INTEGRATED AUTOMATIC USER SUPPORT AND ASSISTANCE

• US 20110289076A1
• Filed: 11/22/2010
• Published: 11/24/2011
• Est. Priority Date: 01/28/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Zhang, Yu, Boyle, Peter C.
• Granted Patent: US 8,521,675 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

A method of integrated automatic support and assistance includes identifying a user and retrieving models representing the user'"'"'s device, apparatus, service, or system, receiving a query from the user, as necessary refining the query, determining if the received query is a machine translatable query, restructuring machine translatable terms of the received query into semantic components based upon the retrieved models, determining a set of candidate knowledge bases both related to the semantic components, submitting the machine translatable query to each knowledge base of the set of candidate knowledge bases, receiving a set of responses from each knowledge base of the set of knowledge bases in response to the submitting, formatting the set of responses, submitting the formatted set of responses to the user, determining if a response of the submitted formatted set of responses is accepted by the user, applying updated weights within the formatted set of responses, and storing the updated weights for future queries.

Claims

1. A method of integrated automatic support and assistance, comprising:

identifying a user, wherein identifying the user includes retrieving models representing a device, apparatus, service, or system operated by the user;

receiving a query or statement from the user, the query or statement being related to a question about or a problem with at least one component on the system;

determining if the received query or statement is a machine translatable query or statement;

restructuring machine translatable terms of the received query or statement into semantic components based upon the retrieved models;

determining a set of candidate knowledge bases both internal and external to the assistance providing computer system related to the semantic components;

submitting the machine translatable query or statement to each knowledge base of the set of candidate knowledge bases;

receiving a set of responses from each knowledge base of the set of knowledge bases in response to the submitting;

formatting the set of responses;

submitting the formatted set of responses to the user;

determining if a response of the submitted formatted set of responses is accepted by the user;

applying updated weights within the formatted set of responses; and

storing the updated weights for future queries.

2. The method of claim 1, wherein identifying the user further includes retrieving a client identification from the system, querying a user profile database with the client identification to determine a set of attributes associated with the user profile, and retrieving the models based on the set of associated attributes.

3. The method of claim 1, wherein receiving a query or statement from the user includes presenting the user with an automated virtual interface, presenting a query entry field with the automated virtual interface, and receiving the query through the automated virtual interface.

4. The method of claim 3, wherein the automated virtual interface comprises computer executable code being processed by a processor of the computer system, and the automated virtual interface is in communication with an artificial intelligence engine disposed to receive the query.

5. The method of claim 1, wherein determining if the received query includes parsing the query based on a set of associating algorithms or relationships with the user, and determining if the parsed query includes attributes associated with the retrieved models.

6. The method of claim 1, wherein restructuring the machine translatable terms includes parsing the machine translatable query into the semantic components based on matching algorithms related to the retrieved models.

7. The method of claim 1, wherein determining a set of candidate knowledge bases includes submitting the semantic components to a meta knowledge database, applying a set of attribute matching words to compare the semantic components with a plurality of attributes associated with a plurality of knowledge bases stored in the meta knowledge database, and determining the set of candidate knowledge bases based on matches between the plurality of attributes and the semantic components.

8. The method of claim 7, further comprising:

refining the machine translatable query or statement based on matching analysis between attributes of the received set of responses and associating models or relationships with the user profile;

restructuring the refined query or statement into semantic components;

determining an updated set of candidate knowledge bases using the refined semantic components;

submitting the refined semantic components to the updated set of candidate knowledge bases; and

receiving an updated set of responses from each knowledge base of the updated set of candidate knowledge bases.

9. The method of claim 1, wherein formatting the set of responses includes categorizing each response of the set of responses into related groups of responses.

10. The method of claim 1, wherein if a response of the submitted set of responses is not accepted by the user:

determining a form of submission used to receive the query or statement from the user;

determining an entry format of the form of submission;

requesting a new query or statement from the user in the determined entry format;

requesting validation of the correctness of the new query or statement; and

storing validation results in the user profile.

11. The method of claim 1, wherein if a response of the submitted set of responses is not accepted by the user:

iteratively refining the received query or statement with the user, wherein iteratively refining includes a plurality of requests for refinement from the user;

displaying parsing information for the refined query or statement;

requesting parsing corrections for the displayed parsing information;

receiving the parsing corrections; and

storing the parsing corrections in the user profile.

12. The method of claim 1, wherein if a response of the submitted set of responses is not accepted by the user, querying the user to determine if a user-based solution is effective, and storing the user-based solution in a knowledge base of the plurality of knowledge bases for subsequent queries.

13. The method of claim 1, further comprising determining a set of response time expectations based upon the received query or statement, relaying the set of response time expectations to the user, receiving feedback from the user based on the relaying, determining a user satisfaction value from the feedback, and storing the user satisfaction value in the user profile for subsequent queries.

14. A computer-implemented system of integrated automatic support and assistance, comprising:

a user profile knowledge base in communication with an AI inference or semantic based engine, the user profile knowledge base storing a plurality of user information;

a semantic enhanced search engine in communication with the AI inference or semantic based engine, the semantic enhanced search engine disposed to accept user queries from the AI or semantic based inference engine and to restructure the user queries into semantic components;

wherein, the AI inference or semantic based engine is disposed to perform a method of integrated automatic support and assistance, the method comprising;

identifying a user, wherein identifying the user includes retrieving models representing a system operated by the user;

receiving a query or statement from the user through the AI inference or semantic based engine, the query or statement being related to a question about or a problem with at least one component on the system;

determining if the received query or statement is a machine translatable query or statement;

restructuring machine translatable terms of the received query or statement into semantic components based upon the retrieved models;

determining a set of candidate knowledge bases both internal and external to the assistance providing system related to the semantic components;

submitting the machine translatable query or statement to each knowledge base of the set of candidate knowledge bases;

receiving a set of responses from each knowledge base of the set of knowledge bases in response to the submitting;

formatting the set of responses;

submitting the formatted set of responses to the user through the AI inference or semantic based engine;

determining if a response of the submitted formatted set of responses is accepted by the user;

applying updated weights within the formatted set of responses; and

storing the updated weights for future queries.

15. The system of claim 14, wherein identifying the user further includes retrieving a client identification from the system, querying the user profile knowledge base with the client identification to determine a set of attributes associated with the user profile, and retrieving the models based on those attributes.

16. The system of claim 14, wherein receiving a query or statement from the user includes presenting the user with an automated virtual interface driven by the AI inference or semantic based engine, presenting a query entry field with the automated virtual interface, and receiving the query through the automated virtual interface at the AI interface engine.

17. The system of claim 14, wherein determining if the received query or statement is machine translatable includes parsing the query based on a set of associating algorithms or relationships associated with the user, and determining if the parsed query includes associations with the retrieved models.

18. The system of claim 14, wherein restructuring the machine translatable terms includes parsing the machine translatable query into the semantic components at the semantic enhanced search engine based on attribute or relationship matching with the retrieved models.

19. The system of claim 14, wherein determining a set of candidate knowledge bases includes submitting the semantic components to a meta knowledge database in communication with the AI inference or semantic based engine, applying a set of attribute matching algorithms or relationships to the semantic components with a plurality of attributes associated with a plurality of knowledge bases stored in the meta knowledge database, and determining the set of candidate knowledge bases based on matches between the plurality of attributes and the semantic components.

20. A computer readable storage medium including computer executable instructions that, when executed on a computer processor, direct the computer processor to perform a method of integrated automatic support and assistance, the method comprising:

identifying a user, wherein identifying the user includes retrieving models representing the system operated by the user;

receiving a query or statement from the user, the query or statement being related to a question about or a problem with at least one component on the system;

determining if the received query or statement is a machine translatable query or statement;

restructuring machine translatable terms of the received query or statement into semantic components based upon the retrieved models;

determining a set of candidate knowledge bases both internal and external to the assistance providing system related to the semantic components;

submitting the machine translatable query or statement to each knowledge base of the set of candidate knowledge bases;

receiving a set of responses from each knowledge base of the set of knowledge bases in response to the submitting;

formatting the set of responses;

submitting the formatted set of responses to the user;

determining if a response of the submitted formatted set of responses is accepted by the user;

applying updated weights within the formatted set of responses; and

storing the updated weights for future queries.