WO2016129276A1

WO2016129276A1 - Information dissemination method, server, information terminal device, system, and voice interaction system

Info

Publication number: WO2016129276A1
Application number: PCT/JP2016/000687
Authority: WO
Inventors: 勝長辻
Original assignee: パナソニックＩｐマネジメント株式会社
Priority date: 2015-02-12
Filing date: 2016-02-10
Publication date: 2016-08-18
Also published as: JPWO2016129276A1; JP6846617B2

Abstract

Provided is an information dissemination method for a server included in a voice interaction system that interacts with a user riding in a moving body, on the basis of voice interaction with the user. The method includes: a trigger information transmission step for transmitting trigger information indicating a condition as to the status of the moving body or of the user to a client device and requesting the client device to transmit a notification signal when the condition is met, the client device being included in the voice interaction system, and the client device acquiring the voice of the user and disseminating voice information to the user; a generation step for generating voice information by performing a voice interaction process, when the condition has been met; and a guide information transmission step for transmitting voice information to the client device.

Description

Information providing method, server, information terminal device, system, and voice dialogue system

The present disclosure relates to an information providing method in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body.

A speech dialogue apparatus that allows a user to give a command to the apparatus in a natural language by combining speech recognition, dialogue processing, and speech synthesis is widely known. In recent years, as a dialogue technology, it is not limited to a single round-trip response, but it is possible to realize more natural conversations by holding and using information obtained by repeatedly responding to a single topic, and supporting multiple topics. An interactive system has been proposed (see, for example, Patent Document 1). As a result, it is possible to realize a complex conversation that interrupts a conversation of another topic during a conversation of a certain topic.

Further, in a voice dialogue system (server / client type voice dialogue system) in which dialogue processing is performed by a server and a client device communicates with the server, a dialogue scenario (important when constructing a complicated dialogue as described above ( It is thought that maintenance of the part that describes the response contents of the dialogue can be easily performed and expandability is also improved.

Also, a system for performing a push-type utterance as in Patent Document 2 has been proposed.

JP 2007-52043 A JP 11-37766 A

In a voice dialogue system in which a part of such dialogue processing is performed by a server, it is desired that the amount of database held by the client device can be reduced and the amount of data transmitted between the server and the client device can be reduced. Yes.

This disclosure is intended to provide an information providing method capable of reducing the amount of database held by the client device and reducing the amount of data transmitted between the server and the client device.

In order to achieve the above object, an information providing method according to an aspect of the present disclosure is an information providing method in a server included in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body. is there. An information providing method is included in a voice interaction system, and when trigger information indicating a condition of a moving object or a user is transmitted to an information terminal device that acquires voice and provides voice information to a user, and satisfies the condition A trigger information transmission step for requesting transmission of a notification signal, a generation step for generating voice information by performing a process for voice interaction when a condition is satisfied when the notification signal is received, and a voice information A voice information transmission step to be transmitted to the information terminal device.

An information providing method according to an aspect of the present disclosure is included in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body, and the information provision method in an information terminal device that acquires voice It is. The information providing method includes a trigger information receiving step for receiving trigger information indicating a condition of a moving object or a user from a server included in the voice interactive system, a determination step for determining whether the condition is satisfied, and a condition When the condition is satisfied, a transmission step of transmitting a notification signal to the server, a voice information reception step of receiving the voice information generated by the voice interaction processing when the condition is satisfied from the server, and the voice information A providing step to provide to the user.

Also, the information providing method according to one aspect of the present disclosure is an information providing method in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body. The voice interactive system includes an information terminal device that acquires voice and a server, and the information providing method includes trigger information transmission in which the server transmits trigger information indicating a condition of a moving object or a user to the information terminal device. A step for determining whether or not the condition is satisfied when the information terminal device receives the trigger information, and a transmission for transmitting a notification signal to the server when the condition is satisfied A step of generating voice information by performing a voice interaction process when the condition is satisfied when the notification signal is received by the server, and a voice by which the server transmits the voice information to the information terminal device The information transmitting step may include a providing step in which the information terminal device receives the voice information and provides the voice information to the user.

These general or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM. The system, method, integrated circuit, computer program Also, any combination of recording media may be realized.

This disclosure provides an information providing method capable of reducing the amount of database held by the client device and reducing the amount of data transmitted between the server and the client device.

The figure which shows the whole structure of the voice dialogue system in embodiment Block diagram showing a configuration of a client device according to an embodiment The block diagram which shows the structure of the dialog processing part in embodiment The figure which shows operation | movement of the speech dialogue system in embodiment Flowchart showing the operation of the client system in the embodiment The flowchart which shows operation | movement of the server in embodiment The figure which shows an example of operation | movement of the speech dialogue system in embodiment The figure which shows an example of operation | movement of the speech dialogue system in embodiment The figure which shows an example of operation | movement of the speech dialogue system in embodiment The figure which shows an example of the information hold | maintained in keyword DB in embodiment The figure which shows an example of the state transition in the dialogue processing in embodiment The figure which shows an example of the synthetic | combination character string template in embodiment The figure which shows an example of the trigger template in embodiment The figure which shows an example of the trigger condition in embodiment The figure which shows the example of the dialog stack in embodiment The figure which shows an example of operation | movement of the speech dialogue system in embodiment The figure which shows an example of operation | movement of the speech dialogue system in embodiment The figure which shows an example of the trigger condition in embodiment The figure which shows an example of the trigger condition in embodiment

(Knowledge that became the basis of this disclosure)
The present inventor has found that the following problems occur with respect to the voice interaction system described in the “Background Art” section.

In a system that performs a push-type utterance, an utterance is made from a voice dialogue system based on information that changes sequentially such as the state of the vehicle (for example, the position or moving speed of the vehicle). Therefore, when all interactive processes are performed by the server, it is necessary to sequentially transmit these pieces of information detected by the client device to the server. This causes a problem that the amount of data transmitted between the server and the client device increases.

Furthermore, it is not preferable from the viewpoint of personal data protection or the like to transmit vehicle position information or the like to the server.

On the other hand, when processing for realizing such a push-type dialogue is performed in the client device, a predetermined behavior must be incorporated into the client device as a database. Specifically, there are an infinite number of such triggers, and an enormous database is required to determine combinations of conditions. There is also a problem that the processing amount of the client device increases. In particular, when it is incorporated into a server / client type voice interactive system, the client device must have a huge database, and there is a problem that the advantages (maintenability and expandability) of the server / client type cannot be utilized.

In order to address these problems, this embodiment performs push-type conversations only by providing the minimum necessary information from the server without having a huge database in the client in the server-client type voice interaction apparatus. And a spoken dialogue system capable of performing flexible behavior according to the utterance from the user.

The information providing method according to an aspect of the present disclosure is an information providing method in a server included in a voice interaction system that interacts with a user based on a voice from a user who is on a moving body. An information providing method is included in a voice interaction system, and when trigger information indicating a condition of a moving object or a user is transmitted to an information terminal device that acquires voice and provides voice information to a user, and satisfies the condition A trigger information transmission step for requesting transmission of a notification signal, a generation step for generating voice information by performing a process for voice interaction when a condition is satisfied when the notification signal is received, and a voice information A voice information transmission step to be transmitted to the information terminal device.

According to this, it is possible to reduce the amount of data transmitted between the server and the client device (information terminal device). Further, since the client device only determines the condition, it is not necessary for the client device to hold a huge database for interactive processing. In addition, an increase in the processing amount in the client device can be suppressed.

For example, the condition may include a condition of a moving body or a user acquired by a sensor included in the moving body or the information terminal device.

For example, the condition may include a condition of the position of the moving object.

For example, the condition may include a condition of a moving distance of the moving body.

For example, the notification signal includes information indicating the priority of the voice conversation processing based on the notification signal. In the generation step, the voice conversation processing currently being executed and the voice conversation processing based on the notification signal are performed based on the priority. Among the processes, a voice interaction process with a high priority may be executed.

According to this, it is possible to realize appropriate dialogue processing according to priority. Further, the server can immediately grasp the processing priority using the priority included in the notification signal.

For example, the notification signal includes information indicating the transition destination of the state transition in the voice interaction processing based on the notification signal. In the generation step, the state is transitioned to the transition destination, and voice information is generated based on the state after the transition. May be.

According to this, the server can immediately execute the dialogue process using the information of the transition destination included in the notification signal.

An information providing method according to an aspect of the present disclosure is included in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body, and the information provision method in an information terminal device that acquires voice It is. The information providing method includes a trigger information receiving step for receiving trigger information indicating a condition of a moving object or a user from a server included in the voice interactive system, a determination step for determining whether the condition is satisfied, and a condition When the condition is satisfied, a transmission step of transmitting a notification signal to the server, a voice information reception step of receiving the voice information generated by the voice interaction processing when the condition is satisfied from the server, and the voice information Providing steps to the user.

Also, the information providing method according to one aspect of the present disclosure is an information providing method in a voice dialogue system that interacts with a user based on voice from a user who is on a moving body. The voice interactive system includes an information terminal device that acquires voice and a server, and the information providing method includes trigger information transmission in which the server transmits trigger information indicating a condition of a moving object or a user to the information terminal device. A step for determining whether or not the condition is satisfied when the information terminal device receives the trigger information, and a transmission for transmitting a notification signal to the server when the condition is satisfied A step of generating voice information by performing a voice interaction process when the condition is satisfied when the notification signal is received by the server, and a voice by which the server transmits the voice information to the information terminal device An information transmission step, and an information terminal device receiving the voice information and providing the user with the voice information.

Further, a server according to an aspect of the present disclosure is a server included in a voice interaction system that interacts with a user based on a voice from a user who is on a moving body, the information terminal device, and a trigger information transmission unit And a generation unit and a voice information transmission unit.

The information terminal device is included in the voice interaction system, acquires voice, and provides voice information to the user. A trigger information transmission part transmits the trigger information which shows the conditions of a mobile body or a user's state to an information terminal device, and requests | requires transmitting a notification signal, when the said conditions are satisfy | filled. When the generation unit receives the notification signal, the generation unit generates voice information by performing a voice interaction process when the condition is satisfied. The voice information transmitting unit transmits voice information to the information terminal device.

Further, an information terminal device according to an aspect of the present disclosure is included in a voice interaction system that interacts with a user based on a voice from a user boarding a moving body, and includes a trigger information reception unit, a determination unit, and a transmission Unit, a voice information receiving unit, and a providing unit.

Information terminal device acquires voice. The trigger information receiving unit receives trigger information indicating a condition of a moving object or a user from a server included in the voice interactive system. The determination unit determines whether or not the condition is satisfied. The transmission unit transmits a notification signal to the server when the condition is satisfied. The voice information receiving unit receives voice information generated by the voice interaction process when the condition is satisfied from the server. The providing unit provides audio information to the user.

In addition, a voice interaction system according to an aspect of the present disclosure is a voice interaction system that interacts with a user based on voice from a user who is on a moving body, obtains the voice, and provides voice information to the user An information terminal device and a server, and the server includes an information transmission unit, a generation unit, and a voice information transmission unit, and the information terminal device includes a trigger information reception unit, a determination unit, a transmission unit, A voice information receiving unit and a providing unit are provided.

The trigger information transmitting unit transmits to the information terminal device trigger information indicating the condition of the mobile object or the user, and requests to transmit a notification signal when the condition is satisfied. When the generation unit receives the notification signal, the generation unit generates voice information by performing a voice interaction process when the condition is satisfied. The voice information transmitting unit transmits voice information to the information terminal device. The trigger information receiving unit receives trigger information from the server. The determination unit determines whether or not the condition is satisfied. The transmission unit transmits a notification signal to the server when the condition is satisfied. The voice information receiving unit receives voice information from the server. The providing unit provides audio information to the user.

Note that these comprehensive or specific modes may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, and the system, method, integrated circuit, and computer program. Also, any combination of recording media may be realized.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that each of the embodiments described below shows a specific example of the present disclosure. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are merely examples, and are not intended to limit the present disclosure. In addition, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims indicating the highest concept are described as optional constituent elements.

(Embodiment)
In the voice dialogue system according to the present embodiment, basically, dialogue processing for voice dialogue is performed in the server. Further, when a process for determining the condition of the vehicle information occurs in the dialogue process, the condition is notified to the client device. The client device determines whether the vehicle information satisfies the above condition and notifies the server of the determination result. Thus, since only the determination of the condition is performed by the client device, it is not necessary to sequentially transmit vehicle information from the client device to the server. Thereby, the amount of data transmitted between the server and the client device can be reduced. Further, since the client device only determines the condition, it is not necessary for the client device to hold a huge database for interactive processing. In addition, an increase in the processing amount in the client device can be suppressed.

First, the configuration of the voice interaction system 100 according to the present embodiment will be described. FIG. 1 is a diagram showing an overall configuration of a voice interaction system 100 according to the present embodiment. A voice interaction system 100 shown in FIG. 1 includes a client system 110 and a server 120. The client system 110 and the server 120 can communicate with each other via a network. The client system 110 is set, for example, in a vehicle (for example, an automobile) on which the user is boarded.

The client system 110 indicates a client apparatus 101 that communicates with the server 120, a microphone 102 that is an example of a device that acquires a user's voice, a speaker 103 that is an example of a device that reproduces synthesized voice, and the state of the vehicle. A vehicle information acquisition unit 104 that acquires vehicle information.

The server 120 also includes a speech recognition unit 107 that converts an utterance voice signal indicating a user's utterance voice into an utterance character string, and an interaction processing unit 108 that generates a synthesized character string by performing an audio dialogue process based on the utterance character string. And a speech synthesizer 109 for converting the synthesized character string into a synthesized speech signal. In the following, an example in which the voice recognition unit 107, the dialogue processing unit 108, and the voice synthesis unit 109 are individual server devices will be described. Note that all or any two of the speech recognition unit 107, the dialogue processing unit 108, and the speech synthesis unit 109 may be realized as a single server device.

FIG. 2 is a block diagram of the client device 101. As illustrated in FIG. 2, the client apparatus 101 includes a voice acquisition unit 201 that generates a speech voice signal from a microphone input signal from the microphone 102, and a voice output unit 202 that outputs a speaker output signal based on the synthesized voice signal to the speaker 103. And a communication unit 203 that transmits / receives data to / from the server 120. Furthermore, the trigger information interpretation unit 204 that interprets the trigger information received from the server 120, the client trigger condition holding unit 205 that holds the trigger condition indicated by the trigger information, and the vehicle information acquired by the vehicle information acquisition unit 104 are stored. A vehicle state management unit 206 that performs determination of a trigger condition, and a notification unit 208 that generates a notification signal for notifying the server 120 that the trigger condition is satisfied.

FIG. 3 is a block diagram of the dialogue processing unit 108. As shown in FIG. 3, the dialogue processing unit 108 includes an input character string management unit 301 that receives an utterance character string and a notification signal, a state management unit 302 that performs state transition processing, and a keyword DB (database) that holds keywords. 303, a matching processing unit 304 that performs a matching process on an utterance character string, a keyword holding unit 305 that holds a keyword character string, and a dialogue processing execution unit 306 that executes dialogue processing. Furthermore, a synthetic character string template DB (database) 307 that holds a synthetic character string template, a trigger template DB (database) 308 that holds a trigger template, an output character string management unit 309 that outputs a synthetic character string and trigger information, A server trigger condition holding unit 310 that holds the trigger condition.

Hereinafter, the operation of the spoken dialogue system 100 configured as described above will be described. FIG. 4 is a diagram illustrating the operation of the voice interaction system 100 according to the present embodiment.

First, when the user speaks, the microphone 102 of the client apparatus 101 generates a microphone input signal. The voice acquisition unit 201 acquires a microphone input signal and encodes the microphone input signal to generate a speech voice signal that is a digital signal. The communication unit 203 transmits the generated utterance voice signal to the voice recognition unit 107 (S101).

The voice recognition unit 107 converts the received utterance voice signal into an utterance character string by voice recognition, and transmits the utterance character string to the dialogue processing unit 108 via the client device 101 (S102).

The input character string management unit 301 of the dialogue processing unit 108 receives the utterance character string and holds the received utterance character string. The matching processing unit 304 acquires, from the keyword DB 303, a keyword to be subjected to matching processing in the current state managed by the state management unit 302. The matching processing unit 304 performs matching processing between the acquired utterance character string and the keyword, and holds the matched keyword in the keyword holding unit 305 (S103).

Then, the state management unit 302 performs state transition based on the matched keyword. The dialogue processing execution unit 306 generates a synthesized character string and trigger information by performing dialogue processing associated with the state transition.

Specifically, the dialogue processing execution unit 306 (1) database acquisition, change or setting, (2) condition determination, (3) information search, acquisition or processing, and (4) composite character string generation And so on. More specifically, the dialogue processing execution unit 306 acquires the composite character string template from the composite character string template DB 307, sets the character string read from the keyword holding unit 305 to the acquired composite character string template, and will be described later. A synthetic character string is generated by tagging with the <VOICE> tag.

Furthermore, the dialogue processing execution unit 306 acquires a trigger template from the trigger template DB 308, and generates trigger information by setting a character string read from the keyword holding unit 305 to the acquired trigger template. The trigger condition indicated by the trigger information is held in the server trigger condition holding unit 310. Then, the dialog processing execution unit 306 tags the generated trigger information with a <RULE> tag, which will be described later, and assigns it to the synthesized character string (S104).

The output character string management unit 309 transmits the generated synthesized character string to the voice synthesis unit 109 via the client device 101. At this time, the communication unit 203 of the client device 101 acquires trigger information given to the composite character string.

The speech synthesizer 109 generates a synthesized speech signal from the received synthesized character string and transmits the generated synthesized speech signal to the client device 101 (S105). The communication unit 203 of the client device 101 receives the synthesized voice signal, and the voice output unit 202 generates a speaker output signal by decoding the synthesized voice signal. The speaker 103 reproduces the synthesized voice based on the generated speaker output signal (S106).

On the other hand, the trigger information interpretation unit 204 interprets the trigger information acquired by the communication unit 203 and holds the trigger condition indicated by the trigger information in the client trigger condition holding unit 205. For example, the trigger condition held in the client trigger condition holding unit 205 is the same as the trigger condition held in the server trigger condition holding unit 310 included in the server 120.

音声 Voice conversation is established by repeating this series of flows.

Furthermore, the vehicle state management unit 206 of the client device 101 holds the vehicle information acquired by the vehicle information acquisition unit 104. The determination unit 207 periodically determines whether the vehicle state indicated by the vehicle information satisfies the trigger condition held in the client trigger condition holding unit 205 (S107). When the vehicle state matches the trigger condition (trigger firing), the notification unit 208 generates a notification signal. Further, the communication unit 203 transmits the generated notification signal to the dialogue processing unit 108. At this time, the dialogue processing unit 108 deletes the trigger condition that is held in the client trigger condition holding unit 205 and that matches the vehicle state.

The input character string management unit 301 of the dialogue processing unit 108 receives the notification signal. The matching processing unit 304 interprets that the notification signal is a message for performing state transition. The state management unit 302 performs state transition based on the notification signal. At this time, the state management unit 302 deletes the trigger condition held in the server trigger condition holding unit 310 and corresponding to the notification signal. Further, the dialogue processing execution unit 306 generates a composite character string based on the state after the transition (S108). Further, the output character string management unit 309 transmits the generated synthesized character string to the voice synthesis unit 109 via the client device 101.

The speech synthesizer 109 generates a synthesized speech signal from the synthesized character string and transmits the generated synthesized speech signal to the client device 101 (S109). The communication unit 203 of the client device 101 receives the synthesized voice signal, and the voice output unit 202 generates a speaker output signal by decoding the synthesized voice signal. The speaker 103 reproduces the synthesized speech by outputting the generated speaker output signal (S110). In this way, a push-type dialogue is realized.

At this time, the utterance from the system side in the push-type dialogue is performed at an arbitrary timing. Therefore, it is possible that the conversation is already in progress. Therefore, a parameter called priority is set for the conversation. Then, the priorities of the current dialogue and the push dialogue are compared, and the dialogue with the lower priority is performed after the dialogue with the higher priority is completed.

That is, when the priority is described in the notification signal, the state management unit 302 can determine whether the state transition should be performed. When the priority of the push dialog is low, this state transition process is stored in the dialog stack, and the high-priority dialog is loaded after the end. For example, the priority is described in advance in the dialogue scenario. The priority is described according to the content of the dialogue, and the priority of the notification signal notified from the client side is compared with the priority of the dialogue currently being performed to control whether the state transition is performed.

Next, the flow of processing in each of the client system 110 and the server 120 will be described.

FIG. 5 is a flowchart showing the flow of processing by the client system 110. Note that the process of FIG. 5 is repeatedly performed at predetermined intervals.

First, the client apparatus 101 determines whether or not the voice acquisition unit 201 has acquired a speech voice (microphone input signal) (S201). When the voice acquisition unit 201 acquires a microphone input signal (Yes in S201), the voice acquisition unit 201 generates an utterance voice signal from the microphone input signal, and the communication unit 203 transmits the utterance voice signal to the server 120 ( S202).

Further, the client apparatus 101 determines whether the communication unit 203 has received a voice synthesis signal (S203). When the communication unit 203 receives the voice synthesis signal (Yes in S203), the voice output unit 202 generates a speaker output signal by decoding the synthesized voice signal. The speaker 103 outputs the generated speaker output signal (S204).

Further, the client apparatus 101 determines whether the communication unit 203 has received trigger information (S205). When the communication unit 203 receives the trigger information (Yes in S205), the trigger information interpretation unit 204 interprets the trigger information acquired by the communication unit 203 and sets the trigger condition indicated by the trigger information to the client trigger condition holding unit 205. Hold on. Then, the determination unit 207 starts trigger determination as to whether the vehicle state managed by the vehicle state management unit 206 satisfies the trigger condition held in the client trigger condition holding unit 205 (S206).

Further, when the trigger determination is performed (Yes in S207), the determination unit 207 performs the trigger determination (S208). When the vehicle state matches the trigger condition (trigger firing) (Yes in S208), the notification unit 208 generates a notification signal. In addition, the communication unit 203 transmits the generated notification signal to the dialogue processing unit 108 (S209).

Note that the order of the processes in steps S201 and S202, the processes in steps S203 and S204, the processes in steps S205 and S206, and the processes in steps S207 to S209 is an example, and may be other than the order shown in FIG. Alternatively, some processes may be performed simultaneously (in parallel) or with overlapping processing times.

Next, the flow of processing by the server 120 will be described. FIG. 6 is a flowchart showing the flow of processing by the server 120. Note that the process of FIG. 6 is repeatedly performed at predetermined intervals.

The server 120 determines whether an utterance voice signal has been received (S301). When an utterance voice signal is received (Yes in S301), the voice recognition unit 107 converts the utterance voice signal into an utterance character string by voice recognition (S302).

Next, the input character string management unit 301 of the dialogue processing unit 108 receives the utterance character string and holds the received utterance character string. The matching processing unit 304 acquires, from the keyword DB 303, a keyword to be subjected to matching processing in the current state managed by the state management unit 302. The matching processing unit 304 performs matching processing between the acquired utterance character string and the keyword, and holds the matched keyword in the keyword holding unit 305 (S303).

Then, the state management unit 302 performs state transition based on the matched keyword. The dialogue processing execution unit 306 generates a synthesized character string by performing dialogue processing associated with the state transition (S304).

The speech synthesizer 109 generates a synthesized speech signal from the synthesized character string and transmits the generated synthesized speech signal to the client device 101 (S305).

In addition, when the determination with the trigger condition occurs in accordance with the state transition in step S304 (Yes in S306), the dialogue processing execution unit 306 generates trigger information indicating the trigger condition, and the output character string management unit 309 The generated trigger information is transmitted to the client apparatus 101 (S307).

Also, the server 120 determines whether a notification signal has been received (S308). When the notification signal is received (Yes in S308), the matching processing unit 304 interprets that the notification signal is a message for performing state transition. The state management unit 302 performs state transition based on the notification signal. In addition, the dialogue processing execution unit 306 generates a synthesized character string by performing dialogue processing based on the state after the transition (S309).

The speech synthesizer 109 generates a synthesized speech signal from the synthesized character string and transmits the generated synthesized speech signal to the client device 101 (S310).

Note that the order of the processes of steps S301 to S307 and the processes of steps S308 to S310 is merely an example, and may be other than the order shown in FIG. 6, or some processes may be performed simultaneously (parallel) or processing time. May be performed in duplicate.

In addition, here, an example in which the speech recognition unit 107, the dialogue processing unit 108, and the speech synthesis unit 109 included in the server 120 are individual server devices has been described, but the speech recognition unit 107, the dialogue processing unit 108, and the like. All or any two of the speech synthesizers 109 may be realized as a single server device. In this case, the utterance character string is sent from the voice recognition unit 107 to the dialogue processing unit 108 without going through the client device 101. Similarly, the synthesized character string is sent from the dialogue processing unit 108 to the voice synthesis unit 109 without passing through the client device 101.

Further, at least one of the speech recognition unit 107 and the speech synthesis unit 109 may be included in the client system 110.

A specific example of the flow so far will be described with reference to FIGS. 7A to 12. FIG. 7A to 7C are diagrams for explaining a specific operation example. FIG. 8 is a diagram illustrating an example of keywords held in the keyword DB 303. FIG. 9 is a diagram illustrating an example of state transition in the dialogue processing. FIG. 10 is a diagram illustrating an example of a composite character string template stored in the composite character string template DB 307. FIG. 11 is a diagram illustrating an example of a trigger template stored in the trigger template DB 308. FIG. 12 is a diagram illustrating an example of trigger conditions held in the client trigger condition holding unit 205 and the server trigger condition holding unit 310.

As shown in FIG. 7A, the voice recognizing unit 107 recognizes the voice spoken by the user as “I want to go to the AAA tower” (S401). The matching processing unit 304 of the dialogue processing unit 108 performs keyword matching on the uttered character string of the speech recognition result (S402). Here, as shown in FIG. 8, the keyword DB 303 stores a keyword 410 and a reference keyword group 420. The keyword 410 includes a plurality of tables 401-405. Each of the tables 401 to 405 is a keyword list including one or more keywords (for example, “I want to go to {location}” in the table 401). In each of the tables 401 to 405, a transition source state and a transition destination state are set.

Each keyword may include a keyword group (indicated by {} in FIG. 8). The reference keyword group 420 includes lists 406 to 409 each indicating this keyword group. Each of the lists 406 to 409 is a list of a plurality of words included in the keyword group.

Also, as an initial state, the transition state is set to “normal state 0100” shown in FIG.

First, the matching processing unit 304 acquires the tables 401, 404, and 405 in which the current state 0100 is set as the transition source from the keywords 410 illustrated in FIG. 8, and the keywords included in the tables 401, 404, and 405 are obtained. From the above, a keyword matching the utterance character string is searched. Here, “I want to go to {location}” included in the table 401 is searched.

Also, when the keyword group is included in the keyword, the matching processing unit 304 holds all the words of the keyword group (in this example, the list 406 of {location}) from the reference keyword group 420 in the keyword holding unit 305.

In addition, the state management unit 302 performs state transition to the transition destination state 0101 set in the table 401. As described above, the state management unit 302 can determine the transition destination as the state 0101 based on the result of matching with the utterance character string “I want to go to the AAA tower”. That is, the state management unit 302 performs a state transition from the normal state 0100 illustrated in FIG. 9 to the destination setting state 0101 for performing the destination setting dialogue. At that time, the keyword holding unit 305 holds “AAA tower” as a destination. Further, the dialogue processing unit 108 performs processing such as acquisition of the position of the AAA tower.

Next, the dialog processing execution unit 306 generates a composite character string by performing dialog processing based on the transition state.

As illustrated in FIG. 10, the composite character string template stored in the composite character string template DB 307 includes a state 501 indicating a transition state, a condition 502 for generating a composite character string, and a composite character string template 503. .

The dialog processing execution unit 306 sets the template 503 “<VOICE> [Destination] as the destination?” In the state 501 of the composite character string template shown in FIG. Is obtained. Next, the dialogue processing execution unit 306 acquires the keyword “AAA tower” set as the destination earlier from the keyword holding unit 305, and applies the acquired character string to [Destination], so that “<VOICE> AAA tower”. Is set as the destination? </ VOICE> "is generated (S403).

Also, the dialogue processing execution unit 306 acquires a trigger template from the trigger template DB 308. As illustrated in FIG. 11, the trigger template includes a state 511 indicating a transition state, a condition 512 for generating trigger information, and a trigger condition template 513.

The dialogue processing execution unit 306 acquires a template 513 that has a state 511 of 0101 and satisfies the condition 512 from the trigger template shown in FIG. In this example, since there is no matching template 513, the composite character string is transmitted to the client apparatus 101 as it is.

The client apparatus 101 transmits the contents of the <VOICE> tag to the voice synthesizer 109 and receives a synthesized voice signal that is a voice synthesis result. Then, the client apparatus 101 outputs “Do you want to set the AAA tower for the purpose?” Indicated by the synthesized voice signal (S404). Further, since the client apparatus 101 has not received the trigger information, the trigger condition is not updated.

Next, when the voice recognition unit 107 recognizes the voice uttered by the user as “Yes” (S405), the matching processing unit 304 of the dialogue processing unit 108 changes the utterance character string “Yes” acquired from the voice recognition unit 107. Keyword matching is performed for this. Specifically, the table 402 is selected, and the state management unit 302 changes the state from the destination setting state 0101 shown in FIG. 9 to the destination determination state 0102 (S406).

Further, the dialogue processing execution unit 306 acquires the template “<VOICE> [Destination] set as destination </ VOICE>” shown in FIG. 10 and sets “AAA tower” as [Destination]. Thus, the composite character string “<VOICE> AAA tower is set as the destination </ VOICE>” is generated (S407).

Furthermore, the dialogue processing execution unit 306 acquires a trigger template from the trigger template DB 308 and generates trigger information (S408).

Specifically, the dialogue processing execution unit 306 has a template 513 “<RULE> [ID], GPS, [latitude], [longitude], which satisfies the condition 512 from the trigger template shown in FIG. 5,0301, M </ RULE> ". Here, it is assumed that the destination is a facility that is not within 5 km from the current location and has no parking lot. Further, the template has a content that push dialogue is performed with a priority “medium” for a dialogue [destination approaching state 0301 shown in FIG. 9] for guiding a parking lot when a vehicle enters within a 5 km range of the destination.

The dialogue processing execution unit 306 triggers by setting a value (here, “AAA”) unique to [ID], the latitude of the destination in [Latitude], and the longitude of the destination in [Longitude]. Generate information. Based on the contents of the trigger information, the server trigger condition holding unit 310 holds the trigger conditions shown in FIG. As shown in FIG. 12, the trigger condition is an ID 521 that is a unique identifier for identifying the trigger condition, a condition 522 that indicates the condition to be determined, a content 523 that indicates the determination content, and the trigger condition is satisfied. Transition destination 524 indicating the state of the transition destination in the case, and priority 525 indicating the priority of processing after the trigger condition is satisfied.

In addition, the dialog processing unit 108 adds the tag <RUELIST> to the trigger information and assigns it to the composite character string, thereby setting the character string “<VOICE> AAA tower as the destination </ VOICE> <RULELIST>. <RULE> AAA, GPS, [latitude], [longitude], 5,0301, M </ RULE> </ RULELIST> ", and the generated character string is transmitted to the client apparatus 101.

The client device 101 transmits the contents of the <VOICE> tag to the speech synthesizer 109 and receives a synthesized speech signal that is a speech synthesis result. The client apparatus 101 then outputs “AAA tower set for the purpose” indicated by the synthesized voice signal (S409).

Further, the client apparatus 101 acquires the contents of the <RULE> tag as trigger information, and holds the trigger condition indicated by the trigger information in the client trigger condition holding unit 205 as shown in FIG. Then, the client apparatus 101 performs determination according to the trigger condition. That is, the determination unit 207 obtains GPS information as vehicle information, obtains the distance between the position of the vehicle indicated by the GPS information and the latitude and longitude of the destination, and determines whether the obtained distance is 5 km or more. For example, it is performed at a cycle of about 10 [s].

When the destination distance is 5 km or less, the notification unit 208 includes a notification signal including the trigger condition ID “AAA”, the transition destination “0301”, and the priority “M”. “<STATE> AAA, 0301, M </ STATE>” is generated. As described above, the notification signal includes information for uniquely identifying the trigger condition, information indicating the transition destination of the transition state when the trigger condition is satisfied, and interaction processing performed when the trigger condition is satisfied. And information indicating the priority of the. Then, this notification signal is transmitted to the dialogue processing unit 108. Also, the trigger condition of ID “AAA” stored in the client trigger condition holding unit 205 is deleted (S410).

The dialogue processing unit 108 determines the priority between the currently performed dialogue processing and the dialogue processing based on the notification signal based on the priority included in the received notification signal. A specific example of this process will be described with reference to FIG. Note that FIG. 13 shows an example in which a parking lot search process with normal (medium) priority is performed based on the notification signal.

(1) Based on a notification signal such as when the conversation is not in progress as shown in FIG. 13 (a), or (2) in the schedule confirmation dialogue with low priority as shown in FIG. 13 (b) When the priority of the parking lot search process is higher than the priority of the currently performed dialogue process, the state management unit 302 changes from the normal state 0100 shown in FIG. 9 to the destination approach state 0301 based on the notification signal. Transition state to. In addition, the dialogue processing execution unit 306 deletes the trigger condition having the ID 521 of “AAA” from the server trigger condition holding unit 310, and through dialogue processing, “has arrived near the destination. Will you guide the parking lot?” The generated composite character string is generated, and the generated composite character string is transmitted to the client apparatus 101 (S411).

As a result, the client apparatus 101 outputs a sound “Arrive near the destination, would you like to guide the parking lot?” (S412). At that time, the client device 101 may reproduce some sound indicating that it is near the destination, or may display some character or picture on a display in the vehicle.

Further, as shown in FIG. 13C, the priority of the parking lot search process based on the notification signal is higher than that of the interactive process currently being performed, such as during a conversation of a convenience store search process having a higher priority. If it is lower than the priority, the parking lot search process is stored in the dialog stack, and the currently performed dialog process is given priority.

In addition, although the example which guides a parking lot near the destination was demonstrated above, this Embodiment can be coped with when a conditional instruction is given from the user side. 14A and 14B are diagrams for explaining this operation example. For example, as shown in FIG. 14A, the user speaks “I want to put gasoline when I run for another 10 km” (S501). The matching processing unit 304 of the dialogue processing unit 108 performs keyword matching on the uttered character string of the speech recognition result (S502). Based on the result of keyword matching, the state management unit 302 changes the state from the normal state 0100 shown in FIG. 9 to the conditional instruction state 0200.

At this time, information indicating that the trigger condition is a condition related to the travel distance of the car and that the travel condition is another 10 km (“travel distance” = 10 ”, [condition] =“ 10 km travel ”) is a keyword. It is held by the holding unit 305.

Next, based on the state after the transition, the dialogue processing execution unit 306 acquires a gas station search state 0400 that is a dialogue state corresponding to “I want to put gasoline”. After that, the dialog processing execution unit 306 confirms that the vehicle can travel 10 km from the state of gasoline in the car, and then the trigger list character string template “<RULE> [ID], CAN, dist, [travel distance], [transition dialog”. Status], H </ RULE> ". Then, the dialogue processing execution unit 306 sets a unique value “BBB” in [ID]. Here, a case will be described in which a trigger condition (ID521 = “BBB]) relating to the remaining amount of gasoline already exists and this trigger condition is overwritten as shown in FIG.

Also, the dialogue processing execution unit 306 sets “10” in the “travel distance” and “0400” indicating the gas station search state in the “transition dialogue state”. Thus, trigger information “<RULE> BBB, CAN, dist, 10, 0400, H </ RULE>” is generated. Further, the dialogue processing execution unit 306 overwrites the trigger condition with this content. As a result, the server trigger condition holding unit 310 is updated as shown in FIG. In addition, the dialogue processing execution unit 306 generates a composite character string “<VOICE> is accepted. We will notify you when you run another 10 km. </ VOICE>”, and the generated trigger information and composite character string are displayed on the client device 101. (S503).

The client device 101 receives the composite character string and outputs “I understand. I will let you know when I run for another 10 km” (S504).

Further, the client device 101 receives the trigger information, and overwrites the trigger condition stored in the client trigger condition holding unit 205 with the trigger condition indicated by the received trigger information. For example, the trigger condition shown in FIG. 15 is held in the client trigger condition holding unit 205, and the trigger condition having the same ID “BBB” as the ID of the trigger condition is overwritten on the trigger condition indicated by the received trigger information. Is done. As a result, the client trigger condition holding unit 205 is updated as shown in FIG.

Also, the client device 101 compares the target travel distance with the current travel distance according to the updated trigger condition, and periodically determines whether the travel distance has reached the target travel distance. When the travel distance has reached the target travel distance, the notification unit 208 generates a notification signal “<STATE> BBB, 0400, H </ STATE>” and transmits it to the dialogue processing unit 108 (S505).

The dialogue processing unit 108 receives the notification signal, and the state management unit 302 changes the state from the normal state 0100 shown in FIG. 9 to the gas station search state 0400. Based on the state after the transition, the dialogue processing execution unit 306 generates a composite character string indicating “traveled 10 km. Do you want to search for a gas station?” (S506). The generated composite character string is transmitted to the client device 101, and the client device 101 emits a sound “Drived 10 km. Do you want to search for a gas station?” (S507).

In this way, you can start a push dialogue to search for a gas station after traveling 10 km.

In the above description, both the server trigger condition holding unit 310 of the dialogue processing unit 108 and the client trigger condition holding unit 205 of the client apparatus 101 have the ID 521, the condition 522, the content 523, the transition destination 524, and the priority 525. Although the example of holding each has been described, part or all of the information may be held only in one holding unit.

In the above description, the trigger information and the notification signal include the ID, the information indicating the transition destination, and the information indicating the priority. However, at least one of these may not be included.

For example, at least one of the transition destination 524 and the priority 525 may be managed only by the dialogue processing unit 108. In this case, this information is not included in the trigger information and the notification signal. When receiving the notification signal, the dialogue processing unit 108 determines the transition destination and the priority based on the ID included in the notification signal and the managed information.

Alternatively, at least one of the transition destination 524 and the priority 525 may be managed only by the client device 101. In this case, this information is included in the trigger information and the notification signal. When receiving the notification signal, the dialogue processing unit 108 determines the transition destination or priority based on the transition destination or priority included in the notification signal.

Also, when the transition destination and priority are included in the notification signal, the dialog processing unit 108 does not need to hold the trigger condition. In this case, when receiving the notification signal, the dialogue processing unit 108 determines the transition destination or priority based on the transition destination or priority included in the notification signal. Further, when the transition destination is included in the notification signal, the dialogue processing unit 108 can perform processing based only on the transition destination, and thus the notification signal may not include the ID.

That is, the trigger information should at least indicate the trigger condition. The notification signal may indicate that the trigger condition indicated by the trigger information is satisfied.

In the above description, the content of the dialogue is immediately used as a trigger condition. However, keywords of past dialogue are accumulated in the keyword holding unit 305, and the dialogue processing unit 108 generates a trigger condition based on the accumulated information. May be. For example, when a dialog indicating that the area is the first visited area is performed, the dialog processing unit 108 generates a first trigger condition for determining that the user has arrived at the area. Further, when the first trigger condition is satisfied, a second trigger condition for determining that the user has approached the spot information of the sightseeing spot or the spot advertisement of the store is generated. When the second trigger condition is satisfied, the dialog processing unit 108 performs a dialog regarding sightseeing guide or advertisement. As described above, the dialogue processing unit 108 may generate a two-stage trigger condition.

In addition, when it is confirmed in some dialogs (such as a driving calendar or a dialog regarding the number of accident responses) that the user is not familiar with the car, the dialog processing unit 108 is a trigger for determining that an abnormality has occurred in the car. Generate a condition. When this condition is satisfied, the dialogue processing unit 108 gives information indicating what kind of abnormality has occurred and how to deal with it by dialogue. Thereby, the help function only for beginners is realizable using the result of a plurality of dialogs.

Furthermore, when an Italian restaurant is frequently searched at noon, the dialogue processing unit 108 generates a trigger condition for determining whether it is a lunch hour, and if the condition is satisfied, the store of the Italian restaurant Is guided in a dialogue. Thereby, a recommendation function can also be realized.

In the above description, an example in which the trigger condition is a condition such as a travel distance of the vehicle has been described. However, the trigger condition may be a condition of the vehicle state. For example, the trigger condition may be a parameter condition that can be acquired by a client device installed in a vehicle. For example, the trigger conditions are vehicle information (accelerator depression amount, brake depression amount, steering depression angle, shift position, blinker state, wiper state, light state, gasoline state, etc. acquired from CAN (Controller Area Network). Conditions, such as amount, travel distance, vehicle speed, vehicle body acceleration, vehicle body angular velocity, inter-vehicle distance, proximity sensor, water temperature, oil amount, various warnings, window open / closed degree, or air conditioner setting).

Further, the trigger condition may be a condition of the state of the user who is in the car. For example, the trigger condition is information indicating a user's state obtained by sensors arranged around the driver (line of sight, face orientation, voice, number of passengers, personal recognition information, body weight, body temperature, pulse, blood pressure, sweating, brain wave , Arousal level or concentration level).

Also, the trigger condition may be a condition such as information (GPS information, in-vehicle temperature, outside air temperature, humidity, time, etc.) obtained by other in-vehicle sensors.

That is, the trigger condition is a condition of a vehicle or a user state acquired by a sensor included in the vehicle or the client device. In other words, the trigger condition is a condition of a vehicle or a user that changes sequentially.

Furthermore, in the above description, an example in which the client device 101 is mounted on an automobile has been described. However, the client device 101 may be mounted on a moving body (for example, a train, an airplane, a bicycle, or the like). In addition, the client device 101 may be possessed or carried by a user who rides on these moving objects. That is, the trigger condition may be a condition of the state of the moving body or a condition of the state of the user who is on the moving body.

Also, the trigger condition may be an AND condition, an OR condition, or a combination thereof. For example, <RULELIST> <AND> <RULE> [ID], GPS, [latitude], [longitude], 5,0301, H </ RULE> <RULE> [ID], TIME, [time], 0301, H </ RULE> </ AND> </ RULELIST> may define an AND condition of two rules. As a result, push utterance is performed when both the position condition and the time condition are satisfied.

<RULELIST> <OR> <RULE> [ID], GPS, [latitude 1], [longitude 1], 5,0301, H </ RULE> <RULE> [ID], GPS, [latitude 2], The OR condition of the two rules may be defined by [longitude 2], 5, 0301, H </ RULE> </ AND> </ RULELIST>. Thereby, a push dialog is started when either condition is satisfied.

By combining these, for example, when the user speaks in a dialog that he / she wants to use the auto cruise control, the dialogue processing unit 108 detects the case where the vehicle is traveling near the highway and running at a high speed steady state. It is also possible to guide the auto cruise control function by voice. In addition, when the destination is set in the dialogue and the destination is far, the dialogue processing unit 108 detects either a decrease in the user's arousal level or a decrease in the concentration level, and recommends the user to take a break. It is also possible.

In addition, the dialogue processing unit 108 monitors (1) conversation between people in the vehicle, when the conversation is interrupted, (2) monitors driving load, and when the driving load decreases, (3) user's brain wave Alternatively, the user's mental state may be detected from a heartbeat or the like, and push-type speech may be performed when the user's mental state is at rest.

Furthermore, in the present embodiment, each function is described separately for the server 120 and the client system 110, but the client system 110 may have a part of the functions of the server 120.

In the present embodiment, an example is described in which the speech recognition unit 107, the dialogue processing unit 108, and the speech synthesis unit 109 are not directly connected. However, the output signal of the speech recognition unit 107 is directly input to the dialogue processing unit 108. Of the output signals from the dialogue processing unit 108, a synthesized character string may be directly input to the speech synthesis unit 109 and trigger information may be transmitted to the client device 101.

Furthermore, in the above description, the trigger condition is erased when the condition is satisfied. However, when the erase condition is given to the trigger condition and the erase condition is satisfied, the client trigger condition holding unit of the client device 101 is satisfied. The trigger condition may be deleted from 205. In this case, the client apparatus 101 transmits an erasure command to the server 120, and the server 120 that has received the erasure command deletes the trigger condition of the server trigger condition holding unit 310.

As described above, the voice dialogue system 100 according to the present embodiment is a voice dialogue system that interacts with a user based on voice from a user who is on a moving body, and obtains voice from the user, A client device 101 that is an information terminal device that provides voice information to a user and a server 120 are included.

The server 120 transmits to the client apparatus 101 trigger information indicating the condition of the mobile object or the user, and requests that the notification signal be transmitted to the server 120 when the condition is satisfied (S307 in FIG. 6). When the server 120 receives the notification signal (Yes in S308), the server 120 generates speech information (synthetic character string or speech synthesis signal) by performing the voice interaction process when the above condition is satisfied (S309). The server 120 transmits audio information to the client device 101 (S310).

Further, the client apparatus 101 receives the trigger information from the server 120 (S205 in FIG. 5), and determines whether or not the condition indicated by the trigger information is satisfied (S206 and S208). When the condition indicated by the trigger information is satisfied (Yes in S208), the client apparatus 101 transmits a notification signal to the server 120 (S209). The client apparatus 101 receives voice information (synthetic character string or voice synthesis signal) from the server 120 (S203), and provides the received voice information to the user (S204).

For example, the condition indicated by the trigger information includes a condition of the moving object or the user acquired by a sensor included in the moving object or the client device 101. For example, this condition includes a condition of the position of the moving object or a condition of the moving distance of the moving object.

As described above, in the server-client type voice interaction system, the client device 101 can be realized with a very simple and inexpensive structure by determining the trigger condition generated by the server 120 by the client device 101. In addition, since the server 120 can maintain the conditions for the push-type conversation, maintenance and expandability can be sufficiently secured. In addition, even when a conditional instruction such as “when it comes to” is received from the user, which is difficult to realize with the conventional system, it can be realized with the same mechanism.

Also, the notification signal includes information indicating the priority of the voice conversation processing based on the notification signal. Based on the priority, the server 120 executes a voice conversation process with a higher priority among the voice conversation process currently being executed and the voice conversation process based on the notification signal.

In addition, the notification signal includes information indicating the transition destination of the state transition in the voice dialogue processing based on the notification signal. The server 120 changes the state to the transition destination indicated by the information, and generates voice information based on the state after the transition.

As described above, the voice interaction system according to the embodiment of the present disclosure has been described. However, the present disclosure is not limited to this embodiment.

For example, the present disclosure is not limited to the voice interaction system, but may be realized as a server or a client device (information terminal device) included in the voice interaction system, or an information providing method in the voice interaction system, the server, or the client device. It may be realized as.

In addition, a part or all of the processing units included in the voice interaction system according to the above embodiment is typically realized as an LSI that is an integrated circuit. These may be individually made into one chip, or may be made into one chip so as to include a part or all of them.

Further, the integration of circuits is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.

In the above embodiment, each component may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

Further, the present disclosure may be the above-described program, or a non-transitory computer-readable recording medium on which the above-described program is recorded. Needless to say, the program can be distributed via a transmission medium such as the Internet.

In addition, the dialogue contents, numbers, and the like used above are all exemplified for specifically explaining the present disclosure, and the present disclosure is not limited to the exemplified dialogue contents, numbers, and the like.

In addition, division of functional blocks in the block diagram is an example, and a plurality of functional blocks can be realized as one functional block, a single functional block can be divided into a plurality of functions, or some functions can be transferred to other functional blocks. May be. In addition, functions of a plurality of functional blocks having similar functions may be processed in parallel or time-division by a single hardware or software.

Similarly, the information providing method in the above spoken dialogue system is for illustration in order to specifically explain the present disclosure, and the information providing method according to the present disclosure does not necessarily include all the above steps. Absent. In addition, the order in which the above steps are executed is for illustration in order to specifically describe the present disclosure, and may be in an order other than the above. Further, a part of the above steps may be executed simultaneously with other steps (in parallel) or with overlapping processing times.

As described above, the voice interaction system according to one or more aspects has been described based on the embodiment. However, the present disclosure is not limited to this embodiment. Unless it deviates from the gist of the present disclosure, various modifications conceived by those skilled in the art have been made in this embodiment, and forms constructed by combining components in different embodiments are also within the scope of one or more aspects. May be included.

The present disclosure can be applied to a voice interaction system, and is useful, for example, for a system that performs a voice interaction with a user in a car.

DESCRIPTION OF SYMBOLS 100 Voice interactive system 101 Client apparatus 102 Microphone 103 Speaker 104 Vehicle information acquisition part 107 Voice recognition part 108 Dialog processing part 109 Voice synthesis part 110 Client system 120 Server 201 Voice acquisition part 202 Voice output part 203 Communication part 204 Trigger information interpretation part 205 Client trigger condition holding unit 206 Vehicle state management unit 207 Determination unit 208 Notification unit 301 Input character string management unit 302 State management unit 303 Keyword DB
304 matching processing unit 305 keyword holding unit 306 dialogue processing execution unit 307 composite character string template DB
308 Trigger template DB
309 Output string management unit 310 Server trigger

condition holding unit

401, 402, 403, 404, 405 Table 406, 407, 408, 409 List 410 Keyword 420 Reference keyword group 501, 511

State

502, 512, 522

Condition

503, 513 Template 521 ID
523 Contents 524 Transition destination 525 Priority

Claims

An information providing method in a server included in a voice dialogue system that interacts with the user based on voice from a user boarding a moving body,
When trigger information indicating a condition of the state of the mobile body or the user is transmitted to an information terminal device included in the voice interaction system, which acquires the voice and provides voice information to the user, and satisfies the condition Trigger information sending step for requesting to send a notification signal to,
When the notification signal is received, a generation step of generating the voice information by performing a voice interaction process when the condition is satisfied;
A voice information transmitting step of transmitting the voice information to the information terminal device.
The information providing method according to claim 1, wherein the condition includes a condition of a state of the moving object or the user acquired by a sensor included in the moving object or the information terminal device.
The information providing method according to claim 2, wherein the condition includes a condition of a position of the moving body.
The information providing method according to claim 2, wherein the condition includes a condition of a moving distance of the moving body.
The notification signal includes information indicating the priority of the voice interaction processing based on the notification signal,
5. In the generation step, based on the priority, a voice conversation process having a higher priority is executed among a voice conversation process currently being executed and a voice conversation process based on the notification signal. The information providing method according to any one of the above.
The notification signal includes information indicating a transition destination of state transition in the voice interaction processing based on the notification signal,
5. The information providing method according to claim 1, wherein in the generation step, the state is changed to the transition destination, and the voice information is generated based on the state after the transition.
An information providing method in an information terminal device, which is included in a voice dialogue system that interacts with the user based on voice from a user who is on a moving body, and obtains the voice,
A trigger information receiving step of receiving trigger information indicating a condition of the state of the mobile object or the user from a server included in the voice interaction system;
A determination step of determining whether or not the condition is satisfied;
A transmission step of transmitting a notification signal to the server when the condition is satisfied;
A voice information receiving step for receiving voice information generated by the voice interaction process when the condition is satisfied from the server;
Providing the voice information to the user. An information providing method.
An information providing method in a voice interaction system for interacting with a user based on a voice from a user boarding a moving body,
The spoken dialogue system includes:
An information terminal device for acquiring the voice;
Server and
The information providing method includes:
A trigger information transmission step in which the server transmits trigger information indicating a condition of the state of the mobile object or the user to the information terminal device;
A determination step of determining whether or not the condition is satisfied when the information terminal device receives the trigger information; and
When the information terminal device satisfies the condition, a transmission step of transmitting a notification signal to the server;
When the server receives the notification signal, a generation step of generating voice information by performing a voice interaction process when the condition is satisfied;
A voice information sending step in which the server sends the voice information to the information terminal device;
A providing step in which the information terminal device receives the voice information and provides the voice information to the user.
A server included in a voice interaction system that interacts with a user based on a voice from a user boarding a moving body,
When trigger information indicating a condition of the state of the mobile body or the user is transmitted to an information terminal device included in the voice interaction system, which acquires the voice and provides voice information to the user, and satisfies the condition A trigger information transmitter for requesting to transmit a notification signal to
When the notification signal is received, a generation unit that generates the voice information by performing a voice interaction process when the condition is satisfied;
A voice information transmitting unit configured to transmit the voice information to the information terminal device;
An information terminal device that is included in a voice interaction system that interacts with the user based on a voice from a user boarding a moving body, and that acquires the voice,
A trigger information receiving unit for receiving trigger information indicating a condition of the state of the mobile object or the user from a server included in the voice interaction system;
A determination unit for determining whether or not the condition is satisfied;
A transmission unit that transmits a notification signal to the server when the condition is satisfied;
A voice information receiving unit that receives voice information generated by the voice interaction process when the condition is satisfied from the server;
An information terminal device comprising: a providing unit that provides the voice information to the user.
A voice interaction system for interacting with a user based on a voice from a user boarding a moving body,
An information terminal device that acquires the voice and provides the user with voice information;
Server and
The server
A trigger information transmitter that transmits trigger information indicating a condition of the state of the mobile object or the user to the information terminal device, and requests transmission of a notification signal when the condition is satisfied;
When the notification signal is received, a generation unit that generates the voice information by performing a voice interaction process when the condition is satisfied;
A voice information transmitter that transmits the voice information to the information terminal device;
The information terminal device
A trigger information receiving unit for receiving the trigger information from the server;
A determination unit for determining whether or not the condition is satisfied;
A transmission unit that transmits a notification signal to the server when the condition is satisfied;
A voice information receiving unit for receiving the voice information from the server;
A voice interaction system comprising a providing unit for providing the voice information to the user.
An information providing method in a system for communicating information between an information terminal device and a server,
The information providing method includes:
The information terminal device acquiring information;
An information transmitting step in which the information terminal device transmits information to the server;
A condition generating step in which the server generates a condition from the information based on a current state;
A trigger information transmission step in which the server transmits trigger information indicating the condition to the information terminal device;
A determination step of determining whether or not the condition is satisfied when the information terminal device receives the trigger information; and
A notification signal return step of returning a notification signal to the server when the information terminal device satisfies the condition;
When the server receives the notification signal, a character string information generating step for generating character string information by performing processing when the condition is satisfied;
A character string information transmitting step in which the server transmits the character string information report to the information terminal device;
An information providing method comprising: an information output step in which the information terminal device receives the character string information and outputs the character string information.
An information providing method in a server included in a system for communicating information between an information terminal device and a server,
A condition generation step of generating a condition based on the current state from the information acquired and transmitted by the information terminal device;
Trigger information transmission step of transmitting trigger information indicating the condition to the information terminal device;
A notification signal receiving step of receiving a notification signal from the information terminal device when the condition is satisfied;
When the notification signal is received, a character string information generation step for generating character string information by performing processing when the condition is satisfied;
A character string information transmitting step of transmitting the character string information to the information terminal device.
An information providing method in the information terminal device included in a system for communicating information between an information terminal device and a server,
Obtaining the information;
Sending information to a server included in the system;
A trigger information receiving step for receiving trigger information indicating a condition generated from the information from the server;
A determination step of determining whether or not the condition is satisfied;
A notification signal return step of returning a notification signal to the server when the condition is satisfied;
An information providing method including: an information output step of receiving character string information generated by processing when the condition is satisfied from the server and outputting the character string information.
The information providing method according to claim 12, wherein the information provided from the information terminal device is audio information.
The information providing method according to claim 15, wherein the voice information is generated from voice input to the information terminal device.
The information providing method according to claim 12, wherein the information provided from the information terminal device is sensor information received by the information terminal device.
The information providing method according to claim 12, wherein the information provided from the information terminal device is information on a sensor connected to the information terminal device.
The information providing method according to claim 17, wherein the information on the sensor received by the information terminal device is information on a sensor installed in a mobile body on which the information terminal device is mounted or a sensor located around the information terminal device.
The information providing method according to claim 12, wherein the character string information is voice information.
The information providing method according to claim 19, wherein the condition includes a condition of a position of the moving body.
The information providing method according to claim 19, wherein the condition includes a condition of a moving distance of the moving body.
In the condition generation step, the character string information is generated by a voice interaction process of the voice information,
The notification signal includes information indicating the priority of the voice interaction processing based on the notification signal,
The voice conversation process with a high priority is executed based on the priority among the voice conversation process currently being executed and the voice conversation process based on the notification signal. Information providing method described in 1.
The notification signal includes information indicating a transition destination of state transition in processing based on the notification signal,
The information providing method according to any one of claims 12 to 23, wherein in the character string information generation step, a state is changed to the transition destination, and the character string information is generated based on a state after the transition.
A system for communicating information between an information terminal device and a server,
The server
An information receiver;
A condition generator;
A trigger information transmitter;
A notification signal receiver;
A string information generator,
A character string information transmission unit,
The information terminal device
An information acquisition unit;
An information transmitter;
A trigger information receiver;
A determination unit;
A character string information receiver;
An output unit,
The information transmitting unit transmits information to the information receiving unit,
The information receiving unit receives the information,
The condition generation unit generates a condition based on the current state from the information,
The trigger information transmitting unit transmits trigger information indicating the condition to the trigger information receiving unit,
The trigger information receiving unit receives trigger information indicating a condition generated from the information from the server,
The determination unit determines whether the condition is satisfied,
The notification signal transmission unit returns a notification signal to the notification signal reception unit when the condition is satisfied,
The notification signal receiving unit receives a notification signal from the notification signal transmitting unit when the condition is satisfied,
The character string information generation unit generates character string information based on the notification signal when the notification signal is received,
The character string information transmitting unit transmits the character string information to the character string information receiving unit,
The character string information receiving unit receives the character string information,
The output unit is a system for outputting the character string information.
A server included in a system for communicating information between an information terminal device and a server,
An information receiver;
A condition generator;
A trigger information transmitter;
A notification signal receiver;
A string information generator,
A character string information transmission unit,
The information receiving unit receives information transmitted from the information terminal device,
The condition generation unit generates a condition based on the current state from the information,
The trigger information transmitting unit transmits trigger information indicating the condition to the information terminal device,
The notification signal receiving unit receives a notification signal from the information terminal device when the condition is satisfied,
The character string information generation unit, when receiving the notification signal, generates character string information based on the notification signal,
The character string information transmitting unit is a server that transmits the character string information to the information terminal device.
The information terminal device included in a system for communicating information between an information terminal device and a server,
An information transmitter;
A trigger information receiver;
A determination unit;
A character string information receiver;
An output unit,
The information transmission unit transmits information to a server included in the system,
The trigger information receiving unit receives trigger information indicating a condition generated from the information from the server,
The determination unit determines whether the condition is satisfied,
The notification signal transmission unit returns a notification signal to the server when the condition is satisfied,
The voice information receiving unit receives character string information generated based on the notification signal from the server,
The output unit outputs the character string information.
The voice dialogue system according to claim 25, wherein the information provided from the information terminal device is voice information.