Voice response service apparatus

• US 6,052,441 A
• Filed: 11/09/1995
• Issued: 04/18/2000
• Est. Priority Date: 01/11/1995
• Status: Expired due to Term

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Sato, Atsuko
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US08/556,013
• Time in Patent Office: 1,622 Days
• Field of Search: 379/67, 379/88, 379/89, 379/111, 379/112, 379/113, 379/114, 379/115, 379/201, 379/67.1, 379/88.16, 379/88.17, 379/88.22, 379/88.23, 379/88.24, 395/2.79
• US Class Current: 379/88.16
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: H04M 1/651 with speech synthesis
• CPC Class Codes: H04M 3/40 Applications of speech amplifiers
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A voice response service apparatus comprises a log data storage unit, an identification data input unit and a voice response reproduction unit. The log data storage unit stores contents of a plurality of processes executed in an interactive form with a user through voice responses in the form of log data showing a record of time transitions and also stores identification data for identifying each of the contents of the plurality of processes as a part of contents of the voice responses. The identification data input unit inputs the identification data stored in the log data storage unit. The voice response reproduction unit reads the contents of the interactive-form processes of the log data corresponding to the identification data inputted by the identification data input unit from the log data storage unit and reproduces the thus read process contents into voices.

Claims

1. A voice response service apparatus comprising:

service execution means for executing a service transaction in response to interaction with a user, the interaction formed by providing voice guidance to the user and receiving character responses from the user;

a log data storage storing log data indicating a history of the interaction and identification data identifying the log data;

means for specifying identification data from the stored identification data responsive to an indication from said service execution means to read a stored character response from the stored log data, the specified identification data corresponding to a character response input by the user during the interaction; and

voice reproduction means for reading the contents of the log data identified by the specified identification data from said log data storage and outputting speech corresponding to the contents of the identified log data.

2. A voice response service apparatus according to claim 1, wherein the log data contains time data about at least one of a connection time of a telephone line and a disconnection time of the telephone line.

3. A voice response service apparatus according to claim 1, wherein said log data storage stores a push button signal received from the user via the telephone line as a piece of the character response.

4. A voice response service apparatus according to claim 1, wherein the voice guidance is defined as character data, and

said voice reproduction means includes:

a voice synthesization processing device which synthesizes voices from the character data in the log data.

5. A voice response service apparatus according to claim 4, further comprising:

log data extraction means for extracting log data identified by the identification data by said specifying means from the log data stored in said log data storage;

wherein said service execution means executes a re-play of the service transaction in response to the history of the interaction indicated in the log data extracted by said log data extraction means; and

wherein said voice synthesization processing device synthesizes the voices in cooperation with said service execution means.

6. A voice response service apparatus according to claim 5, further comprising:

line control means for controlling the telephone line and outputting a push button signal from the user and an item of line connection notifying data to said service execution means.

7. A voice response service apparatus according to claim 6, further comprising:

switching means for connecting said service execution means to said line control means when the item of line connection notifying data and the push button signal from said line control means are outputted to said service execution means and connecting said service execution means to said log data extraction means when the log data extracted by said log data extraction means are to be reproduced.

8. A voice response service apparatus according to claim 6, further comprising:

narrative data transmitting means for transmitting narrative data to said service execution means.

9. A voice response service apparatus according to claim 8, wherein said services execution means executes a service in accordance with an item of narrative data from said narrative data transmitting means and offers the service conforming to a value of the push button signal.

10. A voice response service apparatus according to claim 8, further comprising:

log data writing means for writing the narrative data received from said narrative date transmitting means to said log data storage as log data when said service execution means executes the voice response service.

11. A voice response service apparatus according to claim 8, further comprising:

text file means for converting the narrative data from said narrative data transmitting means into character data and writing the converted character data in a text file format when said service execution means executes the voice response service.

12. A voice response service apparatus according to claim 11, wherein said voice synthesization processing means converts the character data, written to said text file means, into voice data.

13. A voice response service apparatus according to claim 8, wherein said voice synthesization processing means converts the narrative data, from said narrative data transmitting means, into voice data, said voice response service apparatus including:

accumulated voice file means for storing the voice data converted by said voice synthesization processing means.

14. A voice response service apparatus according to claim 1, further comprising a log data writing means for writing the log data to said log data storage.

wherein said voice response reproducing means reproduces the log data written by said log data writing means to said log data storage.

15. A voice response service apparatus according to claim 12, wherein said voice synthesization processing means is connected to a pseudo line control means for controlling a pseudo line and transmits converted voice data to a loud speaker via said pseudo line control means.

16. A method of providing a voice response service comprising:

executing a voice response service transaction based on interaction with a user, the interaction formed by providing voice guidance to the user and receiving character responses from the user;

storing log data to indicate a history of the interaction and storing identification data identifying the log data;

specifying identification data from the stored identification data responsive to an indication to read a stored character response, the specified identification data identifying a relevant portion of the stored log data and corresponding to a character response input by the user during the interaction;

reading the history according to the log data identified by the specified identification data; and

outputting the history read in the reading step as speech.

17. A computer-readable medium encoded with a program for providing a voice response service, said program comprising instructions for:

executing a voice response service transaction based on interaction with a user, the interaction formed by providing voice guidance to the user and receiving character responses from the user;

storing log data to indicate a history of the interaction and storing identification data identifying the log data;

specifying identification data identifying a relevant portion of the stored log data, the specified identification data corresponding to a character response input by the user during the interaction;

reading the history according to the log data identified by the specified identification data; and

outputting the history read in the reading step as speech.