embeddings) can confirm whether an object in the cluster is different and thus is potentially miscategorized.

    LEAKAGE DETECTION FOR LARGE LANGUAGE MODELS
    9.
    发明申请
    LEAKAGE DETECTION FOR LARGE LANGUAGE MODELS 有权

    公开(公告)号：US20250111092A1

    公开(公告)日：2025-04-03

    申请号：US18478931

    申请日：2023-09-29

    Applicant: Intuit Inc.

    Inventor： Itsik Yizbak MANTIN ,  Ron BITTON

    IPC: G06F21/62 ,  G06F40/20

    Abstract: A method includes receiving, at a server from a user device, a user query to a large language model (LLM), creating an LLM query from the user query and an application context, gathering confidential information from the LLM query, and sending the LLM query to the LLM. The method includes receiving, from the LLM, an LLM response to the LLM query, comparing the LLM response to the confidential information to generate comparison result, and setting a leakage detection signal based on comparison result.

Patent Agency Ranking