Salesforce Com, Inc.

Salesforce, Inc.

Edgar Gerardo Velasco

Jayesh Govindarajan

Na Cheng

Zachary Alexander

Anuprit Kale

Weiping Peng

Peter Francis White

Naren M Chittar

Marc Brette

Francisco Borges

Jacob Nathaniel Huffman

Guillaume Kempf

Anjan Goswami

Pingping Xiu

Aditya Sakhuja

Sitaram Asur

Khoa Le

Victor Winslow Yee

Colleen Smith

Vishal Shah

Alejandro Gabriel Perez Rodriguez

Ziwei Chen

Suhas Satish

A method and system for recommending articles including: receiving a customer request from the customer during the session; generating case data for a case, by an article recommender app; configuring a training set based on the subject and description data of the customer request; identifying, by an artificial intelligence (AI) app, a first pool of articles from a knowledge database; identifying by at least one query, a second pool of articles from a case article database to into a merged pool of articles; assigning, by the AI app, an implicit label to one of the first pool and the second pool of the articles; applying a model derived by the AI app based on customer behavior and a set of features related to the case to classify each article of the merged pool of articles based at least in part on the predicted relevance of the article.

Method and system for service agent assistance of article recommendations to a customer in an app session

A system is provided for a machine learning engine using clustered case objects in a case management system. The system includes a multi-layer neural network. The system is configured to receive case object data comprising a case object and contextual objects in the case management system associated with the case object, the contextual objects comprising word vectors, generate a context embedding for the case object using the word vectors for the contextual objects, and cluster the case object with other case objects in the case management system based on the context embedding for the case object and other context embeddings for the other case objects.

Case object context embeddings for machine learning training of case context

A system is configured to analyze a corpus of historical chat data to identify the list of 'best' responses. As such, the user is not required to identify a list of canned responses for input into the system. The described system uses a context word embedding function and response word embedding function to generate context vectors and response vectors corresponding to the corpus of conversation data, and the vectors are represented by a respective context matrix and a response matrix. The system processes these matrices to generate scores for responses, clusters the responses, and identifies the responses corresponding to the best scores for each cluster.

Identification of response list

As part of providing the services to users, an online system stores multiple records that are accessible by users of the online system. When a user provides a search query, the online system extracts morphological and dictionary features from the query. The online system provides the extracted features to a machine learning model as an input. The machine learning model outputs a score for each potential entity type that indicates a likelihood that the search query is for a record associated with the entity type. The output from the machine learning model is used by the online system to select one or more entity types that the user is likely searching for. The online system searches the stored records based on the search query but limits the searching to records associated with at least one of the selected entity types.

Predicting a type of a record searched for by a user

A method is provided for providing a final result set to a user. In some embodiments, the method includes receiving from the user an input question directed to an organization belonging to a particular category. The method includes applying a plurality of rules to the input question, at least one rule being assigned a weight dependent on the particular category to which the organization belongs. The method further includes extracting, based on applying the plurality of rules, multiple collections of keywords and generating a plurality of search queries. Each search query includes a different collection of keywords. The method also includes submitting the plurality of search queries to a database and in response, receiving multiple result sets from the database. The method further includes in response to the input question, providing a final result including a subset of documents included in the multiple result sets to the user.

Extraction of keywords for generating multiple search queries

A data processing system analyzes a corpus of conversation data received at an interactive conversation service to train a response recommendation model. The response recommendation model generates response vectors based on custom responses and using the trained model and generates a context vector based on received input at the interactive conversation service. The context vector is compared to the set of response vectors to identify a set of recommended responses, which are recommended to an agent conversing with a user using the interactive conversation service.

Response recommendation system

Growing community of inventors

San Francisco, CA, United States of America

Edgar Gerardo Velasco