JP6351987B2 - Speech control device, speech device, speech control system, speech control method, speech device control method, and control program - Google Patents

Description

  The present invention relates to an utterance device that utters voice to a user, an utterance control device that causes an utterance device to utter, and the like.

  In recent years, speech devices such as robots that speak in response to user calls and the like have been widely spread and improved. For example, Japanese Patent Application Laid-Open Publication No. 2004-228620 describes that robot operation information is distributed from a broadcast station together with video information. Then, from a receiver that is a separate device from the TV, video information is output to the TV, and an operation command based on the operation information is output to the robot, thereby allowing the robot owned by the viewer to interact with the broadcast program. Is described.

JP 2003-169305 A (released on June 13, 2003)

  Here, in the above prior art, before outputting the video information to be displayed on the television to the receiver, the receiver is a device different from the television to synchronize the video information with the operation of the robot. Yes. That is, the television broadcast image information is not received directly but received via the receiver.

  With such a configuration, the video output on the television is delayed as compared with the case where no receiver is used. Also, when switching TV channels, it is necessary to cause the receiver to switch the output video, and it is necessary to perform control different from normal channel switching. In other words, the above-described prior art has a problem that the receiver that controls the robot needs to transmit and output the video to the television in order to synchronize the video information to be displayed on the television and the operation of the robot. It was.

  The present invention has been made in view of this problem, and an object of the present invention is to utter an utterance corresponding to the content being output by the output device without transmitting content such as video information to the output device such as a television. An object of the present invention is to provide an utterance control device or the like that can be performed by a device.

  In order to solve the above-described problem, an utterance control device according to an aspect of the present invention is an utterance control device that causes an utterance device having an utterance function by voice to speak, and is used as an apparatus used together with the utterance device. An output device associated with the utterance device specifies content that is received and output from a device other than the utterance control device, and content corresponding to the content specified by the content specification device. Utterance control means for causing the apparatus to utter.

  In order to solve the above-described problem, an utterance device according to one aspect of the present invention is an utterance device having a speech utterance function, and is associated with the utterance device as a device used together with the utterance device. Content specifying means for specifying the content received and output by the output device, and utterance means for uttering the content according to the content specified by the content specifying means.

  In order to solve the above problems, an utterance control system according to an aspect of the present invention is an utterance control system that causes an utterance device having a speech function by voice to utter, and is used together with the utterance device. The content specifying device for specifying the content received and output from a device other than the speech control device that causes the output device associated with the speaking device to speak, and the content specified by the content specifying device The utterance control device that causes the utterance device to utter with the content corresponding to the utterance device, and the utterance device.

  In order to solve the above problem, an utterance control method according to one aspect of the present invention is an utterance control method for uttering an utterance device having an utterance function by voice, and is used together with the utterance device. The output device associated with the utterance device as specified in the content specification step for specifying the content received and output from a device other than the utterance control device that utters the utterance device, and the content specification step An utterance control step of causing the utterance device to utter with a content corresponding to the content.

  And in order to solve said subject, the control method of the speech apparatus which concerns on 1 aspect of this invention is a control method of the speech apparatus provided with the speech function by voice, Comprising: As an apparatus used with the said speech apparatus A content specifying step for specifying the content received and output by the output device associated with the speech device; and an utterance step for speaking with a content corresponding to the content specified in the content specifying step.

  According to each aspect of the present invention, there is an effect that the utterance device can make the utterance according to the content being output by the output device without transmitting the content to the output device.

It is a block diagram which shows the principal part structure of the speech control server which concerns on Embodiment 1 of this invention, and a dialogue apparatus. It is a figure which shows the outline | summary of the dialog system containing the said speech control server and a dialog apparatus. It is a figure which shows an example of the information for producing | generating the utterance content according to a program. It is a figure which shows an example of a program-utterance content corresponding information. It is a figure which shows an example of TV-viewing program corresponding information. It is a figure which shows the data used in order to specify the response | compatibility with the said interactive apparatus and the program currently output on TV. It is a figure which shows an example of speech management information. It is a flowchart which shows an example of the speech content production | generation process which the said speech control server performs. It is a flowchart which shows an example of the viewing-and-listening information transmission process which the said TV performs, and the viewing-and-listening program registration process which the said speech control server performs. It is a flowchart which shows an example of the speech control process which the said speech control server performs, and the speech process which the said dialogue apparatus performs. It is a figure which shows the outline | summary of the dialogue system which concerns on Embodiment 2 of this invention. It is a flowchart which shows an example of the utterance content production | generation process which a program information collection server performs, and the utterance content registration process which a TV information collection server performs. It is a flowchart which shows an example of the utterance content transmission process which the said TV information collection server performs, and the utterance control process which an utterance control server performs. It is a figure which shows the outline | summary of the dialogue system which concerns on Embodiment 3 of this invention. It is a flowchart which shows an example of the viewing-and-listening program notification process which a TV information collection server performs, the utterance content production | generation process which a program information collection server performs, and the utterance control process which an utterance control server performs. It is a figure which shows the outline | summary of the dialogue system which concerns on Embodiment 4 of this invention. It is a flowchart which shows an example of the viewing-and-listening program registration process and speech control process which an speech control server performs. It is the block diagram which illustrated the composition of the computer which can be used as each above-mentioned server or the above-mentioned dialog device.

Embodiment 1
Hereinafter, Embodiment 1 of the present invention will be described in detail with reference to FIGS. First, the outline | summary of the dialogue system which concerns on this embodiment is demonstrated based on FIG. FIG. 2 is a diagram showing an outline of the dialogue system (speech control system) 5.

  As shown in the figure, the dialogue system 5 includes an utterance control server (speech control device) 1 and a dialogue device (speech device) 3. The utterance control server 1 is a server that controls the dialog device 3 to perform a predetermined utterance, and the dialog device 3 utters according to the control of the utterance control server 1 to interact with the user by voice. In addition, in the same figure, although the dialogue apparatus 3 has shown the example which is a self-propelled cleaning robot which cleans a floor automatically, it may be equipped only with the speech function and is equipped with arbitrary functions other than speech. May be. That is, the dialogue apparatus 3 only needs to have a function of uttering (outputting voice) according to the control of the utterance control server 1.

  The main feature of the dialogue system 5 is that the utterance control server 1 causes the dialogue device 3 to utter with contents corresponding to a program being viewed on a TV (television receiver, output device) 500. More specifically, the utterance control server 1 receives viewing program information indicating a program output from the TV 500 and a TV ID for identifying the TV 500 from the TV 500. Then, the utterance control server 1 notifies the dialog device 3 previously associated with the TV indicated by the received TVID and utters the utterance content corresponding to the program indicated by the received viewing program information. As a result, it is possible to cause the dialogue apparatus 3 to utter the content according to the program that the user is viewing without transmitting the video of the program from the utterance control server 1 to the dialogue apparatus 3.

  In the figure, for simplicity, only one TV 500 and one interactive device 3 are shown. However, the utterance control server 1 utters the conversation apparatus 3 corresponding to the TV 500 with the contents corresponding to the program output by each TV 500 even when there are a plurality of pairs of the conversation apparatus 3 and the TV 500. Can be made.

[Configuration details]
Next, the details of the configuration of each device included in the interactive system 5 will be described with reference to FIG. FIG. 1 is a block diagram showing a main configuration of the utterance control server 1 and the dialogue apparatus 3. In the figure, the main configuration of the TV 500 that is not a component of the dialogue system 5 is also shown.

[Main Configuration of Speech Control Server 1]
As shown in the figure, the utterance control server 1 includes a server storage unit 10 that stores various data used in the utterance control server 1 and a server control unit 20 that controls the utterance control server 1 in an integrated manner. The utterance control server 1 includes blocks such as a communication unit for controlling the interactive device 3 and accessing information on the Internet and an input unit for inputting data to the utterance control server 1. These blocks are not shown.

  The server storage unit 10 includes a program information table 11, an advertisement search information table 12, a program search information table 13, a TV-viewing program correspondence information 14, a program-utterance content correspondence information 15, and a TV-interactive device correspondence information (correspondence information). 16 and utterance management information 17 are stored. The server control unit 20 also includes a program information acquisition unit 21 (sponsor specifying means), a related information acquisition unit (related information acquisition unit) 22, a viewing program information acquisition unit (content specification unit) 23, and an utterance content generation unit (utterance content). Generating means) 24, utterance target specifying unit (speech target specifying means) 25, and utterance control unit (speech control means) 26.

  The program information table 11, the advertisement search information table 12, and the program search information table 13 are information for generating utterance contents corresponding to a program, and may be data as shown in FIG. 3, for example. FIG. 3 is a diagram illustrating an example of information for generating utterance contents corresponding to a program.

  FIG. 3A shows an example of the program information table 11. The program information table 11 is a table in which a program ID for identifying a program is associated with the start time and end time of the program. By referring to the program information table 11, it is possible to specify the currently broadcast program and the end time of the program. Therefore, it is possible to generate the utterance content about the program before or after the broadcast, It is possible to set the utterance timing according to the end time. For example, it is possible to generate utterance content that tells the user that the program will start five minutes before the broadcast start time. Also, for example, it is possible to make an utterance about the program 5 minutes after the broadcast end time of the program, and to set the expiration date of the utterance content at or near the broadcast end time. If such utterance control is unnecessary, the information on the start time and end time is omitted, and only the program ID of the program being broadcast may be registered.

  FIG. 3B shows an example of the program search information table 13. The program search information table 13 is a table in which a program ID for identifying a program is associated with a search keyword used for searching related information of the program. By referring to the program search information table 13, related information of each program (hereinafter also referred to as program related information) can be detected by keyword search.

  FIG. 3C shows an example of the advertisement search information table 12. The advertisement search information table 12 is a table in which a program ID for identifying a program, a genre of the program, and a sponsor ID indicating a sponsor of the program are associated with each other. By referring to the advertisement search information table 12, it is possible to generate the utterance content related to the advertisement corresponding to each program or its sponsor. For example, by using the genre included in the advertisement search information table 12, the advertisement corresponding to the genre of the program is specified from the advertisements stored in advance in the utterance control server 1 or other devices, and the advertisement is set as the utterance content. can do. Further, for example, by using the sponsor ID included in the advertisement search information table 12, the advertisement of the sponsor of the program is specified as the utterance content among the advertisements stored in advance in the utterance control server 1 or other devices. be able to.

  Furthermore, the content of the utterance can be determined using the advertisement search information table 12 and the advertisement sponsor management table as shown in FIG. The advertisement sponsor management table shown in (d) of FIG. 3 is a table in which a sponsor ID, a sponsor name of a sponsor specified by the ID, and an utterance content are associated with each other. By referring to the advertisement search information table 12 and the advertisement sponsor management table, the utterance content corresponding to the sponsor of the program can be generated.

  For example, in the example of FIG. 3D, the sponsor name “Sponsor 1” and the utterance content “Advertisement of Sponsor 1” are associated with SP0001. As a result, the user of the television 500 outputting the program whose sponsor is SP0001 can be uttered by the dialogue device 3 as “Advertisement of sponsor 1”. The content of the utterance may be a content desired by the sponsor, and may be a PR of the sponsor, its product, service, or the like. Further, if the time at which each sponsor's commercial is broadcast is known, the above-mentioned utterance can be performed in accordance with the broadcast time. In addition, in FIG. 3D, an advertisement that does not target a specific sponsor, such as a record that includes “general-purpose” in the sponsor name, may be used as the utterance content.

  In addition, when making an utterance content into an advertisement, it is good also as an utterance content which publicizes the goods and service which appear in a program. For example, the utterance content that publicizes the area, the store, the clothes and the decorations worn by the performers appearing in the program may be generated. In this case, a person who wants to publicize the area, store, performer's clothes and decorations that appear in the program generates such utterance content and registers it in the utterance control server 1 in association with the program. Or just send.

  The program-utterance content correspondence information 15 is information in which the utterance content generated by the utterance content generation unit 24 is associated with the program corresponding to the utterance content, and is generated by the utterance content generation unit 24. Further, the program-utterance content correspondence information 15 may include information for designating the timing of speaking with the speech content.

  For example, the program-utterance content correspondence information 15 may be data as shown in FIG. FIG. 4 is a diagram showing an example of the program-utterance content correspondence information 15. The illustrated program-utterance content correspondence information 15 is a table in which a program ID for identifying a program, an utterance content, and an utterance timing are associated with each other, and each record is numbered sequentially. As a result, it is possible to specify the utterance content corresponding to the program and the timing at which the utterance should be uttered based on the utterance content. Note that “immediately” in the figure indicates that the user speaks as soon as it becomes possible to speak without waiting for a specific time.

  The TV-viewing program correspondence information 14 is information that associates the TV 500 with the program being output by the TV 500. The TV-viewing program correspondence information 14 is generated by the viewing program information acquisition unit 23 and is updated when the program output by the TV 500 is switched.

  For example, the TV-viewing program correspondence information 14 may be data as shown in FIG. FIG. 5 is a diagram illustrating an example of the TV-viewing program correspondence information 14. The illustrated TV-viewing program correspondence information 14 is a table in which a TV ID for identifying the TV 500 and a program ID of a program being output by the TV 500 identified by the TV ID are associated with each other. Numbered. Thereby, even when there are a plurality of TVs 500, it is possible to specify a program being output by each TV 500.

  The TV-interactive device correspondence information 16 is information indicating the interactive device 3 associated with the TV 500. The utterance control server 1 is a server that controls the utterance of the dialog device 3, and can specify the dialog device 3 to be controlled. Therefore, the TV-interactive device correspondence information 16 can be generated by receiving registration of the TV 500 used in the same room as the interactive device 3 from, for example, the user of the interactive device 3.

  The TV-interactive device correspondence information 16 may be data as shown in FIG. FIG. 6 is a diagram showing data used to identify the correspondence between the interactive device 3 and the program being output on the TV 500, (a) shows an example of the TV-interactive device correspondence information 16, (b) An example of interactive apparatus-viewing program correspondence information is shown. The illustrated TV-interactive device correspondence information 16 is a table in which a TV ID for identifying the TV 500 and an interactive device ID for identifying the interactive device 3 are associated with each other, and each record is numbered sequentially. . As a result, even when there are a plurality of TVs 500, it is possible to specify the interactive devices 3 corresponding to the TVs 500 (used together with the TVs 500).

  Here, it is assumed that the program-utterance content correspondence information 15 in which the program ID indicating the program being output by the TV 500 and the speech content are associated as shown in FIG. 4 is used. Therefore, using the TV-viewing program correspondence information 14 and the TV-dialogue device correspondence information 16, the correspondence between the program being output by the TV 500 and the dialogue device 3 corresponding to the TV500 is specified. Therefore, instead of storing the TV-viewing program correspondence information 14, interactive device-viewing program correspondence information as shown in FIG. 6B may be stored.

  The utterance management information 17 is management information for causing the dialogue apparatus 3 to utter, and is generated and updated by the utterance control unit 26. The utterance management information 17 may be data as shown in FIG. 7, for example. FIG. 7 is a diagram illustrating an example of the utterance management information 17. In the illustrated utterance management information 17, an interactive device ID for identifying the interactive device 3 to be uttered, an utterance content, an assumed response to the utterance content, a secondary utterance to the assumed response, and an expiration date are associated with each other. It is a table, and each record is numbered sequentially.

  The assumed response is registered in advance assuming the user's response content to the utterance content. The secondary utterance indicates the utterance content to be uttered by the dialogue apparatus 3 when the user makes an assumed response. “Generic” in the assumed response and the secondary utterance means that a specific assumed response or secondary utterance is not set, and after the assumed response and the secondary utterance are uttered with the utterance content of “general” The dialogue apparatus 3 makes a predetermined response according to the user's utterance content. The expiration date indicates a time limit for performing the utterance of the corresponding record, and no utterance instruction based on a record for which no utterance instruction has been issued even after this time limit has passed.

  By referring to such utterance management information 17, it is possible to cause each of the plurality of interactive devices 3 to make an utterance corresponding to the program being output by the TV 500 associated with each interactive device 3. Further, when the user makes an assumed response to the dialogue apparatus 3, the dialogue apparatus 3 can be caused to make a secondary utterance.

  The program information acquisition unit 21 acquires program information indicating a program being broadcast. For example, the program information acquisition unit 21 may specify a program broadcast at the current time from an EPG (Electronic Program Guide) and acquire it as the program information. The EPG may be acquired from a broadcast wave, the Internet, or the like, or may be manually input by the administrator of the speech control server 1 and acquired by the program information acquisition unit 21. Further, the program information acquisition unit 21 generates a program information table 11 including the acquired program information and stores it in the server storage unit 10. Further, the program information acquisition unit 21 generates the advertisement search information table 12 and the program search information table 13 using information indicating the performers, genres, and sponsors of the program included in the EPG and stores them in the server storage unit 10. To do. Note that these tables may be generated by other devices. Further, the program information acquisition unit 21 may acquire program information including a program that is not being broadcast (a program after the broadcast ends or a program that will be broadcast in the future).

  The related information acquisition unit 22 acquires the program related information of each program indicated in the program information acquired by the program information acquisition unit 21 by performing a predetermined search process. Specifically, the related information acquisition unit 22 acquires program related information by performing a search on a search site or the like using a search keyword included in the program search information table 13. Since the EPG includes information related to the program such as the performer in addition to the program name, the EPG may be searched to acquire the program related information. Of course, the program related information may be obtained from any information source.

  Further, the related information acquisition unit 22 detects that a predetermined event has occurred and notifies the utterance content generation unit 24 of it. In each event, the utterance content is registered in advance, so that when the event occurs, the dialog device 3 can utter the content according to the event. The occurrence of an event can be detected by determining whether or not a predetermined condition for each event is satisfied.

  For example, recently, a comment on a program being broadcast has been posted on a short text posting site or the like. In such a site, many comments having the same or similar contents may be posted in a specific scene of a specific program. For example, it is known that words in a scene of a famous movie are posted by many users at the timing when the scene is broadcast. Therefore, in the short posting site, it may be detected as the event that a predetermined number of specific comments are posted within a predetermined time. In this case, by registering the specific comment as the utterance content corresponding to this event, it is possible to cause the dialogue apparatus 3 to utter in conjunction with posting to the short sentence posting site. Moreover, when making the above-mentioned specific comment into utterance content, the word with high appearance frequency may be extracted from the posted comment, and the utterance content containing this word may be produced | generated. As a result, it is possible to automatically generate the utterance contents corresponding to the contents written at that time on the short text posting site.

  Further, it may be detected as an event that a predetermined time has elapsed from the broadcast start time of the program (or that the remaining time until the broadcast end time has reached a predetermined time). For example, in a program in which a specific line is described at the end of the program, when such an event is set and occurrence of the event is detected (detected that a predetermined time has elapsed from the broadcast start time) ), You can also speak that line. In this configuration, it may be difficult to completely match the timing at which the dialogue is described in the program with the timing at which the dialogue apparatus 3 utters the dialogue. Therefore, in order to cope with such a case, a response indicating that the timing of the speech is bad (too early or too late) is registered as an assumed response, and as a secondary utterance, for example, content that apologizes for poor timing You may register utterances.

  In addition, using information terminals such as data broadcasting and smartphones, collecting information reflecting user's feelings on the broadcasted program is performed. Therefore, the utterance content may be determined using such information. For example, when the number of data receptions from the information terminal possessed by each viewer is used as an index indicating the degree of excitement of the program, it is detected as the event that the total number of data receptions has reached a predetermined number of times, and the program You may be asked to speak about the excitement. It is also possible to make an utterance according to the excitement of the program, taking into account the genre of the program. For example, if the genre of the program is “Comedy” or “Variety”, it is related to the excitement of the game such as “Let ’s laugh” or “Sports” if the program genre is “Sports” Utterances can be made. Further, utterances corresponding to the number of data receptions in the program may be performed after the broadcast of the program ends or near the end time. For example, if the number of times is greater than or equal to the predetermined number, make a positive utterance such as “It was a good game” or “It was interesting”, and if it has not reached the predetermined number, “I wanted you to do a little more hard” Negative utterances may be made.

  The viewing program information acquisition unit 23 acquires viewing program information (program ID) indicating a program that the user of the dialogue apparatus 3 is viewing. Specifically, the viewing program information acquisition unit 23 receives TVID and viewing program information indicating the program of the program being output from the TV 500 associated with the dialogue apparatus 3. Then, the viewing program information acquisition unit 23 associates the program ID specified from the received viewing program information with the received TVID, and stores it in the server storage unit 10 as TV-viewing program correspondence information 14.

  Note that the viewing program information is not particularly limited as long as it is information indicating the program of the program that is being output by the TV 500. Here, an example in which the viewing program information is information indicating the user's operation performed on the TV 500 will be described. . The operation contents of the user are assumed to be, for example, power ON / OFF operation, music selection operation, channel sending (returning) operation, and the like, and the TV 500 outputs the viewing program information indicating such operation contents. It is possible to specify the program inside. The program ID may be any program ID that can uniquely identify the program, and may be set by the viewing program information acquisition unit 23 or may be an ID used in EPG or the like. Further, the program being output on the TV 500 side may be specified, and information indicating the specified program (for example, program ID) may be transmitted to the utterance control server 1.

  The utterance content generation unit 24 generates utterance content corresponding to each program indicated in the program information acquired by the program information acquisition unit 21, associates the generated utterance content with the program ID, and shows program-utterance content correspondence information. 15 is stored in the server storage unit 10. The utterance content to be generated is not particularly limited as long as it is related to the program. For example, the utterance content is generated by incorporating the program related information acquired by the related information acquisition unit 22 into the standard sentence, using the above-described advertisement sponsor management table, or incorporating the program title or performer into the standard sentence. May be. Moreover, the utterance content may be registered in advance in the utterance control server 1 or another device. For example, the utterance content for each genre may be registered in advance, and the utterance content corresponding to the genre of the program may be acquired from the registered utterance content. Further, for example, the utterance content for each program may be registered and used. Furthermore, the utterance content may be related to the back program. For example, as an utterance content of a certain program, an utterance introducing a back program such as “The program XX is being broadcast in the back program now” Content may be generated. The back program can be specified by referring to EPG or the like.

  Furthermore, the utterance content generation unit 24 may determine the utterance timing for each generated utterance content. The utterance timing may be in accordance with the start and end times of the program included in the program information table 11. In the dialog system 5, since the program being viewed on the TV 500 is detected and uttered, the utterance timing is basically “immediate”. For this reason, determination of the utterance timing may be omitted.

  The utterance target specifying unit 25 specifies the dialog device 3 that utters the utterance content generated by the utterance content generation unit 24. Specifically, the utterance target specifying unit 25 refers to the program-utterance content correspondence information 15, extracts a record at the utterance timing, and specifies a program ID included in the record. Then, with reference to the TV-viewing program correspondence information 14 and the TV-dialogue device correspondence information 16, the dialogue device 3 corresponding to the identified program ID is identified, and the list of the identified dialogue devices 3 is set as the utterance control unit 26. Notify

  The utterance control unit 26 uses the conversation contents 3 (the conversation apparatus identified by the utterance target identification unit 25) with the utterance contents generated in advance by the utterance content generation unit 24 according to the program being output by the TV 500 specified by the viewing program information acquisition unit 23. Let 3) speak. Specifically, the utterance control unit 26 generates the utterance management information 17 from the list of the dialog devices 3 notified from the utterance target specifying unit 25 and the program-utterance content correspondence information 15. Then, utterance data (voice data) corresponding to the utterance content is generated, and the utterance data and the utterance instruction are transmitted to the dialogue device 3 in accordance with the generated utterance management information 17.

[Configuration of main part of the dialogue apparatus 3]
As shown in FIG. 1, the dialogue device 3 includes a dialogue device control unit 30 that controls the dialogue device 3 in an integrated manner, a voice output unit 40 that outputs voice, and a storage unit that stores various data used in the dialogue device 3. 41 and a voice input unit 42 for receiving voice input. The interactive device control unit 30 includes an utterance unit (speech means) 31, a response generation unit 32, and an analysis unit 33.

  The utterance unit 31 causes the dialogue apparatus 3 to utter by causing the voice output unit 40 to output the utterance data received from the utterance control server 1. In addition, when the utterance unit 31 receives information indicating the content of the assumed response and the utterance data of the secondary utterance from the utterance control server 1, the utterance unit 31 stores these data in the storage unit 41.

  The response generation unit 32 performs control for responding to the user's call to the dialogue apparatus 3. For example, when the call from the user is an assumed response, the utterance unit 31 is controlled to utter the utterance data of the secondary utterance corresponding to the assumed response. When a call that is not an assumed response is made, a response content corresponding to the content of the call is generated, and the utterance unit 31 is uttered with the generated content.

  The analysis unit 33 analyzes the content of the user's call to the dialogue device 3. Specifically, the analysis unit 33 recognizes the voice input to the voice input unit 42 and notifies the response generation unit 32 of the recognition result.

[Main part of TV500]
The TV 500 includes a viewing program information transmission unit 501 as illustrated. Note that the TV 500 includes a communication unit for transmitting information to the utterance control server 1 and various configurations for receiving and outputting TV programs, but is not shown in FIG.

  The viewing program information transmission unit 501 transmits viewing program information indicating the program being output by the TV 500 to the utterance control server 1. Specifically, the viewing program information transmission unit 501 transmits viewing program information indicating the user's operation details performed on the TV 500. As described above, the viewing program information is not limited to this example.

[Flow of utterance content generation processing]
Next, the flow of the utterance content generation process will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of utterance content generation processing executed by the utterance control server 1. First, the program information acquisition unit 21 acquires program information of a program being broadcast (S1), and stores the acquired program information as the program information table 11 in the server storage unit 10. Further, the program information acquisition unit 21 generates the program search information table 13 and the advertisement search information table 12 and stores them in the server storage unit 10.

  Next, the related information acquisition unit 22 searches for the program related information using the stored program search information table 13 (S2), and notifies the utterance content generation unit 24 of the detected program related information. Further, the related information acquisition unit 22 determines whether or not the event condition is satisfied (S3), and if there is an event that satisfies the condition, notifies the utterance content generation unit 24 of the event.

  Then, the utterance content generation unit 24 uses the program related information notified from the related information acquisition unit 22 and the advertisement search information table 12 stored in the server storage unit 10 to determine each program included in the program information table 11. Corresponding utterance content is generated (S4). If an event that satisfies the condition is notified, the utterance content corresponding to the event is generated. When the advertisement sponsor management table (see FIG. 3D) is stored in advance or acquired from the outside, the utterance content generation unit 24 uses the advertisement sponsor management table and the advertisement search information table 12. To generate utterance content.

  Finally, the utterance content generation unit 24 associates the utterance content generated in S4 with information specifying the timing of utterance with the utterance content, and stores it in the server storage unit 10 as program-utterance content correspondence information 15. (S5). Thereby, the utterance content generation process ends. Since the program being broadcast changes from time to time, the utterance control server 1 executes the processing of the above-described flow every predetermined time.

[Flow of viewing information transmission processing and viewing program registration processing]
Next, the flow of viewing information transmission processing and viewing program registration processing will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of viewing information transmission processing executed by the TV 500 and viewing program registration processing executed by the speech control server 1.

  In the viewing information transmission process, the viewing program information transmission unit 501 of the TV 500 transmits viewing program information and TVID to the utterance control server 1 when receiving a user operation on the TV 500 (S21) (S22). These processes are continuously performed during the operation of the TV 500. Note that the viewing program information transmission unit 501 transmits viewing program information and TVID even when it is detected that a user operation is not detected for a predetermined period of time. In this case, the content of the last detected user operation is transmitted as viewing program information.

  In the viewing program registration process, the viewing program information acquisition unit 23 of the utterance control server 1 receives the transmitted viewing program information and TVID (S31, content specifying step). Then, it is determined from the received viewing program information whether the TV program specified by the TVID is viewing a TV program (S32). Specifically, when viewing program information indicating that an operation to turn off the TV is performed or an operation to switch to an external output other than a TV program is received, the TV program is being viewed. Judge that there is no. Note that it may be determined that the TV program is not being watched even when reception of the viewing program information and TVID from the TV 500 is not detected for a certain period of time. As a result, it is possible to determine that the TV program is not being watched even when the TV 500 is not operated, such as the power cord of the TV 500 being disconnected, but the TV viewing is ended. The end time of the program may be specified with reference to the program information table 11, and it may be determined that the program is not being viewed if that time has passed.

  If it is determined that the program is not being viewed (NO in S32), the viewing program information acquisition unit 23 receives the TVID received in S31 from the TV-viewing program correspondence information 14 stored in the server storage unit 10. Delete the record. That is, for the TV 500 that has not output the program, the association between the TVID and the program is released. Thereafter, the viewing program information acquisition unit 23 enters a waiting state for receiving new viewing program information and TVID. If the TVID record received in S31 is not included in the TV-viewing program correspondence information 14, the process of S33 is omitted.

  On the other hand, when it is determined that the TV program is being viewed (YES in S32), the viewing program information acquisition unit 23 reads the TV-viewing program correspondence information 14 from the server storage unit 10 (S34), and the TVID received in S31. It is confirmed whether or not a record including is registered (S35).

  Here, when it is confirmed that it is not registered (YES in S35), the process proceeds to S37. On the other hand, when it is confirmed that it is registered (NO in S35), the viewing program information acquisition unit 23 deletes the TVID record received in S31 from the TV-viewing program correspondence information 14, and the process of S37 Proceed to

  In S37, the viewing program information acquisition unit 23 registers a record in which the program ID of the program identified from the viewing program information received in S31 and the TVID received in S31 are associated with the TV-viewing program correspondence information 14 ( S37). Thereafter, the viewing program information acquisition unit 23 enters a waiting state for receiving new viewing program information and TVID.

[Flow of speech control processing and speech processing]
Next, the flow of speech control processing and speech processing will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of the utterance control process executed by the utterance control server 1 and the utterance process executed by the dialogue apparatus 3.

  In the utterance control process, the utterance target specifying unit 25 of the utterance control server 1 checks whether there is an utterance content to be uttered (to be uttered by the dialogue apparatus 3) (S51). Specifically, the utterance target specifying unit 25 refers to the program-utterance content correspondence information 15 stored in the utterance content generation unit 24, and determines whether or not there is utterance content that has reached the utterance timing. I do. A timer may be set for each generated utterance content, and it may be specified by referring to the timer that there is an utterance content to be uttered.

  Then, when it is confirmed that there is an utterance content to be uttered (YES in S51), the utterance target specifying unit 25 specifies the dialog device 3 that utters the utterance content for each utterance content and specifies the specified dialog. A list of devices 3 is acquired (S52), and the utterance control unit 26 is notified. Specifically, the utterance target specifying unit 25 specifies the program ID corresponding to the utterance content to be uttered by the dialogue apparatus 3 from the program-utterance content correspondence information 15, and TV-viewing the TVID corresponding to the program ID. The interactive device ID corresponding to the TVID is specified from the program correspondence information 14 and the TV-interactive device correspondence information 16 is specified. The dialog device ID specified in this way is a list of dialog devices 3 to be uttered.

  Next, the utterance control unit 26 having received the notification of the list of dialog devices 3 to be uttered (list of dialog device IDs) uses the notified list and the program-utterance content correspondence information 15 to determine the utterance management information 17. Generate. Further, the utterance control unit 26 generates utterance data (data that can be output by the dialogue apparatus 3) for each utterance content included in the utterance management information 17 (S53). Then, the utterance control unit 26 transmits the generated utterance data to the dialogue device 3 that utters according to the utterance data, and instructs to speak using the utterance data (S54, utterance control step). In addition, when transmitting the utterance data corresponding to the utterance content in which the assumed response or the secondary utterance is set, information indicating the content of the assumed response and the utterance data of the secondary utterance may be transmitted together.

  Next, an utterance process executed by the dialogue apparatus 3 will be described. When the utterance instruction and the utterance data are received from the utterance control server 1 (S61), the utterance unit 31 transmits the received utterance data to the voice output unit 40 and outputs the voice. Thereby, the utterance according to the utterance data is performed (S62).

  Here, when the user responds to the utterance of S62, the response voice is acquired by the voice input unit 42, analyzed by the analysis unit 33 (S63), and the analysis result (content of the input voice) is the response. The generation unit 32 is notified. Upon receiving this notification, the response generation unit 32 determines whether or not the content of the input voice is an assumed response (S64).

  If it is determined that the response is an assumed response (YES in S64), the response generation unit 32 notifies the utterance unit 31 of the utterance data of the secondary utterance corresponding to the assumed response and causes the voice output unit 40 to output the utterance data. . On the other hand, when it is determined that the response is not an assumed response (NO in S64), the response generation unit 32 performs a normal response (S66). Specifically, the response generation unit 32 generates utterance data corresponding to the analysis result of the analysis unit 33, notifies the utterance unit 31, and causes the voice output unit 40 to output the utterance data. The above processing is performed every time an utterance instruction is received.

  In the processing of S63 to S66, the speech control server 1 may perform speech recognition and utterance data generation. In this case, the response generation unit 32 and the analysis unit 33 are provided in the utterance control server 1, and the voice data transmission unit for transmitting the voice data acquired by the voice input unit 42 to the utterance control server 1 is provided in the dialogue apparatus 3. And it is sufficient.

[Embodiment 2]
The following will describe another embodiment of the present invention with reference to FIGS. For convenience of explanation, members having the same functions as those described in the above embodiment and processes similar to those described in the above embodiment are denoted by the same reference numerals as those in the above embodiment. Is omitted.

  First, the outline | summary of the dialogue system which concerns on this embodiment is demonstrated based on FIG. FIG. 11 is a diagram showing an outline of the dialogue system 205. As illustrated, the dialogue system (speech control system) 205 includes an utterance control server (speech control device) 201, a TV information collection server 202 (content identification device), a program information collection server 203, and a dialogue device 3. The dialogue system 205 of this embodiment has a configuration in which some of the functions of the utterance control server 1 of the above embodiment are distributed to the TV information collection server 202 and the program information collection server 203.

  The utterance control server 201 is a server that controls the interactive apparatus 3 to perform a predetermined utterance. The utterance control server 201 includes the utterance target specifying unit 25 and the utterance control unit 26 of FIG. 1, and stores TV-interactive device correspondence information 16 in advance.

  The TV information collection server 202 is a server that identifies a program received and output by the TV 500, and receives viewing program information and TVID from the TV 500. The TV information collection server 202 includes the viewing program information acquisition unit 23 of FIG. Also, the TV information collection server 202 has an utterance content acquisition unit for acquiring the program-utterance content correspondence information 15 generated by the program information collection server 203 and an utterance timing for each utterance content included in the program-utterance content correspondence information 15. An utterance timing control unit to be specified is provided.

  The program information collection server 203 is a server that collects information about a program being broadcast and generates utterance contents corresponding to the program. The program information collection server 203 includes the program information acquisition unit 21, the related information acquisition unit 22, and the utterance content generation unit 24 shown in FIG. The function of the utterance content generation unit 24 is substantially the same as that of the above embodiment, but the embodiment further includes a function of transmitting the generated utterance content (specifically, the program-utterance content correspondence information 15). Is different.

  As shown in FIG. 11, in the interactive system 205, the TV information collection server 202 receives viewing program information and TVID from the TV 500. Also, the TV information collection server 202 receives the utterance contents corresponding to each program being broadcast and the program ID corresponding to the utterance contents from the program information collection server 203. Then, the TV information collection server 202 associates the TVID with the utterance content and transmits the utterance to the utterance control server 201, and the utterance control server 201 transmits the received utterance to the dialogue apparatus 3 associated with the received TVID. Instruct them to speak with content. As a result, it is possible to cause the dialogue apparatus 3 to utter the content according to the program that the user is viewing without transmitting the video of the program from the utterance control server 201 to the dialogue apparatus 3.

[Flow of utterance content generation processing and utterance content registration processing]
Next, the flow of utterance content generation processing and utterance content registration processing will be described with reference to FIG. FIG. 12 is a flowchart showing an example of utterance content generation processing executed by the program information collection server 203 and utterance content registration processing executed by the TV information collection server 202.

  First, the program information acquisition unit 21, the related information acquisition unit 22, and the utterance content generation unit 24 included in the program information collection server 203 perform the processing of S1 to S5 similar to FIG. 15 is registered. Then, the utterance content generation unit 24 transmits the program-utterance content correspondence information 15 in which the utterance content is associated with the program ID corresponding to the utterance content to the TV information collection server 202 (S201). Thereafter, the process waits for a predetermined time (S202) and returns to the process of S1. Thereby, the program-utterance content correspondence information 15 corresponding to the change of the program being broadcast is transmitted as needed.

  In the utterance content registration process, the utterance content acquisition unit included in the TV information collection server 202 receives the utterance content and the program ID (specifically, the program-utterance content correspondence information 15) transmitted by the utterance content transmission unit (S211). . Then, the utterance timing control unit included in the TV information collection server 202 registers an utterance timer for each utterance content (S212). The utterance timer is a timer for specifying the utterance timing, and is registered according to information indicating the utterance timing included in the program-utterance content correspondence information 15. These processes are performed each time the program-utterance content correspondence information 15 is received.

[Flow of utterance content transmission processing and utterance control processing]
Next, the flow of the utterance content transmission process and the utterance control process will be described with reference to FIG. FIG. 13 is a flowchart illustrating an example of the utterance content transmission process executed by the TV information collection server 202 and the utterance control process executed by the utterance control server 201. Although not shown in the figure, the viewing program information acquisition unit 23 of the TV information collection server 202 stores the TV-viewing program correspondence information 14 by performing viewing program registration processing as shown in FIG. ing.

  The utterance content transmission process is performed each time the utterance timer registered in the utterance content registration process is fired. When a plurality of utterance timers are fired, etc., utterance content transmission processing corresponding to each utterance timer is executed in parallel. When the utterance timing control unit confirms that the registered utterance timer has fired (S221), the utterance timing control unit searches the TV 500 corresponding to the utterance content corresponding to the uttered utterance timer (S222). Specifically, the utterance timing control unit specifies the program ID corresponding to the uttered utterance timer from the program-utterance content correspondence information 15, and is associated with this program ID in the TV-viewing program correspondence information 14. Search TV500.

  Then, the utterance timing control unit transmits the utterance contents corresponding to the uttered utterance timer and the TVID list detected in the process of S222 to the utterance control server 201 (S223). Note that the utterance content to be transmitted may include information indicating the assumed response and the content of the secondary utterance.

  In the utterance control process, the utterance control unit 26 of the utterance control server 201 receives the utterance content and TVID list from the TV information collection server 202 (S231), and notifies the utterance target specifying unit 25 of the received TVID list. As a result, the utterance target specifying unit 25 refers to the TV-interactive device correspondence information 16 to specify the interactive device ID corresponding to each TVID included in the notified list, and acquires the list (S52). . Thereafter, as in FIG. 10, utterance data generation (S53) and utterance instruction transmission (S54) are performed. Further, in the dialogue apparatus 3 that has received the utterance instruction, the utterance process similar to that shown in FIG. 10 is performed.

[About control of speech timing]
In the above description, the TV information collection server 202 transmits the utterance content according to the utterance timer to control the utterance timing of the dialogue apparatus 3. However, the present invention is not limited to this example. For example, the utterance content whose utterance timing is “immediate” may be transmitted to the utterance control server 201 without registering the utterance timer. Specifically, after the process of S211 in FIG. 12, the process of S212 is omitted, and the process proceeds to the process of S222 in FIG. 13. In S223, the utterance content and the target TV list (list of TVID corresponding to the utterance content) May be sent. Also, if the utterance content is an advertisement, it is expected to improve the advertising effect by making the utterance every predetermined time, so it is transmitted to the utterance control server 201 every predetermined time (for example, every 15 minutes), You may make it speak.

  Further, the method for controlling the speech timing is not limited to the above example. For example, the program information collection server 203 that generates the utterance content may control the utterance timing. In this case, the program information collection server 203 sets the utterance content at the utterance timing among the generated utterance content as the TV information. What is necessary is just to transmit to the collection server 202. In addition, the utterance control server 201 and the dialogue apparatus 3 may control the utterance timing. In these cases, information indicating the utterance timing may be transmitted to the utterance control server 201 and the dialogue apparatus 3.

[Embodiment 3]
The following will describe another embodiment of the present invention with reference to FIGS. For convenience of explanation, members having the same functions as those described in the above embodiment and processes similar to those described in the above embodiment are denoted by the same reference numerals as those in the above embodiment. Is omitted.

  First, the outline | summary of the dialogue system which concerns on this embodiment is demonstrated based on FIG. FIG. 14 is a diagram showing an outline of the dialogue system 305. As illustrated, the dialogue system (speech control system) 305 includes an utterance control server (speech control device) 301, a TV information collection server (content specifying device) 302, a program information collection server 303, and the dialogue device 3. The dialogue system 305 of this embodiment has a configuration in which some of the functions of the utterance control server 1 of the above embodiment are distributed to the TV information collection server 302 and the program information collection server 303.

  The utterance control server 301 is a server that controls the interactive apparatus 3 to perform a predetermined utterance. The utterance control server 301 includes the utterance target specifying unit 25 and the utterance control unit 26 of FIG. 1, and stores TV-interactive device correspondence information 16 in advance.

  The TV information collection server 302 is a server that identifies a program received and output by the TV 500, and receives viewing program information and TVID from the TV 500. The TV information collection server 302 includes the viewing program information acquisition unit 23 and the program information acquisition unit 21 of FIG. The viewing program information acquisition unit 23 and the program information acquisition unit 21 have a function of transmitting the acquired information to the program information collection server 303 in addition to the functions described in the above embodiment.

  The program information collection server 303 is a server that collects information related to a program notified from the TV information collection server 302 and generates utterance contents corresponding to the program. The program information collection server 303 includes the program information acquisition unit 21, the related information acquisition unit 22, and the utterance content generation unit 24 shown in FIG. In addition, the program information collection server 303 includes a viewing state specifying unit that determines whether or not the TV 500 is viewing a program.

  As shown in FIG. 14, in the interactive system 305, the TV information collection server 302 receives viewing program information and TVID from the TV 500, and the received TVID is associated with the program ID specified from the received viewing program information. It transmits to the information collection server 303. Next, the program information collection server 303 generates utterance content corresponding to the program specified by the received program ID, and transmits the generated utterance content and TVID to the utterance control server 301 in association with each other. Then, the utterance control server 301 instructs the dialogue apparatus 3 associated with the received TVID to utter with the received utterance content. As a result, it is possible to cause the dialogue apparatus 3 to utter the content according to the program that the user is viewing without transmitting the video of the program from the utterance control server 301 to the dialogue apparatus 3.

[Flow of viewing program notification processing, utterance content generation processing, and utterance control processing]
Next, the flow of the viewing program notification process, the utterance content generation process, and the utterance control process will be described with reference to FIG. FIG. 15 is a flowchart illustrating an example of a viewing program notification process executed by the TV information collection server 302, an utterance content generation process executed by the program information collection server 303, and an utterance control process executed by the utterance control server 301.

  First, in the viewing program notification process, the viewing program information acquisition unit 23 included in the TV information collection server 302 receives viewing program information and TVID transmitted from the TV 500 (S301, content specifying step), and TV-viewing program correspondence information. 14 is generated. When the program ID cannot be specified, such as when the viewing program information indicates that the TV 500 has been turned off or has been switched to an external output other than the broadcast program, etc. Only TVID may be registered in the TV-viewing program correspondence information 14. Thereby, it is possible to identify the TV 500 that is not viewing the program.

  Next, the program information acquisition unit 21 acquires program information of the program indicated by the viewing program information received in S301 (S302), and generates the program information table 11 from the acquired program information. In addition, the program information acquisition unit 21 generates a program search information table 13. The advertisement search information table 12 may also be generated.

  Then, the program information acquisition unit 21 transmits the generated program information table 11 and program search information table 13 to the program information collection server 303, and the viewing program information acquisition unit 23 transmits to the program information collection server 303 (S303). .

  Next, in the utterance content generation process, the viewing state specifying unit included in the program information collection server 303 receives the program information table 11, the program search information table 13, and the TV-viewing program correspondence information 14 (S311). Then, the viewing state specifying unit refers to the received TV-viewing program correspondence information 14 and determines whether the TV 500 is viewing the program (S312). Specifically, in the TV-viewing program correspondence information 14, it is determined that the TV ID TV 500 that is not associated with the program ID does not view the program. Even if the TV ID is associated with the program ID, it may be determined that the program ID is not being viewed if the end time of the program has passed.

  Here, for the TV 500 that is determined not to be viewed (NO in S312), the process ends without generating the utterance content. On the other hand, when there is a TV 500 that is determined to be being viewed (YES in S312), the viewing state specifying unit notifies the related information acquisition unit 22 of the program ID corresponding to the TV 500. Next, the related information acquisition unit 22 searches for the program related information of the program specified by the notified program ID using the program search information table 13 received in S311 (S2), and detects the detected program related information. The utterance content generation unit 24 is notified.

  Next, the utterance content generation unit 24 generates utterance content corresponding to each program being output by each TV 500 determined to be viewing in S312 using the notified program related information (S4). . Note that the utterance content corresponding to the event and the utterance content related to the advertisement may be generated in the same manner as the utterance content generation processing of the first embodiment.

  And the utterance content production | generation part 24 matches and registers the utterance content produced | generated by S4, and the information which designates the timing which speaks by this utterance content (S5). Then, the TVID is associated with each utterance content and transmitted to the utterance control server 301 (S313). The TVID corresponding to the utterance content is specified with reference to the TV-viewing program correspondence information 14 received in S311.

  Next, in the utterance control process, the utterance control unit 26 included in the utterance control server 301 receives the utterance content and TVID (S321), and notifies the utterance target specifying unit 25 of the received TVID. Thereby, the utterance target specifying unit 25 refers to the TV-interactive device correspondence information 16 and specifies the interactive device ID corresponding to the notified TVID (S52). Thereafter, as in FIG. 10, utterance data generation (S53) and utterance instruction transmission (S54) are performed. Further, in the dialogue apparatus 3 that has received the utterance instruction, the utterance process similar to that shown in FIG. 10 is performed.

  In the illustrated example, the processing from S312 onward is performed with S311 as an opportunity. However, as long as one program is viewed, the generation of the utterance content corresponding to the program may be continuously performed. Good. That is, after S313, the process may transition to S312. As a result, it is possible to detect program-related information according to the progress of the program and generate utterance contents with higher real-time characteristics.

  Further, after transmitting the utterance content to the TV 500, if it is determined NO in S312, the utterance control server 301 may be notified so that the utterance based on the utterance content is stopped. As a result, it is possible to prevent an utterance relating to a program that has not been viewed.

[Embodiment 4]
Another embodiment of the present invention will be described below with reference to FIGS. 16 and 17. For convenience of explanation, members having the same functions as those described in the above embodiment and processes similar to those described in the above embodiment are denoted by the same reference numerals as those in the above embodiment. Is omitted.

  First, the outline | summary of the dialogue system which concerns on this embodiment is demonstrated based on FIG. FIG. 16 is a diagram showing an outline of a dialogue system (speech control system) 405. As illustrated, the dialogue system 405 includes an utterance control server (speech control device) 401, a TV information collection server (content specifying device) 402, a program information collection server 403, and the dialogue device 3. The dialogue system 405 of this embodiment has a configuration in which a part of the functions of the utterance control server 1 of the above embodiment is distributed to the TV information collection server 402 and the program information collection server 403.

  The utterance control server 401 is a server that controls the interactive apparatus 3 to perform a predetermined utterance. The utterance control server 401 includes the utterance target specifying unit 25 and the utterance control unit 26 of FIG. 1, and stores TV-interactive device correspondence information 16 in advance.

  The TV information collection server 402 is a server that identifies a program received and output by the TV 500, and receives viewing program information and TVID from the TV 500. The TV information collection server 402 includes the viewing program information acquisition unit 23 of FIG.

  The program information collection server 403 is a server that generates utterance contents corresponding to each program being broadcast. The program information collection server 403 includes the program information acquisition unit 21, the related information acquisition unit 22, and the utterance content generation unit 24 shown in FIG.

  As shown in FIG. 16, in the interactive system 405, the TV information collection server 402 receives the viewing program information and TVID from the TV 500, and utters the received TVID in association with the program ID specified from the received viewing program information. Transmit to the control server 401. Further, the program information collection server 403 generates utterance contents corresponding to each program being broadcast, and transmits the generated utterance contents and the program ID to the utterance control server 401 in association with each other. Then, the utterance control server 401 notifies the dialog device 3 previously associated with the TV 500 that is outputting the program corresponding to the utterance content of the utterance content received from the program information collection server 403 to utter. As a result, it is possible to cause the dialogue apparatus 3 to utter the content according to the program that the user is viewing without transmitting the video of the program from the utterance control server 401 to the dialogue apparatus 3.

[Flow of viewing program notification processing and utterance control processing]
Next, the flow of the viewing program notification process and the speech control process will be described with reference to FIG. FIG. 17 is a flowchart illustrating an example of a viewing program registration process and an utterance control process executed by the utterance control server 401. Although not shown in the figure, the TV information collection server 402 performs the same processing as the viewing program notification processing in FIG. 15 to perform TV-viewing program correspondence information in which the program ID and the TVID are associated with each other. 14 is transmitted to the utterance control server 401. However, in this embodiment, transmission of the program information table 11 and the program search information table 13 is not performed. Further, the program information collection server 403 transmits the utterance content generation processing of FIG. 12 to the utterance control server 401 by transmitting the program-utterance content correspondence information 15 indicating the correspondence between the utterance content and the program ID.

  In the viewing program registration process, the utterance control unit 26 of the utterance control server 401 receives the TV-viewing program correspondence information 14 from the TV information collection server 402 (S 401), and sets the TVID included in the TV-viewing program correspondence information 14. The utterance target specifying unit 25 is notified. Subsequently, the utterance target specifying unit 25 refers to the TV-interactive device correspondence information 16 stored in advance in the utterance control server 401, and specifies the interactive device ID corresponding to each notified TVID (S402).

  Then, the utterance target specifying unit 25 associates the interactive device ID specified in S402 with the program ID included in the TV-viewing program correspondence information 14 received in S401, and thus the interactive device-viewing program correspondence information (FIG. 6). (See (b) of FIG. 2) (S403). These processes are performed each time the TV-viewing program correspondence information 14 is received from the TV information collection server 402.

  Next, in the utterance control process, when the utterance control unit 26 receives the program-utterance content correspondence information 15 from the program information collection server 403 (S411), the utterance control unit 26 notifies the utterance target specifying unit 25 of this. The utterance target specifying unit 25 specifies the utterance contents to be uttered by the dialog device 3 among the utterance contents included in the program-utterance content correspondence information 15 by referring to information indicating the utterance timing, and further specifies the utterance contents. The program ID corresponding to the uttered content is specified.

  Then, the utterance target specifying unit 25 searches for the dialog device ID associated with the specified program ID from the dialog device-viewing program correspondence information registered in S403 (S412), thereby the dialog device to be controlled. 3 is specified. Thereafter, as in FIG. 10, utterance data generation (S53) and utterance instruction transmission (S54) are performed. Further, in the dialogue apparatus 3 that has received the utterance instruction, the utterance process similar to that shown in FIG. 10 is performed.

  Note that the process of S53 may be performed before the process of S412 or may be performed in parallel with the process of S412. However, when the processing is performed after the processing of S412, the generation of the utterance data can be narrowed down to the utterance contents instructed to utter in S54. This eliminates the need to generate utterance data for all of the utterance contents received in S411, thereby distributing the load of utterance data generation processing.

[About content]
In each of the above embodiments, an example is shown in which an utterance corresponding to a broadcast program received and output by the TV 500 is performed. However, the content may be transmitted from an apparatus other than the utterance control server. Not limited to. Further, the output device that outputs content is not limited to the TV 500. For example, utterances according to content distributed via a communication network such as the Internet (for example, on-demand content), content on a network such as a LAN, or content that does not involve video such as radio are performed instead of broadcasting. Also good. The output device may be a portable communication terminal such as a smartphone or a tablet terminal.

[Modified example of interactive device]
In each of the above-described embodiments, the example in which the utterance content of the dialog device 3 is controlled by the utterance control server has been described, but the utterance content may be determined in the dialog device 3. In this case, the dialogue apparatus includes content specifying means for specifying the program being output by the TV 500, and the utterance unit 31 performs utterance according to the program specified by the means. The interactive apparatus control method in this example includes a content specifying step for specifying a program received and output by the TV 500 associated with the interactive apparatus, and a content corresponding to the content specified in the content specifying step. An utterance step of uttering at. In this configuration, each server described in the above embodiment can be omitted, and the configuration for communicating with the server from the interactive device 3 can also be omitted.

  The method by which the content specifying unit specifies a program is not particularly limited, and for example, information indicating a program may be acquired from the TV information collection server 202 or the like described in each of the above embodiments. Further, the interactive apparatus may be provided with an output device operation means for operating the TV 500, and the program may be specified using information indicating the content of the operation performed by the output device operation means. For example, the output device operating means may perform operations such as power ON / OFF and channel switching for the TV 500, and the program is specified by storing information indicating the contents of such operations. Can do. According to this configuration, it is possible to make an utterance corresponding to a program output by a general TV that does not include the viewing program information transmission unit 501 shown in FIG. Further, the utterance content corresponding to the program may be generated by the interactive device, or may be generated by the program information collection server 203 described in each of the above embodiments.

[Embodiment 5]
Each block of the utterance control server 1, 201, 301, 401, TV information collection server 202, 302, 402, program information collection server 203, 303, 403, and interactive device 3 is formed in an integrated circuit (IC chip) or the like. Alternatively, it may be realized by a logic circuit (hardware) or by software using a CPU (Central Processing Unit). In the latter case, each of the above-described servers or interactive devices 3 can be configured using a computer (electronic computer) as shown in FIG. FIG. 18 is a block diagram illustrating the configuration of a computer 100 that can be used as each of the servers or the interaction device 3 described above.

  As shown in FIG. 18, the computer 100 includes an arithmetic device 120, a main storage device 130, an auxiliary storage device 140, and an input / output interface 150 connected to each other via a bus 110. The arithmetic device 120, the main storage device 130, and the auxiliary storage device 140 may be, for example, a CPU, a random access memory (RAM), and a hard disk drive, respectively. The main storage device 130 may be a computer-readable “non-temporary tangible medium”. For example, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used.

  The input device 200 and the output device 300 are connected to the input / output interface 150. The input device 200 and the output device 300 of each server receive data transmitted from another server or the TV 500 and transmit data to another server or the interactive device 3. The input device 200 and the output device 300 of the interactive device 3 receive data from the utterance control servers 1, 201, 301, 401, utter the user, and acquire the user's voice.

  The auxiliary storage device 140 stores various programs for causing the computer 100 to operate as each of the above servers or the interactive device 3. Then, the arithmetic device 120 expands the respective programs stored in the auxiliary storage device 140 on the main storage device 130, and executes instructions included in the respective programs expanded on the main storage device 130. The computer 100 is caused to function as each unit included in each of the servers or the interactive device 3 described above.

  Here, the configuration has been described in which the computer 100 is made to function using each of the programs recorded in the auxiliary storage device 140, which is an internal recording medium. However, a program recorded in an external recording medium may be used. . The program may be supplied to the computer via an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the program. The present invention can also be realized in the form of a data signal embedded in a carrier wave in which the program is embodied by electronic transmission.

[Summary]
An utterance control device (speech control server 1, 401) according to aspect 1 of the present invention is an utterance control device that utters an utterance device (dialogue device 3) having an utterance function by voice, and is used together with the utterance device. Content specifying means (viewing program information acquisition unit 23) that specifies the content (program) received and output from the device other than the speech control device by the output device (TV 500) associated with the speech device as a device that ) And utterance control means (speech control unit 26) that causes the utterance device to utter in accordance with the content specified by the content specifying means.

  According to said structure, the output apparatus matched with the utterance apparatus as an apparatus used with an utterance apparatus specifies the content received and output from apparatuses other than an utterance control apparatus, and responds to the specified content. Talk to the utterance device with the contents. Therefore, the utterance control apparatus can cause the utterance apparatus to utter according to the content being output by the output apparatus without transmitting the content to the output apparatus. That is, in Patent Document 1 described in [Background Art], it is necessary to transmit video information from a receiver that controls the operation of the robot to the television. According to the above configuration, the utterance control that causes the utterance device to utter. The device does not need to send content to the output device.

  In Patent Document 1, after the motion information and the video information are in a state where they are aligned in the receiver, the motion control of the robot is performed based on the motion information and the video information is transmitted to the television. On the other hand, in the configuration of the present invention, it is not necessary to prepare the utterance contents and the contents in advance. This is because the content of the output device is specified in the configuration of the present invention. Then, by specifying the content output by the output device, it is also possible to generate utterance content during the output of the content based on the specified content and to utter with the content. Therefore, even if the output device outputs content that is difficult to generate in advance, such as a live broadcast program, for example, it is generated at that time and is output in substantially real time during the broadcast. It is also possible to make an utterance according to the scene.

  Note that the relationship between the utterance device and the output device, which means “the output device used with the utterance device”, is likely to be uttered by the utterance device to the user who is viewing the content output by the output device. It is a relationship. In other words, regardless of whether or not the output device communicates with or cooperates with the utterance device, if there is a probability of being used in the same room as the utterance device, the “output device used with the utterance device” is there.

  The speech control apparatus according to aspect 2 of the present invention is the speech control apparatus according to aspect 1, wherein the content specifying means is performed on the information transmitted from the output device and indicating the content output by the output device, or on the output device. The content is specified using information indicating the details of the operation. According to this aspect, when the output device transmits information indicating the content to be output, the content output from the output device can be specified using this information. Further, if information indicating the details of the operation performed on the output device is acquired, the content output by the output device can be specified from this information.

  The utterance control device according to aspect 3 of the present invention is the utterance control device according to aspect 1 or 2, wherein there are a plurality of the utterance devices to be controlled, and correspondence information (TV-utterance) indicating the association between the output device and the utterance device Referring to the device correspondence information 16), among the plurality of utterance devices, the utterance target specifying means (speech target specification) for specifying the utterance device associated with the output device that specified the content being output by the content specification means Section 25), and the speech control means causes the speech device specified by the speech target specifying means to speak. According to this aspect, it is possible to control a plurality of utterance devices and perform utterances according to the content output by the output device associated with each utterance device.

  An utterance control device according to aspect 4 of the present invention is related to any one of aspects 1 to 3 above, related information acquisition means (related information) for acquiring related information (program related information) related to the content specified by the content specifying means. And an utterance content generation unit (utterance content generation unit 24) that generates utterance content including the related information acquired by the related information acquisition unit. According to this aspect, the utterance content corresponding to the content can be automatically generated, and this can be uttered by the utterance device.

  The utterance control device according to aspect 5 of the present invention is the utterance control device according to any one of the aspects 1 to 4, wherein the sponsor specifying means (program information acquisition unit 21) for specifying the sponsor of the content specified by the content specifying means; An utterance content generating means for generating utterance contents corresponding to the sponsor specified by the means is provided. According to this aspect, the utterance content corresponding to the sponsor can be automatically generated for the content with the sponsor, and this can be uttered by the utterance device. For example, an advertisement related to a sponsor can be uttered.

  An utterance device (dialogue device 3) according to an aspect 6 of the present invention is an utterance device having a speech utterance function, and is received by an output device associated with the utterance device as a device used with the utterance device. Content specifying means for specifying the content being output, and utterance means (speech unit 31) for uttering in accordance with the content specified by the content specifying means.

  According to said structure, the content which the output device matched with the speech apparatus is output as an apparatus used with a speech apparatus is specified, and it speaks by the content according to the specified content. Therefore, it is possible to make an utterance according to the content being output by the output device without transmitting the content to the output device.

  An utterance device according to aspect 7 of the present invention includes the output device operating means for operating the output device in the above aspect 6, and the content specifying means indicates details of an operation performed by the output device operating means. Identify content using information. According to this configuration, the output device can be operated via the speech device. And since the content which the output device is outputting is specified using the information which shows the content of this operation, the output device does not need to be provided with the function to transmit the output content. That is, according to the above configuration, even when an output device that does not have a function of transmitting output content, such as a general television receiver, is used, the output device outputs Speak according to the content being played.

  An utterance control system (dialogue systems 205, 305, and 405) according to an aspect 8 of the present invention is an utterance control system that causes an utterance apparatus having an utterance function by voice to utter, and is an apparatus used together with the utterance apparatus. A content specifying device (TV) that specifies content received and output from a device other than the speech control device (speech control servers 201, 301, 401) that causes the output device associated with the speech device to speak. Information collection servers 202, 302, and 402), the utterance control device that causes the utterance device to utter the content according to the content specified by the content specifying device, and the utterance device. According to this aspect, the same effects as those of the above aspect 1 are obtained.

  An utterance control method according to an aspect 9 of the present invention is an utterance control method for causing an utterance apparatus having an utterance function by voice to utter, and an output device associated with the utterance apparatus as an apparatus used with the utterance apparatus Depending on the content specified in the content specifying step (S31, S301, S401) for specifying the content received and output from a device other than the utterance control device that causes the utterance device to speak, and the content specified in the content specifying step An utterance control step (S54) for causing the utterance device to utter the content. Therefore, the same effect as in aspect 1 is produced.

  A control method for an utterance device according to aspect 10 of the present invention is a control method for an utterance device having a voice utterance function, wherein an output device associated with the utterance device is used as a device used with the utterance device. A content specifying step for specifying the content received and output and an utterance step for uttering the content according to the content specified in the content specifying step are included. Therefore, the same effect as in aspect 6 is obtained.

  The utterance control device and the utterance device according to each aspect of the present invention may be realized by a computer. In this case, the utterance control is performed by operating the computer as each means included in the utterance control device and the utterance device. The utterance control apparatus and the utterance apparatus control program for realizing the apparatus and the utterance apparatus by a computer, and a computer-readable recording medium recording the utterance apparatus are also included in the scope of the present invention.

  The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims, and embodiments obtained by appropriately combining technical means disclosed in different embodiments. Is also included in the technical scope of the present invention. Furthermore, a new technical feature can be formed by combining the technical means disclosed in each embodiment.

  INDUSTRIAL APPLICABILITY The present invention can be used for an utterance device that utters a user and control thereof.

1, 201, 301, 401 Speech control server (speech control device)
16 TV-dialogue device correspondence information (correspondence information)
21 Program information acquisition unit (sponsor identification means)
22 related information acquisition unit (related information acquisition means)
23 viewing program information acquisition unit (content specifying means)
24 Utterance content generation unit (utterance content generation means)
25 Utterance target specifying part (speech target specifying means)
26 Speech control unit (speech control means)
3 Dialogue device (speech device)
31 Utterance part (speech means)
5, 205, 305, 405 Dialogue system (speech control system)
202, 302, 402 TV information collection server (content specifying device)
500 TV (output device)

Claims (12)

An utterance control device for uttering to an utterance device having an utterance function by voice,
An output device associated with the utterance device as a device used with the utterance device, content specifying means for specifying content received and output from a device other than the utterance control device;
According to the information for specifying the timing of speech, the speech control unit, characterized in that the content corresponding to the content in which the content specifying means has specified and a, a speech control means for causing the speech to the speech device in the above timing.   The content specifying means specifies content using information transmitted from the output device and indicating information output by the output device or information indicating an operation performed on the output device. The utterance control device according to claim 1. An utterance control device for uttering to an utterance device having an utterance function by voice,
An output device associated with the utterance device as a device used with the utterance device, content specifying means for specifying content received and output from a device other than the utterance control device;
Utterance control means for causing the utterance device to utter with the content according to the content specified by the content specifying means,
There are a plurality of the utterance devices to be controlled,
Referring to the correspondence information indicating the correspondence between the output device and the utterance device, the utterance device associated with the output device that has identified the content being output by the content specifying unit among the plurality of utterance devices. It has an utterance target identification means to identify
It said speech control means, utterance controller you characterized thereby uttered speech apparatus identified above utterance target identification means. Related information acquiring means for acquiring related information related to the content specified by the content specifying means;
The utterance content generation means for generating the utterance content including the related information acquired by the related information acquisition means as the utterance content corresponding to the content is provided. The utterance control device described. Sponsor identification means for identifying the sponsor of the content identified by the content identification means;
5. The utterance content generation means for generating the utterance content corresponding to the sponsor specified by the sponsor specifying means as the utterance content corresponding to the content. 5. Utterance control device. An utterance device having a voice utterance function,
Content specifying means for specifying content received and output by an output device associated with the utterance device as a device used with the utterance device;
According to the information for specifying the timing of utterance, speech apparatus characterized by a content corresponding to the content in which the content specifying means has specified and a, a speech means to speak the above timing. An output device operating means for operating the output device;
The utterance device according to claim 6, wherein the content specifying means specifies content using information indicating details of an operation performed by the output device operating means. An utterance control system for uttering to an utterance device having an utterance function by voice,
An output device associated with the utterance device as a device used with the utterance device, a content specifying device for specifying content received and output from a device other than the utterance control device that utters the utterance device;
The utterance control device that causes the utterance device to utter at the timing the content according to the content specified by the content specifying device according to the information specifying the utterance timing ;
An utterance control system including the utterance device. An utterance control method for uttering to an utterance device having an utterance function by voice,
A content specifying step for specifying content received and output from a device other than the speech control device that causes the output device associated with the speech device to be used by the speech device as an apparatus used with the speech device;
According to the information for specifying the timing of speech, the speech control method characterized by the contents corresponding to content identified by the content specifying step including a speech control step of speech to the speech device in the above timing. A method of controlling an utterance device having a speech utterance function,
A content specifying step of specifying content received and output by an output device associated with the utterance device as a device used with the utterance device;
According to the information specifying the timing of speech, the control method of the utterance apparatus which comprises a speech step, the uttering a content corresponding to content identified by the content identification step above timing.   A control program for causing a computer to function as the speech control device according to any one of claims 1 to 5, wherein the control program causes the computer to function as each of the means. A control program for causing a computer to function as the utterance device according to claim 6 or 7, wherein the control program causes the computer to function as each of the means.

Images