Intuit, Inc.

Steve George Goyette

Yogish Pai

Robert Bruce MacMartin

Anil Kumar Sharma

Jayanth Saimani

Anshu Verma

Bharath Kadaba

Kiran Aswath

Merrin Kurian

Narayana Hari

Ram Mohan Shamanna

Anu Singh

Peter Thomas

Madhusudhanan Dharumaraj

Yi Xu Ng

Xuerui Han

Robert Bruce Macmartin

Robert Macmartin

A system for account mapping includes functionality for obtaining more than one labeled accounts labeled by more than one accountant; pre-processing more than one labeled accounts using natural language processing, using the more than one pre-processed labeled accounts to train an account mapping model that performs multinomial classification; receiving an account name from an accounting application where the account name includes a text label for an account included in a chart of accounts; generating an account mapping by applying the account mapping model to the account name, where the account mapping includes a type of the account, a sub-type of the account, a code, and a series associated with an accounting form; returning the account mapping to the accounting application through an Application Programming Interface (API); and receiving a corrected account mapping from an accountant and using the corrected account mapping as a new text label to incrementally update the account mapping model.

Automated field-mapping of account names for form population

A method identifies a plurality of product categories by applying a categorization model to product data that includes product names and product descriptions. The product data is obtained from internal sources and external sources. The method creates a knowledge graph for a plurality of business entities from inputs that include the plurality of product categories, published data that includes merchant categorizations, and geographical data. The method generates cohort clusters of similar business entities by applying a clustering algorithm to the knowledge graph. The method uses the cohort clusters to learn a first extrapolation model for predicting inventory. And the method provides access to the first extrapolation model to predict inventory level at a specific point in time. The access is provided via a merchant application that runs on an online merchant platform.

Finding business similarities between entities using machine learning

A method identifies a plurality of product categories by applying a categorization model to product data that includes product names and product descriptions. The product data is obtained from internal sources and external sources. The method creates a knowledge graph for a plurality of business entities from inputs that include the plurality of product categories, published data that includes merchant categorizations, and geographical data. The method generates cohort clusters of similar business entities by applying a clustering algorithm to the knowledge graph. The method uses the cohort clusters to learn an extrapolation model for predicting inventory. The method makes a prediction as to the inventory level using the extrapolation model for a user of the merchant application. The method determines a confidence level for the user and orders additional inventory for the user without further input, if the confidence level is above a specified threshold.

User behavior confidence level of automation

A method to configure a software solution may include receiving a first specification of a type of configuration data items and a second specification of system selected user attributes associated with the type of configuration data items, and receiving a configuration data item that is used to configure a first localized version of the software solution. The method may further include receiving a contributing user attribute specification that specifies a first user attribute and a second user attribute of the system selected user attributes, and generating a search tag assigned to the configuration data item. The method may further include receiving a search request to search the configuration data items, selecting, in response to the search request, the configuration data item based on the search tag, and configuring, in response to selecting the configuration data item, a second localized version of the software solution based on the configuration data item.

Matching adopting users and contributing users for decentralized software localization

A method to configure a localizable software solution, which includes receiving a search request to search a requested type of configuration data items, accessing a first configuration data item of the requested type, in response to the search request, scanning contents of the first configuration data item to identify a key within the first configuration data item, accessing, by resolving the key within the first configuration data item and based on the at least one user attribute, a second configuration data item of a second type, generating a custom configuration data item by replacing, within the first configuration data item, the key with the second configuration data item, and returning the custom configuration data item to a configuration engine. The configuration engine localizes the localizable software solution using the custom configuration data item.

Content recommendation using layered types

A system includes (i) a configuration service executing on a computer processor and configured to select, based on a user attribute of a user, a configurable user interface, and select, based on the user attribute of the user, a configurable workflow, (ii) a contribution management system that generates a statistical measure of a plurality of users by tracking the plurality of users using the plurality of configurable user interfaces and the plurality of configurable workflows to perform a task according to a geographical region of the user, and verifies the configurable user interfaces and the configurable workflows based on the statistical measure, and (iii) a computer server configured to perform a task by at least receiving, via the configurable user interface, a user input, and executing, based on user input and according to the configurable workflow, multiple functional engines of the software solution.

Globally scalable solution

A system to configure a software solution involves a system that includes (i) a configuration service executing on a computer processor and configured to select, based on a user attribute of a user, a configurable user interface from multiple configurable user interfaces of the software solution, and select, based on the user attribute of the user, a configurable workflow from multiple configurable workflows of the software solution, (ii) a computer server configured to perform a pre-determined task by at least receiving, via the configurable user interface, a user input, and executing, based on user input and according to the configurable workflow, multiple functional engines of the software solution, and (iii) a data repository configured to store the multiple configurable user interfaces and the multiple configurable workflows.

A method to generate a regulatory filing workflow for a geographical region. The method includes displaying a regulatory filing form to a user in the geographical region, displaying a user attribute list identifying user attributes from the BMAs used by the user, receiving, from the user and in response to displaying the regulatory filing form and the user attribute list, a user input that specifies a rule for determining input data of the regulatory filing form based at least on user attributes, and generating, based at least on the user input, regulatory filing report metadata including a specification for generating a regulatory filing report by completing the regulatory filing form based at least on the rule, where the regulatory filing workflow includes generating and filing the regulatory filing report to satisfy the regulatory requirement specific to the geographical region.

Determining local regulatory filing workflow through user contribution

A method to customize an online software application. The method includes displaying, using a user interface of the online software application, a message inviting user contribution to a customizable component of the online software application, receiving, from an initial seed user via a network connection and in response to displaying the message, a structural specification of the customizable component suggested by the initial seed user according to a requirement based on an attribute of the initial seed user, determining that a new user of the online software application matches the attribute of the initial seed user, and configuring, based on the structural specification of the customizable component suggested by the initial seed user, an instantiation of the online software application for the new user to perform a pre-determined task according to the requirement.

Growing community of inventors

Maple Ridge, Canada

Steve George Goyette