知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.018 seconds)

    ATTRIBUTE PREDICTION WITH MASKED LANGUAGE MODEL
    1.
    发明公开
    ATTRIBUTE PREDICTION WITH MASKED LANGUAGE MODEL 审中-公开

    公开(公告)号：US20240005096A1

    公开(公告)日：2024-01-04

    申请号：US17855799

    申请日：2022-07-01

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Ramasubramanian Balasubramanian ,  Saurav Manchanda

    IPC: G06F40/284 ,  G06F40/186 ,  G06N5/02

    CPC classification number: G06F40/284 ,  G06F40/186 ,  G06N5/022

    Abstract: A masked language model is used to predict an attribute of an object, such as a physical item or product based on the predicted value of a masked token. The masked language model may be trained on a general corpus of text for the language, such that the masked language model learns context and text token relationships. Information about the object may then be added to a query template that structures the item information in an attribute query that may be interpretable by the masked language model to provide a resulting token related to the provided information or to confirm or reject an attribute specified in the query template.

    Search Relevance Model Using Self-Adversarial Negative Sampling
    2.
    发明公开
    Search Relevance Model Using Self-Adversarial Negative Sampling 审中-公开

    公开(公告)号：US20230252549A1

    公开(公告)日：2023-08-10

    申请号：US18107854

    申请日：2023-02-09

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Yuqing Xie ,  Taesik Na ,  Saurav Manchanda

    IPC: G06Q30/0601 ,  G06Q30/0201

    CPC classification number: G06Q30/0631 ,  G06Q30/0201

    Abstract: To train an embedding-based model to determine relevance between items and queries, an online system generates training data from previously received queries and interactions with results for the queries. The training data includes positive training examples including a query and an item with which a user performed a specific interaction after providing the query. To generate negative training examples for the query to include in the training data, the online system determines measures of similarity between items with which the specific interaction was not performed and the query. The online system may weight a loss function for the embedding-based model by the measure of similarity for a negative example, increasing the effect of a negative example including a query and an item with a larger measure of similarity. In other embodiments, the online system selects negative training examples based on the measures of similarities between items and queries in pairs.

    CONTENT SELECTION WITH INTER-SESSION REWARDS IN REINFORCEMENT LEARNING
    3.
    发明公开
    CONTENT SELECTION WITH INTER-SESSION REWARDS IN REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20240330695A1

    公开(公告)日：2024-10-03

    申请号：US18129023

    申请日：2023-03-30

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Saurav Manchanda ,  Ramasubramanian Balasubramanian

    IPC: G06N3/092 ,  G06N3/04

    CPC classification number: G06N3/092 ,  G06N3/04

    Abstract: A reinforcement learning model selects a content composition based, in part, on inter-session rewards. In addition to near-in-time rewards of user interactions with a content composition for evaluating possible actions, the reinforcement learning model also generates a reward and/or penalty based on between-session information, such as the time between sessions. This permits the reinforcement learning model to learn to evaluate content compositions not only on the immediate user response, but also on the effect of future user engagement. To determine a composition for a search query, the reinforcement learning model generates a state representation of the user and search query and evaluates candidate content compositions based on learned parameters of the reinforcement learning model that evaluates inter-session rewards of the content compositions.

    ITEM ATTRIBUTE DETERMINATION USING A CO-ENGAGEMENT GRAPH
    4.
    发明公开
    ITEM ATTRIBUTE DETERMINATION USING A CO-ENGAGEMENT GRAPH 审中-公开

    公开(公告)号：US20240104632A1

    公开(公告)日：2024-03-28

    申请号：US17935916

    申请日：2022-09-27

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Creagh Briercliffe ,  Chuan Lei ,  Saurav Manchanda ,  Min Xie

    IPC: G06Q30/06

    CPC classification number: G06Q30/0635 ,  G06Q30/0613 ,  G06Q30/0627 ,  G06Q30/0639

    Abstract: An online concierge system uses a co-engagement graph to assign attribute values to items for which those attribute values are uncertain. A co-engagement graph is a graph with nodes that represent items and edges that represent co-engagement between items. The online concierge system generates a co-engagement graph for a set of items based on item engagement data and item data for the items. The set of items includes items for which the online concierge system has an attribute value for a target attribute and items for which the online concierge system does not have an attribute value for the target attribute. The online concierge system identifies a node that corresponds to an unknown item and identifies a node connected to that first node that corresponds to a known item. The online concierge system assigns the attribute value for the known item to the unknown item.

    USING UNSUPERVISED CLUSTERING AND LANGUAGE MODEL TO NORMALIZE ATTRIBUTE TUPLES OF ITEMS IN A DATABASE
    6.
    发明申请
    USING UNSUPERVISED CLUSTERING AND LANGUAGE MODEL TO NORMALIZE ATTRIBUTE TUPLES OF ITEMS IN A DATABASE 有权

    公开(公告)号：US20250005279A1

    公开(公告)日：2025-01-02

    申请号：US18215505

    申请日：2023-06-28

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Shih-Ting Lin ,  Prithvishankar Srinivasan ,  Saurav Manchanda ,  Shishir Kumar Prasad ,  Min Xie

    IPC: G06F40/247 ,  G06F16/21 ,  G06F16/215 ,  G06F16/28

    Abstract: A computer system uses clustering and a large language model (LLM) to normalize attribute tuples for items stored in a database of an online system. The online system collects attribute tuples, each attribute tuple comprising an attribute type and an attribute value for an item. The online system initially clusters the attribute tuples into a first plurality of clusters. The online system generates prompts for input into the LLM, each prompt including a subset of attribute tuples grouped into a respective cluster of the first plurality. Based on the prompts, the LLM generates a second plurality of clusters, each cluster including one or more attribute tuples that have a common attribute type and a common attribute value. The online system maps each attribute tuple to a respective normalized attribute tuple associated with each cluster. The online system rewrites each attribute tuple in the database to a corresponding normalized attribute tuple.

    DOMAIN-ADAPTIVE CONTENT SUGGESTION FOR AN ONLINE CONCIERGE SYSTEM
    8.
    发明公开
    DOMAIN-ADAPTIVE CONTENT SUGGESTION FOR AN ONLINE CONCIERGE SYSTEM 审中-公开

    公开(公告)号：US20230186361A1

    公开(公告)日：2023-06-15

    申请号：US17550960

    申请日：2021-12-14

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Saurav Manchanda ,  Ramasubramanian Balasubramanian

    IPC: G06Q30/06 ,  G06Q30/02

    CPC classification number: G06Q30/0619 ,  G06Q30/0282 ,  G06Q30/0641

    Abstract: An online concierge system uses a domain-adaptive suggestion module to score products that may be presented to a user as suggestions in response to a user’s search query. The domain-adaptive suggestion module receives data that is relevant to scoring products as suggestions in response to a search query. The domain-adaptive suggestion module uses one or more domain-neutral representation models to generate a domain-neutral representation of the received data. The domain-neutral representation is a featurized representation of the received data that can be used by machine-learning models in the search domain or the suggestion domain. The domain-adaptive suggestion module then scores products by applying one or more machine-learning models to domain-neutral representations generated based on those products. By using domain-neutral representations, the domain-adaptive suggestion module can be trained based on training examples from a similar prediction task in a different domain.

    MACHINE LEARNING MODEL FOR CLICK THROUGH RATE PREDICTION USING THREE VECTOR REPRESENTATIONS
    9.
    发明申请
    MACHINE LEARNING MODEL FOR CLICK THROUGH RATE PREDICTION USING THREE VECTOR REPRESENTATIONS 有权

    公开(公告)号：US20230135683A1

    公开(公告)日：2023-05-04

    申请号：US17513739

    申请日：2021-10-28

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Ramasubramanian Balasubramanian ,  Saurav Manchanda

    IPC: G06Q30/06 ,  G06Q30/02

    Abstract: An online concierge system uses a machine learning click through rate model to select promoted items based on user embeddings, item embeddings, and search query embeddings. Embeddings obtained by an embedding model may be used as inputs to the click through rate model. The embedding model may be trained using different actions to score the strength of a customer interaction with an item. For example, a customer purchasing an item may be a stronger signal than a customer placing an item in a shopping cart, which in turn may be a stronger signal than a customer clicking on an item. The online concierge system generates a ranking of candidate promoted items based on the search query and using the click through rate model. Based on the ranking, the online concierge system displays promoted items along with the organic search results to the customer.

Patent Agency Ranking