System for automatic classification and routing

• US 10,198,477 B2
• Filed: 03/03/2016
• Issued: 02/05/2019
• Est. Priority Date: 03/03/2016
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Malatesha, Rathnakara, Wong, Lana, Kitada, Hiroshi
• Primary Examiner(s): Syed, Farhan M
• Application Number:
  US15/060,352
• Publication Number:
  US 20170255680A1
• Time in Patent Office: 1,069 Days
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 9/453 Help systems

Abstract

A request classifier service implemented on a server computer receives an input request from a client device. The request classifier service accesses classification data from a knowledge repository. The knowledge repository includes one or more defined input requests mapped to one or more classification types. The request classifier service determines confidence values for the one or more defined input requests. The confidence values represent a relative match score between the input request from the client device and each of the one or more defined input requests. The request classifier service sends classification types to a processing service implemented on the server computer. The processing service determines a process response type for the input request based upon the one or more classification types. The processing logic routes the process response type and the input request to a destination mapped to the process response type.

Claims

1. An apparatus providing an improvement in processing queries in computer networks, the apparatus comprising:

one or more processors; and

one or more memories storing instructions which, when processed by one or more processors, cause;

a request classifier service, executing on a server computer, receiving via one or more computer networks, a query request from a client device;

in response to the request classifier service receiving the query request from the client device, the request classifier service;

accessing classification data from a knowledge repository, where the classification data comprises one or more sample query requests mapped to one or more classification types;

determining a confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, where the confidence value represents a relative match score between each sample query request and the query request from the client device;

in response to the request classifier service determining the confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, sending one or more classification types for the one or more sample query requests mapped to the one or more classification types to a processing service executing on the server computer;

the processing service, determining a query response type, based upon the one or more classification types for the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing, via the one or more computer networks, the query response type, determined by the processing service, and the query request from the client device, to a destination mapped to the query response type;

the processing service receiving, from the destination mapped to the query response type, a query result that is based upon the query response type and the query request from the client device;

in response to receiving the query result that is based upon the query response type and the query request from the client device, the processing service sending, via the one or more computer networks, the query result to the client device.

2. The apparatus of claim 1, wherein determining a query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service further comprises evaluating the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service based upon the confidence values for each of the one or more sample query requests;

wherein the confidence values are evaluated against a configured confidence value threshold.

3. The apparatus of claim 1, wherein the one or more memories storing instructions which, when processed by the one or more processors, further cause:

the processing service, determining a second query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing the second query response type, determined by the processing service, and the query request from the client device to a second destination mapped to the second query response type.

4. The apparatus of claim 3, wherein the one or more memories storing instructions which, when processed by the one or more processors, further cause:

the processing service receiving, from the second destination mapped to the second query response type, a second query result that is based upon the second query response type and the query request from the client device;

in response to receiving the second query result that is based upon the second query response type and the query request from the client device, sending the second query result to the client device.

5. The apparatus of claim 4, wherein the one or more memories storing instructions which, when processed by the one or more processors, further cause merging the query result and the second query result into a combined query result and sending the combined query result to client device.

6. The apparatus of claim 1, wherein the query result includes contact information for one or more persons related to the query response type.

7. The apparatus of claim 1, wherein the query result comprises a set of results, wherein the number of results in the set of results is configurable.

8. One or more non-transitory computer-readable media providing an improvement in processing queries in computer networks, the one or more non-transitory computer-readable media storing instructions, which, when processed by one or more processors, cause:

a request classifier service, executing on a server computer, receiving via one or more computer networks, a query request from a client device;

in response to the request classifier service receiving the query request from the client device, the request classifier service;

accessing classification data from a knowledge repository, where the classification data comprises one or more sample query requests mapped to one or more classification types;

determining a confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, where the confidence value represents a relative match score between each sample query request and the query request from the client device;

in response to the request classifier service determining the confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, sending one or more classification types for the one or more sample query requests mapped to the one or more classification types to a processing service executing on the server computer;

the processing service, determining a query response type, based upon the one or more classification types for the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing, via the one or more computer networks, the query response type, determined by the processing service, and the query request from the client device, to a destination mapped to the query response type;

the processing service receiving, from the destination mapped to the query response type, a query result that is based upon the query response type and the query request from the client device;

in response to receiving the query result that is based upon the query response type and the query request from the client device, the processing service sending, via the one or more computer networks, the query result to the client device.

9. The one or more non-transitory computer-readable media of claim 8, wherein determining a query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service further comprises evaluating the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service based upon the confidence values for each of the one or more sample query requests;

wherein the confidence values are evaluated against a configured confidence value threshold.

10. The one or more non-transitory computer-readable media of claim 8, further comprising storing instructions, which, when processed by the one or more processors, cause:

the processing service, determining a second query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing the second query response type, determined by the processing service, and the query request from the client device to a second destination mapped to the second query response type.

11. The one or more non-transitory computer-readable media of claim 10, further comprising storing instructions, which, when processed by the one or more processors, cause:

the processing service receiving, from the second destination mapped to the second query response type, a second query result that is based upon the second query response type and the query request from the client device;

in response to receiving the second query result that is based upon the second query response type and the query request from the client device, sending the second query result to the client device.

12. The one or more non-transitory computer-readable media of claim 11, further comprising storing instructions, which, when processed by the one or more processors, cause merging the query result and the second query result into a combined query result and sending the combined query result to client device.

13. The one or more non-transitory computer-readable media of claim 8, wherein the query result includes contact information for one or more persons related to the query response type.

14. The one or more non-transitory computer-readable media of claim 8, wherein the query result comprises a set of results, wherein the number of results in the set of results is configurable.

15. A computer-implemented method providing an improvement in processing queries in computer networks, the computer-implemented method comprising:

a request classifier service, executing on a server computer, receiving via one or more computer networks, a query request from a client device;

in response to the request classifier service receiving the query request from the client device, the request classifier service;

accessing classification data from a knowledge repository, where the classification data comprises one or more sample query requests mapped to one or more classification types;

determining a confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, where the confidence value represents a relative match score between each sample query request and the query request from the client device;

in response to the request classifier service determining the confidence value for each sample query request from the one or more sample query requests mapped to the one or more classification types, sending one or more classification types for the one or more sample query requests mapped to the one or more classification types to a processing service executing on the server computer;

the processing service, determining a query response type, based upon the one or more classification types for the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing, via the one or more computer networks, the query response type, determined by the processing service, and the query request from the client device, to a destination mapped to the query response type;

the processing service receiving, from the destination mapped to the query response type, a query result that is based upon the query response type and the query request from the client device;

in response to receiving the query result that is based upon the query response type and the query request from the client device, the processing service sending, via the one or more computer networks, the query result to the client device.

16. The method of claim 15, determining a query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service further comprises evaluating the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service based upon the confidence values for each of the one or more sample query requests;

wherein the confidence values are evaluated against a configured confidence value threshold.

17. The method of claim 15, further comprising:

the processing service, determining a second query response type, based upon the one or more classification types from the one or more sample query requests mapped to the one or more classification types received from the request classifier service;

the processing service, routing the second query response type, determined by the processing service, and the query request from the client device to a second destination mapped to the second query response type.

18. The method of claim 17, further comprising:

the processing service receiving, from the second destination mapped to the second query response type, a second query result that is based upon the second query response type and the query request from the client device;

in response to receiving the second query result that is based upon the second query response type and the query request from the client device, sending the second query result to the client device.

19. The method of claim 18, further comprising merging the query result and the second query result into a combined query result and sending the combined query result to client device.

20. The method of claim 15, wherein the query result includes contact information for one or more persons related to the query response type.