Dynamic personalized multi-turn interaction of cognitive models
First Claim
1. A computer-based conversation system for interacting with a user, comprising:
- a CPU, a computer readable memory, and a computer readable storage medium associated with a computer device;
program instructions defining a statement and question framer that is configured to;
obtain insights about a user from a remote big data engine, the insights including likes, dislikes and opinions of the user; and
generate a response to an input from the user, wherein the response generated is personalized for the user based on the insights and the input, and wherein the statement and question framer comprises;
a data enrichment and filtering module that;
sends an identity of the user to the remote big data engine to obtain a plurality of insights associated with the user;
determines relevance scores for each of the plurality of insights associated with the user based on a relevance of each of the plurality of insights to the input from the user; and
filters the plurality of insights received from the big data engine based on the relevancy scores of each of the plurality of insights with respect to the input from the user to determine filtered insights relevant to the input;
a text fragment and construction module that constructs text fragments based on the filtered insights in response to the input, wherein the text fragment and construction module uses natural language processing (NLP) to construct the text fragments;
an assembly generation module that generates plural sentences from the text fragments; and
a selection module that selects a single one of the plural sentences as the response; and
program instructions to output the response to the user,wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.
1 Assignment
0 Petitions
Accused Products
Abstract
Multi-turn conversation systems that are personalized to a user based on insights derived from big data are described. A computer-based conversation system for interacting with a user includes: a CPU, a computer readable memory, and a computer readable storage medium associated with a computer device; and program instructions defining a statement and question framer that is configured to: obtain insights about a user from a big data engine; and generate a response to an input from the user based on the insights and the input. The program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.
36 Citations
19 Claims
-
1. A computer-based conversation system for interacting with a user, comprising:
-
a CPU, a computer readable memory, and a computer readable storage medium associated with a computer device; program instructions defining a statement and question framer that is configured to;
obtain insights about a user from a remote big data engine, the insights including likes, dislikes and opinions of the user; and
generate a response to an input from the user, wherein the response generated is personalized for the user based on the insights and the input, and wherein the statement and question framer comprises;a data enrichment and filtering module that;
sends an identity of the user to the remote big data engine to obtain a plurality of insights associated with the user;
determines relevance scores for each of the plurality of insights associated with the user based on a relevance of each of the plurality of insights to the input from the user; and
filters the plurality of insights received from the big data engine based on the relevancy scores of each of the plurality of insights with respect to the input from the user to determine filtered insights relevant to the input;a text fragment and construction module that constructs text fragments based on the filtered insights in response to the input, wherein the text fragment and construction module uses natural language processing (NLP) to construct the text fragments; an assembly generation module that generates plural sentences from the text fragments; and a selection module that selects a single one of the plural sentences as the response; and program instructions to output the response to the user, wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer program product for generating conversational responses to user input, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer device to cause the computer device to:
-
receive an input from a user; determine context data based on the input; obtain additional data including time data, location data, and external data; send an identity of the user to a remote big data engine; obtain insights about the user from the remote big data engine, the insights comprising likes of the user, dislikes of the user, and opinions of the user; determine relevance scores for each of the insights obtained from the remote big data engine based on relevance of each of the insights to the input from the user; filter the insights, based on a relevance of each of the insights to the input from the user, to determine a set of filtered insights; generate a response to the input, wherein the response generated is personalized for the user based on the context data, the set of filtered insights, and the additional data, and wherein the generating the response includes; constructing text fragments based on the set of filtered insights and the additional data, wherein the additional data includes location data and time data; generating plural sentences from the text fragments; and selecting a single one of the plural sentences as the response; and
output the response. - View Dependent Claims (14, 15, 16, 17, 18, 19)
-
Specification