24/7 Customer, Inc.

International Business Machines Corporation

[24]7.ai, Inc.

Vaibhav Srivastava

R Mathangi Sri

Ravi Vijayaraghavan

Subhajit Bhuiya

Nitin Hardeniya

Prashant V Ullegaddi

Ajay Chebbi

Vijay S Patil

Robin Dautricourt

Kathy L Brown

Andrew Chang

Pramod Chandoria

Vijay G Patil

Nitin Kumar Hardeniya

R Sri

A computer implemented method and an apparatus for facilitating voice user interface (VUI) design are provided. The method comprises identifying a plurality of user intentions from user interaction data. The method further comprises associating each user intention with at least one feature from among a plurality of features. One or more features from among the plurality of features are extracted from natural language utterances associated with the user interaction data. Further, the method comprises computing a plurality of distance metrics corresponding to pairs of user intentions from among the plurality of user intentions. A distance metric is computed for each pair of user intentions from among the pairs of user intentions. Furthermore, the method comprises generating a plurality of clusters based on the plurality of distance metrics. Each cluster comprises a set of user intentions. The method further comprises provisioning a VUI design recommendation based on the plurality of clusters.

Method and apparatus for facilitating voice user interface design

Embodiments of the invention relate to chat and, more particularly, to determining an that is to be action taken based on the type of chat session. The resolution of the chat is categorized to decide the necessary steps taken and also to monitor the agent's performance. A chat filter extracts relevant portions of a chat session. The relevant factors are taken into consideration and scored based on the feature vectors. A model is built and the type of resolution is determined. An analysis of the chat session is then performed taking into consideration several factors.

Segregation of chat sessions based on user query

User interactions are categorized into predefined hierarchical categories by classifying user interactions, such as queries, during a user interaction session by labeling text data into predefined hierarchical categories, and building a scoring model. The scoring model is then executed on untagged user interaction data to classify the user interactions into either action-based or information-based interactions.

Categorization of user interactions into predefined hierarchical categories

The stages of an interaction between a potential customer (the user) and a sales representative (the agent) during a sales interaction are identified to understand the interaction factors that drive sales and, by doing so, to serve the customer better and thus increase sales. Initially, a user makes contact with an agent via a communications network. During the interaction, a dropping point is reached, i.e. the point in the interaction at which either the user or the agent ends the interaction. The dropping point and other interaction factors is analyzed. Based upon such analysis, various recommendations are made to the agents to improve the user's sales experience.

Stage-wise analysis of text-based interactions

Negotiating a multi-vehicle environment using vehicle-to-vehicle network tokens for intra-vehicle communication. Preliminary routing assignments are efficiently improved by available intra-vehicle communication.

Reference tokens for managing driverless cars

In an approach to determining an importance value of an artifact in a collaborative software development environment, a computer determines a snapshot of a collaborative software development environment, wherein the snapshot includes an artifact and at least one relationship between the artifact and one or more nodes in one or more hierarchical levels. The computer then determines, based, at least in part, on the snapshot, a plurality of parameters for the artifact in the collaborative software development environment. The computer calculates, based, at least in part, on the plurality of parameters, an importance value of the artifact.

Determining importance of an artifact in a software development environment

An IVR system is disclosed in which customer experience is enhanced by improving the accuracy and intent prediction capabilities of an interactive voice response system. Customers are allowed to make a natural language queries to specify their intent, while the accuracy of traditional IVR systems is maintained by using key features in language along with the customer's past transactions, CRM attributes, and customer segment attributes to identify customer intent.

Method and apparatus for predicting intent in IVR using natural language queries

A method for determining a common sequence of statements from one or more sets of ordered statements. A data object is created that has a first group of data entries, which is created from a first sequence of statements of a first set of statements. Each data entry defines a link between a source and destination statement from the first sequence. Data entries created from a second sequence of statements of a second set are added to the first group of data entries. Each data entry from the second sequence defines a link between a source statement and a destination statement from the second sequence. A second group of data entries is created, which is determined from the first group of data entries that have an equivalent source and destination statements. The second group of data entries is stored in a database as the common sequence of statements.

Data object with common sequential statements

A computing method and system is disclosed for analyzing interactions between a user and a customer support agent. Typical interactions include inquiries about a product or service, and a service call. When the user purchases a good or service, or successfully completes a service call, the customer converts, e.g. the sales pitch or service solution was successful. If the customer does not convert, then the interaction between user and agent is analyzed to determine why the user did not convert and whether the user should be categorized for potential retargeting.

Growing community of inventors

Bengaluru, India

Vaibhav Srivastava