Patents Assigned to Intuit
-
Publication number: 20250181623Abstract: Aspects of the invention provide a method, computer system, and computer program product for retrieval augmented generation. In one aspect, the method includes receiving a query. The method further includes classifying the query to a first domain within a multitude of domains. The method additionally includes retrieving an index of domain-specific vector embeddings corresponding to the domains. The method further includes prompting a Large Language Model (LLM) with the query and the domain-specific vector embeddings. The method also includes receiving a query response from the LLM as grounded with the most relevant index results. The method further includes forwarding the query response.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: Intuit Inc.Inventors: Siddharth JAIN, Venkat VEDAM
-
Publication number: 20250181964Abstract: A method including receiving a domain vector including a first data structure describing a first domain with which a subject interacts. A multilabel classification model is applied to the domain vector to generate a classification prediction including a classification vector. The classification vector has a second data structure describing a likelihood that a second domain, which is different than the first domain, is related to the subject. The classification prediction is based on the first domain. An uplift model is applied to the classification vector to generate an uplift value. The uplift value represents a probability that the subject is positively associated with the second domain. A vectorization algorithm is applied to the subject, the second domain, and the uplift value to generate an uplift vector including a third data structure describing a triplet of the subject, the second domain, and the uplift value. The uplift vector is returned.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: Intuit Inc.Inventors: Aleksandr KIM, Yair HORESH, Itay MARGOLIN
-
Publication number: 20250181835Abstract: A method including applying a large language model to a query to generate a query vector. The query vector has a query data structure storing a semantic meaning of the query. The method also includes applying a semantic matching algorithm to both the query vector and a lookup vector. The lookup vector has a lookup data structure storing semantic meanings of entries of a lookup table. The semantic matching algorithm compares the query vector to the lookup vector and returns, as a result of comparing, a found entry in the lookup table. The method also includes looking up, using the found entry in the lookup table, a target entry in the lookup table. The method also includes returning the target entry.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: Intuit Inc.Inventors: Lan JIN, Shivani GOWRISHANKAR, Shankar SANKARARAMAN
-
Publication number: 20250182180Abstract: Methods and a computer system are provided for recommending digital products based on user state. An application state is received at an endpoint. The endpoint is a single endpoint that includes a plurality of models. Each model of the plurality is trained on a corresponding dataset including features of the application state extracted at different stages of a workflow. The application state is matched to a first stage of the workflow and the first model is selected from the plurality of models. The first model corresponds to a first stage of the workflow. The first model processes the application state to select a first digital product of a plurality of digital products, which is presented as a recommendation to the user at the first stage of the workflow.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: Intuit Inc.Inventors: Jingyuan ZHANG, Shankar SANKARARAMAN
-
Publication number: 20250181843Abstract: At least one processor can obtain configuration instructions to direct operations of a natural language processing (NLP) machine learning (ML) pipeline. The configuration instructions can comprise at least one plain-language indicator of at least one NLP operation to be performed by the ML pipeline. The at least one processor can configure the ML pipeline using the configuration file. The at least one processor can perform NLP on text data using the configured ML pipeline.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: INTUIT INC.Inventors: Jineet Hiren DOSHI, Maya Vered LIVSHITS, Pragya TRIPATHI
-
Publication number: 20250181619Abstract: Aspects of the invention provide a method, computer system, and computer program product for retrieval augmented generation. In one aspect, the method includes receiving a query. The method further includes classifying the query to a first domain within a multitude of domains. The method additionally includes retrieving an index of domain-specific vector embeddings corresponding to the domains. The method further includes prompting a large language model (LLM) with the query and the domain-specific vector embeddings. The method also includes receiving a query response from the LLM as grounded with the most relevant index results. The method further includes forwarding the query response.Type: ApplicationFiled: November 30, 2023Publication date: June 5, 2025Applicant: Intuit Inc.Inventors: Siddharth JAIN, Vijay THOMAS, Venkat VEDAM, Pratik LALA
-
Patent number: 12315515Abstract: Certain embodiments of the present disclosure provide techniques training a user detection model to identify a user of a software application based on voice recognition. The method generally includes receiving a data set including a plurality of voice interactions with users of a software application. For each respective recording in the data set, a spectrogram representation is generated based on the respective recording. A plurality of voice recognition models are trained. Each of the plurality of voice recognition models is trained based on the spectrogram representation for each of the plurality of voice recordings in the data set. The plurality of voice recognition models are deployed to an interactive voice response system.Type: GrantFiled: January 30, 2024Date of Patent: May 27, 2025Assignee: Intuit Inc.Inventors: Shanshan Tuo, Divya Beeram, Meng Chen, Neo Yuchen, Wan Yu Zhang, Nivethitha Kumar, Kavita Sundar, Tomer Tal
-
Patent number: 12299551Abstract: Aspects of the present disclosure provide techniques for training a machine learning model. Embodiments include receiving a historical support record comprising time-stamped actions, a support initiation time, and an account indication. Embodiments include determining features of the historical support record based at least on differences between times of the time-stamped actions and the support initiation time. Embodiments include determining a label for the features based on the account indication. Embodiments include training an ensemble model, using training data comprising the features and the label, to determine an indication of an account in response to input features, wherein the ensemble model comprises a plurality of tree-based models and a ranking model.Type: GrantFiled: July 13, 2020Date of Patent: May 13, 2025Assignee: Intuit Inc.Inventors: Shanshan Tuo, Neo Yuchen, Divya Beeram, Valentin Vrzheshch, Tomer Tal, Ngoc Nhung Ho
-
Publication number: 20250148508Abstract: A method implements brand engine for extracting and presenting brand data with user interfaces. The method includes receiving a blueprint with a set of structure blocks extracted from a selected content. A structure block of the set of structure blocks includes a set of style parameter requests for a section of the selected content. The method further includes processing the set of structure blocks with a first set of smart blocks to generate a set of scores. A smart block of the first set of smart blocks includes brand data with style parameter selections. The method further includes selecting a second set of smart blocks, for the set of structure blocks, from the first set of smart blocks, using the set of scores. The method further includes presenting the second set of smart blocks with the brand data.Type: ApplicationFiled: January 10, 2025Publication date: May 8, 2025Applicant: Intuit Inc.Inventors: Ivan SHEVCHENKO, Tatiana SUKHOVA
-
Publication number: 20250148473Abstract: A method includes receiving an untransformed transaction including unstructured data. An embedding model generates a vector from the unstructured data. A cluster model matches the vector to a vector cluster. A cluster ID is assigned to the vector. The unstructured data in the untransformed transaction is replaced with the cluster ID to obtain a transformed transaction. A query including the cluster ID and based on the transformed transaction is generated. The query is processed to generate a query result from features of prior transformed transactions. A fraud determination model processes the query result to generate a fraud score for the transformed transaction. The fraud score is presented to a user of a software application. The cluster model is updated to add or delete or modify vector clusters to generate cluster IDs, whereby generating the set of cluster IDs does not affect an input or output of the fraud determination model.Type: ApplicationFiled: January 9, 2025Publication date: May 8, 2025Applicant: Intuit Inc.Inventors: Runhua ZHAO, Vinay PATLOLLA, Nikolas TERANI, Taylor J. CRESSY, Henry VENTURELLI
-
Patent number: 12293305Abstract: Systems and methods for training a machine learning model are disclosed. A system may be configured to obtain a plurality of training samples. The system includes a machine learning model to generate predictions and generate a confidence score for each generated prediction. In this manner, the system is configured to, for each training sample of the plurality of training samples, generate a prediction by a machine learning model based on the training sample and generating a confidence score associated with the prediction by the machine learning model. The system is also configured to train the machine learning model based on the plurality of predictions and associated confidence scores. For example, one or more training samples may be excluded from use in training the machine learning model based on the associated one or more confidence scores (such as the confidence score being less than a threshold).Type: GrantFiled: May 27, 2021Date of Patent: May 6, 2025Assignee: Intuit Inc.Inventor: Sricharan Kallur Palli Kumar
-
Publication number: 20250139373Abstract: Output sentences of a primary large language model is provided to a criteria model including a second large language model. The criteria model compares the output to a reference source. As a result of comparing, the criteria model generates a first data structure including a first vector. The first vector stores, an evaluation of the output as being consistent or inconsistent with the reference source, and a corresponding reason for the evaluation. The criteria model identifies an inconsistent sentence, in the sentences, that is inconsistent with the reference source. The method also includes rewriting, by a reason improver model including a third large language model, the inconsistent sentence into a consistent sentence. The consistent sentence is consistent with the reference source. The output is modified by replacing the inconsistent sentence in the sentences with the consistent sentence. Modifying generates a modified output. The method also includes returning the modified output.Type: ApplicationFiled: October 31, 2024Publication date: May 1, 2025Applicant: Intuit Inc.Inventors: Wendi CUI, Jiaxin ZHANG, Damien LOPEZ, Kamalika DAS, Sricharan KUMAR
-
Publication number: 20250139445Abstract: 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.Type: ApplicationFiled: October 31, 2023Publication date: May 1, 2025Applicant: INTUIT INC.Inventors: Xiang GAO, Kamalika DAS
-
Publication number: 20250139556Abstract: Embodiments disclosed herein generate a strategy insight report for a user's business, leveraging generative artificial intelligence—particularly large language models—and pre-stored data associated with the user. The large language models are used to capture subjective information associated with different insight areas, e.g., strength, weakness, opportunity, and threat (SWOT) of a SWOT model. The captured subjective information is augmented, supplemented, and/or modified by the pre-stored data to generate the strategy insight report. In contrast to conventional results and reports, the disclosed strategy insight report provides a current state of the user's business as well as next steps and recommendations.Type: ApplicationFiled: October 31, 2023Publication date: May 1, 2025Applicant: INTUIT INC.Inventors: Daniel Ben DAVID, Byungkyu KANG, Sparsh GUPTA, Kenneth Grant YOCUM, Prarit LAMBA
-
Publication number: 20250139634Abstract: Embodiments disclosed herein provide automated account recommendations for a hierarchical account structure. For an incoming transaction data record, a first language model is used to generate a recommended account name that is agnostic to the existing list of accounts. The recommended account name is appended to the existing list of accounts, which is consolidated to remove synonymous accounts. Additionally, a hierarchical relationship between the different accounts in the consolidated list of accounts is determined. A second language model is used to select an account name from the list of accounts. The selected account name along with any hierarchically related account name may be displayed to the user for selection.Type: ApplicationFiled: October 27, 2023Publication date: May 1, 2025Applicant: INTUIT INC.Inventors: Maria KISSA, Nicholas Jeffrey HOH, Jason WIRTH
-
Publication number: 20250140012Abstract: A method including receiving a digital image including text arranged in a layout. The method also includes generating, by an optical character recognition model, a layout text vector that encodes at least one word in the text of the digital image and a position of the at least one word in the layout of the digital image. The method also includes generating, by a visual encoder model, a visual representation vector embedding a content of the digital image. The method also includes converting both the layout text vector and the visual representation vector into a projected text vector including a digital format suitable for input to a large language model. The method also includes combining, into a prompt, the projected text vector, a system message, and a task instruction. The method also includes generating an output including a key-value pair.Type: ApplicationFiled: October 25, 2023Publication date: May 1, 2025Applicant: Intuit Inc.Inventors: Tharathorn RIMCHALA, Shir Meir LADOR, Xiangru LI
-
Publication number: 20250139374Abstract: Providing an output of a primary large language model to a criteria model including a second large language model. The criteria model compares each of the sentences to a reference source and generates a first data structure including a first vector. The first vector stores, for each of the sentences, a corresponding evaluation of a given sentence as being consistent or inconsistent with the reference source, and a corresponding reason for the corresponding evaluation of the given sentence. The first data structure is provided to a converter model including a third large language model. The converter model converts the first data structure to a second data structure. The second data structure includes a second vector storing scores indicating a corresponding consistency value for each of the sentences. A metric, indicating an overall consistency of the output with respect to the reference source, is generated from the second data structure.Type: ApplicationFiled: October 31, 2024Publication date: May 1, 2025Applicant: Intuit Inc.Inventors: Wendi CUI, Jiaxin ZHANG, Damien LOPEZ, Colin RYAN
-
Publication number: 20250139383Abstract: Systems and methods are provided for solving mathematical word problems using large language models.Type: ApplicationFiled: October 31, 2023Publication date: May 1, 2025Applicant: INTUIT INC.Inventors: Anu SINGH, Xiang GAO, Kamalika DAS
-
Patent number: 12287793Abstract: Systems and methods are described for batch materialization of an incremental change data capture (CDC) changeset with full row changes. The primary keys are extracted from the incremental CDC changeset and an indication of the extracted primary keys are broadcast to a plurality of executors. The primary keys may be added to Bloom filter or a plurality of Bloom filters that are broadcast to the executors. Each executor filters a baseline data table based on the extracted primary keys to generate a baseline match dataframe with all primary keys matching the extracted primary keys, and a baseline unmatched dataframe with all primary keys not matching the extracted primary keys. Each executor receives full row changes from a partitioned incremental CDC changeset and combines the changes with the baseline unmatched dataframe to produce a final changed baseline data table.Type: GrantFiled: June 13, 2024Date of Patent: April 29, 2025Assignee: Intuit Inc.Inventors: Saikiran Sri Thunuguntla, Vishal Reddy Baddam, Suman Ghosh, Rajendra Tiwari
-
Patent number: 12288159Abstract: 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.Type: GrantFiled: March 16, 2023Date of Patent: April 29, 2025Assignee: Intuit Inc.Inventors: Arkadeep Banerjee, Vignesh T. Subrahmaniam