Decision-support application and system for problem solving using a question-answering system
First Claim
1. A method comprising:
- receiving, by a decision-support system for problem solving, an initial query and problem case information regarding a problem in a specific domain, said decision-support system comprising a computerized device that has access to evidence sources containing domain knowledge content comprising knowledge in said specific domain, said computerized device further being in communication with a repository and being programmed with instructions, said instructions causing said computerized device to perform processing comprising;
automatically extracting relevant information from said problem case information and using said relevant information to expand said initial query so as to generate a specific natural language query;
generating answers to said natural language query by applying natural language processing techniques to said domain knowledge content within said evidence sources;
calculating numerical values of evidence dimensions for each of said answers;
calculating corresponding confidence values for each of said answers based on said numerical values of each of said evidence dimensions;
outputting said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions for one or more selected answers to a decision-maker and to said repository, said natural language query, said answers, said corresponding confidence values and said numerical values of each of said evidence dimensions being displayed for said decision-maker on a display and usable by said decision-maker to make a decision regarding said problem;
storing, in said repository, said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions;
in response to new domain knowledge being added to said domain knowledge content in said evidence sources, automatically updating said answers to said natural language query, said numerical values of said evidence dimensions for each of said answers and said corresponding confidence values and determining whether previously generated answers and corresponding confidence values stored in said repository have changed based on said new domain knowledge; and
,automatically sending an alert to said decision-maker based on a change occurring in any of said previously generated answers and corresponding confidence values, said alert being usable by said decision-maker to re-evaluate said decision.
1 Assignment
0 Petitions
Accused Products
Abstract
A decision-support system for problem solving comprises software modules embodied on a computer readable medium, and the software modules comprise an input/output module and a question-answering module. The method receives problem case information using the input/output module, generates a query based on the problem case information, and generates a plurality of answers for the query using the question-answering module. The method also calculates numerical values for multiple evidence dimensions from evidence sources for each of the answers using the question-answering module and calculates a corresponding confidence value for each of the answers based on the numerical value of each evidence dimension using the question-answering module. Further, the method outputs the answers, the corresponding confidence values, and the numerical values of each evidence dimension for one or more selected answers using the input/output module.
-
Citations
21 Claims
-
1. A method comprising:
-
receiving, by a decision-support system for problem solving, an initial query and problem case information regarding a problem in a specific domain, said decision-support system comprising a computerized device that has access to evidence sources containing domain knowledge content comprising knowledge in said specific domain, said computerized device further being in communication with a repository and being programmed with instructions, said instructions causing said computerized device to perform processing comprising; automatically extracting relevant information from said problem case information and using said relevant information to expand said initial query so as to generate a specific natural language query; generating answers to said natural language query by applying natural language processing techniques to said domain knowledge content within said evidence sources; calculating numerical values of evidence dimensions for each of said answers; calculating corresponding confidence values for each of said answers based on said numerical values of each of said evidence dimensions; outputting said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions for one or more selected answers to a decision-maker and to said repository, said natural language query, said answers, said corresponding confidence values and said numerical values of each of said evidence dimensions being displayed for said decision-maker on a display and usable by said decision-maker to make a decision regarding said problem; storing, in said repository, said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions; in response to new domain knowledge being added to said domain knowledge content in said evidence sources, automatically updating said answers to said natural language query, said numerical values of said evidence dimensions for each of said answers and said corresponding confidence values and determining whether previously generated answers and corresponding confidence values stored in said repository have changed based on said new domain knowledge; and
,automatically sending an alert to said decision-maker based on a change occurring in any of said previously generated answers and corresponding confidence values, said alert being usable by said decision-maker to re-evaluate said decision. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A system comprising:
-
a repository maintaining problem case information regarding a problem in a specific domain; and a computer processor operatively connected to said repository and having access to evidence sources containing domain knowledge content comprising knowledge in said specific domain, said computer processor receiving an initial query and said problem case information from said repository, said computer processor automatically extracting relevant information from said problem case information and using said relevant information to expand said initial query so as to generate a specific natural language query, said computer processor generating answers to said natural language query by applying natural language processing techniques to said domain knowledge content within said evidence sources, said computer processor calculating numerical values for multiple of evidence dimensions for each of said answers, said computer processor calculating corresponding confidence values for each of said answers based on said numerical values of each of said evidence dimensions, said computer processor outputting said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions to a decision-maker and to said repository, said natural language query, said answers, said corresponding confidence values and said numerical values of each of said evidence dimensions being displayed for said decision-maker on a display and usable by said decision-maker to make a decision regarding said problem, said repository storing said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions, said computer processor, in response to new domain knowledge being added to said domain knowledge content in said evidence sources, automatically updating said answers to said natural language query, said numerical values of said evidence dimensions for each of said answers and said corresponding confidence values and determining whether previously generated answers and corresponding confidence values stored in said repository changed based on said new domain knowledge, and said computer processor automatically sending an alert to said decision-maker based on a change occurring in any of said previously generated answers and corresponding confidence values, said alert being usable by said decision-maker to re-evaluate said decision. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20)
-
-
21. A computer program product comprising a computer readable storage medium storing computer readable program code comprising instructions executable by a computerized device to perform a method, said method comprising:
-
receiving an initial query and problem case information regarding a problem in a specific domain; automatically extracting relevant information from said problem case information and using said relevant information to expand said initial query so as to generate a specific natural language query; generating answers to said natural language query by applying natural language processing techniques to domain knowledge content within evidence sources, said domain knowledge content comprising knowledge in said specific domain; calculating numerical values of evidence dimensions for each of said answers; calculating corresponding confidence values for each of said answers based on said numerical values of each of said evidence dimensions; outputting said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions for one or more selected answers to a decision-maker and to a repository, said natural language query, said answers, said corresponding confidence values and said numerical values of each of said evidence dimensions being displayed for said decision-maker on a display and usable by said decision-maker to make a decision regarding said problem; storing, in said repository, said natural language query, said answers, said corresponding confidence values, and said numerical values of each of said evidence dimensions; in response to new domain knowledge being added to said domain knowledge content in said evidence sources, automatically updating said answers to said natural language query, said numerical values of said evidence dimensions for each of said answers and said corresponding confidence values and determining whether previously generated answers and corresponding confidence values stored in said repository changed based on said new domain knowledge; and
,automatically sending an alert to said decision-maker based on a change occurring in any of said previously generated answers and corresponding confidence values, said alert being usable by said decision-maker to re-evaluate said decision.
-
Specification