JP2019164615A - Information processing system and information processing method - Google Patents

Abstract

To provide an information processing system in which a processing unit other than a processing unit that has transmitted audio data can receive a processing result.SOLUTION: Processing units 2a to 2c each include a voice input unit 211, a voice data generation unit 215, a voice data transmission unit 213, and a processing result data reception unit 213. The voice input unit 211 inputs a first voice indicating a specific command and a second voice specifying at least one of the plurality of processing units 2a to 2c. The voice data generation unit 215 generates voice data, and the voice data transmission unit 213 transmits the voice data to a server 3. The processing result data reception unit 213 receives processing result data from the server 3. The processing result data indicates a result of execution of processing corresponding to the specific command. Among the plurality of processing units 2a to 2c, the processing unit that has transmitted the voice data and the processing unit that is specified by the voice data receive the processing result data.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing system and an information processing method.

  There is known an information providing system that provides a search result corresponding to a user's utterance to the user (for example, see Patent Document 1). Patent Document 1 discloses an information providing system including an in-vehicle terminal, a server, and a search engine. The in-vehicle terminal converts the user's utterance into a character string by voice recognition processing and transmits it to the server. The server requests the search engine to perform a search according to the character string. The search engine transmits the search result to the server, and the server transmits the search result acquired from the search engine to the in-vehicle terminal.

JP 2017-194850 A

  However, according to the technique disclosed in Patent Document 1, only a terminal that transmits a character string corresponding to an utterance (voice) to a server receives a search result (processing result). Therefore, terminals other than the terminal that has transmitted the character string corresponding to the speech (voice) to the server cannot receive the search result (processing result).

  In view of the above-described problems, the present invention provides an information processing system in which a processing unit other than a processing unit that has transmitted audio data to a server can receive a processing result in addition to the processing unit that has transmitted audio data to the server, and An object is to provide an information processing method.

  The information processing system of the present invention includes a plurality of processing units. The processing unit includes an audio input unit, an audio data generation unit, an audio data transmission unit, and at least one processing result data reception unit. The voice input unit inputs a first voice indicating a specific command and a second voice specifying at least one of the plurality of processing units. The voice data generation unit generates first voice data corresponding to the first voice and second voice data corresponding to the second voice. The voice data transmitting unit transmits the first voice data and the second voice data to a server. The at least one processing result data receiving unit receives processing result data from the server. The processing result data indicates an execution result of processing corresponding to the specific command. Among the plurality of processing units, the processing unit that transmitted the first audio data and the second audio data and the processing unit specified by the second audio data receive the processing result data.

  The information processing method of the present invention includes a step of inputting a first voice indicating a specific command and a second voice specifying at least one of a plurality of processing units, and a first corresponding to the first voice. Generating audio data and second audio data corresponding to the second audio; transmitting the first audio data and the second audio data to a server; and among the plurality of processing units, the first The processing unit that has transmitted the audio data and the second audio data, and the processing unit specified by the second audio data receive processing result data from the server. The processing result data indicates an execution result of processing corresponding to the specific command.

  According to the present invention, in addition to the processing unit that has transmitted the audio data to the server, a processing unit other than the processing unit that has transmitted the audio data to the server can also receive the processing result.

It is a figure which shows the structure of the information processing system which concerns on Embodiment 1 of this invention. It is a figure which shows the structure of the 1st smart speaker which concerns on Embodiment 1 of this invention. It is a figure which shows the structure of the server which concerns on Embodiment 1 of this invention. It is a figure which shows the management table which concerns on Embodiment 1 of this invention. It is a flowchart which shows operation | movement of the 1st smart speaker which concerns on Embodiment 1 of this invention. It is a flowchart which shows operation | movement of the server which concerns on Embodiment 1 of this invention. It is a figure which shows the structure of the information processing system which concerns on Embodiment 2 of this invention. It is a figure which shows the structure of the 1st smart speaker which concerns on Embodiment 2 of this invention. It is a figure which shows the structure of the 1st server which concerns on Embodiment 2 of this invention. (A) is a figure which shows the 1st management table which concerns on Embodiment 2 of this invention. (B) is a figure which shows the 2nd management table which concerns on Embodiment 2 of this invention. It is a figure which shows the structure of the 1st terminal which concerns on Embodiment 2 of this invention. It is a flowchart which shows operation | movement of the 1st server which concerns on Embodiment 2 of this invention. It is a flowchart which shows operation | movement of the 1st terminal which concerns on Embodiment 2 of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the present invention is not limited to the following embodiments. In addition, about the location where description overlaps, description may be abbreviate | omitted suitably. In the drawings, the same or corresponding parts are denoted by the same reference numerals and description thereof will not be repeated.

[Embodiment 1]
FIG. 1 is a diagram illustrating a configuration of an information processing system 1 according to the first embodiment. As shown in FIG. 1, the information processing system 1 includes a first processing unit 2 a to a third processing unit 2 c and a server 3.

  In the present embodiment, the first processing unit 2a includes a first smart speaker 21a. The second processing unit 2b includes a second smart speaker 21b. The third processing unit 2c includes a third smart speaker 21c. Each of the first smart speaker 21a to the third smart speaker 21c is an example of a voice input / output terminal.

  Each of the first smart speaker 21a to the third smart speaker 21c communicates with the server 3 via, for example, the Internet line. Specifically, each of the first smart speaker 21a to the third smart speaker 21c inputs voice generated by the user, converts the input voice into voice data (digital data), and transmits the voice data to the server 3.

  Specifically, each of the first smart speaker 21a to the third smart speaker 21c stores data indicating an activation command. The first smart speaker 21a to the third smart speaker 21c are in a ready state when the user utters a voice indicating an activation command. The first smart speaker 21a to the third smart speaker 21c convert the sound into sound data and transmit it to the server 3 when the user utters the sound before the predetermined period elapses after becoming ready.

  When the server 3 receives audio data from any one of the first smart speaker 21a to the third smart speaker 21c, the server 3 determines whether or not the received audio data indicates a specific command. When the voice data indicates a specific command, the server 3 acquires process result data indicating the execution result of the process corresponding to the specific command. In the present embodiment, the processing result data is audio data. The server 3 transmits the processing result data to the smart speaker that has transmitted the audio data. In the following description, a smart speaker that has transmitted audio data may be referred to as “audio transmitting smart speaker”.

  In the present embodiment, the server 3 transmits the processing result data (voice data) to smart speakers other than the voice transmission smart speaker. Specifically, when the received voice data includes a designated keyword that designates at least one of the first smart speaker 21a to the third smart speaker 21c, the server 3 includes the voice transmitting smart speaker, the designated keyword, The processing result data (sound data) is transmitted to the smart speaker specified by. In the following description, the smart speaker designated by the designated keyword may be described as “designated smart speaker”.

  Next, the configuration of the first smart speaker 21a will be described with reference to FIGS. FIG. 2 is a diagram illustrating a configuration of the first smart speaker 21a according to the first embodiment. As shown in FIG. 2, the first smart speaker 21 a includes an audio input unit 211, an audio output unit 212, a communication unit 213, a storage unit 214, and a control unit 215.

  The voice input unit 211 collects voice uttered by the user and converts it into an analog electrical signal. The analog electrical signal is input to the control unit 215. The voice input unit 211 is, for example, a microphone. In the following description, the voice uttered by the user may be referred to as “user voice”.

  The sound output unit 212 outputs sound corresponding to the sound data received from the server 3. The audio output unit 212 is, for example, a speaker.

  The communication unit 213 controls communication with the server 3. The communication unit 213 includes, for example, a LAN (Local Area Network) board or a wireless LAN board. Specifically, the communication unit 213 transmits audio data to the server 3. The communication unit 213 receives audio data from the server 3.

  In the present embodiment, the communication unit 213 is an example of an audio data transmission unit. The communication unit 213 is an example of a processing result data receiving unit. Specifically, when the voice input unit 211 inputs voice indicating a specific command, the communication unit 213 transmits voice data indicating the specific command. Furthermore, when the voice input unit 211 inputs the voice indicating the designated keyword described with reference to FIG. 1, the communication unit 213 transmits voice data indicating the designated keyword. Further, the communication unit 213 receives the processing result data (voice data) described with reference to FIG.

  The storage unit 214 includes a semiconductor memory such as a RAM (Random Access Memory) and a ROM (Read Only Memory). The storage unit 214 may further include a storage device such as an HDD (Hard Disk Drive). The storage unit 214 stores a control program executed by the control unit 215. The storage unit 214 further stores data indicating the activation command described with reference to FIG.

  The control unit 215 includes a processor such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), or a DSP (Digital Signal Processor). The control unit 215 controls the operation of the first smart speaker 21a based on the control program stored in the storage unit 214.

  Specifically, the control unit 215 converts an analog electrical signal (user voice) input from the voice input unit 211 into a digital signal (voice data), and causes the communication unit 213 to transmit the digital signal. In addition, the control unit 215 converts the digital signal (audio data) received by the communication unit 213 into an analog electric signal, and causes the audio output unit 212 to output audio.

  Specifically, when the voice input unit 211 inputs a user voice, the control unit 215 refers to the data indicating the start command stored in the storage unit 214 and determines whether the voice data corresponding to the user voice indicates the start command. Determine whether. The control unit 215 enters a ready state when the voice data corresponding to the user voice indicates an activation command. When the voice input unit 211 inputs a user voice before a predetermined period has elapsed after entering the ready state, the control unit 215 stores voice data corresponding to the user voice in the storage unit 214. Note that the storage unit 214 stores data indicating a predetermined period. The predetermined period is, for example, 8 seconds.

  In the present embodiment, the control unit 215 saves the audio data corresponding to the user voice in the storage unit 214 every time the voice input unit 211 inputs the user voice until a predetermined period elapses. The control unit 215 determines whether audio data is stored in the storage unit 214 when a predetermined period has elapsed. When audio data is stored in the storage unit 214, the control unit 215 causes the communication unit 213 to transmit the audio data stored in the storage unit 214.

  The configuration of the first smart speaker 21a has been described above with reference to FIGS. In addition, since the structure of the 2nd smart speaker 21b and the 3rd smart speaker 21c is the same as that of the structure of the 1st smart speaker 21a, the description is omitted.

  Next, the configuration of the server 3 will be described with reference to FIGS. 1 and 3. FIG. 3 is a diagram illustrating a configuration of the server 3 according to the first embodiment. As shown in FIG. 3, the server 3 includes a communication unit 31, a voice recognition unit 32, a storage unit 33, and a control unit 34.

  The communication unit 31 controls communication between the first smart speaker 21a to the third smart speaker 21c. The communication unit 31 includes, for example, a LAN board or a wireless LAN board. Specifically, the communication unit 31 receives audio data from the first smart speaker 21a to the third smart speaker 21c. The communication unit 31 also transmits audio data to the first smart speaker 21a to the third smart speaker 21c.

  In the present embodiment, the communication unit 31 is an example of an audio data receiving unit. The communication unit 31 is an example of a processing result data transmission unit. Specifically, the communication unit 31 receives audio data indicating a specific command. Further, the communication unit 31 receives voice data indicating the designated keyword described with reference to FIG. Further, the communication unit 31 transmits the processing result data (voice data) described with reference to FIG.

  The voice recognition unit 32 converts the voice data received by the communication unit 31 into text information (hereinafter may be referred to as “recognition result text”) by voice recognition technology. The voice recognition unit 32 includes, for example, a voice recognition LSI (Large Scale Integration).

  The storage unit 33 includes a semiconductor memory such as a RAM and a ROM. Furthermore, the storage unit 33 includes a storage device such as an HDD. The storage unit 33 stores a control program executed by the control unit 34. The storage unit 33 further stores a management table 331. The specified keyword described with reference to FIG. 1 is registered in the management table 331.

  The control unit 34 includes a processor such as a CPU or MPU. Further, the control unit 34 controls the operation of the server 3 based on the control program stored in the storage unit 33.

  Specifically, the control unit 34 refers to the keyword group stored in the storage unit 33 and determines whether or not a character string indicating a specific command is included in the recognition result text. Alternatively, the control unit 34 analyzes the recognition result text by the intention estimation process, and determines whether or not a character string indicating a specific command is included in the recognition result text. When the control unit 34 executes intention estimation processing, the storage unit 33 stores a corpus. When the recognition result text includes a character string indicating a specific command, the control unit 34 executes processing corresponding to the specific command and acquires processing result data. For example, the specific command indicates a search keyword and a keyword that prompts execution of search processing. In this case, the control unit 34 executes a search process based on the search keyword, and acquires data indicating the search result.

  The control unit 34 causes the communication unit 31 to transmit processing result data. Specifically, the control unit 34 refers to the management table 331 and determines whether or not a character string indicating the specified keyword is included in the recognition result text. When the character string indicating the specified keyword is not included in the recognition result text, the communication unit 31 transmits the processing result data to the voice transmission smart speaker. On the other hand, when the character string indicating the designated keyword is included in the recognition result text, the communication unit 31 transmits the processing result data to the voice transmission smart speaker and the designated smart speaker.

  The server 3 may request another server to execute processing corresponding to a specific command. In this case, the server 3 acquires (receives) processing result data from another server.

  Next, the management table 331 will be described with reference to FIG. FIG. 4 is a diagram illustrating the management table 331 according to the first embodiment. As shown in FIG. 4, the management table 331 has a smart speaker registration field 41 and a designated keyword registration field 42.

  In the smart speaker registration field 41, smart speaker identification information for identifying a smart speaker that can communicate with the server 3 is registered. In the present embodiment, smart speaker identification information for identifying the first smart speaker 21 a to the third smart speaker 21 c is registered in the smart speaker registration field 41. The smart speaker identification information is arbitrarily determined and registered by the user.

  In the designated keyword registration field 42, a keyword (designated keyword) for specifying the smart speaker registered in the smart speaker registration field 41 is registered. The specified keyword is arbitrarily determined and registered by the user. For example, the designated keyword may be a name of a place where the smart speaker is installed. In the designated keyword registration field 42 shown in FIG. 4, “A spot” is registered as the designated keyword of the first smart speaker 21a. Similarly, “B point” is registered as a designated keyword of the second smart speaker 21b, and “C point” is registered as a designated keyword of the third smart speaker 21c. The management table 331 associates smart speaker identification information with a specified keyword.

  The first smart speaker 21a to the third smart speaker 21c transmit their own smart speaker identification information when transmitting audio data to the server 3. The smart speaker identification information is stored in the storage unit 214 (FIG. 2) of the first smart speaker 21a to the third smart speaker 21c. The server 3 transmits the processing result data to the smart speaker that transmitted the audio data based on the smart speaker identification information received together with the audio data.

  Next, the operation of the first smart speaker 21a will be described with reference to FIG. 1, FIG. 2, and FIG. FIG. 5 is a flowchart illustrating the operation of the first smart speaker 21a according to the first embodiment. The operation shown in FIG. 5 starts when the voice input unit 211 of the first smart speaker 21a inputs user voice.

  As shown in FIG. 5, when the voice input unit 211 inputs user voice, the control unit 215 generates voice data corresponding to the user voice (step S1). When generating the voice data, the control unit 215 refers to the data indicating the activation command stored in the storage unit 214 and determines whether or not the voice data indicates the activation command (step S2).

  When the control unit 215 determines that the voice data indicates an activation command (Yes in step S2), the control unit 215 enters a ready state for a predetermined period (step S3). In the ready state, when the voice input unit 211 inputs user voice, the control unit 215 stores voice data corresponding to the user voice in the storage unit 214. When the predetermined period has elapsed, the control unit 215 determines whether or not audio data is stored in the storage unit 214 (step S4).

  If the control unit 215 determines that the audio data is stored in the storage unit 214 (Yes in step S4), the control unit 215 stores the audio data stored in the storage unit 214 and the smart speaker identification information stored in the storage unit 214. Is transmitted to the server 3 (step S5), and the operation shown in FIG.

  In addition, when the control unit 215 determines that the voice data does not indicate an activation command (No in Step S2), or determines that the voice data is not stored in the storage unit 214 (No in Step S4), The operation shown in FIG.

  The operation of the first smart speaker 21a has been described above with reference to FIGS. In addition, the 2nd smart speaker 21b and the 3rd smart speaker 21c perform the operation | movement shown in FIG. 5 similarly to the 1st smart speaker 21a.

  Subsequently, the operation of the server 3 will be described with reference to FIGS. 1, 3, 4 and 6. FIG. 6 is a flowchart illustrating the operation of the server 3 according to the first embodiment. The operation shown in FIG. 6 starts when the communication unit 31 of the server 3 receives audio data and smart speaker identification information.

  As shown in FIG. 6, when the communication unit 31 receives voice data and smart speaker identification information, the voice recognition unit 32 converts the voice data into text information and generates a recognition result text (step S11). As a result, the control unit 34 acquires the recognition result text. In addition, when the communication unit 31 receives the audio data and the smart speaker identification information, the control unit 34 stores the smart speaker identification information received by the communication unit 31 in the storage unit 33 as a transmission destination of the processing result data (audio data). To do.

  When acquiring the recognition result text, the control unit 34 determines whether or not a specific command can be recognized from the recognition result text (step S12). In other words, the control unit 34 determines whether or not a character string indicating a specific command is included in the recognition result text. For example, the control unit 34 refers to the keyword group stored in the storage unit 33 and determines whether or not a character string indicating a specific command is included in the recognition result text. Or the control part 34 determines whether the character string which shows a specific command is contained in the recognition result text by the intention estimation process using the corpus memorize | stored in the memory | storage part 33. FIG.

  When determining that the specific command can be recognized from the recognition result text (Yes in Step S12), the control unit 34 stores the recognized specific command in the storage unit 33 (Step S13).

  When the control unit 34 stores the recognized specific command in the storage unit 33, the control unit 34 refers to the management table 331 stored in the storage unit 33 and determines whether or not the specified keyword can be recognized from the recognition result text ( Step S14). In other words, the control unit 34 determines whether or not a character string indicating the designated keyword is included in the recognition result text.

  When determining that the specified keyword can be recognized from the recognition result text (Yes in step S14), the control unit 34 stores the smart speaker identification information corresponding to the recognized specified keyword as the transmission destination of the processing result data (voice data). 33 is stored (step S15).

  When storing the smart speaker identification information in the storage unit 33, the control unit 34 acquires processing result data (voice data) corresponding to the specific command stored in the storage unit 33 (step S16). Alternatively, when determining that the designated keyword cannot be recognized from the recognition result text (No in step S14), the control unit 34 acquires processing result data (voice data) corresponding to a specific command stored in the storage unit 33 (step S14). S16). Specifically, the control unit 34 executes processing corresponding to a specific command and acquires processing result data. Or the control part 34 requests | requires execution of the process corresponding to a specific command from another server, and acquires process result data from another server.

  When acquiring the processing result data, the control unit 34 refers to the smart speaker identification information stored in the storage unit 33 as a transmission destination of the processing result data, and causes the communication unit 31 to transmit the processing result data (voice data) (step S1). S17), the operation shown in FIG. Specifically, when the specified keyword can be recognized from the recognition result text (Yes in step S14), the server 3 transmits the processing result data to the voice transmission smart speaker and the specified smart speaker. On the other hand, when the designated keyword cannot be recognized from the recognition result text (No in step S14), the server 3 transmits the processing result data to the voice transmission smart speaker.

  If the control unit 34 determines that the specific command cannot be recognized from the recognition result text (No in step S12), the control unit 34 turns on the error flag (step S18). When the error flag is set to ON, the control unit 34 causes the communication unit 31 to transmit voice data indicating an error message (step S17), and ends the operation illustrated in FIG. Specifically, the server 3 transmits an error message (audio data) to the audio transmission smart speaker. The error message indicates that the command cannot be recognized.

  The first embodiment of the present invention has been described above with reference to FIGS. According to the present embodiment, in addition to the smart speaker (processing unit) that has transmitted the audio data to the server, the smart speaker (processing unit) other than the smart speaker (processing unit) that has transmitted the audio data to the server also displays the processing result. Can be received. For example, if the user of the first smart speaker 21a utters a voice indicating an activation command and then utters a voice prompting execution of a search based on a search keyword and a voice indicating a point B within a predetermined period, the search keyword A sound indicating a search result based on the first smart speaker 21a and the second smart speaker 21b is output.

  In the present embodiment, the storage unit 33 of the server 3 stores the designated keywords of the first smart speaker 21a to the third smart speaker 21c, but each of the first smart speaker 21a to the third smart speaker 21c. In addition to the specified keyword, a specified keyword that specifies all of the first smart speaker 21a to the third smart speaker 21c may be further stored. For example, the designated keyword that designates all of the first smart speaker 21a to the third smart speaker 21c may be “ALL”. In this case, for example, after the user of the first smart speaker 21a utters a sound indicating an activation command, a sound prompting execution of a search based on the search keyword and a sound indicating “all” are uttered within a predetermined period. Then, the sound indicating the search result based on the search keyword is output from the first smart speaker 21a to the third smart speaker 21c.

[Embodiment 2]
Subsequently, Embodiment 2 of the present invention will be described with reference to FIGS. However, items different from the first embodiment will be described, and descriptions of the same items as the first embodiment will be omitted. The second embodiment is different from the first embodiment in that the information processing system 1 is a web conference system.

  FIG. 7 is a diagram illustrating a configuration of the information processing system 1 according to the second embodiment. As shown in FIG. 7, the information processing system 1 (web conference system) includes a first processing unit 2 a to a third processing unit 2 c, a first server 3, and a second server 4. The first server 3 corresponds to the server 3 described in the first embodiment.

  In the present embodiment, the first processing unit 2a includes a first smart speaker 21a, a first terminal 22a, and a first display device 23a. The second processing unit 2b includes a second smart speaker 21b, a second terminal 22b, and a second display device 23b. The third processing unit 2c includes a third smart speaker 21c, a third terminal 22c, and a third display device 23c. The first smart speaker 21a to the third smart speaker 21c are examples of voice input / output terminals, and the first terminal 22a to the third terminal 22c are examples of information processing terminals.

  In the present embodiment, the first smart speaker 21a and the first display device 23a are peripheral devices of the first terminal 22a, and the second smart speaker 21b and the second display device 23b are peripheral devices of the second terminal 22b. The third smart speaker 21c and the third display device 23c are peripheral devices of the third terminal 22c.

  In the present embodiment, the first server 3 communicates with each of the first smart speaker 21a to the third smart speaker 21c via, for example, the Internet line. Furthermore, the first server 3 communicates with each of the first terminal 22a to the third terminal 22c via, for example, the Internet line.

  The first server 3 acquires processing result data based on the audio data received from the first smart speaker 21a to the third smart speaker 21c. In the present embodiment, the processing result data is voice data or a terminal command.

  When the processing result data is audio data, the first server 3 transmits the processing result data (audio data) to the audio transmission smart speaker. Furthermore, as described in the first embodiment, the first server 3 transmits the processing result data (voice data) to smart speakers other than the voice transmission smart speaker. Specifically, when the specified keyword is included in the received voice data, the first server 3 transmits the processing result data (voice data) to the voice transmission smart speaker and the specified smart speaker.

  When the processing result data is a terminal command, the first server 3 transmits the processing result data (terminal command) to a terminal connected to the voice transmission smart speaker. Hereinafter, a terminal connected to the voice transmission smart speaker may be referred to as a “connection terminal”.

  Specifically, the first server 3 stores a correspondence relationship between the first smart speaker 21a to the third smart speaker 21c and the first terminal 22a to the third terminal 22c. The first server 3 periodically receives request signals from the first terminal 22a to the third terminal 22c. The request signal requests the first server 3 to transmit processing result data (terminal command). When the processing result data is a terminal command, the first server 3 transmits the processing result data (terminal command) to the connection terminal when receiving a request signal from the connection terminal.

  Further, the first server 3 transmits processing result data (terminal command) to terminals other than the connection terminal. Specifically, when the designated keyword is included in the received voice data, the first server 3 transmits processing result data (terminal command) to the connection terminal and the terminal connected to the designated smart speaker. In the following description, a terminal connected to a designated smart speaker may be referred to as a “designated terminal”.

  The second server 4 performs a web conference between the first terminal 22a and the third terminal 22c by communicating with each of the first terminal 22a to the third terminal 22c via, for example, the Internet line. Let Specifically, the second server 4 transmits the audio data and imaging data received from the first terminal 22a to the second terminal 22b and the third terminal 22c. Similarly, the second server 4 transmits the audio data and imaging data received from the second terminal 22b to the first terminal 22a and the third terminal 22c. Further, the second server 4 transmits the audio data and the imaging data received from the third terminal 22c to the first terminal 22a and the second terminal 22b.

  Next, operations of the first smart speaker 21a, the first terminal 22a, and the first display device 23a included in the first processing unit 2a will be described with reference to FIG.

  The first smart speaker 21a transmits voice data corresponding to the user voice to the first terminal 22a. The first smart speaker 21a receives audio data from the first terminal 22a. The first smart speaker 21a outputs a sound corresponding to the sound data received from the first terminal 22a. Further, the first smart speaker 21a includes an imaging unit, and transmits imaging data to the first terminal 22a.

  The first smart speaker 21a also transmits audio data and imaging data to the first terminal 22a and receives audio data from the first terminal 22a even in the ready state. Further, as described in the first embodiment, when the user utters a voice during a predetermined period after the first smart speaker 21a becomes ready, the first smart speaker 21a Corresponding audio data is transmitted to the first server 3.

  The first terminal 22 a transmits the audio data and imaging data received from the first smart speaker 21 a to the second server 4. In addition, the first terminal 22 a receives audio data and imaging data from the second server 4. The first terminal 22a transmits the audio data received from the second server 4 to the first smart speaker 21a. In addition, the first terminal 22a outputs the imaging data received from the second server 4 to the first display device 23a. The first display device 23a displays a video corresponding to the imaging data input from the first terminal 22a.

  Further, the first terminal 22a transmits a request signal to the first server 3 and requests the first server 3 to transmit processing result data (terminal command). When receiving the terminal command from the first server 3, the first terminal 22 a executes a process corresponding to the received terminal command.

  The operations of the second smart speaker 21b, the second terminal 22b, and the second display device 23b included in the second processing unit 2b are the same as the first smart speaker 21a, the first terminal 22a, Since the operation is the same as that of the first display device 23a, the description thereof is omitted. The operations of the third smart speaker 21c, the third terminal 22c, and the third display device 23c included in the third processing unit 2c are the same as the first smart speaker 21a, the first terminal 22a, Since the operation is the same as that of the first display device 23a, the description thereof is omitted.

  Next, the configuration of the first smart speaker 21a according to the second embodiment will be described with reference to FIGS. FIG. 8 is a diagram illustrating a configuration of the first smart speaker 21a according to the second embodiment.

  As shown in FIG. 8, the first smart speaker 21 a includes an audio input unit 211, an audio output unit 212, a first communication unit 213, a storage unit 214, a control unit 215, an imaging unit 216, and a second communication unit 217. . The first communication unit 213 corresponds to the communication unit 213 described in the first embodiment.

  In the present embodiment, the control unit 215 is an example of an audio data generation unit. The first communication unit 213 is an example of an audio data transmission unit and an example of a first processing result data reception unit.

  The imaging unit 216 images the surrounding environment of the first smart speaker 21a and outputs an image signal (analog electrical signal). For example, the imaging unit 216 includes an imaging element such as a CCD (Charge-Coupled Device).

  The second communication unit 217 controls communication with the first terminal 22a. The second communication unit 217 includes a wireless communication module conforming to the short-range wireless communication standard such as Bluetooth (registered trademark). Alternatively, the second communication unit 217 can be, for example, a USB interface including a USB (Universal Serial Bus) terminal.

  The second communication unit 217 transmits audio data corresponding to the audio input by the audio input unit 211 to the first terminal 22a. In addition, the second communication unit 217 transmits imaging data corresponding to the image signal output from the imaging unit 216 to the first terminal 22a. Further, the second communication unit 217 receives audio data from the first terminal 22a.

  The control unit 215 converts the analog electrical signal (user voice) input from the voice input unit 211 into a digital signal (voice data), and causes the second communication unit 217 to transmit the digital signal. The control unit 215 converts the image signal (analog electrical signal) input from the imaging unit 216 into a digital signal (imaging data), and causes the second communication unit 217 to transmit the digital signal.

  Further, the control unit 215 converts the digital signal (audio data) received by the second communication unit 217 into an analog electric signal, and causes the audio output unit 212 to output audio. Similarly to the first embodiment, the control unit 215 converts the digital signal (audio data) received by the first communication unit 213 into an analog electrical signal, and causes the audio output unit 212 to output audio. Therefore, in the present embodiment, the audio output unit 212 includes the audio received by the second communication unit 217 from the first terminal 22a in addition to the audio corresponding to the audio data received by the first communication unit 213 from the first server 3. Outputs audio corresponding to the data.

  Furthermore, when the voice input unit 211 inputs the user voice before the predetermined period has elapsed since entering the ready state, the control unit 215 causes the second communication unit 217 to transmit voice data corresponding to the user voice. A copy of the voice data corresponding to the user voice is stored in the storage unit 214. When a predetermined period has elapsed, the control unit 215 causes the first communication unit 213 to transmit audio data (a duplicate) stored in the storage unit 214.

  The configuration of the first smart speaker 21a has been described above with reference to FIGS. In addition, since the structure of the 2nd smart speaker 21b and the 3rd smart speaker 21c is the same as that of the structure of the 1st smart speaker 21a, the description is omitted.

  Next, the configuration of the first server 3 will be described with reference to FIGS. 7 and 9. FIG. 9 is a diagram illustrating a configuration of the first server 3 according to the second embodiment. As shown in FIG. 9, the first server 3 includes a communication unit 31, a voice recognition unit 32, a storage unit 33, and a control unit 34.

  In the present embodiment, the storage unit 33 stores a first management table 331 and a second management table 332. The first management table 331 corresponds to the management table 331 described in the first embodiment. Therefore, the designated keyword is registered in the first management table 331. In the second management table 332, correspondence relationships between the first smart speaker 21a to the third smart speaker 21c and the first terminal 22a to the third terminal 22c are registered.

  In addition, the storage unit 33 includes a terminal storage area 333. In the present embodiment, the terminal storage area 333 includes a first storage area 333a, a second storage area 333b, and a third storage area 333c. The first storage area 333a is an area for storing a terminal command (processing result data) to be transmitted to the first terminal 22a. Similarly, the second storage area 333b is an area for storing a terminal command (processing result data) to be transmitted to the second terminal 22b, and the third storage area 333c is a terminal command (to be transmitted to the third terminal 22c). Processing result data).

  The control unit 34 causes the communication unit 31 to transmit processing result data. Specifically, the control unit 34 determines whether the processing result data is voice data or a terminal command. Based on the determination result indicating whether or not the character string indicating the specified keyword is included in the recognition result text, and the determination result indicating whether the processing result data is voice data or a terminal command. Thus, the transmission destination of the processing result data is determined.

  Specifically, when the processing result data is voice data, and the character string indicating the specified keyword is not included in the recognition result text, the communication unit 31 sends the processing result data to the voice transmission smart speaker as in the first embodiment. Send. In addition, when the processing result data is voice data and the recognition result text includes a character string indicating a designated keyword, the communication unit 31 performs a voice transmission smart speaker and a designated smart speaker as in the first embodiment. Process result data is transmitted.

  On the other hand, when the processing result data is a command for a terminal and the character string indicating the specified keyword is not included in the recognition result text, the control unit 34 sets the connection terminal among the first storage area 333a to the third storage area 333c. The terminal command is stored in the corresponding storage area. When the communication unit 31 receives a request signal from the connection terminal, the control unit 34 reads the terminal command from the storage area corresponding to the connection terminal, and the communication unit 31 connects the terminal command read from the storage unit 33. Send to the terminal.

  In addition, when the processing result data is a terminal command and the recognition result text includes a character string indicating a specified keyword, the control unit 34 selects a connection terminal from among the first storage area 333a to the third storage area 333c. The terminal command is stored in the corresponding storage area and the storage area corresponding to the designated terminal. When the communication unit 31 receives a request signal from the connection terminal, the control unit 34 reads the terminal command from the storage area corresponding to the connection terminal, and the communication unit 31 connects the terminal command read from the storage unit 33. Send to the terminal. When the communication unit 31 receives a request signal from the designated terminal, the control unit 34 reads out a terminal command from the storage area corresponding to the designated terminal, and the communication unit 31 reads out the terminal command from the storage unit 33. Is sent to the specified terminal.

  Next, the first management table 331 and the second management table 332 will be described with reference to FIGS. 10 (a) and 10 (b). FIG. 10A illustrates the first management table 331 according to the second embodiment. FIG. 10B is a diagram illustrating the second management table 332 according to the second embodiment. As shown in FIG. 10A, the first management table 331 includes a smart speaker registration field 41 and a designated keyword registration field 42, as with the management table 331 described with reference to FIG.

  As illustrated in FIG. 10B, the second management table 332 includes a smart speaker registration field 101 and a terminal registration field 102. In the smart speaker registration column 101, smart speaker identification information is registered in the same manner as the smart speaker registration column 41 shown in FIG. In the terminal registration field 102, terminal identification information for identifying a terminal that can communicate with the server 3 is registered. The second management table 332 associates smart speaker identification information with terminal identification information.

  In the present embodiment, terminal identification information for identifying the first terminal 22 a to the third terminal 22 c is registered in the terminal registration field 102. The terminal identification information is arbitrarily determined and registered by the user. For example, when registering smart speaker identification information, a user can register terminal identification information in association with smart speaker identification information.

  The first terminal 22a to the third terminal 22c transmit their own terminal identification information when transmitting the request signal to the first server 3. Each of the first terminal 22a to the third terminal 22c stores its own terminal identification information. The first server 3 transmits the processing result data to the terminal that transmitted the request signal based on the terminal identification information received together with the request signal.

  Next, the configuration of the first terminal 22a will be described with reference to FIGS. FIG. 11 is a diagram illustrating a configuration of the first terminal 22a according to the second embodiment. As illustrated in FIG. 11, the first terminal 22a includes a first communication unit 221, a second communication unit 222, an output unit 223, a storage unit 224, and a control unit 225. In the present embodiment, the first terminal 22a is an information processing apparatus such as a notebook PC (personal computer) or a desktop PC. Alternatively, the first terminal 22a is a portable information processing device such as a tablet PC or a smartphone.

  The first communication unit 221 controls communication with the first server 3. The first communication unit 221 controls communication with the second server 4. The first communication unit 221 includes, for example, a LAN board or a wireless LAN board. In the present embodiment, the first communication unit 221 is an example of a second processing result data receiving unit. The first communication unit 221 is an example of a request signal transmission unit.

  Specifically, the first communication unit 221 transmits a request signal and the terminal identification information described with reference to FIG. 10B to the first server 3. The first communication unit 221 receives processing result data (terminal command) from the first server 3.

  Further, the first communication unit 221 transmits audio data and imaging data to the second server 4. Further, the first communication unit 221 receives audio data and imaging data from the second server 4.

  The second communication unit 222 controls communication with the first smart speaker 21a. The second communication unit 222 includes a wireless communication module that conforms to a near field communication standard such as Bluetooth (registered trademark). Alternatively, the second communication unit 222 may be a USB interface including a USB terminal, for example.

  The second communication unit 222 receives audio data from the first smart speaker 21a. The second communication unit 222 transmits audio data to the first smart speaker 21a. Further, the second communication unit 222 receives imaging data from the first smart speaker 21a.

  The output unit 223 outputs the imaging data to the first display device 23a. The output unit 223 is, for example, a digital video interface such as an HDMI (registered trademark) terminal or a display port. Note that the output unit 223 may be an analog video interface such as a D-SUB terminal.

  The storage unit 224 includes a semiconductor memory such as a RAM and a ROM. Furthermore, the storage unit 224 includes a storage device such as an HDD. The storage unit 224 stores a control program executed by the control unit 225. The storage unit 224 stores the terminal identification information described with reference to FIG. In the present embodiment, the storage unit 224 further stores web conference application software.

  The control unit 225 includes a processor such as a CPU or MPU. In addition, the control unit 225 controls the operation of the first terminal 22a based on the control program stored in the storage unit 224.

  Specifically, the control unit 225 periodically generates a request signal and transmits the request signal and the terminal identification information to the first server 3 via the first communication unit 221. For example, the control unit 225 transmits a request signal and connection terminal identification information via the first communication unit 221 every 30 seconds or every minute. In addition, when receiving the processing result data (terminal command) from the first server 3 via the first communication unit 221, the control unit 225 executes processing corresponding to the terminal command.

  For example, the terminal command may be a command for instructing the end of the web conference. When the terminal command is a command for instructing the end of the web conference, the control unit 225 stops the execution of the web conference application software. Alternatively, the terminal command may be a command for instructing execution of printing. When the terminal command is a command for instructing execution of printing, the control unit 225 requests the printer connected to the first terminal 22a to perform printing.

  Next, a process executed by the control unit 225 of the first terminal 22a based on the web conference application software will be described with reference to FIGS. The control unit 225 executes the web conference between the second terminal 22b of the second processing unit 2b and the third terminal 22c of the third processing unit 2c by executing the web conference application software.

  Specifically, the control unit 225 transmits audio data and imaging data received from the first smart speaker 21 a via the second communication unit 222 to the second server 4 via the first communication unit 221. As a result, the sound input to the first smart speaker 21a is output from the second smart speaker 21b of the second processing unit 2b and the third smart speaker 21c of the third processing unit 2c. In addition, the second display device 23b of the second processing unit 2b and the third display device 23c of the third processing unit 2c display images captured by the first smart speaker 21a.

  In addition, the control unit 225 transmits the audio data received from the second server 4 via the first communication unit 221 to the first smart speaker 21a via the second communication unit 222. As a result, the sound input from the second smart speaker 21b of the second processing unit 2b is output from the first smart speaker 21a. Further, the sound input from the first smart speaker 21a by the third smart speaker 21c of the third processing unit 2c is output.

  In addition, the control unit 225 outputs imaging data received from the second server 4 via the first communication unit 221 to the first display device 23a via the output unit 223. As a result, the first display device 23a displays the video imaged by the second smart speaker 21b of the second processing unit 2b and the video imaged by the third smart speaker 21c of the third processing unit 2c.

  The configuration of the first terminal 22a has been described above with reference to FIGS. Note that the configurations of the second terminal 22b and the third terminal 22c are the same as the configuration of the first terminal 22a, and thus description thereof is omitted.

  Subsequently, the operation of the first server 3 will be described with reference to FIGS. 7, 9, 10 (a), 10 (b), and 12. FIG. 12 is a flowchart illustrating the operation of the first server 3 according to the second embodiment. The operation shown in FIG. 12 starts when the communication unit 31 of the first server 3 receives audio data and smart speaker identification information.

  As shown in FIG. 12, when the communication unit 31 receives voice data and smart speaker identification information, the voice recognition unit 32 converts the voice data into text information in the same manner as the operation described with reference to FIG. The recognition result text is generated (step S21). In addition, when the communication unit 31 receives the audio data and the smart speaker identification information, the control unit 34 stores the smart speaker identification information received by the communication unit 31 in the storage unit 33 as a transmission destination of the processing result data (audio data). To do.

  When acquiring the recognition result text, the control unit 34 determines whether or not a specific command can be recognized from the recognition result text, similarly to the operation described with reference to FIG. 6 (step S22).

  When determining that the specific command can be recognized from the recognition result text (Yes in step S22), the control unit 34 stores the recognized specific command in the storage unit 33 as in the operation described with reference to FIG. (Step S23).

  When the control unit 34 stores the recognized specific command in the storage unit 33, the control unit 34 recognizes the specific command with reference to the first management table 331 stored in the storage unit 33, similarly to the operation described with reference to FIG. 6. It is determined whether or not the specified keyword can be recognized from the result text (step S24).

  When the control unit 34 determines that the designated keyword can be recognized from the recognition result text (Yes in step S24), the smart speaker identification information corresponding to the recognized designated keyword is obtained in the same manner as the operation described with reference to FIG. The processing result data (voice data) is stored in the storage unit 33 as a transmission destination (step S25).

  When the control unit 34 stores the smart speaker identification information in the storage unit 33, whether the specific command stored in the storage unit 33 is a command for acquiring voice data as the processing result data, or a terminal command as the processing result data. It is determined whether the command is to be acquired (step S26). Alternatively, if the control unit 34 determines that the specified keyword cannot be recognized from the recognition result text (No in step S24), is the specific command stored in the storage unit 33 a command for acquiring voice data as processing result data? Then, it is determined whether the command is a command for acquiring a terminal command as processing result data (step S26).

  When the control unit 34 determines that the specific command is a command for acquiring the voice data (“voice data” in step S26), the control unit 34 executes a process corresponding to the specific command to obtain the voice data (processing result data). Obtain (step S27). Or the control part 34 requests | requires execution of the process corresponding to a specific command to another server, and acquires audio | voice data (process result data) from another server (step S27).

  When acquiring the audio data (processing result data), the control unit 34 refers to the smart speaker identification information stored in the storage unit 33 as the transmission destination of the processing result data, and transmits the audio data (processing result data) to the communication unit 31. The transmission is performed (step S28), and the operation shown in FIG. Specifically, when the specified keyword can be recognized from the recognition result text (Yes in step S24), the first server 3 transmits voice data (processing result data) to the voice transmission smart speaker and the specified smart speaker. On the other hand, when the designated keyword cannot be recognized from the recognition result text (No in step S24), the first server 3 transmits voice data (processing result data) to the voice transmission smart speaker.

  On the other hand, when the control unit 34 determines that the specific command is a command for acquiring a terminal command (“command” in step S26), the control unit 34 executes a process corresponding to the specific command to execute a terminal command (processing result). Data) is acquired (step S29).

  When acquiring the terminal command (processing result data), the control unit 34 refers to the smart speaker identification information stored in the storage unit 33 as the transmission destination of the processing result data, and the second management table 332, and stores the first storage. The terminal command is stored in at least one of the areas 333a to 333c (step S30).

  When the communication unit 31 receives the request signal after storing the terminal command in the terminal storage area 333, the control unit 34 transmits the terminal command (processing result data) stored in the terminal storage area 333 to the communication unit 31. (Step S31), and the operation shown in FIG. Specifically, when the designated keyword can be recognized from the recognition result text (Yes in step S24), the first server 3 transmits a terminal command (processing result data) to the connection terminal and the designated terminal. On the other hand, when the designated keyword cannot be recognized from the recognition result text (No in step S24), the first server 3 transmits a terminal command (processing result data) to the connection terminal.

  If the control unit 34 determines that the specific command cannot be recognized from the recognition result text (No in step S22), it sets the error flag to ON as in the operation described with reference to FIG. 6 (step S32). Then, the voice data indicating the error message is transmitted to the communication unit 31 (step S28), and the operation shown in FIG. Specifically, the first server 3 transmits an error message (audio data) to the audio transmission smart speaker.

  Next, the operation of the first terminal 22a will be described with reference to FIG. 11 and FIG. FIG. 13 is a flowchart illustrating the operation of the first terminal 22a according to the second embodiment. The operation shown in FIG. 13 is periodically executed.

  Specifically, as shown in FIG. 13, the control unit 225 transmits a request signal to the first server 3 via the first communication unit 221 (step S41). After transmitting the request signal, the control unit 225 determines whether or not the first communication unit 221 has received a terminal command from the first server 3 (step S42). When the control unit 225 determines that the first communication unit 221 has received the terminal command (Yes in step S42), the control unit 225 executes processing corresponding to the received terminal command (step S43), and the operation illustrated in FIG. Exit. Or if the control part 225 and the 1st communication part 221 determine with not receiving the command for terminals (No of step S42), the operation | movement shown in FIG. 13 will be complete | finished.

  Note that the control unit 225 of the second terminal 22b and the control unit 225 of the third terminal 22c also perform the same operation as the control unit 225 of the first terminal 22a.

  The second embodiment of the present invention has been described above with reference to FIGS. According to this embodiment, in addition to the processing unit that has transmitted the audio data to the server, a processing unit other than the processing unit that has transmitted the audio data to the server can also receive the processing result. For example, when the user of the first processing unit 2a (first terminal 22a) utters a voice indicating an activation command and then utters a voice prompting the end of the web conference and a voice indicating the point B within a predetermined period. The first terminal 22a and the second terminal 22b stop executing the web conference application. Alternatively, after the user of the first processing unit 2a (first terminal 22a) utters a voice indicating an activation command, a voice prompting the end of the web conference and a voice indicating “all” are uttered within a predetermined period. Then, the first terminal 22a to the third terminal 22c stop executing the web conference application.

  In the present embodiment, the configuration in which the first smart speaker 21a to the third smart speaker 21c include the imaging unit 216 has been described, but the first terminal 22a to the third terminal 22c may include an imaging unit. Alternatively, a camera device may be connected as a peripheral device to the first terminal 22a to the third terminal 22c.

  In the present embodiment, the information processing system 1 is a web conference system, but the information processing system 1 may be a video conference system or a telephone conference system. In this case, the first terminal 22a to the third terminal 22c are connected via a LAN.

  When the information processing system 1 is a video conference system or a telephone conference system, the second server 4 can be omitted. Further, when the information processing system 1 is a telephone conference system, the first terminal 22a to the third terminal 22c may be microphone / speaker devices dedicated to the telephone conference. When the information processing system 1 is a telephone conference system, the first display device 23a to the third display device 23c can be omitted.

  Further, in the present embodiment, the configuration in which the first processing unit 2a to the third processing unit 2c include the first terminal 22a to the third terminal 22c has been described, but the first smart speaker 21a to the third smart speaker 21c are the first. You may have the function of the terminal 22a-the 3rd terminal 22c. In this case, the first terminal 22a to the third terminal 22c may be omitted.

  The first and second embodiments of the present invention have been described above with reference to the drawings. However, the present invention is not limited to the above-described embodiment, and can be implemented in various modes without departing from the gist thereof.

  For example, in the embodiment according to the present invention, the information processing system 1 includes three processing units, but the information processing system 1 may include two processing units or four or more processing units.

  In the embodiment according to the present invention, the control unit 215 of the first smart speaker 21a to the third smart speaker 21c transmits the user voice to the server 3 after a predetermined period has elapsed. The control unit 215 of the 3 smart speaker 21c may transmit the user voice to the server 3 before a predetermined period elapses. Specifically, when the control unit 215 of the first smart speaker 21a to the third smart speaker 21c stores the sound data in the storage unit 214 a predetermined number of times (for example, twice), the sound data stored in the storage unit 214 is stored. May be transmitted to the server 3.

  The present invention is useful for a system using a voice input / output terminal such as a smart speaker.

DESCRIPTION OF SYMBOLS 1 Information processing system 2a 1st processing unit 2b 2nd processing unit 2c 3rd processing unit 3 Server 21a 1st smart speaker 21b 2nd smart speaker 21c 3rd smart speaker 22a 1st terminal 22b 2nd terminal 22c 3rd terminal 31 Communication Unit 32 Voice recognition unit 34 Control unit 211 Voice input unit 213 Communication unit 215 Control unit 221 First communication unit 333 Terminal storage area 333a First storage area 333b Second storage area 333c Third storage area

Claims (8)

An information processing system comprising a plurality of processing units,
The processing unit is
A voice input unit for inputting a first voice indicating a specific command and a second voice specifying at least one of the plurality of processing units;
An audio data generation unit that generates first audio data corresponding to the first audio and second audio data corresponding to the second audio;
An audio data transmission unit for transmitting the first audio data and the second audio data to a server;
And at least one processing result data receiving unit for receiving processing result data from the server,
The processing result data indicates an execution result of processing corresponding to the specific command,
Information processing in which the processing unit that has transmitted the first audio data and the second audio data and the processing unit that is specified by the second audio data among the plurality of processing units receive the processing result data. system. The processing unit includes a voice input / output terminal,
The information processing system according to claim 1, wherein the voice input / output terminal includes the voice input unit, the voice data generation unit, the voice data transmission unit, and the processing result data reception unit. The processing unit includes a voice input / output terminal and an information processing terminal,
The voice input / output terminal includes the voice input unit, the voice data generation unit, and the voice data transmission unit,
The information processing system according to claim 1, wherein the information processing terminal includes the processing result data receiving unit. The at least one processing result data receiving unit includes a first processing result data receiving unit and a second processing result data receiving unit,
The processing unit includes a voice input / output terminal and an information processing terminal,
The voice input / output terminal includes the voice input unit, the voice data generation unit, the voice data transmission unit, and the first processing result data reception unit.
The information processing system according to claim 1, wherein the information processing terminal includes the second processing result data receiving unit. The information processing terminal
A control unit that generates a request signal for requesting the server to transmit data;
The information processing system according to claim 3, further comprising: a request signal transmission unit configured to transmit the request signal to the server. The information processing system includes the server,
The server
An audio data receiving unit for receiving the first audio data and the second audio data;
A voice recognition unit that converts the first voice data and the second voice data into text information;
A control unit for obtaining the processing result data based on the text information;
A processing result data transmitting unit for transmitting the processing result data,
The processing result data transmission unit transmits the processing result data to the processing unit that has transmitted the first audio data and the second audio data and the processing unit that is specified by the second audio data. The information processing system according to any one of claims 1 to 5. The server has a storage area corresponding to each of the plurality of processing units;
The control unit of the server includes a storage area corresponding to the processing unit that has transmitted the first audio data and the second audio data, and the processing unit specified by the second audio data. The information processing system according to claim 6, wherein the processing result data is stored in a storage area corresponding to. Inputting a first voice indicating a specific command and a second voice specifying at least one of the plurality of processing units;
Generating first audio data corresponding to the first audio and second audio data corresponding to the second audio;
Transmitting the first audio data and the second audio data to a server;
The processing unit that has transmitted the first audio data and the second audio data and the processing unit that is specified by the second audio data among the plurality of processing units receives processing result data from the server. Including and
The information processing method, wherein the processing result data indicates an execution result of processing corresponding to the specific command.

Images