Apparatus and method for determining adequacy of information retrieving process

• US 7,849,066 B2
• Filed: 04/28/2006
• Issued: 12/07/2010
• Est. Priority Date: 01/18/2006
• Status: Expired due to Fees

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Namba, Isao, Onodera, Sachiko
• Primary Examiner(s): Pham; Hung Q
• Assistant Examiner(s): CHEUNG, HUBERT G
• Application Number:
  US11/412,953
• Publication Number:
  US 20070168337A1
• Time in Patent Office: 1,684 Days
• Field of Search: 707/706
• US Class Current: 707/706
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence

Abstract

The apparatus acquires retrieval history data of information retrieval to be determined, and acquires voice data of the conversation heard about information necessary for the information retrieval. A predetermined keyword dictionary is referred to from the voice data, and an expression matching a keyword indicating necessary information for information retrieval is extracted, and defined as a keyword obtained before retrieval. Then, the keyword obtained before retrieval and the retrieval history data (a retrieval key, a selected document, and an order in the retrieval result of the selected document) are compared with the best case data accumulated in the best case data storage unit, the applicability of the keyword obtained before retrieval and the applicability of the retrieval key are determined, and the applicability of the information retrieving process is obtained based on the determination.

Claims

1. A computer system for determining applicability of information retrieving processes, comprising:

a first computer storage for storing keywords indicating necessary information for an information retrieving process;

a second computer storage for storing past retrieval case data including expressions extracted from voice data associated with an operation of the information retrieving process that matches the stored keywords in the first computer storage, an identification of a document selected in the operation of the information retrieving process, an order of the selected document by the operation of the information retrieving process that represents a highest place in ranking among retrieval results of operations of the information retrieving processes performed in a certain period, and a set of retrieval keys used in the operation of the information retrieving process in which the selected document was retrieved with a best order;

a third computer storage for storing the voice data associated with the operation of the information retrieving process recorded in a conversation between a customer and an operator, wherein the stored voice data includes information necessary for performing the operation of the information retrieving process;

a fourth computer storage for storing retrieval history information from the operation of the information retrieving process, wherein the stored retrieval history information includes an identification of the operator performing the operation of the information retrieving process, a set of retrieval keys actually used in the operation of the information retrieving process, an identification of a document selected by the operator among retrieval results of the operation of the information retrieving process, and an order of the selected document representing a place of the selected document in ranking of retrieval results of the operation of the information retrieving process;

a retrieval history information acquirer for acquiring the stored retrieval history information of the operation of the information retrieving process performed by the operator from the fourth computer storage;

a voice data acquirer for acquiring the stored voice data from the third computer storage associated with the acquired stored retrieval history information;

an extractor for extracting one or more expressions matching the stored keywords in the first computer storage from the acquired stored voice data;

a retrieval applicability determiner for extracting the stored past retrieval case data from the second computer storage having expressions that partially correspond to the extracted one or more expressions;

comparing the set of retrieval keys and the order of the selected document in the acquired stored retrieval history information to a set of best retrieval keys and a best order of the selected document in the extracted stored past retrieval case data;

determining an applicability of the operation of the information retrieving process based on the comparing; and

obtaining and outputting the determined applicability of the operation of the information retrieving process as an information retrieval skill of the operator.

2. The computer system according to claim 1, wherein

the retrieval applicability determiner extracts the stored past retrieval case data further having an identification of the selected document identical to the identification of the selected document in the acquired stored retrieval history information;

and

comparing the set of retrieval keys to the set of best retrieval keys and the order of the selected document to the best order of the same selected document, and determining the applicability of the operation of the information retrieving process based on the comparing.

3. The computer system according to claim 1, wherein

when there exists no stored past retrieval case data having both an expression and the identification of the document selected that correspond to one of the expressions and the identification of the document selected in the stored retrieval history information, the retrieval applicability determiner acquires stored past retrieval case data having the same identification of the document selected in the acquired stored retrieval history information.

4. The computer system according to claim 1, comprising:

a best case generator for generating past retrieval case data with the set of retrieval keys, the identification of the document selected, the order of the selected document in the stored retrieval history information of the operation of the information retrieval process, and the extracted expressions from the voice data associated with the operation of the information retrieving process, and storing the generated past retrieval case data in the second computer storage.

5. The computer system according to claim 1, further comprising:

generating and storing the past retrieval case data based on the retrieval history information.

6. The computer system according to claim 1, further comprising:

selecting the expressions from the extracted stored past retrieval case data and displaying the selected expressions to a call operator at work.

7. The computer system according to claim 1, wherein

the retrieval applicability determiner determines the applicability of the operation of the information retrieving process based on differences between the set of retrieval keys and the set of best retrieval keys and between the order of the selected document and the best order as the result of the comparing.

8. The computer system according to claim 7, wherein, when the order of the selected document is the same as the best order of the selected document, the retrieval applicability determiner provides a certain value to the applicability of the operation of the information retrieving process based on a difference in number of keys between the set of retrieval keys and the set of best retrieval keys.

9. The computer system according to claim 1, further comprising:

a second extractor for extracting an expression corresponding to one of the stored keywords in the first computer storage from the voice data associated with the operation of the information retrieving process recorded in the conversation and acquired in real-time;

a best case retriever for extracting all the extracted stored past retrieval case data that has expressions corresponding to the extracted one or more expressions from the second computer storage; and

a best retrieval key candidate presenter for generating retrieval key candidate information including the best retrieval keys, the identification of the document selected and the best order of the selected document which are extracted from the extracted stored past retrieval case data, and displaying the generated retrieval key candidate information.

10. A method executed by a computer having a first computer storage, a second computer storage, a third computer storage, and a fourth computer storage for determining applicability of information retrieving processes, the method comprising:

storing keywords indicating necessary information for an information retrieving process in the first computer storage;

acquiring retrieval history information of an operation of the information retrieving process performed by an operator from the fourth computer storage, wherein the fourth computer storage stores retrieval history information of the operation of the information retrieving process, which includes an identification of the operator performing the operation of the information retrieving process, a set of retrieval keys actually used in the operation of the information retrieving process, an identification of a document selected by the operator among retrieval results of the operation of the information retrieving process, and an order of the selected document representing a place of the selected document in ranking of retrieval results of the operation of the information retrieving process;

acquiring voice data associated with the acquired retrieval history information from the third computer storage, wherein the third computer storage stores the voice data associated with the operation of the information retrieving process recorded in a conversation between a customer and the operator, wherein the stored voice data includes information necessary for performing the operation of the information retrieving process;

extracting one or more expressions corresponding to the stored keywords in the first computer storage from the acquired voice data;

extracting past retrieval case data having expressions that partially correspond to the extracted one or more expressions from the second computer storage, wherein the second computer storage stores the past retrieval case data, wherein the stored past retrieval case data includes expressions extracted from the voice data associated with the operation of the information retrieving process that matches the stored keywords in the first computer storage, an identification of a document selected in the operation of the information retrieving process, an order of the selected document by the operation of the information retrieving process that represents a highest place in ranking among retrieval results of operations of the information retrieving processes performed in a certain period, and a set of retrieval keys used in the operation of the information retrieving process in which the selected document was retrieved with a best order;

comparing the set of retrieval keys and the order of the selected document in the acquired retrieval history information to a set of best retrieval keys and a best order of the selected document in the extracted past retrieval case data;

determining an applicability of the operation of the information retrieving process based on the comparing; and

obtaining and outputting the determined applicability of the operation of the information retrieving process as an information retrieval skill of the operator.

11. The method according to claim 10, wherein

in the extracting the past retrieval case data, wherein the past retrieval case data further having an identification of the selected document identical to the identification of the selected document in the acquired retrieval history information is acquired;

and

in the comparing, the set of retrieval keys to the set of best retrieval keys and the order of the selected document to the best order of the same selected document are compared.

12. The method according to claim 10, wherein

in the extracting the past retrieval case data, when there exists no past retrieval case data having both an expression and the identification of the document selected that correspond to one of the expressions and the identification of the document selected in the retrieval history information, the past retrieval case data having the same identification of the document selected in the acquired retrieval history information is acquired.

13. The method according to claim 10, further comprising:

generating past retrieval case data with the set of retrieval keys, the identification of the document selected in the operation of the information retrieving process, the order of the selected document in the retrieval history information of the operation of the information retrieval process, and the extracted expressions from the voice data associated with the operation of the information retrieving process; and

storing the generated past retrieval case data in the second computer storage.

14. The method according to claim 10, further comprising:

extracting an expression corresponding to one of the stored keywords in the first computer storage from the voice data associated with the operation of the information retrieving process recorded the conversation and acquired in real-time;

extracting all the extracted past retrieval case data that has expressions corresponding to the extracted one or more expressions from the second computer storage;

generating retrieval key candidate information including the best retrieval keys, the identification of the document selected and the best order of the selected document which are extracted from the extracted past retrieval case data; and

displaying the generated retrieval key candidate information.