JPH08251307A - Audio response service device - Google Patents

Abstract

PURPOSE: To revise sound quality in matching with an attribute of the user and an operation environment and to reproduce preceding service automatically. CONSTITUTION: The device is provided with a log information storage section 11 that stores plural processing contents as log information representing recording of a timewise transit in an interactive form with the user by audio response and stores identification information to identify each of the plural processing contents as part of the contents of audio response, an identification information entry section 12 entering identification information stored in the log information storage section 11 and an audio response reproduction section 18 reading the processing content in the interactive form of the log information corresponding to the entered identification information from the log information storage section 11 and reproducing the read processing content into an audio signal.

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD The present invention relates to a voice response service device. In particular, the present invention relates to a voice response service device that quickly reproduces history information and changes the sound quality in accordance with attributes such as the gender and age group of the telephone service user and the operating environment of the other party.

[0002]

2. Description of the Related Art A telephone service is known as a voice response service device that automatically responds by a computer.

In this telephone service, a voice is played with a preset sound quality (speed, volume, sex or background music BGM). When a telephone service is provided, this type of voice response service device sets, for example, a standard sound quality suitable for a specific age group.

Such a voice service device is, for example,
JP-A-59-181767 or JP-A-3-16
No. 0868. The voice response service device described in these publications provides a service such as a deposit balance inquiry by using a voice recognition device in the voice service device.

The device disclosed in Japanese Patent Laid-Open No. 61-235940 corrects the voice output level of the telephone so that the voice output level is always a constant value. As a result, the user can easily hear the voice information.

However, in the apparatus disclosed in Japanese Patent Laid-Open No. 61-235940, it is necessary for the user to specify the volume and sex in order to correct the output level. That is, since the correction is performed manually, the work is difficult.

Further, the devices of the other publications do not provide services with sound quality tailored to users. In this kind of voice response service device, it is necessary to make a fine adjustment so that the other party can easily understand by making the voice louder depending on the person who is talking, or speaking slowly. Therefore, there has been a demand for a voice response service device that automatically changes the sound quality according to the age and sex of the user.

Further, the voice response service device can carry out mail order sales of products by utilizing a telephone service. This voice response service device normally collects user information and product input information from the user as history information.

[0009] In the voice response service device, when an inquiry is made by the user due to an ordering trouble such as an item ordered by the user, a quantity, an amount of money, etc., the operation of the user is confirmed by tracing past history information. It was necessary to do the work.

Further, the voice response service apparatus manually reproduces the operation of the user based on the history information when a failure occurs.

[0011]

However, in the voice response service apparatus described above, the history information must be manually reproduced when an ordering trouble occurs, for example. This not only took a lot of time, but also increased labor costs. In addition, it was necessary to automatically track the erroneous operation location.

Further, in this type of voice response service apparatus, the test for the cause of the order trouble and the smooth voice response service was manually performed, so that a lot of test man-hours were required during development and maintenance. .

Therefore, an object of the present invention is to provide a highly comfortable service by changing the sound quality in accordance with the attributes of the telephone service user such as gender and age group and the operating environment of the other party. .

Further, the present invention is to reproduce a past service from the history information and easily confirm the content of the service. Further, an object of the present invention is to reduce test man-hours and labor costs during development and maintenance.

[0015]

The voice response service apparatus of the present invention adopts the following means in order to solve the above-mentioned problems.

A first aspect of the present invention stores a plurality of processing contents interactively performed with a user by a voice response as log information indicating a record of temporal transition and identifies each of the plurality of processing contents. Log information storage unit for storing identification information for storing the identification information as a part of the content of the voice response, an identification information input unit for inputting the identification information stored in the log information storage unit, and an input by the identification information input unit. And a voice response reproducing unit that reads out the interactive processing content of the log information corresponding to the identification information from the log information storage unit and reproduces the processing content read out as voice (corresponding to claim 1).

Here, the first aspect of the invention is also realized by adding the following additional components. The log information to be stored in the log information storage unit may include time information of at least one of a telephone line connection time and a telephone line disconnection time (corresponding to claim 2).

The log information storage unit may store a push button signal received from a user via a telephone line as character information (corresponding to claim 3). Further, the content of the voice response stored in the log information storage unit is character information, and the voice response reproduction unit synthesizes a voice to be responded from the character information stored in the log information storage unit. A processing unit may be provided (corresponding to claim 4).

The voice synthesis processing section performs voice synthesis by a voice rule synthesis method for synthesizing voice from a character string, for example.
In addition to the above, the voice synthesis method includes a waveform encoding method that encodes a voice waveform by utilizing the characteristics of the voice signal, an analysis and synthesis method that encodes the voice signal according to a voice generation model, and the like.

A second aspect of the present invention is, in a voice response service device for performing processing in an interactive manner with a user by a voice response, an attribute storage section for storing the attribute of the user and the attribute storage section. A user sound quality changing unit that changes the sound quality of the voice that responds to the user based on the attribute information of the user (corresponding to claim 5).

Here, the second aspect of the invention is also realized by adding the following additional constituent elements. That is, the sound quality of the sound changed by the user sound quality changing unit may be the volume level (corresponding to claim 6).

The sound quality of the sound changed by the user sound quality changing section may be at least one of a male sound and a female sound (corresponding to claim 7). In the first invention, the identification information input unit includes a log information extraction unit that extracts log information to be used by a user based on the identification information from the log information stored in the log information storage unit. A service execution unit that inputs the log information extracted by the log information extraction unit as input information from a user and executes a voice response service. The voice synthesis processing unit may synthesize voice from log information sent from the service execution unit (corresponding to claim 8).

In the first invention, the device may include a line control unit for controlling a telephone line and outputting a push button signal and a line connection notification information from a user to the service execution unit (claim 9). Corresponding to).

In the first aspect of the invention, when the push button signal and the line connection notification information from the line control unit are output to the service execution unit, the service execution unit is connected to the line control unit and the log When reproducing the log information extracted by the information extraction unit, the device may include a switching unit that connects the service execution unit to the log information extraction unit (corresponding to claim 10).

In the first invention, a narration information sending section for sending narration information to the service executing section may be provided (corresponding to claim 11). 1st invention WHEREIN: The said service execution part performs a service according to the narration information from the said narration information transmission part, and provides a user with the service according to the value of the said push button signal (corresponding to claim 12). .

In the first invention, when the service executing unit executes the voice response service, a log information writing unit for writing the narration information from the narration information sending unit as log information in the log information storage unit is provided. It may be (corresponding to claim 13).

In the first aspect of the invention, when the service executing unit executes the voice response service, the text in which the narration information from the narration information sending unit is converted into character information and the converted character information is written as a file format text. A file unit may be provided (claim 14).
Corresponding to).

In the first invention, the voice synthesis processing section may convert the character information written in the text file section into voice information (corresponding to claim 15). First
In the invention, the voice synthesis processing unit may convert the narration information from the narration information sending unit into voice information. It may include a stored sound file unit that stores the voice information converted by the voice synthesis processing unit (corresponding to claim 16).

In the first invention, a log information writing unit for writing log information in the log information storage unit is provided. The voice response reproducing unit may reproduce the log information written in the log information storage unit by the log information writing unit (corresponding to claim 17).

In the first invention, the voice synthesis processing unit may be connected to a pseudo line control unit for controlling a pseudo line, and may send the converted voice information to a speaker through the pseudo line control unit ( (Corresponding to claim 18).

Further, in the second invention, the attribute storage section includes a sex rule table storing male or female sounds according to the gender of the user, and a volume table storing volume levels suitable for the age of the user. May be provided (corresponding to claim 19). In the second invention, a state rule table for setting the volume and the sound speed in accordance with the state of the input operation of the user may be provided (corresponding to claim 20).

In the second invention, the user sound quality changing unit may include a voice attribute setting unit for setting a voice attribute by referring to the state rule table (corresponding to claim 21). A voice synthesis processing unit that synthesizes voice information that matches the voice attribute of the user set by the setting unit may be provided (corresponding to claim 22).

In the second invention, the user sound quality changing section may include a voice attribute setting section for setting a voice attribute by referring to the gender rule table and the volume table (corresponding to claim 23). ), And a voice synthesis processing unit for synthesizing voice information suitable for the voice attribute of the user set by the voice attribute setting unit (corresponding to claim 24).

The above-mentioned inventions may be combined as appropriate. According to the present invention, the log information storage unit stores a plurality of processing contents to be performed interactively with the user by a voice response as log information indicating a record of temporal transition, and stores each of the plurality of processing contents. Identification information for identification is stored as a part of the content of the voice response. When the identification information input unit inputs the identification information stored in the log information storage unit, the voice response reproduction unit displays the interactive processing contents of the log information corresponding to the identification information input by the identification information input unit. The processing content read from the log information storage unit and read out is reproduced as voice.

With this, it is possible to automatically reproduce the past service from the log information and easily confirm the content of the service. Further, the processing content can be specified by the time information of connection / disconnection of the telephone line included in the log information.

Further, the push button signal received from the user via the telephone line is stored in the log information storage section as character information. Therefore, the log information can be reproduced by the stored push button signal.

The voice synthesis processing unit synthesizes a voice to be responded from the character information stored in the log information storage unit. The attribute storage unit stores the attribute of the user, and the user sound quality change unit changes the sound quality of the voice that the user responds to based on the attribute information of the user stored in the attribute storage unit. Therefore, the service can be provided with the sound quality tailored to the user.

The sound quality of the voice to be changed is a volume level, and a volume level that is easy to hear is automatically set. Further, the sound quality of the voice to be changed is a male sound or a female sound, and the user can select either male sound quality or female sound quality and receive the service with the sound that is easier to hear.

When the log information extraction unit extracts the log information to be used by the user from the log information stored in the log information storage unit based on the identification information, the service execution unit extracts the log information. The log information extracted by the section is input as input information from the user to execute the voice response service. The voice synthesis processing unit synthesizes voice from the log information sent from the service execution unit. As a result, the specific processing content can be reproduced from the log information.

Further, the line control unit controls the telephone line and outputs the push button signal and the line connection notification information from the user to the service execution unit. The dialogue between the user and the voice response service device is smoothly performed.

Further, since the switching unit connects the service executing unit to the line control unit, a normal service is provided. Since the switching unit connects the service execution unit to the log information extraction unit, the past service can be reproduced from the log information.

Further, the service execution unit can execute the service according to the narration information from the narration information transmission unit. In addition, the service execution unit,
The service is executed according to the narration information from the narration information sending unit, and the service according to the value of the push button signal is provided to the user. As a result, since the dialogue between the user and the voice response service device can be performed according to the narration information, the burden on the user can be reduced.

When the service executing unit executes the voice response service, the log information writing unit writes the narration information from the narration information sending unit as log information in the log information storage unit. Thereby, for example, when the order information is incorrect, the log information can be read from the log information storage unit to trace the erroneous operation location.

Further, since the text file section converts the narration information from the narration information sending section into character information and writes it as text in a file format, the character information can be combined with the voice information by, for example, voice rule composition.

The voice synthesis processing section can convert the narration information from the narration information sending section into voice information, and the accumulated sound file section can write the converted voice information.

The voice response reproducing section reproduces the log information written in the log information storing section by the log information writing section. As a result, it is possible to shorten the test time of the reproduction test performed when a failure occurs.

Further, the voice synthesis processing section sends the voice information to the speaker via the pseudo line control section. As a result, the output of the speaker allows the user to recognize the error in the log information by voice.

Further, a male sound or a female sound is set according to the sex of the user by the sex rule table, and a volume level suitable for the age of the user is set by the volume table. As a result, the volume can be set according to the taste of the user.

Further, since the volume and the sound speed are set in the state rule table according to the state of the input operation of the user, the operation load on the user can be reduced. Also, the voice attribute setting unit sets a voice attribute by referring to the state rule table. As a result, the voice attribute can be set according to the user.

The voice synthesis processing unit synthesizes voice information that matches the voice attribute of the user set by the voice attribute setting unit. That is, by changing the volume and speed according to the operation state of the user, it is possible to provide a highly comfortable service corresponding to the user's attribute and skill level.

Further, by using the sex rule table and the volume table, the volume,
By changing the speed, it is possible to provide a highly comfortable service corresponding to the user's attribute and skill level.

[0052]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of a voice response service apparatus of the present invention will be described in detail below with reference to the drawings. <First Embodiment> FIG. 1 is a block diagram showing a first embodiment of a voice response service system including a voice response service device of the present invention.

The system according to the first embodiment automatically reproduces the interactive processing between the user and the computer from the history information storage unit and performs the overtime business such as the product ordering business, the reservation business, the material request business and the bank transfer business. Apply to reduce labor costs.

In FIG. 1, the voice response service system comprises a computer C which operates as a voice response service device and a telephone side U which is connected to the computer C and used by a user. The voice response service system is used for telephone service business.

The voice response service system, for example, outputs a push button signal to the computer C by the telephone side U such as a home or office, and carries out an interactive process between the computer C and the telephone side U so as to perform the various operations. Do business.

The computer C comprises a voice response service section 10 surrounded by a dotted line, a history information extraction section 12, a pseudo line control section 19, and a speaker 33. The voice response service unit 10 operates when normally providing a telephone service. The voice response service unit 10 includes a narration story output unit 15, a history information storage unit 11, a switching unit 20, a line control unit 14, a service execution unit 17, and a voice synthesis processing unit 18.

FIG. 5 is a diagram describing service contents.
Here, the service content is, for example, a product ordering business. This service content is called a narration story. The narration story output unit 15 outputs a narration story.

FIG. 2 is a diagram showing history information stored in the history information storage unit 11. When the voice response service is performed as shown in the narration story of FIG. 5, an example of history information recorded in FIG. 2 is shown. History information storage unit 11
Records service content over time.

That is, the history information storage unit 11 stores the time A
Stores log information (history information) that represents the temporal transition of service content from the start to the end of the service provided by the user from the connection of the telephone line applied to the product ordering system to the disconnection of the telephone line. . History information storage unit 1
1 records time information such as the connection time of the telephone line, the disconnection time, the time when the computer starts reading the narration, and the time when the user inputs the push button.

FIGS. 3 and 4 are diagrams showing operation sequences on the user side (U) and the computer side (C). FIG. 3 is a diagram showing a sequence in which a service is executed according to the narration story of FIG. FIG. 4 is a diagram showing an example in which a failure occurs during the execution of the service.

The history information extraction unit 12 is connected to the history information storage unit 11 and operates when reproducing a service. The history information extraction unit 12 includes a history information storage unit 1
The touch-tone data inputted by the user is extracted from the history information stored in 1. A switching unit 20 is connected to the history information extraction unit 12.

The switching unit 20 is composed of contacts, and when the line control unit 14 is connected to the service execution unit 17, that is, when a normal service is provided, a push button signal input by the user is transmitted from the telephone 30. The service execution unit 17 reads and operates.

The switching unit 20 extracts the touch-tone data input by the user from the history information storage unit 11 when connecting the history information extraction unit 12 to the service execution unit 17, that is, when reproducing the past service. It is sent to the service execution unit 17 via the unit 12. The service execution unit 17 executes the past service from the history information extraction unit 12.
The voice synthesis processing unit 18 reproduces the service provided by the service execution unit 17 in the past by voice.

The speech synthesis processing section 18 synthesizes speech from a character string representing pronunciation by a rule synthesis method of synthesizing speech from a character string in the speech synthesis method shown in FIG. As shown in FIG. 6, the voice synthesis method used in the voice response service system includes a waveform coding method, an analysis synthesis method, a rule synthesis method, and the like.

The rule composition method is described in FIGS. 7 and 8. The rule synthesizing method is a method in which a character string mixed with kana-kanji is sentence-analyzed, and a signal waveform composed of the analyzed character string is synthesized to convert it into voice. This rule synthesizing method requires less amount of information than other methods, so that the number of output words can be infinite and is suitable for a voice response service system.

The waveform coding method is a method in which words to be read are recorded in advance and the words are connected to each other to synthesize the words. The analysis-synthesis method is a speech synthesis method that encodes a speech signal based on a speech generation model, and speech can be synthesized by these methods as well.

In the telephone service, in addition to the pronunciation by the voice synthesis method, the voice by reproducing the accumulated sound is also used. The accumulated voice generally has a better quality than the regular synthesized voice, but since the recording work is required to change the content, the operability becomes poor. This accumulated voice is good for reading aloud content.

On the other hand, the regular synthesized voice is suitable for reproducing an irregular voice such as a transient sentence, an irregular sentence, or a partially variable document. FIG. 7 is a diagram showing a specific configuration example of a voice synthesis processing unit adopting a voice synthesis method. In FIG. 7, the speech synthesis processing section 18 is composed of a language processing section 31 and a sound processing section 32. The language processing unit 31 includes a sentence analysis unit 34, a word dictionary 35, and a reading / prosodic symbol adding unit 3.
6 is provided.

The sentence analysis unit 34 divides the input sentence into analysis units and performs word division by matching the divided sentences with the words stored in the word dictionary 35, and reading, accent type, and grammar for each word. Set the information. The reading / prosodic sign adding unit 36 adds readings and prosodic signs based on the information obtained from the sentence analyzing unit 34. Prosodic symbols are, for example, poses, accents of phrases, intonations, and the like.

In the language processing unit 31, when the reading / prosodic symbol assigning unit 36 imparts reading or prosodic symbols, the acoustic processing unit 32 adds intonation and outputs sound by waveform synthesis or the like. The sound processing unit 32 includes the intonation generation unit 37 and the waveform synthesis unit 3.
8 and a phoneme piece 39 which is a phoneme database. The intonation generation unit 37 generates intonation patterns representing the time length of each phoneme and the pitch of the voice based on the reading and prosody symbols. The waveform synthesizing unit 38 reads the phoneme piece data stored in the phoneme piece unit 39, and smoothly connects the phoneme piece data according to the phoneme time length and intonation pattern to synthesize a speech waveform.

The sound processing section 32 outputs the sound whose waveform is synthesized from the waveform synthesizing section 38 to the speaker 33, and the speaker 33 outputs, for example, "core, on-the-go sedes".

FIG. 8 is a diagram showing a specific example of performing voice synthesis by the voice synthesis method shown in FIG. For example, in FIG.
Voice synthesis will be described by taking the sentence "This is voice synthesis" as shown in FIG. First, the sentence analysis unit 34 inputs the sentence and performs word division. The sentence analysis unit 34 divides the sentence into words, such as "this / ha /, voice / synthesis / de / su.".

Next, the text analysis unit 34 sets a phrase. The sentence analysis unit 34 sets a phrase such as "This is /, voice synthesis." The reading / prosodic sign adding section 36
Based on the result of the sentence analysis unit 34, reading is added, and a prosody code indicating a pose, a phrase accent, and an intonation is added. The reading is "Kore / Wa /, Oh ^, Nse / Goeze / Death /.". The prosody code is "Colewa, Onsego ^, Saedes."

Next, in the acoustic processing section 32, the intonation generating section 37 generates an intonation pattern indicating the pitch of the sound, and the waveform synthesizing section 38 reads out the phoneme piece data from the phoneme piece section 39 and the phoneme time length information and the intonation. The phoneme piece data is connected according to the pattern information to synthesize a voice waveform.

By performing the above processing, the sound data is output from the sound processing section 32. (Description of Operation During Normal Service) Next, the operation during normal service of the first embodiment of the voice response service system configured as described above will be described.

First, the switching unit 20 connects the line control unit 14 to the service execution unit 17. When the narration story output unit 15 outputs the narration story to the narration story analysis unit 16, the narration story analysis unit 16 analyzes the narration story.

The service execution unit 17 follows the analyzed narration story to give a voice output instruction to the voice synthesis processing unit 18, an instruction to the history information writing unit 27, a push button reading instruction to the line control unit 14, and read. A process is branched according to the result, and an access instruction to the database access unit 22 is given. The push button signal input by the user is read by the service execution unit 17 from the telephone 30.

Regarding the output of voice, the service is executed using the accumulated sound file 26, the text file 25, etc. according to the narration story. The database 23 comprises a user database in which information about users is written, a product database in which product information is written, or an order database in which order information is written.

The database access unit 22 performs a writing / reading process of the database 23. The text file 25 stores text information in advance, and the accumulated voice file 26 stores accumulated voice information. The history information writing unit 27 writes the service content instructed by the service execution unit 17 into the history information storage unit 11. Speech synthesis processing unit 18
Synthesizes speech by the speech synthesis method already described in FIGS. 6 to 8.

The switching unit 50 causes the voice synthesis processing unit 1 to operate.
The voice data output from 8 can also be output to the telephone 30 via the line control unit 14. At this time, the contents of the voice response service can be modeled and the models can be analyzed without connecting to the telephone line.

Further, the voice data from the voice synthesis processing section 18 can be controlled by controlling the pseudo line control section 19 to cause the speaker 33 to ring. The operator can hear the service content as voice data. <Narration Story Output Unit> Next, the narration story output unit 15 will be described in detail according to the procedure from procedure number 1 to procedure number 23 shown in FIG.

In the narration story output unit 15, the contents of the narration are procedure number 1 to procedure number 23.
It is decided according to the procedure up to. That is, in the procedure number 1, the accumulated voice file "op
Since "en.pcm" is specified, "open.pcm" is read from the accumulated sound file 26 of FIG. 1, and "open.pcm" is read aloud by the voice response service unit 10.

In procedure number 2, the voice response service unit 10 reads aloud the user number input narration of the narration story output unit 15, for example, "Please input user number".

In the procedure number 3, when the user inputs the user number from the push button of the telephone 30, the content of the push button is read and the user number is input to the voice response service unit 10.

In the procedure number 4, the voice response service unit 10
When the user inquires, the user database of the database 23 is accessed. In the procedure number 5, the result of inquiring the database 23 in the procedure number 4 is used as a narration of "user number of the narration story output unit 15 and confirmation of the user number," XX, XX, isn't it? " Read out from the voice response service unit 10.

In procedure number 6, the voice response service section 10 branches the process based on the confirmation result from the user. In this procedure number 6, for example, the user selects "1" from the telephone 3
When the push button 0 is selected, the process is procedure number 7.
Go to processing. When the user selects, for example, "9" with the push button of the telephone 30, the process of procedure number 2 is executed again.

In the procedure number 7, the voice response service unit 10 reads aloud the narration “Please input the product number” which is the product number input guidance narration of the narration story output unit 15.

In the procedure number 8, when the product number is input to the voice response service unit 10 by, for example, a push button, the voice response service unit 10 reads the product number. In procedure number 9, the voice response service unit 10 accesses the product database of the database 23 when there is a product inquiry.

In the procedure number 10, the result of the database inquiry in the procedure number 9 is used as a narration of the product number confirmation narration of the narration story output section 15 as a narration of "XX, XX, isn't it?" Read from the service department 10.

In procedure number 11, the voice response service section 10 branches the process based on the confirmation result from the user.
In this procedure number 11, for example, when the user selects “1” with the push button of the telephone 30, the process proceeds to the procedure number 12.

Also, for example, if the user selects "9", the telephone 30
When the push button is selected, the process of procedure number 7 is executed again. In the procedure number 12, the voice response service unit 10 reads aloud the narration “Please input the number”, which is the number input narration of the narration story output unit 15.

In the procedure number 13, for example, if the number is input to the voice response service unit 10 by the push button,
The voice response service unit 10 reads the number. Procedure number 1
In 4, the narration story output unit 15 reads the narration “Is this all right?” Which is the input completion confirmation narration from the voice response service unit 10.

In procedure number 15, the voice response service section 10 branches the process based on the confirmation result from the user.
In the procedure number 15, for example, when the user selects “1” with the push button of the telephone 30, the process proceeds to the procedure number 16.

Further, for example, the user inputs "9" by the telephone 30
When the push button is selected, the process of procedure number 7 is executed again. In procedure number 16, the voice response service unit 10 reads aloud, "Is it okay?", Which is the input confirmation narration of the narration story output unit 15.

In procedure number 17, the voice response service section 10 branches the process based on the confirmation result from the user.
For example, when the user selects “1” with the push button of the telephone 30, the process proceeds to the process of procedure number 18.

Further, for example, if the user selects "9", the telephone 30
When the push button is selected, the process of procedure number 7 is performed. In the procedure number 18, since the text file "order.txt" is specified in the narration story output unit 15 for repeated order content narration, the voice response service unit 10 reads the narration read from the text file 25.

In the procedure number 19, the voice response service unit 10 reads aloud the narration "Is this all right?" Which is the order confirmation narration of the narration story output unit 15.

At this time, in the procedure number 20, the voice response service section 10 branches the process based on the confirmation result from the user. In this procedure number 20, for example, when the user selects "1" with the push button of the telephone 30, the procedure number 21 is processed.

Also, for example, if the user selects "9", the telephone 30
When the push button is selected, the process of procedure number 23 is executed. In the procedure number 21, the voice response service unit 10 reads the narration “Order number is XX?” Which is the order number narration of the narration story output unit 15.

In procedure number 22, ordering processing is performed. The contents of the received order are written in the ordering database of the database 23. In the procedure number 23, “close.pcm”, which is the accumulated voice, is specified as the ending narration of the service of the narration story output unit 15, so the voice response service unit 10 reads it from the accumulated voice file 26 and reads it.

According to the voice response service device of FIG. 5 described above, the telephone 30 of the user U and the computer C are used.
The processing with the voice response service unit 10 can be surely performed in an interactive manner. (Description of Sequence of FIG. 3) The process of FIG. 3 will be described using the narration story output unit 15 of FIG. 1 described above.

For example, on the user U side, when the user number “6511123” is input by the push button of the telephone set 30 as the input 103, the user number “6511223” is transmitted to the computer C side. The transmission information, which is the user number “651123” transmitted to the computer C side, is confirmed by the line control unit 14 on the computer C side, and then the narration story output unit 15 outputs the narration story 104. Then, the user number / user name confirmation guide 104 is transmitted to the telephone set 30 on the user U side.

On the other hand, on the computer C side, after the line controller 14 confirms the confirmation ok of the user number / user name sent from the user U side as shown in FIG. The narration story output unit 1 is provided to output a product number input guidance instruction to the U-side telephone 30.
The narration story 106 is output from 5.

The narration story output unit 15 outputs the narration story to the narration story analysis unit 16, and the narration story analysis unit 16 analyzes the narration story.

The service execution unit 17 follows the database 23 or the files 25 and 26 according to the narration story analyzed by the narration story analysis unit 16.
To execute the service. (Processing at the time of ordering) Further, the telephone 30 on the user U side follows the product number input instruction guide 106 sent from the narration story output unit 15 on the computer C side.
The user inputs the product number “321” from the push button of the telephone 30. The product number “321” is code information representing a specific product.

When the user U inputs the product number “321” to the computer C side as the input 107 from the telephone 30, the line control unit 14 on the computer C side confirms the product number “321”, and further, Product number "3
21 ”in the product database of the database 23. Then, the confirmation instruction guidance for the product number “321” is transmitted from the computer C side to the telephone 30 on the user U side as transmission 108.

The telephone number 30 on the side of the user U has a product number "3".
When the confirmation instruction guide “21” is received from the computer C side, the confirmation information “1” indicating that the product ordered by itself is the product represented by the product number “321” is the push button of the telephone 30. Will be entered more.

Next, the product number input guide 110 is transmitted from the computer C side to the telephone 30 on the user U side.
The telephone 30 on the side of the user U who received the number input guidance 110
Indicates the number of products to be ordered, for example, "3" on the telephone 3
It is input as the input 111 by the push button 0.

When the information on the number of products to be ordered is transmitted from the user U side to the computer C side, the computer C side confirms that the product database of the database 23 has the stock of the products, and confirms the number of the products. Confirmation information 1
12 is transmitted from the computer C side to the telephone 30 on the user U side.

At this time, the telephone number 30 on the user U side inputs the number confirmed information "1" as an input 114 from the push button of the telephone number 30. When the input end confirmation guide 114 is sent from the computer C side to the telephone set 30 of the user U side, the intention to complete the input, for example, if it is "1", the end instruction is input as the input 115 from the push button of the telephone set 30, and the end The instruction is transmitted from the user U side to the computer C side.

When the above-mentioned response instruction is given between the telephones 30 of the computer C side and the user U side, in order to confirm the intention of ordering, in order to confirm the intention of ordering, the order confirmation confirmation guide 116 and the order confirmation guide 117 of the narration story output unit 15 are confirmed. Is transmitted from the computer C side to the telephone 30 on the user U side.

In response to these guides, the user inputs the ordering process “1” as an input 118 from the push button of the telephone 30 on the telephone 30 of the user U. When the computer C confirms that the order processing information “1” is transmitted from the telephone 30 of the user U to the computer C, the order number guide 119 and the service end guide 12 are displayed.
0 is transmitted from the computer C side to the user U side. Then, the computer C side is disconnected as a disconnection 121 from the telephone line of the telephone 30 of the user U side.

As described above, in the first embodiment, the user U
When the product ordering work is performed by the interactive format between the computer side and the computer side, the history information writing section 27
Shows the log information shown in FIG. 2 in the history information storage unit 1 shown in FIG.
It is possible to write in one specific writing area. Further, the history information extraction unit 12 appropriately reads the written log information. As a result, when the order information is incorrect, the ordering work can be smoothly performed. (Processing When Trouble Occurs on Computer Side) Next, processing when a trouble occurs on the computer C side will be described.
The sequence diagram of FIG. 4 is a diagram showing a process when an ordering trouble occurs. The detailed description of the processes from the outline description 101 of the same service as in FIG. 3 to the user confirmation instruction 105 is omitted.

Further, in the explanation of FIG. 4, FIG. 1 to FIG.
Description will be made with reference to the symbols up to. In the first embodiment, after the user inputs "1" of confirmation OK 105 from the push button of the telephone 30, a failure occurs in the software on the computer C side, the database 23, the text file 25, the accumulated voice file 26, and the like. To do.

In this case, in order to inform the user that the fault occurrence 130 was on the computer C side, the computer C sends a fault occurrence signal to the user's telephone 30 and the telephone line is disconnected as disconnection 121. To be done.

As described above, when a failure occurs during service, a reproduction test or a confirmation test after the failure is corrected is performed. In this case, the history information stored in the history information storage unit 11 of FIG. 1 is reproduced. This allows
The user can be made aware that the computer C has a cause of failure. Also, testing time can be shortened because testing can be performed automatically. (Reproduction of Voice Response Service) Next, reproduction of the voice response service will be described. As described above, when the normal service is provided, the signal input by the user U from the push button of the telephone 30 is recognized by the line control unit 14, and the push button signal is read by the service execution unit 17.

On the other hand, when reproducing the voice response service, the switching unit 20 connects the service execution unit 17 to the history information extraction unit 12. The history information extraction unit 12 extracts (specifies) a service that the user used in the past from the history information storage unit 11, and uses the numerical value input from the push button recorded in the history information storage unit 11 as the read value of the push button. , To the service execution unit 17.

The voice synthesis processing section 18 is the service execution section 17
The history information extracted by the history information extracting unit 12 via the, ie, the past voice response service is reproduced. As described above, in the first embodiment, the voice response service can be reproduced by executing the pseudo voice response service.

The operation at this time will be described with reference to the description of FIGS. 1, 2 and 5. For example, September 6, 1994
The content of the service of the user number 651123 who used the service on the day is reproduced.

At this time, the voice reproduced by the voice synthesis processing section 18 is sent to the telephone set 30 of the user U by the line control section 14. Users can listen to past service contents.

The history information extraction unit 12 is the history information storage unit 1
The history information of the user who wants to reproduce is specified from the history information of FIG. A method of specifying history information will be described in detail in the section of (Operation for specifying user history) using FIG. Here, for example, the history information A is specified from among the history information shown in FIG.

Further, the switching unit 20 includes the service executing unit 17
By connecting the history information extraction unit 12 to and activating the history information extraction unit 12, reproduction is started according to the service story of FIG.

The operation of the narration story output unit 15 has already been described in detail in the section <Narration story output unit>, so the description thereof is omitted here. In procedure number 1 and procedure number 2 in FIG. 5, the voice response service unit 10 reads out the service outline description and the user number input as usual.

When the user number of the procedure number 3 is input, the service execution section 17 instructs the history information extraction section 12 to read the push button. The history information extraction unit 12 reads the user number "651123" 103 of the history information shown in FIG. 2, and the voice synthesis processing unit 18 obtains voice data by synthesizing "Rokugoichiichisan".
The voice data is transmitted by the line controller 14 to the telephone 3 of the user U.
0, and the user is informed of the user number.

The procedure number 5 is a normal operation.
In the procedure number 6, the process is branched based on the result from the user, so the service execution unit 17 uses the history information extraction unit 1
Instruct 2 to read the push button. The history information extraction unit 12 reads the user confirmation “1” 105, and the voice synthesis processing unit 18 synthesizes “Ichi” to obtain voice data. The voice data is sent by the line controller 14 to the telephone 30 of the user U, the confirmation result is transmitted to the user, and the process branches to procedure number 7.

Although the description of the subsequent processing is omitted, the past service can be reproduced by performing the service up to the line disconnection 121. When the voice synthesis processing unit 18 is connected to the pseudo line control unit 19 by the switching unit 50, the voice data from the voice synthesis processing unit 18 is output to the speaker 33 via the pseudo line control unit 19. Good.

Further, in this example, the voice synthesis processing section 18 converts the push button number into voice and notifies the user of the number. For example, it is possible to prevent the push button number from being transmitted to the user by not sending the push button number to the voice synthesis processing unit 18, if necessary. (Operation for Specifying User History) Next, the operation for specifying the user history will be described in detail. FIG. 9 is a flowchart showing a process for identifying a record that the user wants to reproduce from the history file. The operation for identifying the user history is performed by the history information extraction processing of the history information extraction unit 12.

First, the history file of the date of use in the history information storage unit 11 is opened (ST40). Here, the history file of FIG. 2 will be described as an example. The following processing is performed until the end of this history file.

First, one line is read from the history file (ST42). For example, when "line disconnection" is recorded in the line read in ST42, there is a possibility of the reproduction start position. Therefore, the line number 1 is recorded in the history information storage unit 11 (ST43, ST44).

When "line disconnection" is recorded in the line read in ST42 (ST45) and the user history is found (ST46), line number 1 is determined to be the reproduction start position ( ST47).

When "user number input narration" is recorded in the line read in ST42 (ST
In step 48), the push button input numerical value from the next line is set as the user number (ST49).

Here, the user number to be reproduced and ST49
When the user numbers of (1) and (2) match (ST50), it is determined that the corresponding user history has been found (ST51). After performing the above processing until the history file is completed, close the history file of the usage date. Thereby, the user history can be specified.

As described above, in the first embodiment, the user U
2 can be written in a specific writing area of the history information storage unit 11 in an interactive form between the computer side and the computer C side, for example, when a product ordering operation is performed. By appropriately reading the written log information, the ordering work can be smoothly performed when the ordering information has an error.

Also, by exchanging the interaction between the user U side and the computer C side in a voice response service such as a telephone service as log information and letting the user hear the log information, a push at the time of the push button input by the user is performed. It is possible to trace the location of an erroneous operation due to a wrong button press.

For example, time-series information such as the time of connection / disconnection of the telephone line in the history information storage unit 11, the time when the user starts reading the user information of the user, and the time when the user inputs from the push button. Etc. can be written. Therefore, when the user makes an input error or the like, the user can easily recognize the erroneous operation portion by reproducing the information.

Furthermore, the number of test steps can be reduced by performing automatic testing. <Second Embodiment> FIG. 10 is a block diagram showing a second embodiment of a voice response service system including a voice response service device of the present invention. When the service is provided by humans, depending on the situation of the other party, the voice is made louder or the voice is slowly spoken. That is, the volume is adjusted so that the other party can easily understand.

In the second embodiment, the computer automatically changes the sound quality in accordance with the information such as the age, sex, audibility and difficulty of hearing of the other party, and the service is provided dynamically according to the user's sound quality. Carry out.

In the structure shown in FIG. 10, only the structure different from that of the first embodiment shown in FIG. 1 will be described. The other components are denoted by the same reference numerals, and detailed description thereof will be omitted here.

In FIG. 10, an attribute table 40 and a state rule table 41 are connected to the service execution section 17. These tables are provided in a database (not shown). The attribute table 40 sets the volume level according to the sex of the user and the age group of the user. The state rule data database 41 sets the volume or speaking speed according to the state of the input operation of the user.

FIG. 11 is a structural block diagram showing the main parts of the second embodiment shown in FIG. In FIG. 11, the attribute table 40 is composed of a sex rule table 40a in which male or female sounds are stored according to the gender of the user, and a volume table 40b in which the volume level changes depending on the age of the user.

In the sex rule table 40a, when the user is a male, a female voice that has been voice-synthesized is selected in order to give a soft voice. When the user is a female, a voice-synthesized male sound is selected in order to produce a vocalization.

In the volume table 40b, the volume level suitable for the age group of the user can be roughly set. For example, the volume level is set to 4 when the user age is 0 to 59, and the volume level is set to 5 when the user age is 60 to 69. When the age of the user is 70 to 79, the volume level is set to 6, and when the age of the user is 80 to 89, the volume level is set to 7.

That is, for example, the volume level is increased from the volume level 1, and the larger the numerical value, the larger the volume. A rough volume is set according to the user's gender and age group.

The gender rule table 40a and the volume table 40b set the volume level suitable for the general user. The state rule table 41 adjusts the volume or the speed of voice according to the user.

The sex rule table 40a, the volume table 40b, and the state rule table 41 are the service execution unit 1
7d is connected. The voice attribute setting event generating unit 42 and the voice synthesis processing unit 18 are connected to the service executing unit 17d.

For example, when an instruction indicating that the volume is low and the speed is low is transmitted from the push button to the voice attribute setting event generating unit 42, the voice attribute setting event generating unit 42 sets the voice attribute of the user. Fire an event to do so.

The service execution unit 17d is a rule check processing unit 1 for checking the rules of the attribute table 40.
7a, a voice attribute setting unit 17b that sets a voice attribute according to the processing output of the rule check processing unit 17a, and a narration sentence output that outputs a narration sentence from the narration story output unit 15 according to the voice attribute output of the voice attribute setting unit 17b. And part 17c.

The state rule table 41 can be set so that the volume is increased by one level and the voice speed is reduced by one level. The voice synthesis processing unit 18
Output of voice attribute setting unit 17b and narration sentence output unit 1
Speech synthesis processing is performed from the output of 7c. (Operation of Second Embodiment) Next, the operation of the second embodiment will be described. For example, when the user's attribute exists in the database, if the user's attribute is obtained from the user number or any user inputs his own attribute from the push button of the telephone 30, the voice attribute setting event generating unit 15 Is
Generates a voice attribute setting event.

The rule check processing unit 17a refers to the sex rule table 40a and the volume table 40b according to the output from the voice attribute setting event generating unit 15, and outputs the referred table information to the voice attribute setting unit 17b.
The voice attribute setting unit 17b sets a voice attribute of the user.

For example, when a male, 61 years old, uses this voice response service, the sex rule table 40
a, the volume table 40b is referred to, the female sound is set, and the volume level is set to 5 in order to soften the voice gender.

When the user's input operation occurs in the voice attribute setting event generating section 15, the rule check processing section 17a refers to the state rule table 41. The voice attribute setting unit 17b sets the voice attribute from the table information of the state rule table 41.

For example, when the user makes an input error, the voice speed is reduced by one level and the volume is increased by one level. That is, it is considered that the narration is fast, the volume is low, and the voice cannot be heard. In this case, the sound quality is changed to speak slowly and loudly.

On the other hand, when a voice attribute setting command suitable for the user is output from the voice attribute setting unit 17b and narration is output from the narration sentence output unit 17c,
The voice synthesis processing unit 18 synthesizes to a sound quality suitable for the user.

As described above, according to the second embodiment, by automatically changing the sound quality in accordance with the information such as the user's age group, sex, pronunciation state such as ease of listening and difficulty of hearing, it is possible to determine what kind of user It is possible to provide a voice response service with easy-to-listen sound quality.

As a result, it is possible to improve the user service by eliminating an erroneous operation due to a mistake in listening.
Further, even when the second embodiment is applied to a product ordering business, a reservation business, and a material request business, erroneous recognition by a user's voice is reduced, and the business can be smoothly performed.

[0156]

According to the present invention, the log information storage unit stores, as log information, a plurality of processing contents performed in an interactive manner with a user by a voice response and stores identification information for identifying each of the plurality of processing contents. It is stored as a part of the content of the voice response. When the identification information input unit inputs the stored identification information, the voice response reproduction unit reproduces the interactive processing content of the log information corresponding to the input identification information as voice.

As a result, the past service can be automatically reproduced from the log information, and the content of the service can be easily confirmed. Further, the processing content can be specified by the time information of connection / disconnection of the telephone line included in the log information.

Also, the push button signal received from the user via the telephone line is stored in the log information storage section as character information. Therefore, the log information can be reproduced by the stored push button signal.

The voice synthesis processing section synthesizes a voice to be responded from the character information stored in the log information storage section. The attribute storage unit stores the attribute of the user, and the user sound quality change unit changes the sound quality of the voice that the user responds to based on the attribute information of the user stored in the attribute storage unit. Therefore, the service can be provided with the sound quality tailored to the user.

The sound quality of the voice to be changed is the volume level, and the volume level that is easy to hear is automatically set. Further, the sound quality of the voice to be changed is a male sound or a female sound, and the user can select either male sound quality or female sound quality and receive the service with the sound that is easier to hear.

When the log information extraction unit extracts the log information to be used by the user from the log information stored in the log information storage unit, the service execution unit extracts the extracted log information from the user. Input as input information and execute voice response service. The voice synthesis processing unit synthesizes voice from the log information sent from the service execution unit. This allows
Specific processing content can be reproduced from the log information.

The line control unit controls the telephone line and outputs the push button signal and the line connection notification information from the user to the service execution unit. The dialogue between the user and the voice response service device is smoothly performed.

Also, since the switching unit connects the service executing unit to the line control unit, normal service is provided.
Since the switching unit connects the service execution unit to the log information extraction unit, the past service can be reproduced from the log information.

Further, the service execution unit can execute the service according to the narration information from the narration information transmission unit. In addition, the service execution unit,
The service is executed according to the narration information from the narration information sending unit, and the service according to the value of the push button signal is provided to the user. As a result, since the dialogue between the user and the voice response service device can be performed according to the narration information, the burden on the user can be reduced.

When the service execution unit executes the voice response service, the log information writing unit writes the narration information from the narration information sending unit as log information in the log information storage unit. Thereby, for example, when the order information is incorrect, the log information can be read from the log information storage unit to trace the erroneous operation location.

Further, since the text file section converts the narration information from the narration information sending section into character information and writes it as file format text, the character information can be combined with the voice information by, for example, voice rule composition.

The voice synthesis processing section can convert the narration information from the narration information sending section into voice information, and the accumulated sound file section can write the converted voice information.

Further, the voice response reproducing section reproduces the log information written in the log information storing section by the log information writing section. As a result, it is possible to shorten the test time of the reproduction test performed when a failure occurs.

Further, the voice synthesis processing section sends the voice information to the speaker via the pseudo line control section. As a result, the output of the speaker allows the user to recognize the error in the log information by voice.

Further, a male sound or a female sound is set according to the sex of the user by the sex rule table, and a volume level suitable for the age of the user is set by the volume table. As a result, the volume can be set according to the taste of the user.

Further, since the state rule table sets the volume and the sound speed according to the state of the input operation of the user, the operation load on the user can be reduced. Also, the voice attribute setting unit sets a voice attribute by referring to the state rule table. As a result, the voice attribute can be set according to the user.

The voice synthesis processing unit synthesizes voice information that matches the voice attribute of the user set by the voice attribute setting unit. That is, by changing the volume and speed according to the operation state of the user, it is possible to provide a highly comfortable service corresponding to the user's attribute and skill level.

Further, by using the sex rule table and the volume table, the volume,
By changing the speed, it is possible to provide a highly comfortable service corresponding to the user's attribute and skill level.

[Brief description of drawings]

FIG. 1 is a block diagram showing a first embodiment of a voice response service system including a voice response service device of the present invention.

FIG. 2 is a diagram showing history information according to the first embodiment of the present invention.

FIG. 3 is a diagram showing a sequence in which a service is executed according to a narration story according to the first embodiment.

FIG. 4 is a diagram showing an example in which a failure occurs during execution of the service according to the first embodiment.

FIG. 5 is a diagram describing service contents according to the first embodiment.

FIG. 6 is a diagram showing an example of a voice synthesis method according to the first embodiment.

FIG. 7 is a diagram illustrating a specific configuration example of a voice synthesis processing unit that employs a voice synthesis method.

8 is a diagram showing a specific example of performing voice synthesis by the voice synthesis method shown in FIG.

FIG. 9 is a flowchart showing a process for specifying a record desired to be reproduced by a user from a history file.

FIG. 10 is a block diagram showing a second embodiment of a voice response service system including the voice response service device of the present invention.

11 is a configuration block diagram showing a main part of the second embodiment shown in FIG.

[Explanation of symbols]

 10 voice response service unit 11 history information storage unit 12 history information extraction unit 14 line control unit 15 narration story output unit 16 narration story analysis unit 17 service execution unit 17a rule check processing unit 17b voice attribute setting unit 17c narration sentence output unit 18 voice Synthesis processing unit 19 Pseudo line control unit 20 Switching unit 22 Database access unit 23 Database 25 Text file 26 Stored voice file 27 History information writing unit 30 Telephone 31 Language processing unit 32 Sound processing unit 33 Speaker 34 Sentence analysis unit 35 Word dictionary 36 Reading -Prosodic symbol assigning unit 37 Inflection generating unit 38 Waveform synthesizing unit 39 Phoneme segment 40 Attribute table 41 State rule table 42 Voice attribute setting event generating unit

Claims (24)

[Claims] 1. Identification information for storing a plurality of processing contents to be performed interactively with a user by a voice response as log information indicating a record of temporal transition and for identifying each of the plurality of processing contents. Corresponding to the identification information input by the identification information input unit, an identification information input unit for inputting the identification information stored in the log information storage unit, A voice response service unit, comprising: a voice response reproducing unit that reads out interactive process contents of the log information from the log information storage unit and reproduces the read process contents into voice. 2. The voice information according to claim 1, wherein the log information to be stored in the log information storage unit includes time information of at least one of a connection time of a telephone line and a disconnection time of a telephone line. Response service device. 3. The voice response service device according to claim 1, wherein the log information storage unit stores a push button signal received from a user via a telephone line as character information. . 4. The content of the voice response stored in the log information storage unit is character information, and the voice response reproduction unit synthesizes a voice to be responded from the character information stored in the log information storage unit. The voice response service device according to any one of claims 1 to 3, further comprising a voice synthesis processing unit. 5. A voice response service device for performing processing in an interactive manner with a user by voice response, the attribute storage unit storing the attribute of the user, and the attribute information of the user stored in the attribute storage unit. And a user sound quality changing unit that changes the sound quality of a voice responding to the user based on the above. 6. The voice response service device according to claim 5, wherein the voice quality changed by the user voice quality changing unit is a volume level. 7. The voice response service device according to claim 5, wherein the voice quality changed by the user voice quality changing unit is at least one of a male sound and a female sound. 8. The log information extraction unit extracts the log information to be used by a user from the log information stored in the log information storage unit, and the identification information input unit extracts the log information by the log information extraction unit. And a service execution unit that executes a voice response service by inputting the generated log information as input information from the user, and the voice synthesis processing unit synthesizes voice from the log information sent from the service execution unit. The voice response service device according to claim 4, wherein 9. The voice response service device according to claim 8, further comprising a line control unit for controlling a telephone line and outputting a push button signal and a line connection notification information from a user to the service executing unit. . 10. When outputting a push button signal and line connection notification information from the line control unit to the service execution unit, the service execution unit is connected to the line control unit and the log information extraction unit is used. 10. The voice response service device according to claim 9, further comprising a switching unit that connects the service execution unit to the log information extraction unit when reproducing the extracted log information. 11. The voice response service apparatus according to claim 8, further comprising a narration information sending unit that sends narration information to the service executing unit. 12. The service executing unit executes a service according to the narration information from the narration information sending unit, and provides the user with a service according to the value of the push button signal. The voice response service device described. 13. A log information writing unit for writing the narration information from the narration information sending unit as log information into the log information storage unit when the service execution unit executes the voice response service. 13. The voice response service device according to claim 11 or 12. 14. A text file unit for converting the narration information from the narration information sending unit into character information and writing the converted character information as text in a file format when the service execution unit executes a voice response service. The voice response service device according to any one of claims 11 to 13, wherein 15. The voice response service apparatus according to claim 14, wherein the voice synthesis processing unit converts the character information written in the text file unit into voice information. 16. The voice synthesis processing unit includes a stored sound file unit that converts the narration information from the narration information sending unit into voice information and stores the voice information converted by the voice synthesis processing unit. Claim 11 characterized by
14. The voice response service device according to claim 13. 17. A log information writing unit for writing log information in the log information storage unit, wherein the voice response reproducing unit reproduces the log information written in the log information storing unit by the log information writing unit. The voice response service device according to claim 1. 18. The voice synthesis processing unit is connected to a pseudo line control unit for controlling a pseudo line, and sends the converted voice information to a speaker through the pseudo line control unit. 18. The voice response service device according to claim 17. 19. The attribute storage unit comprises a gender rule table storing male or female sounds according to the gender of the user, and a volume table storing volume levels suitable for the age of the user. The voice response service device according to claim 5. 20. The voice response service device according to claim 5, further comprising a state rule table that sets a volume and a sound speed according to a state of a user's input operation. 21. The voice response service device according to claim 20, wherein the user voice quality changing unit includes a voice attribute setting unit that sets a voice attribute by referring to the state rule table. 22. The voice response service device according to claim 21, further comprising a voice synthesizing processing unit for synthesizing voice information suitable for the voice attribute of the user set by the voice attribute setting unit. 23. The voice response according to claim 19, wherein the user sound quality changing unit includes a voice attribute setting unit that sets a voice attribute by referring to the gender rule table and the volume table. Service equipment. 24. The voice response service device according to claim 23, further comprising a voice synthesizing processing unit for synthesizing voice information that matches a voice attribute of the user set by the voice attribute setting unit.