JP2013009434A - Service server device, service provision method, and service provision program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a service server device that can realize a service making a user feel as if he was talking face-to-face by using an existing application.SOLUTION: A service server device comprises: a service activation unit 250 which receives an instruction to perform a task during communication; a telephone/call control enabler 201 which records telephone conversation voice of a speaker during communication between voice communication terminal devices 241a, 241b; a voice recognition enabler 203 which performs a task on the basis of the recorded telephone conversation voice if the instruction has been accepted; a text translation enabler 204; a voice synthesis enabler 202; and a communication control unit 224 which provides task data obtained by performing the task for the voice communication terminal devices 241a, 241b. The task data is formed by text data into which the telephone conversation voice is converted, translation text data into which the text data is translated in another language, and voice data into which the translation text data is converted.

Description

  The present invention relates to a service server device, a service providing method, and a service providing program that provide a service via communication, and in particular, a service server device, a service providing method, and a service providing that provide a service other than a call during a call using a telephone. Regarding the program.

Currently, translators and translation systems that automatically translate the content spoken by a speaker into an arbitrary language into other languages have been put into practical use. Conventional translators include a so-called single-person or face-to-face conversation type and a remote conversation type.
FIG. 13A is a diagram illustrating a translation machine for one person. In FIG. 13 (a), for example, a speaker inputs "How much is this book?" Then, the translation function of the translator translates this Japanese speech into English and outputs a synthesized speech of “How much is this book?”. A translator for one person can be used as a Japanese-English dictionary or used by a speaker to convey his / her intention to another person by letting others in the meeting listen to synthesized speech. Such a conventional translator is described in Non-Patent Document 1, for example.

  FIG. 13B is a diagram illustrating a remote conversation type translator. The translator shown in FIG. 13B has a telephone voice communication function and a translation function. In FIG. 13 (b), for example, a Japanese speaker is voice-inputted to the translation machine in his native language, “Please make a reservation with three people”. Then, the translation function of the translator translates this Japanese speech into English and outputs a synthesized speech of “Please make a reservation for 3 people”. A remote-conversation type translator allows a speaker to communicate in his / her own language while speaking in his / her native language. Such a conventional translator is described in Non-Patent Document 2, for example.

  Further, as a remote conversation type translator, there is one described in Patent Document 1. The telephone system described in Patent Document 1 can not only translate the contents of the telephone and transmit it to the called party, but can also transmit the call voice of the speaker to the called party. For this reason, the invention described in Patent Document 1 can give the user a feeling as if he / she is talking to the other party via an interpreter.

Japanese Patent No. 3741025

andro navi, [online], "iTranslator for Android-high-performance translation app that supports 20 languages-", [May 13, 2011 search], Internet <URL: http: //andronavi.com/2010/ 09/40880> iplatform. org, [online], Sekaiphone [May 13, 2011 search], Internet <URL: http://www.iplatform.org/>

By the way, when two people who use different languages have a conversation, it is common that an interpreter translates both languages. A service with a sense of presence such that the interpreter translates both languages in a face-to-face manner should be realized regardless of whether the above Non-Patent Document 1 or Non-Patent Document 2 is used. I can't.
Moreover, the above-described invention described in Patent Document 1 can also transmit a call voice of a speaker to a call destination. However, in the invention described in Patent Document 1, a dedicated application is activated to send data in which the contents of a call are translated together with the voice of the speaker. Such an invention described in Patent Document 1 requires the development of a new application in order to implement the invention, and there is a problem that this development requires time, human resources, and financial costs.

  The present invention has been made in view of the above points, and it is necessary to develop a new dedicated application that can realize a service with a sense of presence such as being in a face-to-face conversation while being in a remote place. It is an object of the present invention to provide a service server device, a service providing method, and a service providing program that do not have a service.

  In order to solve the above problems, the service server device of the present invention (for example, the service server device 200 shown in FIG. 2) includes a plurality of voice communication terminal devices (for example, the calling communication terminals shown in FIG. 2) that communicate with each other by voice. A service server device that is connected to the device 241a and the destination communication terminal device 241b) and provides a service by another task that is an operation executed by an application different from the application related to voice communication performed between the voice communication terminal devices. An instruction receiving unit (for example, the service activation unit 250 shown in FIG. 2) that receives an instruction to execute the separate task during voice communication, and a speaker during voice communication between the plurality of voice communication terminal devices. By a recording unit (for example, the telephone / call control enabler 201 shown in FIG. 2) and the instruction receiving unit. When the indication is accepted, a task execution unit (for example, the speech recognition enabler 203, the text translation enabler 204, the speech synthesis enabler 202 shown in FIG. 2) that executes the different task based on the call voice recorded by the recording unit. ) And text data obtained by executing the another task by the task execution unit, and voice data obtained by executing the other task by the task execution unit. A task data providing unit (for example, the communication control unit 224 shown in FIG. 2) that provides each of the plurality of voice communication terminal devices performing communication, and the task execution unit converts the call voice into text. To generate text data, translate the text data into other languages, and translate the text data Generating the speech data by converting the translated text data into speech, and the task data providing unit, the task data providing the text data, the translated text data, and the speech data together with the call speech As a plurality of voice communication terminal devices that are performing voice communication.

  Further, the service server device of the present invention (for example, the service server device 900 shown in FIG. 10) includes a plurality of voice communication terminal devices (for example, the calling communication terminal device 241a and the called communication terminal shown in FIG. Device 241b), which is a service server device that provides a service by another task that is an operation executed by an application different from an application related to voice communication performed between the voice communication terminal devices, Is recorded during communication between the instruction receiving unit (for example, the service activation unit 250 shown in FIG. 10) and the plurality of voice communication terminal devices. The instruction is received by a recording unit (for example, the telephone / call control enabler 201 shown in FIG. 10) and the instruction receiving unit. A task execution unit (for example, the voice recognition enabler 203, the information management enabler 214, the image / video synthesis / editing enabler shown in FIG. 10) that executes the separate task based on the call voice recorded by the recording unit. 215) and a task data providing unit (for example, shown in FIG. 10) that provides task data indicating the result of execution of the other task by the task execution unit to a plurality of the voice communication terminal devices performing voice communication. The task execution unit determines an instruction given by the user of the voice communication terminal device based on the call voice, and extracts pre-registered information according to the instruction. Generating task data including at least one of a text and an image using the extracted information, and the task data Test unit, the task data including at least one of the text and the image, and providing each one of a plurality of voice communication terminal apparatus is performing a voice call with the call voice.

  The service server device according to the present invention provides a correction instruction receiving unit that receives a correction instruction for the task data transmitted to the voice communication terminal device and a correction instruction that is received by the correction instruction receiving unit. Based on this, it is desirable to further include a learning unit (for example, the learning unit 280 shown in FIGS. 2 and 10) that weights the data used when generating the task data.

In the service server device according to the present invention, in the above-described invention, when the task execution unit determines that the instruction given by the user is adjustment of the user's schedule, It is desirable to extract schedule information related to the date and time when the action is performed, and extract the common date and time when the actions of the plurality of users of the voice communication terminal device are not registered, using the extracted schedule information.
In the service server device of the present invention, in the above-described invention, the task data providing unit is associated with the voice communication terminal device instead of the voice communication terminal device, and is capable of text communication. It is desirable to send the text data of the task data to a communication terminal device.

  The service providing method of the present invention is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice, and is executed by an application different from an application related to voice communication performed between the voice communication terminal devices. A service providing method of a service server device that provides a service by another task, an instruction receiving step for receiving an instruction to execute the another task during voice communication, and during communication between the plurality of voice communication terminal devices In addition, when the instruction is accepted in the recording step for recording the call voice of the speaker and the instruction receiving step, the call voice is converted into text based on the call voice recorded in the recording step. Generate text data and translate the text data into other languages to generate translated text data. A task execution step of converting the translated text data into speech to generate speech data; and the text data, the translated text data, and the speech data as task data for voice communication with the call speech. And providing task data to each of the plurality of voice communication terminal devices.

  The service providing method of the present invention is an operation that is performed by an application that is connected to a plurality of voice communication terminal apparatuses that perform voice communication with each other by voice and that is different from an application related to voice communication performed between the voice communication terminal apparatuses. A service providing method for a service server device that provides a service by another task, an instruction receiving step for receiving an instruction to execute the another task during voice communication, and voice communication between the plurality of voice communication terminal devices During the recording step of recording the call voice of the speaker, and when the instruction is accepted in the instruction receiving step, the voice communication terminal device user is made based on the call voice recorded in the recording step. The information registered in advance according to the instructions, A task execution step for generating task data including at least one of text and image using the information, and a plurality of the voices performing voice communication with the task data including at least one of text and images together with the call voice And a task data providing step provided to each of the communication terminal devices.

  The service providing program of the present invention is an operation that is executed by an application that is connected to a plurality of voice communication terminal apparatuses that perform voice communication with each other by voice and that is different from an application related to voice communication performed between the voice communication terminal apparatuses. A service providing program that is executed in a service server device that provides a service according to another task, the instruction receiving function for receiving an instruction for executing the different task during voice communication, and a plurality of the voice communications A recording function for recording a call voice of a speaker during communication between terminal devices, and the call voice based on the call voice recorded by the recording function when the instruction is received by the instruction reception function. Convert text to text data and translate the text data into other languages Generating translated text data, converting the translated text data into speech and generating speech data, the text data, the translated text data, and the speech data as task data, And a task data providing function that is provided to each of the plurality of voice communication terminal devices that perform voice communication together with call voice.

  The service providing program of the present invention is an operation that is executed by an application that is connected to a plurality of voice communication terminal apparatuses that perform voice communication with each other by voice and that is different from an application related to voice communication performed between the voice communication terminal apparatuses. A service providing program that is executed in a service server device that provides a service according to another task, the instruction receiving function for receiving an instruction for executing the different task during voice communication, and a plurality of the voice communications A recording function for recording a call voice of a speaker during voice communication between terminal devices, and when the instruction is received by the instruction reception function, the voice based on the call voice recorded by the recording function An instruction given by the user of the communication terminal device is determined, and in advance according to the instruction A task execution function for extracting recorded information and generating task data including at least one of text and image using the extracted information; and the task data including at least one of text and image together with the call voice And a task data providing function provided to each of the plurality of voice communication terminal devices performing voice communication.

  According to the present invention, since the task is executed by an application different from the application related to voice communication, the task voice is executed by using the existing voice application and the application that executes the task. The result can be sent to the other party. The present invention as described above can provide a call service with a sense of presence such that a user is talking face-to-face while using an existing application.

It is a figure for demonstrating the outline | summary of the service used as the premise of Embodiment 1 of this invention. It is a block diagram which shows the example of 1 structure of the service server apparatus of Embodiment 1 of this invention. It is a functional block diagram for demonstrating the learning part shown in FIG. It is a figure for demonstrating the procedure of the process performed by the service server apparatus shown in FIG. It is a figure for demonstrating concretely the CS network and PS network which connect the service server apparatus shown in FIG. 2, FIG. 4, a calling communication terminal device, and a destination communication terminal device. It is a figure for demonstrating concretely the PS network which connects the service server apparatus shown in FIG. 2, FIG. 4, an originating communication terminal device, and a destination communication terminal device. It is a figure for demonstrating the service provision method implement | achieved by the service server apparatus of Embodiment 1. FIG. 3 is a flowchart for explaining a service providing method according to the first embodiment. It is a figure for demonstrating the outline | summary of the scheduler application of Embodiment 2. FIG. It is the figure which showed the service server apparatus of Embodiment 2. It is the figure which illustrated task data of Embodiment 2. 10 is a flowchart for explaining a service providing method according to the second embodiment. FIG. 13A is a diagram for explaining the configuration of a general translator, and FIG. 13B is a diagram for explaining the configuration of a general translation system.

  Embodiments 1 and 2 of a service server device, a service providing method, and a service providing program according to the present invention will be described below with reference to the drawings. In each drawing referred to below, components similar to those in other drawings are denoted by the same reference numerals, and a part of the description may be omitted.

(Embodiment 1)
[Communication Concierge]
FIG. 1 is a diagram for explaining an outline of a service that is a premise of the first embodiment. This service is developed to support communication (hereinafter referred to as “call”) by a communication terminal device having a call function, and to realize communication such as meeting directly. The service that is the premise of the first embodiment is hereinafter also referred to as a CC (communication concierge) service.

  The CC service is a service provided to communication terminal apparatuses c1 to c5 connected to the network N as shown in FIG. Either a telephone having a telephone call function, a communication terminal apparatus that can transmit and receive text by packet communication by connecting to the network N, or a communication terminal apparatus (for example, a smartphone or the like) that can transmit and receive both voice and text. It can be used as the devices c1 to c5. The communication terminal devices c1 to c5 may have a function of transmitting / receiving not only text but also still images, moving images, and music.

  In the first embodiment, it is assumed that a voice call is performed between a user of at least one of the communication terminal devices c1 to c5 connected to the network N and a user of at least one other device. ing. A user who is in a call using the telephone can activate another task and execute the task during the call. Information obtained by executing the activated task can be received by the telephone in communication or another communication terminal device corresponding to the telephone.

  In order to realize the first embodiment, a service server device that provides a service by a task different from a call during a call using a telephone is necessary. The service server device for realizing the first embodiment translates a call content, generates synthesized speech of the translated call content, generates data (hereinafter also referred to as task data) by inserting synthesized speech into the call speech, The translated call contents are converted into text, and the task data and the text data (hereinafter also referred to as text data) are linked and transmitted to the telephone or the like during the call.

Hereinafter, the service server device for realizing the first embodiment will be described more specifically.
[Service server device]
(I) Function FIG. 2 is a block diagram illustrating a configuration example of the service server apparatus according to the first embodiment. 2 is configured to be able to communicate with an enabler group 261 including a plurality of enablers. The enabler is driver software for operating a computer, and refers to software (application) designed for each purpose.

  The enabler group 261 includes an enabler group 205 for a telephone function and an enabler group 206 added to realize a translation function that is a function unique to the first embodiment. The enabler group 205 includes a session cooperation enabler 218, a data storage enabler 207, a device management control enabler 208, a presence enabler 209, a telephone directory enabler 210, an SNS (Social Networking Service) enabler 211, a location information detection enabler 262, and telephone / call control. An enabler 201, a messaging enabler 212, and the like are included.

  The enabler group 206 includes a point management enabler 219, a community management enabler 213, an information management enabler 214 that manages predetermined information according to the application, a voice synthesis enabler 202, an image / video synthesis / editing enabler 215, and a font conversion enabler 216. , A voice recognition enabler 203, an image / video recognition enabler 217, a text translation enabler 204, and the like.

  The enabler group 205 for the telephone function is a set of enablers related to voice communication. The enabler group 206 is a set of enablers different from the application related to communication by voice. That is, in this specification, the enabler included in the enabler group 205 is a task executed by an application related to voice communication, and the enabler included in the enabler group 206 is a task executed by an application related to voice communication. Is another task that is an operation performed by another application.

  The enabler groups 205 and 206 included in the enabler group 261 constitute an environment for providing a service on the network side, a so-called service enabler network (hereinafter referred to as SEN) 2. SEN2 can provide various services in cooperation with a plurality of Internet players P that can provide a plurality of services including a translation service.

  In the first embodiment, the service server apparatus 200 acquires the telephone / call control enabler 201 of the enabler group 205 and stores it in the service application unit in order to execute a task related to translation. Also, the service server device 200 stores the speech synthesis enabler 202, the speech recognition enabler 203, and the text translation enabler 204 from the enabler group 206 in the service application unit. Further, as described above, in the first embodiment, all service application units include the service activation unit 250. As a result, in the first embodiment, the service application unit becomes the service application unit 225 that provides a service related to translation.

The service server device 200 can select and obtain an enabler necessary for executing a task according to the type of service. The enabler acquired by the service server device 200 is stored for each service in the service server device 200 as a service application (service application software) unit described later.
With this configuration, the service server device 200 according to the first embodiment can construct an application necessary for a service by combining existing enablers. For this reason, according to the first embodiment, it is not necessary to newly develop a dedicated application, and time and cost for developing the application do not occur. Furthermore, according to the first embodiment, since a service can be provided using an existing application with a proven track record, it is possible to provide a service with higher reliability compared to developing a new application.

  In the first embodiment, it is assumed that the calling communication terminal device 241a and the called communication terminal device 241b receive service from the service server device 200 while talking to each other. The service server device 200 executes a task when providing a service to the calling communication terminal device 241a and the called communication terminal device 241b. The originating communication terminal device 241a and the receiving communication terminal device 241b in the first embodiment are, for example, mobile phones that have both a telephone function and a function capable of transmitting and receiving text, still images, moving images, and the like.

  The service server device 200 has an existing configuration for controlling a telephone call as well as a service application unit having an enabler corresponding to a service. As a configuration for controlling a call, a subscriber profile storage unit 221 that stores data relating to a CC service subscriber (that is, a user who receives the CC service, hereinafter simply referred to as a “user”), a request for providing the CC service There are an authentication permission unit 222 that authenticates and authorizes, a charging processing unit 223 that performs processing related to charging imposed on a call, and a communication control unit 224 that controls call and packet communication. The communication control unit 224 also has a function as a providing unit that provides task data to the invention communication terminal device 241a and the destination communication terminal device 241b, respectively.

In the subscriber profile storage unit 221, the language type used by the user is registered in advance together with the user's name and the telephone number of the telephone being used. In addition, MSISDN (Mobile Subscriber ISDN Number: telephone number registered in the SIM card of the telephone) included in the data communication session of the telephone is registered in the subscriber profile storage unit 221 as information for specifying the telephone. Yes. Further, in order to associate the devices such as the tablet PC and the photo frame with the telephone, the identifiers of the devices may be registered in the subscriber profile storage unit 221 in association with the telephone number of the corresponding telephone.
Further, the communication control unit 224 provides the task data generated in the service server device 200 to the originating communication terminal device 241a and the terminating communication terminal device 241b. Furthermore, the service server device 200 according to the first embodiment includes a learning unit 280. The learning unit 280 will be described later.

  The service server device 200 may include a plurality of service application units 225, 226, and 227. In the first embodiment, the plurality of service application units 225, 226, and 227 may be storage areas that can store, for example, a plurality of enablers. In this case, the storage area can be any of the service application units 225, 226, and 227 by the stored enabler. In addition, a service activation unit 250 is stored in the storage area serving as the service application unit of the first embodiment. The service activation unit 250 has a function of activating an enabler to receive an instruction transmitted from the originating communication terminal device 241a via the IP network 230 and provide a service, for example.

  In the first embodiment, when the user operates the originating communication terminal device 241a, the service activation unit 250 activates the enabler stored in the service application unit 225. When the enabler stored in the service application unit 225 is activated, execution of the task is started. The activated telephone / call control enabler 201 records the voice of the speaker (hereinafter referred to as “call voice”) during communication between the calling communication terminal device 241a and the called communication terminal device 241b. Note that the recording of the call voice may be performed by controlling the recording of a well-known answering machine provided in the telephone / call control enabler 201 and using the call voice recording function of the answering machine.

The voice recognition enabler 203 generates text data from the recorded voice. For example, the voice recognition enabler 203 analyzes the recorded voice by morphological analysis, and converts the voice into text data.
The text translation enabler 204 generates translated text data by translating the text data generated by the speech recognition enabler 203 into a language used by the user of the destination communication terminal device 241b.

The speech synthesis enabler 202 generates speech data to be read out by synthesized speech by converting the translated text data generated by the text translation enabler 204 into speech represented by speech.
In the first embodiment, the voice data generated by the voice synthesis enabler 202 is provided to the calling communication terminal device 241a and the called communication terminal device 241b together with the call voice. In the first embodiment, the text data generated by the speech recognition enabler 203 and the translated text data generated by the text translation enabler 204 are also provided to the calling communication terminal device 241a and the called communication terminal device 241b. In the first embodiment, audio data, text data, and translated text data are also referred to as task data.

As described above, the speech recognition enabler 203, the text translation enabler 204, and the speech synthesis enabler 202 are based on the voice recorded by the telephone / call control enabler 201 when a task execution instruction is received by the service activation unit 250. A task is executed, and task data is generated by executing the task. This task data is provided to the calling communication terminal device 241a and the called communication terminal device 241b.
In the service server device of the first embodiment configured as described above, the service activation unit 250 functions as an instruction receiving unit. In addition, the telephone / call control enabler 201 functions as a recording unit, and the speech recognition enabler 203, the text translation enabler 204, and the speech synthesis enabler 202 function as a task execution unit and a task data generation unit.

  In the first embodiment, the service activation unit 250 does not immediately activate each enabler when the originating communication terminal device 241a and the destination communication terminal device 241b instruct the provision of the service, but from the subscriber profile accumulation unit 221 in advance. You may make it acquire the registered subscriber information. When the subscriber information includes information for specifying at least one of the calling communication terminal device 241a and the called communication terminal device 241b, an instruction from the calling communication terminal device 241a and the called communication terminal device 241b is received. Also good.

  Further, in the first embodiment, when instructing the provision of service, the activation condition of the service activation unit 250 is set so that the mobile phone adds information such as a specific number set in advance to the telephone number of the own device. May be set. When the activation conditions are set in this way, the service activation unit 250 makes a call using at least one of the calling communication terminal device 241a and the called communication terminal device 241b using a telephone number to which predetermined information is added. In this case, an instruction from the calling communication terminal device 241a and the called communication terminal device 241b is received.

  Further, the first embodiment is not limited to the case where the service activation unit 250 activates each enabler by a signal output by an operation of the calling communication terminal device 241a and the called communication terminal device 241b. For example, when a call voice recorded by the telephone / call control enabler 201 is input, the service activation unit 250 may activate each enabler and start executing a task. When the service activation unit 250 is configured in this way, a word that can identify an application, for example, a word such as “translation start” is set in advance. Then, as a result of morphological analysis of the call voice recorded by the voice recognition enabler 203, the service activation unit 250 activates each enabler and executes a task only when a preset wording is included in the call voice. .

  In the first embodiment described above, the calling communication terminal device 241a and the called communication terminal device 241b are not limited to mobile phones capable of transmitting text. When the calling communication terminal device 241a and the called communication terminal device 241b are telephones having only a call function, a task execution result corresponding to a tablet PC 242a, 242b associated with the telephone in advance by a request from a telephone having only a call function, You may make it transmit to the photo frames 243a and 243b.

(Ii) Learning Unit FIG. 3 is a functional block diagram for explaining the learning unit 280 shown in FIG. The learning unit 280 illustrated in FIG. 2n includes a weighting unit 313. The voice recognition enabler 203 shown in FIG. 2 is configured to be able to access a database (hereinafter referred to as DB) 311. The DB 311 may be inside the service server device, or may be connected to the service server device via a network or the like.

  In the first embodiment, a large number of texts are registered in the DB 311 in advance, and the speech recognition enabler 203 accesses the DB 311 and acquires text corresponding to the call speech that has been morphologically analyzed. Then, using the acquired text, the call voice is converted into text to generate text data. The text data is transmitted to the calling communication terminal device 241a and the called communication terminal device 241b as one of task data.

  In the calling communication terminal device, the user can easily detect misrecognition of the call voice and the accompanying mistranslation by confirming the text data. When there is a misrecognition or mistranslation, in the first embodiment, the text data displayed on the display screen of the calling communication terminal device is edited by the user to indicate the location to be corrected and provided to the service server device 200 for text Instructs the data to be corrected. Such a correction instruction can be easily realized by using an existing configuration of a mobile phone capable of transmitting and receiving text and images.

  When a correction instruction signal instructing correction is transmitted from the originating communication terminal device 241a, the correction instruction signal reaches the voice recognition enabler 203. The voice recognition enabler 203 notifies the weighting unit 313 of the fact that the correction instruction signal has been transmitted from the originating communication terminal device and the correction location indicated by the correction instruction signal. The weighting unit 313 accesses the DB 311 and changes the call voice corresponding to the text instructed to reduce the weight assigned to the text.

Then, when the next speech recognition enabler 203 compares the call voice with the DB 311, a text having a large weight is preferentially matched with the call voice. In this way, it is possible to extract text that is more likely to correspond to the call voice in a shorter time.
FIG. 4 is a diagram for explaining a procedure of processing performed by the service server apparatus shown in FIG.

  In the service application unit 225 shown in FIG. 2, the call voice recording is performed by the telephone / call control enabler 201 shown in FIG. 2 (step S311). The recording of the call voice is performed with one unit of the call voice that is emitted from a state where no voice is recorded (hereinafter also referred to as a silent recording state) to the next silent recording state. Next, the speech is analyzed by the speech recognition enabler 203 and analyzed. The analysis is performed for each call voice recorded as one unit. Then, the call voice is converted into text data according to the analysis result (step S312).

  Next, in the service application unit 225, the text data converted in step S312 by the text translation enabler 204 is translated text data in a language registered in the subscriber profile storage unit 221 in advance by the user of the destination communication terminal device 241b. (Step S313). The translated text data after translation is converted into synthesized speech and becomes speech data (step S314). Furthermore, voice data is inserted into the call voice (step S315).

Here, “inserting voice data into the call voice” means determining the timing of sending the voice data in accordance with the call voice. By determining the transmission timing of the voice data in this way, the call voice is transmitted to the calling communication terminal device 241a and the called communication terminal device 241b through the CS (Circuit Switched) network as usual.
Voice data is also transmitted to the calling communication terminal device 241a and the called communication terminal device 241b by a data communication session via the CS network, but may be transmitted via a PS (Packet Switched) network. . However, by transmitting via the CS network, the first embodiment can transmit voice data in real time. Further, text data obtained by translating the call sound properties into text is transmitted using the PS network. In FIG. 4, the CS network and the PS network are denoted by reference numeral 320.

Further, the first embodiment is not limited to the case where the call voice is transmitted through the CS network, and the call voice is transmitted to the calling communication terminal device 241a and the called communication terminal device 241b via the PS network. Also good.
In the first embodiment, as described above, task data is generated by recording, recognizing, and translating communication speech uttered between the silent recording state and the next silent recording state as a unit, and each time the outgoing communication is performed. By transmitting to the terminal device 241a and the destination communication terminal device 241b, the call voice and task data can be synchronized and transmitted to the source communication terminal device 241a and the destination communication terminal device 241b.

  In the first embodiment, in order to avoid a sense of incongruity in a call, the call voice is transmitted to the communication destination terminal device 241a and the destination communication terminal device 241b in real time as usual. For this reason, when voice data is inserted into the call voice, the user may hear the voice based on the voice data superimposed on the call voice. However, when talking through an interpreter, it is generally considered that people tend to refrain from speaking while the interpreter is speaking. For this reason, it is unlikely that the voice based on the voice data and the voice of the call overlap to hinder the conversation.

In the first embodiment, both the calling communication terminal device 241a and the called communication terminal device 241b access the service application unit 225 to acquire text data, translated text data, and voice data. In this way, a method of connecting the originating communication terminal device 241a and the destination communication terminal device 241b via the service application unit 225 is called bridge connection.
Further, the service server apparatus 200 shown in FIG. 1 can identify the telephone line of the calling communication terminal apparatus 241a and the telephone line of the called communication terminal apparatus 241b by a known method. Therefore, it is possible to distinguish the uplink u1 and downlink d1 of the calling communication terminal device 241a, the uplink u2 and downlink d2 of the called communication terminal device 241b, and appropriately translate the user's utterance and transmit it to the call partner can do.

  According to the first embodiment described above, it is possible to provide call voice, synthesized voice data, text data, and translated text data to the calling communication terminal device 241a and the called communication terminal device 241b. For this reason, the user can easily recognize how the content uttered by the user is recognized by the service server apparatus 200, and can take corrective action such as quickly correcting any mistranslation. In addition, since the user can hear both the call voice of the other party and the voice data obtained by translating the call voice, it is possible to realize a conversation with a sense of presence as if the user was talking through an interpreter. .

(Iii) CS Network and PS Network FIG. 5 shows a specific example of the CS network 404 and the PS network 405 that connect the service server apparatus 200 shown in FIGS. 2 and 4 with the originating communication terminal apparatus 241a and the destination communication terminal apparatus 241b. It is a figure for demonstrating. In addition, about the structure similar to the structure shown in FIG. 2, FIG. 4 in FIG. 5, the same code | symbol is attached | subjected and it shall abbreviate | omit a part of the description.

  The calling communication terminal device 241a makes a call to an MPN (Media Processing Node) 408. This call signal reaches the CS network 404 and the existing telephone system 401. The existing telephone system device 401 refers to, for example, CSN (authentication device, home agent for realizing handover, DHCP server, etc.), ASN (wireless base station, etc.). In the existing telephone system 401, non-billing processing and special number routing processing are executed for outgoing calls. The non-billing process is a process for preventing the billing process for a general call. Further, special number routing means changing a communication path to a communication path in which processing different from the original processing is performed when a call is made to a predetermined telephone number (special number).

  Next, the call signal reaches the service server device 200 of the first embodiment from the existing telephone system device 401. The service server device 200 includes a communication control unit 224 that controls communication of the telephone set shown in FIG. 1, a subscriber profile storage unit 221, an authentication permission unit 222, and a billing processing unit 223. Service restriction from other networks and linkage between voice and screen (linkage between voice data and text data, etc.) are performed.

The linkage between voice data, text data, and translated text data can be realized as follows.
That is, when a telephone that can receive provision of this service enters a call state, the communication control unit 224 of the service server apparatus 200 executes a data communication session including an MSISDN that matches the MSISDN included in the signal related to the telephone call. Start monitoring. When a data session that matches the MSISDN included in the signal related to the call is performed, it is determined that the call and the data session should be linked in the CC service.

When calling voice, voice data, text data, and translated text data are transmitted to one communication terminal device, the calling voice and voice data are transmitted in real time by the CS network. However, the voice data can also be transmitted by the PS network, and according to the above configuration, the call voice transmitted by the CS network 404 and the task data transmitted by the PS network 405 can be coordinated.
Further, as described above, in the first embodiment, the call voice can be transmitted via the PS network 405 similarly to the voice data. FIG. 6 shows a configuration for transmitting a call voice together with voice data and the like via the PS network 405.

In the first embodiment, as described above, the subscriber profile storage unit 221 shown in FIG. 2 associates and registers a telephone having only a call function and a communication terminal device capable of transmitting text or the like. . In such a case, when a call is made with the telephone number of the telephone, the communication control unit 224 may transmit a URL that can acquire task data to the address of the registered communication terminal device.
The call voice corresponding to the outgoing call is recorded by the telephone / call control enabler 201 in the MPN 408 and passed to the service server apparatus 200.

  In the service server device 200, the application unit 225 creates voice data, text data, and translated text data based on the recorded call voice. The voice data is transmitted in real time to the destination communication terminal device 241b via the CS network, but can also be transmitted using the PS network. Further, the text data and the translated text data are transmitted to the destination communication terminal device 241b via the PS network 405 from the existing Web system device 402 (gateway or the like) or xGSN (x-GPRS Support Node) / EPC (Evolved Packet Core). Is done.

(Iv) Service Providing Method FIG. 7 is a diagram for explaining a service providing method realized by the service server device 200 according to the first embodiment. In FIG. 7, data communication using HTTP (Hypertext Transfer Protocol) is indicated by a broken line, and a telephone call is indicated by a solid line.
In the calling communication terminal device 241a, for example, the user activates an application for realizing the service providing method of the first embodiment, and the other party's telephone number is input (step S501). By such processing, the address of the calling communication terminal device 241a is transmitted from the calling communication terminal device 241a to the service server device. Then, the service server apparatus 200 receives an instruction to execute the task during communication (call) on the condition that other necessary requirements are satisfied, and starts the translation service (step S502).

The service server device 200 establishes a communication line between the calling communication terminal device 241a and the called communication terminal device 241b (step S503). Then, the service server apparatus 200 records the call voice transmitted from the line of the calling communication terminal apparatus 241a (step S504) and sends it to the line of the called communication terminal apparatus 241b (step S505).
When a silent recording state in which no call voice is transmitted from the line of the calling communication terminal apparatus 241a is entered, the service server apparatus 200 once ends the recording of the call voice transmitted from the line of the calling communication terminal apparatus 241a (step S506). . The recorded call voice is converted into text, translated, and synthesized voice is synthesized by the voice recognition enabler 203, the text translation enabler 204, and the voice synthesis enabler 202 shown in FIGS. 2 and 4 (step S507). Audio data, text data, and translated text data are generated.

  The service server device 200 according to the first embodiment transmits the voice data to both the originating communication terminal devices 241a and 241b, and the text data and the translated text data are both the originating communication terminal device 241a and the terminating communication terminal device 241b. (Steps S508 to 511). Next, when the user of the destination communication terminal apparatus 241b speaks, the service server apparatus 200 performs the above operation on the voice of the user's call transmitted from the telephone line of the destination communication terminal apparatus 241b. In the case where one of the two users speaks while the other speaks, in the first embodiment, the above processing is performed on the call voice of the user who is recording the call voice, and the other user The content of the utterance should not be processed.

  FIG. 8 is a flowchart for explaining the service providing method of the first embodiment performed in the service server device of the first embodiment. The service activation unit determines whether or not an execution of an application related to translation is instructed from the originating communication terminal device (step S701). If the service activation unit determines that an instruction to execute the application has been given (step S701: Yes), the service activation unit activates each enabler of the service application unit. If the service activation unit determines that there is no such instruction (step S701: No), the service activation unit waits until there is an application execution instruction.

  The telephone / call control enabler activated by the service activation unit records the call voice (step S702). The telephone / call control enabler determines whether or not a silent state is reached during recording of the call voice (step S703). When it is determined that the telephone / call control enabler has entered a silent state (step S703: Yes), the recording of the call voice is once ended (step S704). The voice recognition enabler performs morphological analysis on the call voice recorded by the telephone / call control enabler (step S705), and collates the analysis result with the DB 311 shown in FIG. 3 (step S706). Then, the text matching the call voice is extracted and combined to generate text data (step S707).

  The text recognition unit 204 translates the text data into another language and generates translated text data (step S708). The speech synthesis enabler generates speech data by converting the translated text data into synthesized speech (step S709). The text data, the translated text data, and the voice data are transmitted as task data to the calling communication terminal device and the called communication terminal device (step S710).

  The speech recognition enabler determines whether the text data has been corrected by the user based on whether a correction instruction signal has been transmitted (step S711). When the text data is corrected (step S711: Yes), the speech recognition enabler collates the call speech corresponding to the corrected text with the DB again and converts it into another text. Then, text data is created using other text. The text translation enabler and the speech synthesis enabler create translation text data and speech data again based on the text data created again (steps S706 to S711).

  On the other hand, when it is determined by the speech recognition enabler that the correction instruction signal is not input (step S711: Yes), the learning unit 280 illustrated in FIG. 2 changes the weight assigned to the text data stored in the DB. To do. That is, the learning unit 280 changes so as to reduce the weight of the text corrected this time, and reflects the changed content in the DB. After the above processing, the service activation unit determines whether or not the user has instructed the end of the service (step S713).

If the service activation unit determines that the user has not instructed termination of the service (step S713: No), the service activation unit causes the telephone / call control unit to continue recording the call voice. On the other hand, when the service activation unit determines that the user has instructed termination of the service (step S713: Yes), the service activation unit terminates the service according to the instruction.
The first embodiment is not limited to the configuration described above. That is, in the first embodiment described above, the CC service related to translation is executed for a call between two users. However, the first embodiment is not limited to the one intended for a call between two people, and can also be applied to a conference call or the like in which three or more people make a call.

[Service provision program]
In the service server apparatus described above, a service providing program for providing a service by another task different from the voice communication is executed during the voice communication between the voice communication terminal apparatuses that can communicate by voice. The service providing program includes an instruction receiving function for receiving an instruction to execute another task during voice communication, and a recording for recording a speaker's voice during communication between the plurality of voice communication terminal devices. When the instruction is accepted by the function and the instruction reception function, the call voice is converted into text based on the call voice recorded by the recording function to generate text data, and the text data is A task execution function for generating translated text data by translating into a language, converting the translated text data into speech and generating speech data, and using the text data, the translated text data, and the speech data as the task data Task data provided to each of the plurality of voice communication terminal devices performing voice communication together with the call voice. Features and a program for actualizing.
(Embodiment 2)
Next, Embodiment 2 of the present invention will be described. In the second embodiment, the service server device, service control method, and service control program of the present invention are applied to an application that adjusts a user's schedule.

[Scheduler application]
FIG. 9 is a diagram for explaining an overview of an application for adjusting a schedule (hereinafter referred to as a scheduler application) provided in the second embodiment. In the example shown in FIG. 8, the service server device provides a service by a scheduler task different from the voice communication during the communication of the calling communication terminal device 241a and the called communication terminal device 241b. In such an example, the user of the calling communication terminal device 241a instructs the service server device by operating the calling communication terminal device 241a to execute the scheduler task during a call. When the service server device accepts the instruction, the call voice of the user of the calling communication terminal device 241a and the called communication terminal device 241b is recorded during outgoing communication.

  In the example shown in FIG. 9, the service server device acquires call voices from the telephone lines of the calling communication terminal device 241a and the called communication terminal device 241b and records them respectively. The voice recognition unit shown in FIG. 2 detects that a voice meaning “schedule adjustment” is included in the call voice by performing morphological analysis on the recorded call voice. Since “schedule adjustment” is included in the call voice, the task of extracting the date and time and the time zone when the user's schedules of the calling communication terminal device 241a and the called communication terminal device 241b are both free is executed. Judge that it was instructed.

In response to such an instruction, in the second embodiment, the service server apparatus acquires schedule data of users registered in the calling communication terminal apparatus 241a and the called communication terminal apparatus 241b. The schedule data is data registered by the user himself / herself in the calling communication terminal device 241a and the called communication terminal device 241b, and includes data related to the user and information related to the date and time when the behavior is performed.
In the service server device according to the second embodiment, the date and time zone (date and time) common to the originating communication terminal device 241a and the destination communication terminal device 241b in which the user's behavior is not registered are extracted from the acquired schedule data. To do. The extracted date / time is transmitted as image data including text data to both the calling communication terminal device 241a and the called communication terminal device 241b.

[Service server device]
(I) Function FIG. 10 is a diagram illustrating a service server device 900 according to the second embodiment. The service server device 900 according to the second embodiment is different from the service server device 200 according to the first embodiment only in the configuration of the service application unit. That is, in the service server device 900 according to the second embodiment, the telephone / call control enabler 201, the voice recognition enabler 203, the information management enabler 214, and the image / video synthesis / editing enabler 215 acquired from the enabler group 261 have the service application unit 226. Is building.
Then, the information management enabler 214 acquires the schedule data of the users registered in the calling communication terminal device 241a and the called communication terminal device 241b. The information management enabler 214 extracts, from the acquired schedule data, the date when the user's schedule of the originating communication terminal device 241a and the destination communication terminal device 241b is not registered and its time zone.

Information extracted by the information management enabler 214 is passed to the image / video synthesis / editing enabler 215. The image / video composition / editing enabler 215 creates task data including at least one of a text and an image from this information. FIG. 11 is a diagram illustrating task data according to the second embodiment. The task data is transmitted to both the calling communication terminal device 241a and the called communication terminal device 241b.
According to such a configuration, it is possible to provide communication with a sense of presence similar to the case where the schedule adjustment is performed while directly facing the user of the originating communication terminal device 241a and the destination communication terminal device 241b. In addition, it is possible to obtain an effect that the schedule can be easily and definitely adjusted.

(Ii) Service Providing Method FIG. 12 is a flowchart for explaining a service providing method performed in the service server device of the second embodiment. The service activation unit determines whether or not execution of an application related to the scheduler is instructed from the originating communication terminal device (step S1101). If the service activation unit determines that an application execution instruction has been given (step S1101: Yes), the service activation unit activates each enabler of the service application unit. When the service activation unit determines that there is no instruction to execute the application server (step S1101: No), the service activation unit waits until such an instruction is issued.

  When each enabler is activated by the service activation unit, the activated telephone / call control enabler records a call voice (step S1102). The telephone / call control enabler determines whether or not a silent state is reached during recording of the call voice (step S1103). If the telephone / call control enabler determines that a silent state has been reached (step S1103: Yes), the call voice recording is once terminated (step S1104). The voice recognition enabler performs morphological analysis on the call voice recorded by the telephone / call control enabler (step S1105), and if the call voice includes a word meaning “schedule adjustment”, the schedule adjustment is instructed. Detect that. The information management enabler accesses the database, and acquires information on the schedule of each user who is making a call from the database (step S1106).

The database according to the second embodiment is a database in which user schedules are registered in advance. The schedule is preferably registered in a predetermined format set by an application of the mobile phone. The database of the second embodiment may be in the subscriber profile storage unit.
The image / video synthesis / editing enabler uses the extracted schedule to generate task data including text and images as shown in FIG. 11, for example (step S1107). The task data created by the image / video composition / editing enabler is transmitted to the calling communication terminal device and the called communication terminal device by the communication control unit 224 shown in FIG. 10 (step S1108).

  In the second embodiment, the user of the originating communication terminal device can check whether the content instructed by the user matches the task data. As a result of the confirmation, when the task data is different from the content intended by the user, the user of the originating communication terminal device performs an operation to instruct correction from the communication terminal device to the service server device 900. By this operation, a correction instruction signal is transmitted. Note that the task data is different from the intended content, for example, when the schedule for June is presented even though the user utters “schedule for next month”.

  The voice recognition enabler determines whether the task data has been corrected by the user based on whether a correction instruction signal has been transmitted (step S1109). When the task data is corrected by the user (step S1109: Yes), the speech recognition enabler collates the call speech corresponding to the corrected task data with the DB again and converts it into another text. Then, text data is created using the other text extracted as a result of the collation again. The text translation enabler and the speech synthesis enabler again create task data based on the extracted text data (steps S1106 to 1109).

  On the other hand, when it is determined that the correction instruction signal is not input (step S1110: Yes), the learning unit 280 illustrated in FIG. 10 changes the weight assigned to the text data stored in the DB. In other words, the learning unit changes so as to reduce the weight of the text related to the part corrected this time, and reflects the changed content in the DB. After the above processing, the service activation unit determines whether the user has instructed termination of the service (step S1111). If the service activation unit determines that the service termination instruction has not been issued (step S1111: No), the telephone / call control unit continues to record the call voice. If the service activation unit determines that an instruction to terminate the service has been given (step S1111: Yes), the service activation unit terminates the service according to the instruction.

[Service provision program]
In the service server apparatus described above, a service providing program executed by a service server apparatus that provides a service by another task different from voice communication is executed during communication of a voice communication terminal capable of voice communication. Is done. This service providing program records an instruction reception function for receiving an instruction to execute another task during voice communication on a computer and a speaker's call voice during communication between the plurality of voice communication terminal devices. When the instruction is received by the recording function and the instruction receiving function, the instruction made by the user of the voice communication terminal device is determined based on the call voice recorded by the recording function, and according to the instruction The task execution function for extracting pre-registered information and generating task data including at least one of text and image using the extracted information, and the task data including at least one of text and image, and the call voice Task data providing function to provide to each of the plurality of voice communication terminal devices that are performing voice communication with, Is a program to realize.
In the second embodiment, a CC service for adjusting a schedule for a call between two users is executed. However, Embodiment 2 is not limited to the one intended for a call between two people, and can also be applied to a conference call or the like in which three or more people make a call.

  The present invention can provide a service providing apparatus, a service providing method, and a service providing program that are optimal for supporting communication using a smartphone or the like.

200, 900 Service server device 201 Telephone / call control enabler 202 Speech synthesis enabler 203 Speech recognition enabler 204 Text translation enabler 205, 206, 261 Enabler group 208 Device management control enabler 209 Presence enabler 210 Telephone book enabler 211 SNS enabler 212 Messaging enabler 213 Community management enabler 214 Information management enabler 215 Image / video / compositing edit enabler 216 Font conversion enabler 217 Image / video recognition enabler 218 Session cooperation enabler 219 Point management enabler 221 Subscriber profile storage unit 222 Authentication permission unit 223 Charge processing unit 224 Communication control Section 225, 226, 227 Service application section 230 Network network 280 learning section 241a onset communication terminal device 241b clothes communication terminal equipment

In order to solve the above problems, the service server device of the present invention (for example, the service server device 200 shown in FIG. 2) includes a plurality of voice communication terminal devices (for example, the calling communication terminals shown in FIG. A service server device that is connected to the device 241a and the destination communication terminal device 241b) and provides a service by another task that is an operation executed by an application different from the application related to voice communication performed between the voice communication terminal devices. An instruction receiving unit (for example, the service activation unit 250 shown in FIG. 2) that receives an instruction to execute the separate task during voice communication, and a speaker during voice communication between the plurality of voice communication terminal devices. By a recording unit (for example, the telephone / call control enabler 201 shown in FIG. 2) and the instruction receiving unit. When the indication is accepted, a task execution unit (for example, the speech recognition enabler 203, the text translation enabler 204, the speech synthesis enabler 202 shown in FIG. 2) that executes the different task based on the call voice recorded by the recording unit. a) creating a text data obtained by the separate task is performed by the task execution unit, the task data including the audio data obtained by the separate task is performed by the task execution unit a task data creation unit, to each of a plurality of the voice communication terminal apparatus is performing voice communication, the task data providing unit for providing the task data (e.g. the communication control unit 224 shown in FIG. 2), the voice communication A correction instruction receiving unit that receives a correction instruction for the task data transmitted to the terminal device; Based on the serial correction instruction receiving unit correction instruction received by the learning portion for weighting the data used to generate task data (e.g. FIG. 2, the learning unit 280 shown in FIG. 10), the and said including it.

In the service server device of the present invention , in the above-described invention, it is preferable that the task data providing unit provides the task data and the voice of the speaker to the voice communication terminal device .
In the service server device of the present invention, in the above-described invention, the instruction receiving unit acquires subscriber information registered in advance with respect to the service, and specifies the voice communication terminal device in the subscriber information. It is desirable to accept the instructions when information is included .

In the service server device of the present invention, in the above-described invention, the task execution unit starts execution of the separate task when the sound recorded in the recording unit is a sound indicating a predetermined meaning. It is desirable to do.
In the service server device of the present invention, in the above-described invention, the task execution unit executes the separate task when a signal output by an operation of the voice communication terminal device is a predetermined signal. It is desirable to start .

Also, the service server apparatus of the present invention, in the invention described above, the task data providing unit, instead of the voice communication terminal apparatus, corresponding to the voice communication terminal apparatus and can communicate by text It is desirable to send the text data of the task data to a text communication terminal device.
In the service server device of the present invention, in the above-described invention, the instruction receiving unit acquires subscriber information registered in advance with respect to the service, and associates the subscriber information with the voice communication terminal device. It is desirable to receive the instruction when the information specifying the text communication terminal device is included .

The service providing method of the present invention is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice, and is executed by an application different from an application related to voice communication performed between the voice communication terminal devices. A service providing method for a service server device that provides a service by another task, an instruction receiving step for receiving an instruction to execute the another task during voice communication, and voice communication between the plurality of voice communication terminal devices A recording step for recording a call voice of a speaker, and a task execution step for executing the another task based on the voice recorded in the recording step when the instruction is received in the instruction receiving step; Te obtained by the separate task is performed by said task execution step Strike data and the tasks and audio data obtained by the separate task is performed by the execution step, the task data generating step of generating a task data including, a plurality of doing voice communication the voice communication terminal apparatus A task data providing step for providing the task data, a correction instruction receiving step for receiving a correction instruction for the task data transmitted to the voice communication terminal device, and a correction instruction received by the correction instruction receiving step And a learning step of weighting the data used when generating the task data .

The service providing program of the present invention is an operation that is executed by an application that is connected to a plurality of voice communication terminal apparatuses that perform voice communication with each other by voice and that is different from an application related to voice communication performed between the voice communication terminal apparatuses. A service providing program that is executed in a service server device that provides a service based on another task, the computer receiving an instruction receiving function for receiving an instruction to execute the separate task during voice communication, and the plurality of voice communication terminal devices A recording function for recording a call voice of a speaker during voice communication between the two, and a task for executing the different task based on the voice recorded by the recording function when the instruction is received by the instruction receiving function and execution function, that the further task is executed by the task execution function And text data obtained Te, and task data creation functions, including the audio data obtained, the by the further task by the task execution function is performed, each of the plurality of voice communication terminal apparatus is performing voice communication A task data providing function for providing the task data, a correction instruction receiving function for receiving a correction instruction for the task data transmitted to the voice communication terminal device, and a correction instruction received by the correction instruction receiving unit. And a learning function for weighting data used when generating the task data .

Further, in the present embodiment, when an instruction to provide service, the mobile phone telephone number, the start conditions of the service activation unit 250 so as to transmit by adding information such as a specific number set in advance It may be set. When the activation conditions are set in this way, the service activation unit 250 makes a call using at least one of the calling communication terminal device 241a and the called communication terminal device 241b using a telephone number to which predetermined information is added. In this case, an instruction from the calling communication terminal device 241a and the called communication terminal device 241b is received.

Claims (9)

By another task that is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice and that is executed by an application different from a task executed by an application related to voice communication performed between the voice communication terminal devices A service server device for providing a service,
An instruction receiving unit for receiving an instruction to execute the another task during voice communication;
During voice communication between a plurality of the voice communication terminal devices, a recording unit for recording a call voice of a speaker;
When the instruction is received by the instruction receiving unit, a task execution unit that executes the another task based on the call voice recorded by the recording unit;
The task data including the text data obtained by executing the different task by the task execution unit and the voice data obtained by executing the different task by the task execution unit performs voice communication. Task data providing units respectively provided to the plurality of voice communication terminal devices,
Including
The task execution unit
Converting the call voice to text to generate text data, translating the text data into another language to generate translated text data, converting the translated text data to voice to generate voice data;
The task data providing unit includes:
The service server device, wherein the text data, the translated text data, and the voice data are provided to the plurality of voice communication terminal devices performing voice communication as the task data together with the call voice. A service that is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice and that provides a service by another task that is an operation executed by an application different from an application related to voice communication performed between the voice communication terminal devices A server device,
An instruction receiving unit for receiving an instruction to execute the another task during voice communication;
During voice communication between a plurality of the voice communication terminal devices, a recording unit for recording a call voice of a speaker;
When the instruction is received by the instruction receiving unit, a task execution unit that executes the another task based on the call voice recorded by the recording unit;
A task data providing unit that provides task data obtained by executing the different task by the task executing unit to each of the plurality of voice communication terminal devices performing voice communication;
Including
The task execution unit
A task that determines an instruction given by the user of the voice communication terminal device based on the call voice, extracts pre-registered information according to the instruction, and includes at least one of text and image using the extracted information Generate data,
The task data providing unit includes:
The service server device, wherein the task data including at least one of the text and the image is provided to the plurality of voice communication terminal devices performing voice communication together with the call voice. A correction instruction receiving unit that receives a correction instruction for the task data transmitted to the voice communication terminal device;
A learning unit that weights data used when generating the task data based on the correction instruction received by the correction instruction receiving unit;
The service server device according to claim 1, further comprising:   When it is determined that the instruction given by the user is an adjustment of the user's schedule, the task execution unit extracts and extracts schedule information related to the user registered in advance and the date and time when the action is performed. The service server device according to claim 2 or 3, wherein a common date and time when the behavior of the plurality of users of the voice communication terminal device is not registered is extracted using the scheduled information.   The task data providing unit sends the text data of the task data to a text communication terminal device associated with the voice communication terminal device and capable of text communication instead of the voice communication terminal device. The service server device according to any one of claims 1 to 4, wherein the service server device is sent. A service server that is connected to a plurality of voice communication terminal devices that communicate with each other by voice and that provides a service by another task that is an operation executed by an application different from an application related to voice communication performed between the voice communication terminal devices An apparatus service providing method comprising:
An instruction receiving step for receiving an instruction to execute the another task during voice communication;
A recording step of recording a call voice of a speaker during voice communication between the plurality of voice communication terminal devices;
When the instruction is accepted in the instruction receiving step, the call voice is converted into text based on the call voice recorded in the recording step to generate text data, and the text data is converted into another language. A task execution step of generating translated text data by translating, converting the translated text data into speech and generating speech data;
A task data providing step of providing the text data, the translated text data, and the voice data as task data to the plurality of voice communication terminal devices performing voice communication together with the call voice;
A service providing method comprising: Connected to a plurality of voice communication terminal apparatuses that perform voice communication with each other by voice, and provides a service by another task that is an operation performed between the voice communication terminal apparatuses and performed by an application different from the voice communication application A service server service providing method comprising:
An instruction receiving step for receiving an instruction to execute the another task during voice communication;
A recording step of recording a call voice of a speaker during voice communication between the plurality of voice communication terminal devices;
When the instruction is accepted in the instruction accepting step, an instruction made by the user of the voice communication terminal device is determined based on the call voice recorded in the recording step, and information registered in advance according to the instruction A task execution step of generating task data including at least one of text and image using the extracted information;
Providing task data including at least one of text and images to each of the plurality of voice communication terminal devices performing voice communication together with the call voice;
A service providing method comprising: A service that is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice and that provides a service by another task that is an operation executed by an application different from an application related to voice communication performed between the voice communication terminal devices A service providing program executed in the server device,
On the computer,
An instruction receiving function for receiving an instruction to execute the another task during voice communication;
A recording function for recording the voice of a speaker during voice communication between the plurality of voice communication terminal devices;
When the instruction is received by the instruction reception function, the call voice is converted into text based on the call voice recorded by the recording function to generate text data, and the text data is translated into another language. A task execution function for generating translated text data and converting the translated text data into speech to generate speech data;
A task data providing function for providing the text data, the translated text data, and the voice data as task data to each of the plurality of voice communication terminal devices performing voice communication with the call voice;
A service providing program characterized by realizing the above. A service that is connected to a plurality of voice communication terminal devices that perform voice communication with each other by voice and that provides a service by another task that is an operation executed by an application different from an application related to voice communication performed between the voice communication terminal devices A service providing program executed in the server device,
On the computer,
An instruction receiving function for receiving an instruction to execute the another task during voice communication;
A recording function for recording the voice of a speaker during voice communication between the plurality of voice communication terminal devices;
When the instruction is received by the instruction receiving function, the instruction made by the user of the voice communication terminal device is determined based on the call voice recorded by the recording function, and registered in advance according to the instruction A task execution function for extracting information and using the extracted information to generate task data including at least one of a text and an image;
A task data providing function for providing the task data including at least one of a text and an image to each of the plurality of voice communication terminal devices performing voice communication together with the call voice;
A service providing program characterized by realizing the above.

Images