-
公开(公告)号：US20240176674A1
公开(公告)日：2024-05-30
申请号：US18072700
申请日：2022-11-30
Applicant: Maplebear Inc. (dba Instacart)
Inventor： Sahil Khanna , Reza Sadri , Jacob Jensen
CPC classification number: G06F9/5077 , G06F11/3442
Abstract: An online system facilitates various functions using machine learning model microservices. A tuning mechanism tunes various configuration parameters for each microservice that control allocation of computing resources and other configurations of physical and/or virtual machines that implement the microservices. Tuning may be performed in part by executing tests under various configurations and evaluating an objective function associated with the different configurations. Furthermore, parameters of the objective function may be set based on a trained learning model that learns baseline parameters and weights of the objective function based on historical data.
-
公开(公告)号：US20250156451A1
公开(公告)日：2025-05-15
申请号：US18510565
申请日：2023-11-15
Applicant: Maplebear Inc.
Inventor： Jacob Jensen , Fei Jia , Esther Vasiete Allas , Manmeet Singh , Lee Cohn , Tejaswi Tenneti
IPC: G06F16/332 , G06F40/284 , G06F40/40
Abstract: A language model is used to generate autosuggestions to complete or revise a user's partial search query. An initial partial query is applied to the language model to generate query candidates for completing the search query. The language model may generate the query candidates as additional or alternate tokens for the partial search query. When the user revises the partial query, the previously-generated candidates can be re-used to reduce subsequent processing time for generating additional candidates. The previously-generated candidates are compared with the revised partial query to select which of the candidates to be re-used and expanded for generating additional tokens. Additional tokens can be generated in parallel for the previously-generated candidates or with model values from the previous generation, enabling the tokens to be generated effectively with reduced latency consistent with user expectations for search-related autosuggestions.
-
公开(公告)号：US20250133037A1
公开(公告)日：2025-04-24
申请号：US18920765
申请日：2024-10-18
Applicant: Maplebear Inc.
Inventor： Jacob Jensen , Shubhanshu Mishra , Aomin Wu , Rajpal Paryani , Guanghua Shu , Sicheng Zhou
IPC: H04L51/02
Abstract: A system may smartly edit the context of a conversation to be input into a chatbot LLM by using a conversation compression algorithm to prune and compress redundant elements. The system evaluates the conversation context compression algorithm using both a chatbot LLM and an adversarial LLM. The system retrieves a logged conversation and generates a compressed conversation context from the logged conversation. The system generates a synthetic user response by applying the adversarial LLM and generates a test conversation by replacing a user response in the conversation with the synthetic user response. The system generates a compressed context of the test conversation. The system generates a test chatbot LLM response by prompting the chatbot LLM with the compressed context of the test conversation. The system evaluates the conversation context compression algorithm by comparing the test chatbot response with a benchmark chatbot response.
-
4.发明公开公开(公告)号：US20240362523A1
公开(公告)日：2024-10-31
申请号：US18140203
申请日：2023-04-27
Applicant: Maplebear Inc. (dba Instacart)
Inventor： Guanghua Shu , Reza Sadri , Jacob Jensen , Sahil Khanna
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A system maintains a data store for managing machine-learning (ML) models and features that are used by the models. The system generates a graph including nodes for each model and a node for each feature, and edges linking models and features that are used by the models. For a new model to be trained, the system receives a proposed feature corresponding to a node in the graph, and identifies one or more candidate features corresponding to nodes in the graph based in part on relevancy scores between the proposed feature with other features corresponding to nodes in the graph. The system presents in a user interface a suggestion to use one or more candidate features with the new model. Responsive to receiving a user selection of at least one candidate feature, the system causes the new model to be trained using the selected candidate feature and the proposed feature.
-
Patent Agency Ranking
5.发明公开公开(公告)号：US20240362455A1
公开(公告)日：2024-10-31
申请号：US18140210
申请日：2023-04-27
Applicant: Maplebear Inc. (dba Instacart)
Inventor： Guanghua Shu , Reza Sadri , Jacob Jensen , Sahil Khanna
Abstract: A feature management system (the “system”) receives information about a new machine learning (ML) model to be trained. The information includes metadata about the new model. The system applies a trained feature prediction model to the information about the new model and metadata about a plurality of features. The feature prediction model is trained to predict a probability that each of the plurality of features should be selected as an input feature for the new model. The feature management system identifies one or more candidate features based on an output probability score of the feature prediction model. The system presents in a user interface a suggestion to use the one or more candidate features with the new model. The system selects at least one candidate feature and causes the new model to be trained using a set of input features, including the selected candidate feature.
-
公开(公告)号：US20230401186A1
公开(公告)日：2023-12-14
申请号：US17840454
申请日：2022-06-14
Applicant: Maplebear Inc. (dba Instacart)
Inventor： Jacob Jensen
IPC: G06F16/22 , G06F16/2458
CPC classification number: G06F16/22 , G06F16/2477
Abstract: The present disclosure is directed to generating datastore checkpoints. In particular, the methods and systems of the present disclosure may generate, within a datastore, data representing multiple checkpoints. Each checkpoint of the checkpoints may correspond to a respective record of the datastore and may represent a common shared value for a field based at least in part on which the datastore is ordered. Based at least in part on the checkpoints, the datastore may be queried to produce one or more responsive records to one or more criteria of the query. Based at least in part on the responsive record(s), training data may be generated. The training data may be utilized for training one or more machine learning (ML) models configured to process input based at least in part on values for the field based at least in part on which the datastore is ordered.
-
公开(公告)号：US20250139657A1
公开(公告)日：2025-05-01
申请号：US18932041
申请日：2024-10-30
Applicant: Maplebear Inc.
Inventor： Changyao Chen , Jacob Jensen
IPC: G06Q30/0207 , G06Q30/0601
Abstract: An online system accesses user behavior data and incentive data collected for a user prior to a current time period. The online system trains a behavior prediction model to receive user behavior data for a user and an incentive and output an incentive score using the collected user behavior data. The online system receives one or more candidate incentives generated by an incentive generation model based on the accessed user behavior data and incentive data. The online system applies each candidate incentive to the behavior prediction model to generate an incentive prediction describing a degree of user interaction of the particular user with the online system responsive to offering the candidate incentive to the user. The online system offers one or more candidate incentives to the user based on the determined incentive predictions.
-
公开(公告)号：US20250139523A1
公开(公告)日：2025-05-01
申请号：US18925017
申请日：2024-10-24
Applicant: Maplebear Inc.
Inventor： Jacob Jensen , Guanghua Shu
IPC: G06N20/00
Abstract: An online system augments a dataset in conjunction with a model serving system. The online system accesses a dataset for training a machine-learning model. The online system generates a prompt to generate candidate samples in the training dataset to the model serving system. The online system receives a response comprising one or more candidate samples. The online system compares the one or more candidate samples to at least one existing sample of the dataset to determine whether the one or more candidate samples are within a threshold level of similarity to an existing sample. If a candidate sample received from the machine-learning language model is not within the threshold level of similarity to an existing sample, the online system updates the dataset with the candidate sample.
-
公开(公告)号：US20240104271A1
公开(公告)日：2024-03-28
申请号：US17955468
申请日：2022-09-28
Applicant: Maplebear Inc. (dba Instacart)
Inventor： Konrad Gustav Miziolek , Jacob Jensen
Abstract: A variation testing system environment for simulating adaptive experiments of objects is disclosed. An experiment system conducts one or more simulations of an adaptive experiment that includes a plurality of variants of an object. Simulation results based on the one or more simulations are generated that are indicative of at least an estimated amount of time to conduct a real-world adaptive experiment based on the one or more simulations.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.02 seconds)
