Web-based customer service interface

• US 10,055,501 B2
• Filed: 11/06/2015
• Issued: 08/21/2018
• Est. Priority Date: 05/06/2003
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Nelken, Yoram, Jessee, Randy, Kirshner, Steve
• Primary Examiner(s): Lin, Shew-Fen
• Application Number:
  US14/935,174
• Publication Number:
  US 20160063126A1
• Time in Patent Office: 1,019 Days
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 16/9558 Details of hyperlinks; Management of linked annotations

Abstract

A system and method for processing a web-based query is provided. The system comprises a web server for transmitting a web form having a text field box for entering a natural language query, and a language analysis server for extracting concepts from the natural language query and classifying the natural language query into predefined categories via computed match scores based upon the extracted concepts and information contained within an adaptable knowledge base. In various embodiments, the web server selectively transmits either a resource page or a confirmation page to the client, based upon the match scores. The resource page may comprise at least one suggested response corresponding to at least one predefined category. The language analysis server may adapt the knowledge base in accordance with a communicative action received from the client after the resource page is transmitted.

Claims

1. A method for processing an electronic query, comprising:

receiving an electronic query from a client computer at a server computer, wherein the server computer is configured for;

analyzing the query using a language modeling engine and a knowledge base to compute match scores and to classify the query into one or more predefined categories stored in the knowledge base based upon the match scores, wherein each of the predefined categories is associated with a suggested response;

wherein the language modeling engine analyzes a natural language text of the query to generate concepts associated with the query, statistically compares the concepts with rules associated with the rule-oriented nodes and with concepts associated with the concept-oriented nodes stored in the knowledge base, and computes the match scores for one or more concept-oriented nodes representing one or more of the predefined categories;

determining if the query meets any of one or more predetermined threshold levels for an automated response, based upon the match scores;

transmitting a suggested response page to the client computer, if the query does meet any of the predetermined threshold levels for the automated response, wherein the suggested response page includes the suggested response associated with each of the predefined categories with an associated match score greater than or equal to a corresponding one of the predetermined threshold levels;

otherwise routing the query to an agent for further analysis, if the query does not meet any of the predetermined threshold levels for the automated response, wherein the client computer is sent a confirmation page confirming that the query is being routed to the agent for further analysis, and the agent subsequently replies to the query; and

wherein a language analysis server processes the agent'"'"'s reply to the client computer to generate agent-based feedback, and the language analysis server updates the knowledge base based upon the agent-based feedback;

wherein the language analysis server modifies concepts, adds new concepts, eliminates concepts, or modifies weights assigned to different concepts associated with concept-oriented nodes stored in the knowledge base, based upon the agent-based feedback; and

wherein the query is considered resolved, if the client computer selects a suggested response or if the client computer does not select any response;

receiving client-based feedback, in response to the query being resolved, for use in updating the knowledge base, wherein;

if the client computer selects a suggested response corresponding to a high match score, then the client computer generates a positive client-based feedback for use in updating the knowledge base, and

if the client computer selects a suggested response corresponding to a low match score, then the client computer generates a negative client-based feedback for use in updating the knowledge base.

2. The method of claim 1, wherein the knowledge base comprises a plurality of nodes configured in a hierarchically structured branching network, each node is configured as either a rule-oriented or a concept-oriented node, and each concept-oriented node is associated with a predefined category.

3. The method of claim 1, wherein a high match score for a predefined category indicates that a suggested response corresponding to the predefined category is more likely to be a correct response than a suggested response corresponding to a predefined category with a low match score.

4. The method of claim 1, wherein the agent is a human agent.

5. The method of claim 1, wherein the agent is an automated service.

6. The method of claim 1, wherein the language analysis server modifies relationships between nodes stored in the knowledge base, based upon the agent-based feedback.

7. The method of claim 1, wherein the language analysis server modifies classification rules associated with rule-oriented nodes stored in the knowledge base, based upon the agent-based feedback.

8. The method of claim 1, wherein the suggested response includes a message that recites “

no response was found”

.

9. The method of claim 1, wherein, if the associated match score is greater than or equal to a corresponding high-threshold level, then the suggested response page comprises a solution page that provides either a link or a web page to the client computer that resolves the query.

10. The method of claim 1, wherein the client computer responds to the suggested response page and the server determines whether the query is resolved based upon the client response.

11. The method of claim 1, wherein the query is not resolved if the client computer escalates.

12. The method of claim 1, wherein, if the query is resolved, then a language analysis server receives the client-based feedback, and the language analysis server updates the knowledge base based upon the client-based feedback.

13. The method of claim 12, wherein the positive client-based feedback strengthens a concept-oriented node stored in the knowledge base that generated the suggested response.

14. The method of claim 13, wherein the concept-oriented node is strengthened by redistributing weights assigned to concepts associated with the concept-oriented node.

15. The method of claim 12, wherein the negative client-based feedback modifies a concept-oriented node and branching structures stored in the knowledge base that generated the suggested response.

16. A system for processing an electronic query, comprising:

a server computer for receiving an electronic query from a client computer, wherein the server computer is configured for;

analyzing the query using a language modeling engine and a knowledge base to compute match scores and to classify the query into one or more predefined categories stored in the knowledge base based upon the match scores, wherein each of the predefined categories is associated with a suggested response;

wherein the language modeling engine analyzes a natural language text of the query to generate concepts associated with the query, statistically compares the concepts with rules associated with the rule-oriented nodes and with concepts associated with the concept-oriented nodes stored in the knowledge base, and computes the match scores for one or more concept-oriented nodes representing one or more of the predefined categories;

determining if the query meets any of one or more predetermined threshold levels for an automated response, based upon the match scores;

transmitting a suggested response page to the client computer, if the query does meet any of the predetermined threshold levels for the automated response, wherein the suggested response page includes the suggested response associated with each of the predefined categories with an associated match score greater than or equal to a corresponding one of the predetermined threshold levels;

otherwise routing the query to an agent for further analysis, if the query does not meet any of the predetermined threshold levels for the automated response, wherein the client computer is sent a confirmation page confirming that the query is being routed to the agent for further analysis, and the agent subsequently replies to the query; and

wherein a language analysis server processes the agent'"'"'s reply to the client computer to generate agent-based feedback, and the language analysis server updates the knowledge base based upon the agent-based feedback;

wherein the language analysis server modifies concepts, adds new concepts, eliminates concepts, or modifies weights assigned to different concepts associated with concept-oriented nodes stored in the knowledge base, based upon the agent-based feedback; and

wherein the query is considered resolved, if the client computer selects a suggested response or if the client computer does not select any response;

receiving client-based feedback, in response to the query being resolved, for use in updating the knowledge base, wherein;

if the client computer selects a suggested response corresponding to a high match score, then the client computer generates a positive client-based feedback for use in updating the knowledge base, and

if the client computer selects a suggested response corresponding to a low match score, then the client computer generates a negative client-based feedback for use in updating the knowledge base.