Intuit, Inc.

Aliza Duenas Carpio

Joseph Elwell

Damien O'Malley

Amir R Eftekhari

Alan F Buhler

Dharin L Nanavati

Vijoy J Caro

Alan Brian Tifford

Avanish C Pathak

Carolyn Spencer

Ashley K McMahon

Lisa B Greene-Lewis

Tejaswini Hegde

Christine D Roszak

The disclosed embodiments provide a system that improves usage of an application. During operation, the system identifies, in a set of social media posts, a question related to use of the application. Next, the system responds to the set of social media posts with a set of answers to the question on one or more social media platforms and tracks social media responses to the set of answers. The system then calculates a set of relevance scores for the answers based on the tracked social media responses, wherein each relevance score represents a relevance of one of the answers to the question. Upon identifying the question in a subsequent social media post, the system selects an answer from the set of answers based on a relevance score of the answer and posts the answer in response to the subsequent social media post.

Application usage by selecting targeted responses to social media posts about the application

Techniques are disclosed for predicting the probability of successfully building the software application whether an integration build between source components of a software application will be successful. An integration service executing on a server computer determines whether to test an integration build of source components of a software application. The integration service obtains metrics related to the developer of each component as well as any previous integration builds of the components. Based on the metrics, the integration service predicts a probability of a successful integration build of the source components. Based on the probability of a successful integration build, the integration service may notify a developer to perform an action to increase the likelihood of the integration build being successful.

Adaptive system for predicting integration failures in large systems

The present disclosure relates to a system and method for evaluating source code. The system generates training data from a plurality of defect records that identify developers who fixed defects. The system recommends developers for repairing defects in software features using a machine learning algorithm configured using elements from the defect records and the code related to the defect records.

Defect ownership assignment system and predictive analysis for codebases

An application determines an emotional state of a user based on evaluating facial recognition data of the user captured from the user interacting with the application. The application receives a request from the user to initiate a support call. The request identifies the emotional state of the user. The application predicts, from a set of outcomes of support calls processed by support agents interacting with users having different emotional states, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on the emotional state of the user. The application identifies an available support agent having the predicted emotional state, and assigns the user to interact with the identified support agent for the support call.

Emotion recognition to match support agents with customers

The present disclosure relates to a system and method for predicting errors in a software code base. The system generates an element set from a plurality of defect records that identify the developer who originated the defect, the code revisions related to the defect, and a classification of the defect. The system predicts the probability and type of defects in software using a machine learning algorithm configured using elements from the defect records and the code related to the defect records.

Systems, methods and articles of manufacture for delivering website content to an internet user which is personalized to the user based on a persona associated with the user. A persona database system accesses personal and financial data for the user from any suitable source, such as from a tax return of the user or personal finance management application or even a questionnaire. The persona database system matches the user's data to a persona for the user from a predetermined, discrete set of personas, wherein each persona identifies a generalized profile of personal and financial characteristics of the user. Then, when a user access a website hosted by a website server, the website server accesses the persona for the user from the persona database system and the website server personalizes the website content delivered to the user based on the persona for the user.

Systems, methods and articles for providing personalized web content based on portable personas

An application infers emotional states of support agents from facial recognition data collected from support calls processed by the support agents. The application determines an outcome of each of the support calls based on feedback indicating user experience with the support agents. The application correlates outcomes of the support calls based on different topics with the emotional states. Upon receiving a request to initiate a support call, the application predicts, from the correlation, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on a topic identified in the request. The application identifies an available support agent having the predicted emotional state, and assigns the identified support agent to interact with the user for the support call.

A method to communicate driving status from a vehicle. The method includes obtaining, using a mobile device travelling in the vehicle, movement data of the vehicle, determining, using a computer processor of the mobile device, that the vehicle is in motion by analyzing the movement data based on a specified criterion, generating, in response to determining that the vehicle is in motion, driving status data of the vehicle by further analyzing the movement data based on the specified criterion, and transmitting, using the mobile device, the driving status data to a remote user away from the vehicle.

Remote hands-free backseat driver

Disclosed are methods, systems, and articles of manufactures for addressing popular topics in a social sphere. The method or the system continuously monitors conversations in online forum(s), identifies trend(s) of interest, identifies one or more content items that match the trend(s), and delivers the one or more content items to appropriate forum(s). The method or the system may aggregates conversations in a target forum to identify a trend and automatically responds to the trend by identifying and delivering matching existing content items to a target forum. The method or the system may further catalog a newly created content item upon creation and may identify a trend by employing some third-party products or services, by executing one or more Internet bots to monitor the online conversions, or by using trending application(s) offered by forums or social network websites.

Methods, systems, and articles of manufacture for addressing popular topics in a social sphere

A method to qualify a partner candidate, including accessing a social network to retrieve social network data about the partner candidate; parsing the social network data to extract a social network data item corresponding to a characteristics category relating to a characteristic of the partner candidate; determining per category weighting factors corresponding to characteristics categories and representing a focus of the social network; comparing, using a keyword library comprising pre-determined keywords and pre-determined keyword similarity measures, the social network data item and a self-described attribute of the partner candidate to generate a characteristics category score, wherein a range of the characteristics category score is determined by a corresponding per category weighting factor; and assigning the characteristics category score to the self-described attribute, wherein the characteristics category score represents a validity measure of the self-described attribute based on the social network data.

Growing community of inventors

San Diego, CA, United States of America

Aliza Duenas Carpio