Information processing device, information processing method, and information processing program

Abstract

To provide an information processor, method, and program for eliminating the troublesomeness of a voice request when a plurality of agent function sections are present.SOLUTION: In an information processor 100 that presents information for responding to a request by voice from a user, a response acquisition section acquires a plurality of pieces of response information to the request from each of a plurality of agent function sections that received the request. A request destination detection section detects designation information for designating an agent function section to be a request destination from the voice. A determination section determines whether or not each of response information of the agent function section, which is designated as the request destination by the designation information, and response information of a non-request-destination agent function section, which is not designated as the request destination by the request destination, among the plurality of agent function sections can correspond to the request. A presentation control section presents a first response on the basis of the response information of the request-destination agent function section to the user, according to a determination result, and presents a second response on the basis of the response information of the non-request-destination agent function section in addition to the first response.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, techniques have been proposed relating to an agent function that provides information suited to a user by having a dialogue with the user.

[0003] For example, a technology has been proposed in which, if one of multiple agent function units cannot meet the passenger's request and another agent can meet this request, the other agent function unit is recommended to the passenger. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2020-144712 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the above-mentioned conventional technology, the user must make a request by voice to each of the multiple agent function units, which may require the user to make the same request multiple times. For this reason, there is room for improvement in the above-mentioned conventional technology in terms of the complexity involved in making a request by voice.

[0006] The present invention has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can eliminate the complexity of voice requests when, for example, there are multiple agent function units. [Means for solving the problem]

[0007] The information processing device according to claim 1 is an information processing device that presents information in response to a voice request from a user, and includes: a response acquisition unit that acquires a plurality of pieces of response information output as a response to the request by each of a plurality of agent function units that have accepted the request; a request destination detection unit that detects from the voice designation information that specifies which agent function unit the user wants to send the request to; a determination unit that determines whether or not the response information of a request destination agent function unit that has been designated as the request destination by the designation information and the response information of a non-request destination agent function unit that has not been designated as the request destination by the designation information can handle the request; and a presentation control unit that presents to the user a first response based on the response information of the request destination agent function unit, and the presentation control unit presents to the user a second response based on the response information of the non-request destination agent function unit in addition to the first response, depending on a determination result by the determination unit.

[0008] An information processing method according to claim 17 is an information processing method executed by an information processing device that presents information responding to a voice request from a user, and includes: a response acquisition step of acquiring a plurality of pieces of response information that each of a plurality of agent function units that have accepted the request outputs as a response to the request; a request destination detection step of detecting, from the voice, designation information by which the user designates an agent function unit to which the request is to be made; a determination step of determining whether or not the response information of a request destination agent function unit that has been designated as the request destination by the designation information and the response information of a non-request destination agent function unit that has not been designated as the request destination by the designation information can handle the request; and a presentation control step of presenting to the user a first response based on the response information of the request destination agent function unit, wherein the presentation control step is characterized in that, depending on a determination result of the determination step, a second response based on the response information of the non-request destination agent function unit is presented to the user in addition to the first response.

[0009] An information processing program according to claim 18 is an information processing program executed by an information processing device that presents information responding to a voice request from a user, the information processing program causing the information processing device to execute: a response acquisition procedure that acquires multiple pieces of response information that each of multiple agent function units that accepted the request outputs as a response to the request; a request destination detection procedure that detects from the voice designation information that the user designates as an agent function unit to which the request is to be made; a determination procedure that determines whether or not the response information of a request destination agent function unit that has been designated as a request destination by the designation information and the response information of a non-request destination agent function unit that has not been designated as a request destination by the designation information can handle the request; and a presentation control procedure that causes the user to present a first response based on the response information of the request destination agent function unit, and the presentation control procedure causes the user to present a second response based on the response information of the non-request destination agent function unit in addition to the first response, depending on a determination result of the determination procedure. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram (1) showing an example of the configuration of an information processing device according to the first embodiment. [Figure 3] FIG. 3 is a diagram (2) showing an example of the configuration of the information processing device according to the first embodiment. [Figure 4] FIG. 4 is a flowchart (1) showing an information processing procedure according to the first embodiment. [Figure 5] FIG. 5 is a flowchart (2) showing the information processing procedure according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the determination process according to the first embodiment. [Figure 7] FIG. 7 is a flowchart (1) showing an information processing procedure according to the second embodiment. [Figure 8]FIG. 8 is a flowchart (2) showing the information processing procedure according to the second embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. DETAILED DESCRIPTION OF THE INVENTION

[0011] [Embodiment] An example of a form for implementing an information processing device, an information processing method, and an information processing program (hereinafter referred to as an "embodiment") will be described in detail below with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program are not limited to this embodiment. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and duplicated descriptions will be omitted.

[0012] <Outline of the embodiment> In the following, the embodiments will be described separately as a first embodiment and a second embodiment.

[0013] In the first embodiment, when a voice request is input with an agent function unit designated, even if the designated agent function unit is unable to respond to the voice request, a response from another agent function unit is dynamically presented without requiring the user to input the voice request again.

[0014] In the second embodiment, for example, if the user is not satisfied with the response from the agent function unit specified in the voice request and specifies another agent function unit, the response from the other agent function unit is presented without the user having to input the voice request again.

[0015] <System configuration> First, the configuration of an information processing system according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of an information processing system according to an embodiment. Fig. 1 shows an information processing system 1 as an example of an information processing system according to an embodiment.

[0016] 1, the information processing system 1 may include an information processing device 100 and an agent device 300. The information processing device 100 and the agent device 300 are connected to each other via a network N so as to be able to communicate with each other via a wired or wireless connection. The information processing system 1 shown in FIG. 1 may include any number of information processing devices 100 and any number of agent devices 300.

[0017] The information processing device 100 is an example of an information processing device that presents information in response to a voice request from a user. Specifically, the information processing device 100 is an example of an information processing device according to a first embodiment and an information processing device according to a second embodiment, which will be described later.

[0018] 1, the information processing device 100 may be mounted on a vehicle VEx, that is, the information processing device 100 may be an in-vehicle device.

[0019] Specifically, the information processing device 100 may be a dedicated navigation device that is built into or mounted on the vehicle VEx.

[0020] The information processing device 100 may be configured with a navigation device and a recording device. As an example, the information processing device 100 may be a composite device in which a navigation device and a recording device that are independent of each other are connected to each other so that they can communicate with each other. As another example, the information processing device 100 may be a single device that has a navigation function and a recording function.

[0021] The information processing device 100 may also include various sensors. For example, the information processing device 100 may include various sensors such as a camera, an acceleration sensor, a gyro sensor, a GPS sensor, and an air pressure sensor. As a result, the information processing device 100 can provide dialogue and information to assist the user in driving based on sensor information acquired by the various sensors.

[0022] Furthermore, by installing a predetermined application into a portable terminal device (for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a PDA, or the like) that a user uses on a daily basis, the user can make the portable terminal device operate in the same manner as the information processing device 100. In other words, the user can use his or her own portable terminal device as a vehicle-mounted device. For this reason, the portable terminal device possessed by the user can also be considered as an information processing device according to the embodiment.

[0023] The agent device 300 is a server device that actually performs response processing to respond to a voice request from a user. For example, the agent device 300 performs the response processing in accordance with the control of an agent function unit, which will be described later. Furthermore, the agent device 300 and the agent function unit may be paired for each service, and there may be as many agent device 300 as there are agent function units.

[0024] For example, if the agent device 300 is unable to obtain an appropriate response to the request as a result of the response process, it returns response information indicating that it is unable to respond to the agent function unit. On the other hand, if the agent device 300 is able to obtain an appropriate response to the request as a result of the response process, it returns response information including the response to the request to the agent function unit.

[0025] First Embodiment [1. Functional Configuration] From here, information processing according to the first embodiment will be described. First, an information processing device 100A according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram (1) showing an example of the configuration of the information processing device according to the first embodiment.

[0026] The information processing device 100A is an example of an information processing device according to the first embodiment, and is assumed to be an in-vehicle device provided in a vehicle VEx. The information processing device 100A has an agent function that, when it recognizes a user's voice, provides services including a response based on the recognition result. As a result, the user can receive various driving assistance and useful information through dialogue with the agent function.

[0027] As shown in FIG. 2, the information processing device 100A includes a microphone 11, a speaker 12, an application group 30A, a storage unit 120, and a control unit 130A.

[0028] (About Mike 11) The microphone 11 collects sounds generated within the vehicle VEx. For example, the microphone 11 collects speech sounds produced by a passenger in the vehicle VEx.

[0029] (Speaker 12) The speaker 12 corresponds to an output unit that outputs sound. For example, the speaker 12 outputs a response sound corresponding to an utterance input via the microphone 11 in accordance with presentation control (output control) by the control unit 130A.

[0030] (App Group 30A) The application group 30A is a group of applications that provide services related to driving assistance and useful information. The applications (hereinafter abbreviated as "apps") included in the application group 30A may provide different types of services, or may provide the same type of service but with different performance. Each application included in the application group 30A has an agent function unit that acts as an intermediary to provide the service. Each application (agent function unit) is linked to an agent device 300 that performs processing to realize the service corresponding to the application. This point will be explained more specifically using the example of FIG. 2.

[0031] 2, the application group 30A includes an application 30A-1, an application 30A-2, etc. For ease of explanation, only the application 30A-1 and the application 30A-2 are shown in FIG.

[0032] According to the example of FIG. 2, the application 30A-1 has an agent function unit 301A as a voice agent function, and the agent function unit 301A is linked to an agent device 300A-1 (an example of the agent device 300).

[0033] For example, if the application 30A-1 is a general-purpose application for realizing daily conversation with a user, the agent function unit 301A causes the agent device 300A-1 to execute a response process to a voice from the user. The agent function unit 301A also causes the user to provide response information (dialogue information) indicating the result of the response process, thereby realizing a dialogue with the user.

[0034] Also, according to the example of FIG. 2, the application 30A-2 has an agent function unit 302A as a voice agent function, and the agent function unit 302A is linked to an agent device 300A-2 (an example of the agent device 300).

[0035] For example, if the application 30A-2 is an application that provides tourist information, the agent function unit 302A causes the agent device 300A-2 to execute response processing based on the sensor information. Also, the agent function unit 301A causes the agent device 300A-2 to provide the user with response information (tourist destination information) indicating the result of the response processing, thereby realizing tourist information for the user.

[0036] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 may store, for example, data and programs related to the information processing according to the embodiment.

[0037] (control unit 130A) The control unit 130A is realized by executing various programs (for example, the information processing program according to the embodiment) stored in a storage device inside the information processing device 100A using a RAM as a working area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. The control unit 130A is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0038] 2, the control unit 130A has a request destination detection unit 131A, a response acquisition unit 132, a determination unit 133, a presentation control unit 134, and a voice generation unit 135, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 130A is not limited to the configuration shown in FIG. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units included in the control unit 130A is not limited to the connection relationship shown in FIG. 2, and may be other connection relationships.

[0039] (Request destination detection unit 131A) When the request destination detection unit 131A receives a voice request from a user (hereinafter, sometimes referred to as a "first request"), it detects first designation information from the voice that designates one of the agent function units 301A and 302A as the agent function unit to which the first request is to be made.

[0040] In the example of FIG. 2, the first designation information may be a predetermined word that is predetermined for each of the agent function units 301A and 302A.

[0041] For example, the first designation information defined for the agent function unit 301A may be a wake word indicating the name of the agent function unit 301A. Fig. 2 shows an example in which the name of the agent function unit 301A is "NA1." Therefore, the first designation information corresponding to the agent function unit 301A may be the first wake word "NA1."

[0042] Similarly, the first designation information defined for the agent function unit 302A may be a wake word indicating the name of the agent function unit 302A. An example in which the name of the agent function unit 302A is "NA2" is shown in Fig. 2. Therefore, the first designation information corresponding to the agent function unit 302A may be the first wake word "NA2."

[0043] When the request destination detection unit 131A recognizes the spoken voice, it converts the recognized voice into text. Then, the request destination detection unit 131A determines whether the voice is a request voice by intention analysis based on the text obtained by the conversion. For example, if the text contains a keyword indicating a predetermined command (e.g., "What is...?", "Look up," "I want to go," "Call me," etc.) and a keyword indicating the content of the request (e.g., "Weather," "Store," etc.), the request destination detection unit 131A can determine that the recognized voice is a request voice and acquire request content information indicating the content of the request.

[0044] Furthermore, when request destination detection unit 131A determines that the voice is a request, it detects whether the voice contains first designation information that designates one of agent function units 301A and 302A as the agent destination for the request content (first request) indicated by the acquired request content information. In the example of Fig. 2, request destination detection unit 131A detects whether the converted text acquired from the voice contains the first wake word "NA1" or the first wake word "NA2".

[0045] For example, suppose a voice saying "Agent NA1, what's the weather going to be tomorrow?" is input. In this case, the request destination detection unit 131A determines that this voice is a request voice based on the text indicating "Agent NA1, what's the weather going to be tomorrow?" and can recognize "check tomorrow's weather" as the content of the voice request. The request destination detection unit 131A also detects the first wake word "NA1."

[0046] Furthermore, when the request destination detection unit 131A detects first designation information from the voice of the request, it causes the agent function units 301A and 302A to execute a response process to the voice request indicated by the voice of the request, i.e., the first request. As in the above example, assume that the voice, "Agent NA1, what's the weather going to be like tomorrow?" is input. In this case, the request destination detection unit 131A causes not only the request destination agent function unit 301A designated as the request destination by the first wake word "NA1," but also the non-request destination agent function unit 302A not designated as the request destination by the first wake word "NA1." In this way, when the request destination detection unit 131A detects first designation information from the voice of the request, it causes all agent function units associated with the information processing device 100A, which is its own device, to execute a response process to the first request.

[0047] The agent function unit 301A may cause the agent device 300A-1 to execute a response process to the first request in response to control from the request destination detection unit 131A. The agent function unit 302A may cause the agent device 300A-2 to execute a response process to the first request in response to control from the request destination detection unit 131A.

[0048] In the following explanation, the agent function unit designated as the request destination by the first designation information will be referred to as agent function unit 301A (request destination agent function unit 301A), and the agent function unit not designated as the request destination by the first designation information will be referred to as agent function unit 302A (non-request destination agent function unit 302A).

[0049] (Regarding the response acquisition unit 132) The response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 301A in response to the first request from the agent function unit 301A in accordance with control by the request destination detection unit 131A. Also, the response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 302A in response to the first request from the agent function unit 302A in accordance with control by the request destination detection unit 131A.

[0050] The response information may include information indicating an appropriate response to the first request or information indicating that the first request could not be processed appropriately. The response acquisition unit 132 outputs the response information to the determination unit 133.

[0051] (Regarding the determination unit 133) The determination unit 133 determines whether the response information of the requested agent function unit 301A and the response information of the non-requested agent function unit 302A are capable of handling the first request. For example, the determination unit 133 may determine whether each agent function unit is capable of handling the first request based on whether the response information contains information indicating an appropriate response to the first request or whether the response information contains information indicating that the first request could not be processed appropriately.

[0052] (Regarding the presentation control unit 134) The presentation control unit 134 controls the presentation (output) to the user of a first response, which is a response based on the response information of the requested agent function unit 301A. As described above, the response information includes a reply to the first request or information indicating that the first request cannot be accommodated. For this reason, when the response information includes a reply to the first request, the presentation control unit 134 causes this reply to be presented as the first response. On the other hand, when the response information includes information indicating that the request cannot be accommodated, the presentation control unit 134 causes a message indicating that the requested agent function unit 301A cannot be accommodated to be presented as the first response.

[0053] Furthermore, depending on the determination result by the determining unit 133, the presentation control unit 134 may present to the user a second response, which is a response based on the response information of the non-requested agent function unit 302A, in addition to the first response.

[0054] For example, the presentation control unit 134 may present a first response based on the response information of the requested agent function unit 301A, or may present a combination of the first response and a second response based on the response information of the non-requested agent function unit 302A, depending on the four patterns of the judgment result shown below.

[0055] The first pattern is a situation in which, of the requested agent function unit 301A and the non-requested agent function unit 302A, only the requested agent function unit 301A is determined to be able to handle the first request.

[0056] The second pattern is a situation in which it is determined that the requested agent function unit 301A can handle the first request and that the non-requested agent function unit 302A can also handle the first request.

[0057] Pattern 3 is a situation in which the requested agent function unit 301A is unable to handle the first request, while the non-requested agent function unit 302A is determined to be able to handle the first request.

[0058] Pattern 4 is a situation in which it is determined that both the requested agent function unit 301A and the non-requested agent function unit 302A are unable to process the first request.

[0059] For example, as the process of presenting a response as described above, the presentation control unit 134 may create a sentence indicating the content of the response and control the voice generation unit 135 to output a voice reading out the created sentence. Details of the response presentation process by the presentation control unit 134 for each of these four patterns will be described later.

[0060] (Speech generation unit 135) The voice generation unit 135 synthesizes voice in accordance with the control of the presentation control unit 134, and outputs the synthesized voice from the speaker 12. For example, based on a sentence created by the presentation control unit 134, the voice generation unit 135 synthesizes voice that reads out the sentence.

[0061] For example, if the requested agent function unit 301A is agent NA1 with a female voice V1, the voice generation unit 135 may synthesize a voice in which a sentence indicating the content of the first response is read out in the female voice V1. Fig. 2 shows an example in which, in response to a determination that the response information of the requested agent function unit 301A is capable of responding to the first request "Check tomorrow's weather," the first response "Tomorrow's weather will be rainy, then cloudy" is output from the speaker 12 in the female voice V1 of agent NA1.

[0062] On the other hand, if the non-requested agent function unit 302A is agent N2 with a male voice V2, the voice generation unit 135 may synthesize a voice in which a sentence indicating the content of the second response is read out in the male voice V2.

[0063] 2. Modified Functional Configuration For example, a user can install a specific application into a portable terminal device (e.g., a smartphone, tablet terminal, notebook PC, desktop PC, PDA, etc.) to cause the portable terminal device to operate in the same manner as information processing device 100.

[0064] 3 shows an example in which a user installs a predetermined application on his or her smartphone, thereby realizing some (or all) of the functions of information processing device 100A, which is an in-vehicle device, on the smartphone. Specifically, FIG. 3 shows information processing device 100B, which is a smartphone that realizes some of the functions of information processing device 100A.

[0065] As a result, the information processing device 100A and the information processing device 100B can recognize each other's presence, for example, by short-range wireless communication, etc. In this way, the user can add any number of portable terminal devices to the system M11 of the information processing system 1 that corresponds to the user's range.

[0066] In the following, each device will be described taking as an example a case where the information processing device 100A and the information processing device 100B are connected by short-range wireless communication. Fig. 3 is a diagram (2) showing an example of the configuration of the information processing device according to the first embodiment.

[0067] [3. Functional Configuration] From here on, an information processing device 100B according to a modified example corresponding to the first embodiment will be described with reference to Fig. 3. In addition, the operation of the information processing device 100A in response to the information processing device 100B being added to the system M11 will also be described.

[0068] The information processing device 100B is an example of an information processing device according to the first embodiment, and is a smartphone having some of the functions corresponding to those of the information processing device 100A, which is an in-vehicle device. The information processing device 100B has an agent function that, upon recognizing a user's voice, provides services including a response based on the recognition result. As a result, the user can receive various driving assistance and useful information through dialogue with the agent function.

[0069] 3, the information processing device 100B has a microphone 11, an application group 30B, and a control unit 130B. The microphone 11 is the same as that of the information processing device 100A, and therefore a description thereof will be omitted. Although not shown in FIG. 3, the information processing device 100B may have a storage unit equivalent to the storage unit 120.

[0070] (App Group 30B) The application group 30B is a group of applications that provide services related to driving assistance and useful information. The applications included in the application group 30B may each provide a different type of service, or may provide the same type of service but with different performance. Each application included in the application group 30B has an agent function unit that acts as an intermediary to provide the service. Each application (agent function unit) is linked to an agent device 300 that performs processing to realize the service corresponding to the application. This point will be explained more specifically using the example of FIG. 3.

[0071] 3, the application group 30B includes an application 30B-1 and the like. For ease of explanation, only one application 30B-1 is shown in FIG. 3. Also, according to the example of FIG. 3, the application 30B-1 has an agent function unit 301B as a voice agent function, and the agent function unit 301B is linked to an agent device 300B-1 (an example of the agent device 300).

[0072] For example, if the application 30B-1 is an application that realizes specialized conversations with a user on a specific topic, the agent function unit 301B causes the agent device 300B-1 to execute response processing to the voice from the user. The agent function unit 301B also realizes a dialogue with the user by having the agent device 300B-1 provide the user with response information (specialized information) indicating the result of the response processing.

[0073] (control unit 130B) The control unit 130B is realized by executing various programs (for example, the information processing program according to the embodiment) stored in a storage device inside the information processing device 100B using the RAM as a work area by a CPU, an MPU, etc. The control unit 130B is also realized by an integrated circuit such as an ASIC or an FPGA.

[0074] As shown in Fig. 3, control unit 130B has request destination detection unit 131B and registration acceptance unit 136B, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of control unit 130B is not limited to the configuration shown in Fig. 3, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationships between the processing units included in control unit 130B are not limited to the connection relationships shown in Fig. 3, and may be other connection relationships.

[0075] (Registration reception unit 136B / Registration reception unit 136A) For example, from the perspective of the information processing device 100B, the information processing device 100A can be considered as another information processing device 100. Furthermore, from the perspective of the information processing device 100A, the information processing device 100B can also be considered as another information processing device 100. In this way, the information processing device 100B may have a registration acceptance unit 136B in preparation for a case where a plurality of information processing devices 100 are connected to be able to communicate with each other via short-range wireless communication or the like.

[0076] Furthermore, in preparation for a case where a plurality of information processing devices 100 are connected to each other so as to be able to communicate with each other via short-range wireless communication or the like, the information processing device 100A may further include a registration acceptance unit 136A as shown in FIG.

[0077] The registration acceptance unit 136B can accept registration of identification information that identifies the agent function units 301A and 302A that are linked to the information processing device 100A. For example, the registration acceptance unit 136B may accept, as the identification information, a wake word indicating the name "NA1" of the agent function unit 301A and a wake word indicating the name "NA2" of the agent function unit 302A. This enables the request destination detection unit 131B, which will be described later, to recognize which agent function unit is linked to the destination information processing device 100A.

[0078] Meanwhile, the registration reception unit 136A can accept the registration of identification information that identifies the agent function unit 301B that is linked to the information processing device 100B. Here, FIG. 3 shows an example in which the name of the agent function unit 301B is "NA3." In this case, the registration reception unit 136A may accept a wake word indicating the name "NA3" of the agent function unit 301B as the identification information. This allows the request destination detection unit 131A to recognize what agent function unit is linked to the connection destination information processing device 100B.

[0079] (Request destination detection unit 131B / Request destination detection unit 131A) The request destination detection unit 131B is a processing unit corresponding to the request destination detection unit 131A of the information processing device 100A, and may have the same functions as the request destination detection unit 131A.

[0080] In addition, the request destination detection unit 131B recognizes that the registration of identification information has been accepted by the registration acceptance unit 136B, and therefore the information processing device 100A to which it is connected is linked to an agent function unit 301A called agent NA1 and an agent function unit 302A called agent NA2.

[0081] In such a case, when the request destination detection unit 131B receives a request (first request) by voice from a user, it detects first designation information from the voice that designates the agent function unit to be the destination of the first request, from among the agent function unit 301B linked to the information processing device 100B, which is the device itself, and the agent function units 301A and 302A linked to the information processing device 100A, which is the other device.

[0082] In the example of FIG. 3, the first designation information may be a wake word that is predetermined for each of the agent function units 301A, 302A, and 301B.

[0083] Specifically, the first designation information defined for the agent function unit 301A may be a wake word indicating the name of the agent function unit 301A. That is, the first designation information corresponding to the agent function unit 301A is the first wake word "NA1."

[0084] The first designation information defined for the agent function unit 302A may be a wake word indicating the name of the agent function unit 302A. That is, the first designation information corresponding to the agent function unit 302A is the first wake word "NA2."

[0085] Also, according to the example of FIG. 3, the first designation information corresponding to the agent function unit 301B may be the first wake word "NA3."

[0086] When the request destination detection unit 131B recognizes the spoken voice, it converts the recognized voice into text. Then, the request destination detection unit 131B determines whether the voice is a request voice by intention analysis based on the text obtained by the conversion. For example, the request destination detection unit 131B can also recognize the content of the request from the result of the intention analysis.

[0087] Furthermore, when request destination detection unit 131B determines that the voice is a request, it detects whether the voice of the request contains first designation information that designates an agent function unit, among agent function units 301A, 302A, and 301B, to which the recognized request content (first request) is to be requested. In the example of Fig. 3, request destination detection unit 131B detects whether the converted text acquired from the voice contains any of the first wake word "NA1", the first wake word "NA2", and the first wake word "NA3".

[0088] For example, suppose a voice saying "Agent NA1, what's the weather going to be tomorrow?" is input. In this case, the request destination detection unit 131B determines that this voice is a request voice based on the text indicating "Agent NA1, what's the weather going to be tomorrow?" and can recognize "check tomorrow's weather" as the content of the voice request. The request destination detection unit 131B also detects the first wake word "NA1."

[0089] Furthermore, when the request destination detection unit 131B detects first designation information from the voice of the request, it causes the agent function unit 301B to execute a response process to the voice request indicated by the voice of the request, i.e., the first request. As in the above example, assume that the voice "Agent NA1, what's the weather going to be like tomorrow?" is input. In this case, the request destination detection unit 131B also causes the non-request destination agent function unit 301B, which was not designated as a request destination by the first wake word "NA1," to execute a response process to the first request. In this way, when the request destination detection unit 131B detects first designation information from the voice of the request, it causes all agent function units associated with the information processing device 100B, which is its own device, to execute a response process to the first request.

[0090] The agent function unit 301B may cause the agent device 300B-1 to execute a response process to the first request in response to the control from the request destination detection unit 131B.

[0091] In addition, in parallel with the processing performed by the request destination detection unit 131B as in the above example, the request destination detection unit 131A also operates as described in Fig. 2. However, in the example in which the information processing device 100B is added to the system M11, the request destination detection unit 131A detects whether or not the voice of the request contains first designation information that designates the agent function unit that is to be the destination of the first request, among the agent function units 301A, 302A, and 301B.

[0092] In the following explanation, the agent function unit designated as the request destination by the first designation information is referred to as agent function unit 301A (request destination agent function unit 301A), and the agent function units not designated as the request destination by the first designation information are referred to as agent function units 302A and 301B (non-request destination agent function units X). Further, the subsequent processing may be performed on the information processing device 100A side.

[0093] (Regarding the response acquisition unit 132) The response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 301A in response to the first request from the agent function unit 301A in accordance with control by the request destination detection unit 131A. Also, the response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 302A in response to the first request from the agent function unit 302A in accordance with control by the request destination detection unit 131A.

[0094] Furthermore, the response acquisition unit 132 may acquire, under the control of the request destination detection unit 131B, response information indicating the result of the response process performed by the agent function unit 301B in response to the first request, from the agent function unit 301B.

[0095] The response information may include information indicating an appropriate response to the first request or information indicating that the first request could not be processed appropriately. The response acquisition unit 132 outputs the response information to the determination unit 133.

[0096] (Regarding the determination unit 133) The determination unit 133 determines whether or not the response information of the requested agent function unit 301A and the response information of the non-requested agent function unit X can handle the first request. For example, the determination unit 133 may determine whether or not each agent function unit can handle the first request based on whether the response information includes information indicating an appropriate response to the first request or whether the response information includes information indicating that the first request could not be processed appropriately.

[0097] (Regarding the presentation control unit 134 / sound generation unit 135) Detailed explanations regarding the presentation control unit 134 and the sound generation unit 135 will be omitted because they overlap with the example of FIG.

[0098] Simply put, the presentation control unit 134 may, depending on the determination result by the determination unit 133, present to the user a second response, which is a response based on the response information of the non-requested agent function unit X, in addition to the first response.

[0099] FIG. 3 also shows an example in which, in response to a determination that the response information of the requested agent function unit 301A is capable of responding to the first request "Check tomorrow's weather," the first response "Tomorrow's weather will be rainy, then cloudy" is output from the speaker 12 in a female voice V1, which is the voice of agent NA1.

[0100] The information processing device 100B may also have a speaker 12, but the speaker 12 to which the response is output may be the speaker 12 on the information processing device 100A side. The speaker 12 of the information processing device 100A may typically be a vehicle speaker installed in a vehicle.

[0101] [4. Processing Procedure] Next, the procedure of information processing according to the first embodiment will be described with reference to Figures 4 and 5. In Figure 4, the procedure of information processing according to the first embodiment will be described, focusing on an overall picture of information processing according to the first embodiment. On the other hand, in Figure 5, the procedure of information processing according to the first embodiment will be described, focusing on response control according to the above-mentioned four patterns of determination results.

[0102] In addition, Figures 4 and 5 explain the information processing procedure using an example of a situation in which an information processing device 100A, which is an in-vehicle device installed in a vehicle VE1 (an example of a vehicle VEx), is used as the main agent, and a user U1 of the vehicle VE1 adds an information processing device 100B, which is a smartphone, to the system M11 as a sub-agent.

[0103] 4 and 5, the agent function unit 301A of the information processing device 100A is represented by its name as "agent NA1." The agent function unit 302A of the information processing device 100A is represented by its name as "agent NA2." The agent function unit 301B of the information processing device 100B is represented by its name as "agent NA3."

[0104] 4 and 5, the first specified information is expressed as "first WW." For this reason, in the examples of FIGS. 4 and 5, three wake words, "NA1," "NA2," and "NA3," are assumed to be pre-registered as first WWs. The first WWs may be registered in both information processing devices 100A and 100B by user U1, for example.

[0105] [4-1. Processing Procedure (1)] Now, let us consider Fig. 4. Fig. 4 is a flowchart (1) showing the information processing procedure according to the first embodiment.

[0106] First, when the request destination detection unit 131A (and the request destination detection unit 131B) recognizes a spoken voice, it determines whether or not this voice is a request voice. That is, the request destination detection unit 131A (and the request destination detection unit 131B) determines whether or not a voice request, which is a request made by voice, has been accepted (step S401).

[0107] While it is determined that a voice request has not been accepted (step S401; No), the request destination detection unit 131A (and the request destination detection unit 131B) waits until it is determined that a voice request has been accepted.

[0108] On the other hand, if the request destination detection unit 131A (and the request destination detection unit 131B) determines that a voice request has been accepted (step S401; Yes), the process proceeds to step S402.

[0109] 4 shows an example in which user U1 inputs a voice message saying, "Agent NA1, what's the weather going to be tomorrow?" In this example, request destination detection unit 131A (and request destination detection unit 131B) determines in step S401 that the voice request has been accepted, and recognizes the request content, "check tomorrow's weather," from the voice request as a first request VR1. The following processing procedures will be explained using this example.

[0110] For example, the request destination detection unit 131A (and the request destination detection unit 131B) detects whether the voice of the request contains a first WW (either "NA1", "NA2", or "NA3") that specifies the agent to which the first request VR1 is to be made, among the agents NA1, NA2, and NA3 whose registration has been accepted by the registration acceptance unit 136A (registration acceptance unit 136B) (step S402).

[0111] If the request destination detection unit 131A (and the request destination detection unit 131B) cannot detect the first WW (step S402; No), the process returns to step S401.

[0112] On the other hand, if the request destination detection unit 131A (and the request destination detection unit 131B) can detect the first WW (step S402; Yes), it causes the agent associated with its own device to execute a response process to the first request VR1 (step S403).

[0113] 4, the request destination detection unit 131A is able to detect the first WW "NA1" in step S402, and therefore in step S403 causes the request destination agent NA1, which has been designated as the request destination by the first WW "NA1," to execute a response process for the first request VR1. The request destination detection unit 131A also causes the non-request destination agent NA2, which has not been designated as the request destination by the first WW "NA1," to execute a response process for the first request VR1.

[0114] Similarly, the request destination detection unit 131B can detect the first WW "NA1" in step S402, and therefore in step S403, causes the non-request destination agent NA3, which was not designated as the request destination by the first WW "NA1", to execute a response process for the first request VR1.

[0115] Next, the response acquisition unit 132 acquires, from each agent, response information indicating the result of response processing performed by each agent in accordance with control by the request destination detection unit 131A (request destination detection unit 131B) (step S404). Specifically, the response acquisition unit 132 acquires, from agent NA1, response information indicating the result of response processing performed by agent NA1 to the first request VR1. The response acquisition unit 132 also acquires, from agent NA2, response information indicating the result of response processing performed by agent NA2 to the first request VR1. The response acquisition unit 132 also acquires, from agent NA3, response information indicating the result of response processing performed by agent NA3 to the first request VR1.

[0116] Next, the determination unit 133 determines whether or not the response information of the requested agent NA1 and the response information of the non-requested agent X (non-requested agents NA2 and NA3) can handle the first request VR1 (step S405).

[0117] Then, the presentation control unit 134 performs output control according to the determination result in step S405 (step S406). For example, the presentation control unit 134 performs output control so that a requested destination response (first response) based on the response information of the requested destination agent NA1 is output, or a combination of the requested destination response (first response) and a non-requested destination response (second response) based on the response information of the non-requested destination agent X is output, according to the pattern of the determination result.

[0118] [4-2. Processing Procedure (2)] Next, a description will be given of Fig. 5. Fig. 5 is a flowchart (2) showing the information processing procedure according to the first embodiment. Fig. 5 describes in more detail the procedure of the response control performed from step S405 to S406 in Fig. 4.

[0119] First, the determination unit 133 determines whether or not the response information of the requested agent NA1 can handle the first request VR1 (step S501).

[0120] If the judgment unit 133 judges that the response information of the requested agent NA1 is capable of responding to the first request VR1 (step S501; Yes), it judges whether the response information of the non-requested agent X is also capable of responding to the first request VR1 (step S502).

[0121] For example, when the judgment unit 133 judges that the response information of the non-requested agent NA3 is compatible with the first request VR1 (step S502; Yes), it compares the usage frequency between the requested agent NA1 and the non-requested agent NA3 to judge whether the non-requested agent NA3 is used more frequently than the requested agent NA1 (step S503).

[0122] When it is determined that the non-requested agent NA3 is used more frequently than the requested agent NA1 (step S503; Yes), the presentation control unit 134 outputs a non-requested response (second response) based on the response information of the non-requested agent NA3 in addition to the requested response (first response) based on the requested agent NA1 (step S504). At this time, the presentation control unit 134 may output the non-requested response in addition to the requested response by inserting a message explaining the reason for adding the non-requested response between the requested response and the non-requested response.

[0123] Here, in step S503, the determination unit 133 can perform any one of four determination processes, which will be described in more detail below. Therefore, Fig. 6 specifically describes the four determination processes and shows an example of output control in step S504. Fig. 6 is a diagram showing an example of the determination process according to the first embodiment.

[0124] The first determination process will be described. For example, the determination unit 133 compares the number of times that the request destination agent NA1, which is the current request destination, has been designated as a request destination in the first WW in previous requests made by the user U1, with the number of times that the non-request destination agent NA3, which is the current non-request destination, has been designated as a request destination. If the non-request destination agent NA3 has been designated as a request destination more frequently, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by the user U1 for various requests. In the example of FIG. 4, the first request VR1 is a request to check tomorrow's weather. In this determination process, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by the user U1 not only for weather check requests but also for various other requests in general. In other words, the determination unit 133 determines that the non-request destination agent NA3, which is the current non-request destination agent, is an agent that the user U1 is more familiar with overall.

[0125] The second determination process will be explained. For example, the determination unit 133 compares the number of times that the request destination agent NA1, which is the current request destination, has been designated as a request destination in the first WW in previous similar requests (requests similar to the first request VR1) by the user U1 with the number of times that the request destination agent NA1 has been designated as a request destination agent in the first WW with the number of times that the non-request destination agent NA3 has been designated as a request destination agent in the current non-request destination. If the non-request destination agent NA3 has been designated as a request destination more times, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by the user U1 for the target request. The first request VR1 is a request to check tomorrow's weather, and in this determination process, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by the user U1 for weather check requests. In other words, the determination unit 133 determines that the agent NA3, which is the current non-request destination agent, is the agent that the user U1 is more familiar with for weather check requests.

[0126] The third determination process will be explained. For example, the determination unit 133 compares the number of times that the current request destination agent NA1 has been designated as a request destination in the first WW in requests made by an unspecified number of users with the number of times that the current non-request destination agent NA3 has been designated as a request destination. If the non-request destination agent NA3 has been designated as a request destination more times, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently for various requests by an unspecified number of users. The first request VR1 is a request to check tomorrow's weather. In this determination process, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by more users not only for weather check requests but also for various other requests in general. In other words, the determination unit 133 determines that the current non-request destination agent NA3 is an agent that is more popular overall among general users.

[0127] The fourth determination process will be described. For example, the determination unit 133 compares the number of times that the request destination agent NA1, which is the current request destination, has been designated as a request destination in the first WW in previous similar requests (requests similar to the first request VR1) made by an unspecified number of users, with the number of times that the request destination agent NA1 has been designated as a request destination in the first WW in previous similar requests (requests similar to the first request VR1). If the non-request destination agent NA3 has been designated as a request destination more times, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently for target requests by an unspecified number of users. The first request VR1 is a request to check tomorrow's weather. In this determination process, the determination unit 133 determines that the non-request destination agent NA3 is used more frequently by more users for weather check requests. In other words, the determination unit 133 determines that the non-request destination agent NA3, which is the current non-request destination agent, is a more popular agent for weather check requests among general users.

[0128] 6, the presentation control unit 134 controls so that, following the requested destination response, a message explaining the reason, "The answer from agent NA3 is more recommended," is output in the voice of agent NA1. Furthermore, the presentation control unit 134 controls so that a non-requested destination response, "Tomorrow's weather will be rainy, then cloudy. The probability of precipitation is XX, and the wind speed is XX," is output in the voice of agent NA3.

[0129] In addition, when the judgment unit 133 judges that the response information of the non-requested agent NA3 is compatible with the first request VR1 (step S502; Yes), it may judge whether the non-requested agent NA3 has a larger amount of information than the requested agent NA1 by comparing the amount of information between the requested agent NA1 and the non-requested agent NA3, rather than comparing the frequency of use as in the above example (step S503).

[0130] Specifically, the determination unit 133 may determine whether the non-requested destination response has a larger amount of information than the requested destination response by comparing the amount of information between the response information of the requested destination agent NA1 and the response information of the non-requested destination agent NA3. Furthermore, if it is determined that the non-requested destination response has a larger amount of information than the requested destination response (step S503; Yes), the presentation control unit 134 may output the non-requested destination response in addition to the requested destination response (step S504).

[0131] Returning to Fig. 5, if it is determined that the response information of the non-requested agent X cannot respond to the first request VR1 (step S502; No), that is, if it is determined that only the requested agent NA1 can respond, the presentation control unit 134 performs control so that only the requested response based on the response information of the requested agent NA1 is output (step S506). For example, as shown in Fig. 5, the presentation control unit 134 performs control so that the requested response "Tomorrow's weather will be rainy, then cloudy" is output in the voice of agent NA1.

[0132] In addition, if the presentation control unit 134 determines that the requested agent NA1 is used more frequently (or has a larger amount of information) than the non-requested agent NA1 (step S503; No), it may similarly control the output so that only the requested response based on the response information of the requested agent NA1 is output (step S506).

[0133] Furthermore, if the judgment unit 133 judges that the response information of the requested agent NA1 cannot respond to the first request VR1 (step S501; No), it judges whether the response information of the non-requested agent X can respond to the first request VR1 (step S507).

[0134] For example, when it is determined that the response information of the non-requested agent NA3 indicates that the first request VR1 can be handled (step S507; Yes), that is, when it is determined that only the non-requested agent NA3 can handle the request, the presentation control unit 134 controls so that a non-requested response based on the response information of the non-requested agent NA3 is output after an introductory message informing the status of the requested agent NA1 (step S508). For example, as shown in FIG. 5, the presentation control unit 134 controls so that the introductory message "I can't handle it. I'll leave it to agent NA3" is output in the voice of agent NA1. Furthermore, the presentation control unit 134 controls so that the non-requested response "Tomorrow's weather will be rainy, then cloudy" is output in the voice of agent NA3.

[0135] On the other hand, if it is determined that the response information of the non-requested agent X also cannot respond to the first request VR1 (step S507; No), that is, if it is determined that both the requested agent NA1 and the non-requested agent X cannot respond to the first request VR1, the presentation control unit 134 controls to output message information indicating that there is no agent that can respond, and the message information has content mainly directed at the requested agent NA1 (step S509). For example, as shown in Fig. 5, the presentation control unit 134 controls to output "I can't respond. It seems that neither agent NA2 nor agent NA3 know" in the voice of agent NA1.

[0136] <Second embodiment> [1. Functional Configuration] Continuing on, information processing according to the second embodiment will be described. In the information processing according to the second embodiment, the functional configuration according to the first embodiment described with reference to FIGS. 2 and 3 can be adopted. For example, the information processing according to the second embodiment may be realized only by the information processing device 100A, which is an in-vehicle device. Furthermore, the information processing according to the second embodiment may be realized among a plurality of information processing devices 100 in a user-dedicated system M11 created by connecting another information processing device, such as the information processing device 100B, to the information processing device 100A.

[0137] In the first embodiment, the information processing device 100A determines whether a requested agent function unit designated as a request destination by the first designation information and a non-requested agent function unit not designated as a request destination by the first designation information can handle the first request. Furthermore, the information processing device 100A presents a first response corresponding to the requested agent function unit and a second response corresponding to the non-requested agent function unit according to the determination result.

[0138] However, in the second embodiment, the information processing device 100A presents only the first response based on the response information acquired from the requested agent function unit, regardless of whether the requested agent function unit (first agent function unit) designated as the request destination by the first designation information can handle the first request. That is, in the second embodiment, the information processing device 100A does not perform the process of determining whether the requested agent function unit and the non-requested agent function units can handle the first request.

[0139] Therefore, in the second embodiment, the information processing device 100A detects whether or not a predetermined voice command including second designation information that designates any agent function unit other than the request destination agent function unit as a new request destination has been uttered by the user after the first response has been presented as described above. Then, when the predetermined voice command is detected, the information processing device 100A causes the user to present a second response acquired as a response to the first request from the agent function unit (second agent function unit) designated by the second designation information.

[0140] The information processing device 100A according to the second embodiment will be described in more detail below using the example of Fig. 3. The operation of the information processing device 100B in response to the addition of the information processing device 100B to the system M11 will also be described.

[0141] (Request destination detection unit 131A / Request destination detection unit 131B) When a voice request is received, the request destination detection unit 131A detects whether the voice of the request contains first designation information that designates the agent function unit, among the agent function units 301A, 302A, and 301B, to which the request content (first request) recognized from the voice request should be directed.

[0142] When the request destination detection unit 131A detects the first specification information, it causes the agent function units 301A and 302A to execute a response process to the first request.

[0143] Similarly, when a voice request is received, the request destination detection unit 131B detects whether the voice of the request contains first designation information that designates the agent function unit to be the destination of the first request among the agent function units 301A, 302A, and 301B.

[0144] When the request destination detection unit 131B detects the first specification information, it causes the agent function unit 301B to execute a response process to the first request.

[0145] (Response acquisition unit 132) The response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 301A in response to the first request from the agent function unit 301A in accordance with control by the request destination detection unit 131A. Also, the response acquisition unit 132 acquires response information indicating the result of the response processing performed by the agent function unit 302A in response to the first request from the agent function unit 302A in accordance with control by the request destination detection unit 131A.

[0146] Furthermore, the response acquisition unit 132 may acquire, under the control of the request destination detection unit 131B, response information indicating the result of the response process performed by the agent function unit 301B in response to the first request, from the agent function unit 301B.

[0147] In the first embodiment, the response acquisition unit 132 outputs the response information acquired from each agent function unit to the determination unit 133, thereby causing the determination unit 133 to perform the determination process. However, as described above, in the second embodiment, the determination process is not performed by the determination unit 133. Therefore, in the second embodiment, the response acquisition unit 132 may output the response information acquired from each agent function unit to the presentation control unit 134. Furthermore, for this reason, the information processing device 100A according to the second embodiment may not have the determination unit 133.

[0148] In the following explanation, the agent function unit designated as the request destination by the first specification information will be referred to as agent function unit 301A (request destination agent function unit 301A), and the agent function units not designated as the request destination by the first specification information will be referred to as agent function units 302A and 301B (non-request destination agent function unit X).

[0149] (Presentation control unit 134) The presentation control unit 134 controls the presentation (output) to the user of a first response, which is a response based on the response information of the requested agent function unit 301A. The response information may include a reply to the first request or information indicating that the first request cannot be accommodated. For this reason, when the response information includes a reply to the first request, the presentation control unit 134 causes this reply to be presented as the first response. On the other hand, when the response information includes information indicating that the request cannot be accommodated, the presentation control unit 134 causes a message indicating that the requested agent function unit 301A cannot be accommodated to be presented as the first response.

[0150] Here, the presentation control unit 134 does not present responses based on the response information of the non-requested agent function unit X (responses other than the first response). Instead, the presentation control unit 134 saves response information other than the response information of the requested agent function unit 301A, i.e., the response information of the non-requested agent function unit X. For example, the presentation control unit 134 stores the response information of the non-requested agent function unit X in the storage unit 120.

[0151] (Request destination detection unit 131A / presentation control unit 134) The request destination detection unit 131A detects whether or not a predetermined voice command including second designation information that designates any agent function unit other than the request destination agent function unit 301A as a new request destination has been uttered by the user in a state in which the response information (other response information) of the non-request destination agent function unit X is saved (in other words, in a state after the first response has been presented to the user). Specifically, the request destination detection unit 131A detects whether or not a predetermined voice command including second designation information that designates any one of the non-request destination agent function units 302A and 301B as a new request destination has been uttered by the user.

[0152] Here, the second designation information may be a wake word that is predetermined for each of the agent function units 301A, 302A, and 301B, similar to the first designation information.

[0153] For example, the second designation information defined for the agent function unit 301A may be a wake word indicating the name of the agent function unit 301A. Therefore, the second designation information corresponding to the agent function unit 301A may be the second wake word "NA1."

[0154] The second designation information defined for the agent function unit 302A may be a wake word indicating the name of the agent function unit 302A. Therefore, the second designation information corresponding to the agent function unit 302A may be the second wake word "NA2."

[0155] Furthermore, the second designation information defined for the agent function unit 301B may be a wake word indicating the name of the agent function unit 301B. Therefore, the second designation information corresponding to the agent function unit 301B may be the second wake word "NA3."

[0156] The predetermined voice command may be a predetermined phrase that instructs the device to change the request destination and execute the response process for the first request again. Specific examples of the predetermined phrase may include "same question," "please," "what about that one?", etc.

[0157] For example, suppose the voice "Agent NA3, same question" is input. In this case, the request destination detection unit 131A can detect a voice command consisting of the second wake word "NA3" and the phrase "same question" based on the text indicating "Agent NA3, same question." As a result, the request destination detection unit 131A can recognize the agent function unit 301B as a new request destination that replaces the agent function unit 301A that was designated as the request destination of the first request by the first designation information.

[0158] In the following explanation, the agent function unit that is designated as the new request destination for the first request by the second designation information will be described as the agent function unit 301B (new request destination agent function unit 301B). In this example, the new request destination agent function unit 301B can be said to be an example of the second agent function unit that corresponds to the second designation information.

[0159] When the request destination detection unit 131A detects a predetermined voice command including second designation information, the presentation control unit 134 acquires the response information of the new request destination agent function unit 301B from the response information stored in the storage unit 120. Then, the presentation control unit 134 causes the new request destination response (second response), which is a response based on the response information of the new request destination agent function unit 301B, to be presented to the user as a response to the first request.

[0160] For example, as a process of presenting the new request destination response, the presentation control unit 134 may create a sentence indicating the content of the response and control the voice generation unit 135 to output a voice reading out the created sentence.

[0161] (Speech generation unit 135) The voice generation unit 135 synthesizes voice in accordance with the control of the presentation control unit 134, and outputs the synthesized voice from the speaker 12. For example, based on a sentence created by the presentation control unit 134, the voice generation unit 135 synthesizes voice that reads out the sentence.

[0162] For example, if new request destination agent function unit 301B is agent NA3 with a male voice V3, the voice generation unit 135 may synthesize a voice in which a sentence indicating the content of the new request destination response is read out in the male voice V3.

[0163] For example, if the response information of the new requested agent function unit 301B indicates an appropriate answer to the first request "Check tomorrow's weather," the voice generation unit 135 may synthesize a voice in which the new requested response "Tomorrow's weather will be rainy, then cloudy" is read out in a male voice V3.

[0164] On the other hand, if the response information of the new requested agent function unit 301B is unable to respond to the first request "Check tomorrow's weather", the voice generation unit 135 may synthesize a voice in which the new requested response "I cannot respond" is read out in a male voice V3.

[0165] [2. Modifications] In the second embodiment, in the above example, not only the requested agent function unit 301A designated as the request destination by the first specification information, but also the non-requested agent function unit X is controlled to perform response processing to the first request, and as a result, the response information of the non-requested agent function unit X is saved in preparation for detection of the second specification information.

[0166] However, it is also possible to control so that only the request destination agent function unit 301A designated as the request destination by the first designation information performs the response process to the first request, and after the second designation information is detected, to cause an agent function unit designated as a new request destination by the second designation information to perform the response process to the first request.In the following, information processing according to a modified example corresponding to the second embodiment will be described.

[0167] Specifically, a modified example will be described in which the agent function unit designated as the request destination by the first designation information is designated as agent function unit 301A (request destination agent function unit 301A), and the agent function units not designated as the request destination by the first designation information are designated as agent function units 302A and 301B (non-request destination agent function unit X).

[0168] In a modified example, when a voice request is received, the request destination detection unit 131A saves request content information indicating the content of the first request recognized from the voice request. For example, the request destination detection unit 131A stores the request content information indicating the content of the first request in the storage unit 120.

[0169] Furthermore, the request destination detection unit 131A causes the request destination agent function unit 301A to execute response processing for the first request. On the other hand, the request destination detection unit 131A does not cause the non-request destination agent function unit 302A to execute response processing for the first request. Furthermore, the request destination detection unit 131B does not cause the non-request destination agent function unit 301B to execute response processing for the first request.

[0170] As a result, the response acquisition unit 132, under the control of the request destination detection unit 131A, acquires, from the agent function unit 301A, response information indicating the result of the response process performed by the request destination agent function unit 301A in response to the first request.

[0171] Then, the presentation control unit 134 performs control so that the first response, which is a response based on the response information of the requested agent function unit 301A, is presented (output) to the user.

[0172] Here, the request destination detection unit 131A detects whether or not the user has uttered a predetermined voice command including second designation information that designates any agent function unit other than the request destination agent function unit 301A as a new request destination while the request content information is saved (in other words, after the first response has been presented to the user). Specifically, the request destination detection unit 131A detects whether or not the user has uttered a predetermined voice command including second designation information that designates any one of the non-request destination agent function units 302A and 301B as a new request destination.

[0173] When the request destination detection unit 131A detects a predetermined voice command including the second specification information, it causes the new request destination agent function unit 301B to execute a response process to the first request based on the saved request content information.

[0174] As a result, the response acquisition unit 132, under the control of the request destination detection unit 131B, acquires response information indicating the result of the response process performed by the new request destination agent function unit 301B in response to the first request from the new request destination agent function unit 301B.

[0175] The presentation control unit 134 presents to the user a new request destination response (second response), which is a response based on the response information of the new request destination agent function unit 301, as a response to the first request.

[0176] [3. Processing Procedure] Next, the information processing procedure according to the second embodiment and its modified example will be described with reference to Fig. 7 and Fig. 8. Fig. 7 describes the information processing procedure when response information is saved (second embodiment). On the other hand, Fig. 8 describes the information processing procedure when request content information is saved (modified example of the second embodiment).

[0177] In addition, Figures 7 and 8 explain the information processing procedure using an example of a situation in which an information processing device 100A, which is an in-vehicle device installed in a vehicle VE1 (an example of a vehicle VEx), is used as the main agent, and a user U1 of the vehicle VE1 adds an information processing device 100B, which is a smartphone, to the system M11 as a sub-agent.

[0178] 7 and 8, the agent function unit 301A of the information processing device 100A is written using its name as "agent NA1." The agent function unit 302A of the information processing device 100A is written using its name as "agent NA2." The agent function unit 301B of the information processing device 100B is written using its name as "agent NA3."

[0179] 7 and 8, the first specified information is expressed as "first WW." For this reason, in the examples of FIGS. 7 and 8, three wake words, "NA1," "NA2," and "NA3," are assumed to be pre-registered as first WWs. The first WWs may be registered in both information processing devices 100A and 100B by user U1, for example.

[0180] 7 and 8, the second specified information is expressed as "second WW." For this reason, in the examples of FIGS. 7 and 8, three wake words, "NA1," "NA2," and "NA3," are pre-registered as second WWs. The second WWs may be registered in both information processing devices 100A and 100B by user U1, for example.

[0181] [3-1. Processing Procedure (1)] First, a description will be given of Fig. 7. Fig. 7 is a flowchart (1) showing an information processing procedure according to the second embodiment.

[0182] As shown in Fig. 7, the information processing according to the second embodiment (a pattern in which response information is saved) has some parts in common with the information processing according to the first embodiment. These common parts correspond to steps S401 to S404 in Fig. 7. Steps S401 to S404 are as described in Fig. 4, and therefore description thereof in Fig. 7 will be omitted. The information processing according to the second embodiment shown in Fig. 7 may be performed following step S404 in Fig. 4.

[0183] At step S404, the response acquisition unit 132 has acquired, from agent NA1, response information corresponding to requested agent NA1, which has been designated as the request destination by the first WW "NA1." The response acquisition unit 132 has also acquired, from agent NA2, response information corresponding to non-requested agent NA2, which has not been designated as the request destination by the first WW "NA1." The response acquisition unit 132 has also acquired, from agent NA2, response information corresponding to non-requested agent NA3, which has not been designated as the request destination by the first WW "NA1."

[0184] In this state, the presentation control unit 134 stores the response information other than the response information of the requested agent NA1 (the response information of each of the non-requested agents NA2 and NA3) in the storage unit 120 (step S705).

[0185] Then, the presentation control unit 134 outputs a request destination response that is a response based on the response information of the request destination agent NA1 (step S706).

[0186] The request destination detection unit 131A detects whether or not a voice command including a second WW that designates any agent other than the request destination agent NA1 as a new request destination has been uttered by the user U1 during a predetermined period (for example, about 10 seconds) since the output control in step S706 was performed (step S707). Specifically, the request destination detection unit 131A detects whether or not a voice command including a second WW ("NA2" or "NA3") that designates either the non-request destination agent NA2 or NA3 as a new request destination has been uttered by the user U1.

[0187] If the request destination detection unit 131A is unable to detect a voice command including the second WW before the predetermined period of time has elapsed (step S707; No), the process may end at this point and return to step S401.

[0188] On the other hand, if a voice command including a second WW is detected before the specified period has elapsed (step S707; Yes), the presentation control unit 134 acquires the response information of the new request destination agent designated as the new request destination for the first request VR1 by the second WW from the response information stored in the memory unit 120 (step S708).

[0189] 7 shows an example in which the user inputs the voice "Agent NA3, same question." In this example, the request destination detection unit 131A can detect a voice command consisting of the second World Wide "NA3" and the phrase "same question" in step S707. As a result, the request destination detection unit 131A can recognize agent NA3 as a new request destination for the first request VR1. The request destination detection unit 131A may notify the presentation control unit 134 that the request destination for the first request VR1 has changed from agent NA1 to NA3. The following processing procedures will be explained using this example.

[0190] Then, in step S708, the presentation control unit 134 acquires, from the response information stored in the storage unit 120, the response information of the new request destination agent NA3 that has been designated as the new request destination by the second WW.

[0191] Then, the presentation control unit 134 causes a new request destination response, which is a response based on the response information of the new request destination agent NA3, to be output as a response to the first request VR1 (step S709).

[0192] For example, the sound generating unit 135 synthesizes sound in accordance with the control of the presentation control unit 134, and outputs the synthesized sound from the speaker 12 on the information processing device 100A side.

[0193] For example, if the response information of the new requested agent NA3 indicates an appropriate answer to the first request VR1 "Check tomorrow's weather," the voice generation unit 135 can output from the speaker 12 a voice in which the new requested agent's response, "Tomorrow's weather will be rainy, then cloudy," is read out in a male voice V3.

[0194] On the other hand, if the response information of the new requested agent NA3 is such that it cannot respond to the first request VR1 "Check tomorrow's weather", the voice generation unit 135 can output from the speaker 12 a voice in which the new requested agent's response is "I cannot respond" read out in a male voice V3.

[0195] The information processing procedure according to the second embodiment has been described above with reference to Fig. 7. According to this procedure, not only the requested agent but also the non-requested agents perform response processing in parallel, so that the response information of each agent is saved in advance. In this case, when a second WW is detected, the agent corresponding to the second WW can output a response without having to perform response processing, thereby shortening the time until a response is received.

[0196] Furthermore, according to the information processing procedure shown in FIG. 7, even if user U1 is not satisfied with the answer from agent NA1, he or she can obtain an answer from the agent corresponding to the second WW simply by using the second WW without having to re-enter a voice request.

[0197] [3-2. Processing Procedure (2)] Next, a description will be given of Fig. 8. Fig. 8 is a flowchart (2) showing the information processing procedure according to the second embodiment.

[0198] As shown in Fig. 8, the information processing according to the modified example of the second embodiment (a pattern in which request content information is saved) has some parts in common with the information processing according to the first embodiment. These common parts correspond to steps S401 and S402 in Fig. 7. Steps S401 and S402 are as described in Fig. 4, and therefore description thereof in Fig. 8 will be omitted. The information processing according to the second embodiment shown in Fig. 8 may be performed following step S402 in Fig. 4.

[0199] First, at the time step S402 is performed, according to the example of FIG. 8, the request destination detection unit 131A recognizes the agent NA1 as the request destination of the first request VR1 by the first WW "NA1".

[0200] In this state, the request destination detection unit 131A stores request content information indicating the content of the first request VR1 in the storage unit 120 (step S803).

[0201] Furthermore, the request destination detection unit 131A causes the request destination agent NA1 to execute response processing for the first request VR1 (step S804). On the other hand, the request destination detection unit 131A does not cause the non-request destination agent NA2 to execute response processing for the first request VR1. Furthermore, the request destination detection unit 131B does not cause the non-request destination agent NA3 to execute response processing for the first request VR1. This is different from the example in FIG. 7 in that not only the request destination agent NA1 but also the non-request destination agents NA2 and NA3 execute response processing.

[0202] The response acquisition unit 132, under the control of the request destination detection unit 131A, acquires from the agent NA1 response information indicating the result of the response process performed by the request destination agent NA1 in response to the first request VR1 (step S805).

[0203] Then, the presentation control unit 134 outputs a request destination response that is a response based on the response information of the request destination agent NA1 (step S806).

[0204] The request destination detection unit 131A detects whether or not a voice command including a second WW that designates any agent other than the request destination agent NA1 as a new request destination has been uttered by the user U1 during a predetermined period (for example, about 10 seconds) since the output control in step S806 was performed (step S807). Specifically, the request destination detection unit 131A detects whether or not a voice command including a second WW ("NA2" or "NA3") that designates either the non-request destination agent NA2 or NA3 as a new request destination has been uttered by the user U1.

[0205] If the request destination detection unit 131A is unable to detect a voice command including the second WW within the predetermined period of time (step S807; No), it may end the process at this point and return to step S401.

[0206] On the other hand, if the request destination detection unit 131A detects a voice command including the second WW before the specified period has elapsed (step S807; Yes), it causes the new request destination agent designated as the new request destination of the first request VR1 by the second WW to execute response processing for the first request VR1 based on the stored request content information (step S808).

[0207] 8 shows an example in which the user inputs the voice "Agent NA3, same question." In this example, the request destination detection unit 131A can detect a voice command consisting of the second WW "NA3" and the phrase "same question" in step S807. As a result, the request destination detection unit 131A can recognize agent NA3 as a new request destination for the first request VR1. The following processing procedures will be explained using this example.

[0208] Then, in step S808, the request destination detection unit 131A causes the new request destination agent NA3, which has been designated as the new request destination by the second WW, to execute a response process to the first request VR1.

[0209] The response acquisition unit 132, under the control of the request destination detection unit 131A, acquires from the agent NA3 response information indicating the result of the response process performed by the new request destination agent NA3 in response to the first request VR1 (step S809).

[0210] Then, the presentation control unit 134 outputs a request destination response, which is a response based on the response information of the new request destination agent NA3, as a response to the first request VR1 (step S810).

[0211] The information processing procedure according to the second embodiment has been explained above with reference to Fig. 8. According to this procedure, when a second WW is detected, only the agent corresponding to the second WW is made to perform response processing, thereby making it possible to effectively secure resources.

[0212] Furthermore, according to the information processing procedure shown in FIG. 8, even if user U1 is not satisfied with the answer from agent NA1, he or she can obtain an answer from the agent corresponding to the second WW simply by using the second WW without having to re-enter a voice request.

[0213] <Other> [1. Hardware Configuration] The information processing device 100 (e.g., information processing devices 100A and 100B) described above is realized, for example, by a computer 1000 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0214] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0215] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0216] The CPU 1100 controls an output device such as a display and an input device such as a keyboard via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. The CPU 1100 also outputs generated data to the output device via the input / output interface 1600.

[0217] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0218] For example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130 (e.g., control units 130A and 130B). The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0219] [2. Other] Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0220] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0221] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0222] <Summary> Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art. [Explanation of symbols]

[0223] 1. Information Processing Systems 30 apps 100 Information processing device 120 Storage section 130 control section 131 Request destination detection unit 132 Response acquisition unit 133 Judgment section 134 Presentation control unit 135 Voice Generation Unit 300 Agent Device

Claims

1. An information processing device that presents information in response to a voice request from a user, a response acquisition unit that acquires a plurality of pieces of response information output as a response to the request from each of the plurality of agent function units that have received the request; a request destination detection unit that detects, from the voice, designation information by the user that designates an agent function unit to which the request is to be made; a presentation control unit that presents to the user a second response based on the response information of the non-requested agent function unit in addition to a first response based on the response information of the requested agent function unit when it is determined that a requested agent function unit designated as a request destination by the designation information among the plurality of agent function units is capable of handling the request and that a non-requested agent function unit not designated as a request destination by the designation information is also capable of handling the request; An information processing device comprising:

2. The presentation control unit presents the second response to the user in addition to the first response depending on whether a predetermined condition is satisfied between the requested agent function unit and the non-requested agent function unit.

2. The information processing apparatus according to claim 1, wherein:

3. When it is determined that the second response contains more information than the first response, the presentation control unit causes the second response to be presented to the user in addition to the first response.

3. The information processing apparatus according to claim 2, wherein:

4. The presentation control unit presents the second response to the user in addition to the first response according to the frequency of use compared between the requested agent function unit and the non-requested agent function unit.

4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

5. When it is determined that the non-requested agent function unit is used more frequently than the requested agent function unit based on the number of times the non-requested agent function unit has been designated as a request destination by the designation information in requests made up to now, the presentation control unit presents the second response to the user in addition to the first response.

5. The information processing apparatus according to claim 4,

6. When it is determined that the non-requested agent function unit is used more frequently than the requested agent function unit based on the number of times the non-requested agent function unit has been designated as a request destination by the designation information in requests similar to the content of the current request, the presentation control unit presents the second response to the user in addition to the first response.

6. The information processing apparatus according to claim 5,

7. A determination unit is provided that determines whether the non-requested agent function unit is used more frequently than the requested agent function unit based on the number of times the non-requested agent function unit has been designated as a requested destination by the specified information in requests made by one user up to now.

7. The information processing apparatus according to claim 5, wherein the information processing apparatus is a computer.

8. A determination unit is provided that determines whether the non-requested agent function unit is used more frequently than the requested agent function unit based on the number of times the non-requested agent function unit has been designated as a requested destination by the specified information in requests made by a plurality of different users up to now.

7. The information processing apparatus according to claim 5, wherein the information processing apparatus is a computer.

9. When it is determined that the non-requested agent function unit is capable of handling the request, the presentation control unit presents the second response to the user in addition to the first response, following introductory message information explaining the status of the requested agent function unit.

9. The information processing device according to claim 1, wherein the information processing device is a computer.

10. An information processing method executed by an information processing device having a plurality of agent function units and presenting information in response to a voice request from a user, comprising: a response acquisition step of acquiring a plurality of pieces of response information output as a response to the request from each of the plurality of agent function units that have accepted the request; a request destination detection step of detecting, from the voice, designation information by the user that designates an agent function unit to which the request is to be made; a presentation control step of presenting to the user a second response based on the response information of the non-requested agent function unit in addition to a first response based on the response information of the requested agent function unit when it is determined that a requested agent function unit designated as a request destination by the designation information among the plurality of agent function units is capable of handling the request and that a non-requested agent function unit not designated as a request destination by the designation information is also capable of handling the request; An information processing method comprising:

11. An information processing program executed by an information processing device having a plurality of agent function units and presenting information in response to a voice request from a user, comprising: a response acquisition step of acquiring a plurality of pieces of response information output as a response to the request from each of the plurality of agent function units that have accepted the request; a request destination detection step of detecting, from the voice, designation information by the user that designates an agent function unit to which the request is to be made; a presentation control procedure for presenting to the user a second response based on the response information of the non-requested agent function unit in addition to a first response based on the response information of the requested agent function unit when it is determined that a requested agent function unit designated as a request destination by the designation information among the plurality of agent function units is capable of handling the request and that a non-requested agent function unit not designated as a request destination by the designation information is also capable of handling the request; causing the information processing device to execute An information processing program characterized by:

Images