-
公开(公告)号：US20240177212A1
公开(公告)日：2024-05-30
申请号：US18072353
申请日：2022-11-30
发明人： Aditya Subramanian , Prakash Putta , Tejaswi Tenneti , Jonathan Lennart Bender , Xiao Xiao , Taesik Na
IPC分类号： G06Q30/0601
CPC分类号： G06Q30/0631
摘要： To determine search results for an online shopping concierge platform, the platform may receive, from a computing device associated with a customer of an online shopping concierge platform, data describing one or more search parameters input by the customer; identify, based at least in part on the data describing the search parameter(s), products offered by the online shopping concierge platform that are at least in part responsive to the search parameter(s); and determine, for each product and based at least in part on one or more machine learning (ML) models, a relevance of the product to one or more taxonomy levels of a product catalog associated with the online shopping concierge platform, a likelihood that the customer would be offended by inclusion of the product amongst displayed responsive search results, and/or the like.
-
公开(公告)号：US20230252549A1
公开(公告)日：2023-08-10
申请号：US18107854
申请日：2023-02-09
发明人： Yuqing Xie , Taesik Na , Saurav Manchanda
IPC分类号： G06Q30/0601 , G06Q30/0201
CPC分类号： G06Q30/0631 , G06Q30/0201
摘要： 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.
-
公开(公告)号：US20240303711A1
公开(公告)日：2024-09-12
申请号：US18596592
申请日：2024-03-05
申请人： Maplebear Inc.
发明人： Li Tan , Tejaswi Tenneti , Shishir Kumar Prasad , Huapu Pan , Allan Stewart , Taesik Na , Tyler Russell Tate , Joshua Roberts , Haixun Wang
IPC分类号： G06Q30/0601 , G06F16/9532
CPC分类号： G06Q30/0627 , G06F16/9532 , G06Q30/0635
摘要： A system, for example, an online system uses a machine learning based language model, for example, a large language model (LLM) to process high-level natural language queries received from users. The system receives a natural language query from a user of a client device. The system determines contextual information associated with the query. Based on this information, the system generates a prompt for the machine learning based language model. The system receives a response from the machine learning based language model. The system uses the response to generate a search query for a database. The system obtains results returned by the database in response to the search query and provides them to the user. The system allows users to specify high level natural language queries to obtain relevant search results, thereby improving the overall user experience.
-
公开(公告)号：US20240241897A1
公开(公告)日：2024-07-18
申请号：US18415551
申请日：2024-01-17
申请人： Maplebear Inc.
发明人： Haixun Wang , Taesik Na , Li Tan , Jian Li , Xiao Xiao
IPC分类号： G06F16/33 , G06F16/338 , G06N20/00
CPC分类号： G06F16/3344 , G06F16/338 , G06N20/00
摘要： A system may generate a prompt based in part on a search query from a customer client device. The prompt instructs a machine learned model to provide item predictions. And the model was trained by: converting structured data describing items of an online catalog to annotated text data (unstructured data), generating training examples based in part on the annotated text data, and training the model using the training examples. The system may receive item predictions generated by the prompt being applied to the machine learned model, the item predictions may have corresponding item identifiers. The item predictions are processed to identify a recommended item from the item predictions. The processing includes determining item information for the recommended item using an item identifier associated with the recommended item. The item information is provided to the customer client device.
-
15.发明公开公开(公告)号：US20230252049A1
公开(公告)日：2023-08-10
申请号：US17736716
申请日：2022-05-04
发明人： Taesik Na , Tejaswi Tenneti , Haixun Wang , Xiao Xiao
IPC分类号： G06F16/28 , G06F16/2457 , G06F16/248 , G06K9/62
CPC分类号： G06F16/285 , G06F16/24573 , G06F16/24575 , G06F16/248 , G06K9/6276
摘要： An online system leverages stored interactions with items made by users after the online system received queries to determine display of items satisfying the query. For example, the online system trains a model to predict a likelihood of a user performing an interaction with an item displayed after a query was received. As different items receive different amounts of interaction from users, limited historical interaction with certain items may limit accuracy of the model. The online system generates embeddings for previously received queries and uses measures of similarity between embeddings for queries to generate clusters of queries. Previous interactions with queries in a cluster are combined, with the combined data being used for determining display of items in response to a query.
-
公开(公告)号：US20230146336A1
公开(公告)日：2023-05-11
申请号：US17524491
申请日：2021-11-11
发明人： Haixun Wang , Taesik Na , Tejaswi Tenneti , Saurav Manchanda , Min Xie , Chuan Lei
CPC分类号： G06Q30/0603 , G06N20/00
摘要： To simplify retrieval of items from a database that at least partially satisfy a received query, an online concierge system trains a model that outputs scores for items from the database without initially retrieving items for evaluation by the model. The online concierge system pre-trains the model using natural language inputs corresponding to items from the database, with a natural language input including masked words that the model is trained to predict. Subsequently, the model is refined using multi-task training where a task is trained to predict scores for items from the received query. The online concierge system selects items for display in response to the received query based on the predicted scores.
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.017 秒)
