KR-102963093-B1 - Information processing device, information processing method, transmission device, and transmission method

Abstract

The present invention relates to an information processing device, an information processing method, a transmission device, and a transmission method that can improve the convenience of a voice AI assistance service used in conjunction with content. When using a voice AI assistance service linked to content, an information processing device is provided that processes unique information corresponding to a common call name included in the voice of a viewer’s speech, based on corresponding information in which a common call name for a plurality of programs is mapped to unique information for each program as a call name for calling a program that performs corresponding processing for the voice of a viewer’s speech, when the voice AI assistance service linked to content is used. The present invention can be applied, for example, to a system linked to a voice AI assistance service.

Inventors

• 츠루 다쿠미

Assignees

• 소니그룹주식회사

Dates

Publication Date

20260512

Application Date

20190313

Priority Date

20180327

Claims (20)

1. When using a voice AI assistance service linked to content, the system comprises a processing unit that processes the unique information corresponding to the common call name included in the voice of the viewer’s speech, based on corresponding information in which the common call name of a plurality of programs and unique information of each program are correlated as a call name for calling a program that performs corresponding processing for the voice of the speech of a viewer watching the content. The above correspondence information corresponds the above common call name with the unique call name for each above program, and The processing unit converts the common call name included in the voice of the viewer's speech into the unique call name based on the corresponding information. Information processing device.
2. delete
3. In paragraph 1, a recording unit for recording the corresponding information in advance is further provided, and The processing unit converts the common call name into the unique call name based on the recorded corresponding information. Information processing device.
4. In paragraph 1, the receiving device is configured to receive the content transmitted via broadcast, and The above-mentioned unique call name is obtained from metadata transmitted via broadcast, and The processing unit converts the common call name into the unique call name obtained from the metadata. Information processing device.
5. In paragraph 1, the receiving device is configured to receive the content transmitted via broadcast, and Converting the common call name to the unique call name in response to a request from a voice processing device functioning as a user interface of the above voice AI assistance service Information processing device.
6. In paragraph 1, the corresponding information is information that corresponds a unique program with metadata for specifying the content being viewed by the viewer, and is included in a program for switching specified by the common call name, and The above processing unit enables corresponding processing for the voice of the viewer's speech to be performed for the unique program corresponding to the metadata sent together with the common call name, based on the corresponding information corresponding to the above conversion program. Information processing device.
7. In paragraph 6, it is configured as a voice processing device functioning as a user interface for the voice AI assistance service and a server device connected via a network, and The processing unit dispatches to the unique program corresponding to the metadata sent from the voice processing device along with the common call name. Information processing device.
8. In claim 7, the metadata comprises channel information indicating the channel of the content being viewed by the viewer, and time information indicating the time corresponding to the viewer's utterance on the playback time axis of the content. Information processing device.
9. In claim 1, the program includes at least information such as which voice to respond to, which word to use as a parameter to realize which function, or which server device or processing program actually executes the function, and based on said information, performs corresponding processing for the voice of the viewer's speech sent from a voice processing device that functions as a user interface of the voice AI assistance service. Information processing device.
10. In paragraph 4, the above content is distributed via broadcast as a stream compliant with MPEG-DASH, and The above unique call name is transmitted via broadcast using MPD Information processing device.
11. In paragraph 8, the channel information and the time information are sent via communication together with the voice data of the viewer's utterance using an HTTP request. Information processing device.
12. In paragraph 1, the above content is broadcast content distributed via broadcast, and The above program is provided by each broadcaster or broadcast program. Information processing device.
13. In a method of processing information of an information processing device, The above information processing device, When using a voice AI assistance service linked to content, based on corresponding information in which a common call name for a plurality of programs corresponds to unique information for each program as a call name for calling a program that performs corresponding processing for the voice of a viewer watching the content, the unique information corresponding to the common call name included in the voice of the viewer's voice is processed. The above correspondence information corresponds the above common call name with the unique call name for each above program, and The information processing device converts the common call name included in the voice of the viewer's speech into the unique call name based on the corresponding information. method.
14. In a voice AI assistance service linked to content, when using correspondence information in which a common call name for a plurality of programs and a unique call name for each program are correlated as a call name for calling a program that performs corresponding processing for the voice of a viewer watching the content, a generating unit that generates metadata including the unique call name, and It is equipped with a transmitting unit that transmits the generated metadata, The above correspondence information corresponds the above common call name with the unique call name for each above program, and The above-mentioned generating unit is a transmitting device that converts the common call name included in the voice of the viewer's speech into the unique call name based on the above-mentioned corresponding information.
15. In paragraph 14, the generation unit generates an MPD that is identifiable by identification information for identifying the unique call name used in the voice AI assistance service, and The above-mentioned transmitter, together with the MPD, transmits the content via broadcast as a stream compliant with MPEG-DASH. Transmitting device.
16. In a transmission method of a transmitting device, The above transmitting device, In a voice AI assistance service linked to content, when using correspondence information in which a common call name for a plurality of programs and a unique call name for each program are correlated as a call name for calling a program that performs corresponding processing for the voice of a viewer's speech while watching the content, metadata including the unique call name is generated. Transmit the generated metadata above, and The above correspondence information corresponds the above common call name with the unique call name for each above program, and The above-described transmitting device is a transmitting method that converts the common call name included in the voice of the viewer's speech into the unique call name based on the corresponding information.
17. When using a voice AI assistance service linked to content, the processing unit generates a personal program based on generation information that includes at least account information of a viewer watching the content, a program that performs corresponding processing for the voice of the viewer's speech and is specialized for the viewer, and a call name for calling the personal program. The processing unit updates the generated personal program based on the account information, the name of the personal program, and update information that is registered for the personal program and includes at least registration information excluding the call name. Information processing device.
18. In paragraph 17, the voice processing device functioning as a user interface for the voice AI assistance service and the server device connected via a network are configured as such. The above processing unit enables corresponding processing for the voice of the viewer's speech to be performed for the personal program corresponding to the call name sent from the voice processing device. Information processing device.
19. In paragraph 18, the above content is distributed via broadcast as a stream compliant with MPEG-DASH, and The above registration information is transmitted via broadcast using MPD, and The processing unit updates the personal program based on the update information when the version of the registration information is updated or when the channel is switched by the viewer. Information processing device.
20. In a method of processing information of an information processing device, The above information processing device, When using a voice AI assistance service linked to content, the personal program is generated based on generation information that includes at least account information of a viewer watching the content, a program that performs corresponding processing for the voice of the viewer's speech and is specialized for the viewer, and a call name for calling the personal program. Updating the created personal program based on the above account information, the name of the above personal program, and update information that is registered for the above personal program and includes at least registration information excluding the above call name. Information processing method.

Description

Information processing device, information processing method, transmission device, and transmission method The present invention relates to an information processing device, an information processing method, a transmission device, and a transmission method, and in particular, to an information processing device, an information processing method, a transmission device, and a transmission method that can improve the convenience of a voice AI assistance service used in conjunction with content. A broadcasting application that runs in conjunction with broadcasting content has been proposed (see, for example, Patent Document 1). By using the broadcasting application, information related to the broadcasting content can be displayed, for example. In addition, a technology for speech recognition that interprets the content of a user's utterance has been proposed (see, for example, Patent Document 2). For example, if this technology is applied to a television receiver or a mobile terminal device, it becomes possible to interpret the words spoken by the user and perform processing according to the utterance. FIG. 1 is a block diagram illustrating an example of the configuration of an embodiment of a content-voice AI linkage system to which the present technology is applied. Figure 2 is a diagram illustrating a first example of an invocation name for each broadcasting station or broadcast program. Figure 3 is a diagram illustrating a second example of an invocation name for each broadcasting station or broadcast program. Figure 4 is a diagram illustrating a third example of an invocation name for each broadcasting station or broadcast program. FIG. 5 is a drawing illustrating a first example of the configuration of the first embodiment. FIG. 6 is a drawing illustrating a second example of the configuration of the first embodiment. FIG. 7 is a drawing illustrating a third example of the configuration of the first embodiment. FIG. 8 is a block diagram illustrating an example of the detailed configuration of each device of the first embodiment. FIG. 9 is a flowchart illustrating the processing flow of each device of the first embodiment. Figure 10 is a diagram illustrating an example of the technology of invocation name metadata. FIG. 11 is a drawing illustrating a first example of the configuration of a second embodiment. FIG. 12 is a drawing illustrating a second example of the configuration of the second embodiment. FIG. 13 is a drawing illustrating a third example of the configuration of the second embodiment. FIG. 14 is a block diagram illustrating an example of the detailed configuration of each device of the second embodiment. FIG. 15 is a flowchart illustrating the flow of processing for each device of the second embodiment. Figure 16 is a diagram illustrating an example of merging context metadata. FIG. 17 is a drawing illustrating a first example of the configuration of a third embodiment. FIG. 18 is a drawing illustrating a second example of the configuration of the third embodiment. FIG. 19 is a drawing illustrating a third example of the configuration of the third embodiment. FIG. 20 is a block diagram illustrating an example of the detailed configuration of each device of the third embodiment. FIG. 21 is a flowchart illustrating the flow of processing for each device of the third embodiment. Figure 22 is a drawing illustrating an example of MPD technology. Figure 23 is a diagram illustrating an example of the technology of skill registration information metadata. FIG. 24 is a block diagram illustrating an example of another configuration of a receiving device. Figure 25 is a diagram illustrating an example of a computer configuration. Hereinafter, embodiments of the present technology will be described with reference to the drawings. In addition, the description will be carried out in the following order. 1. System Configuration 2. Embodiments of the present technology (1) First embodiment: Configuration for changing the invocation name on the local side (2) Second embodiment: A configuration in which the cloud side uses an Alias skill to switch the target's skill. (3) Third embodiment: A configuration for creating and updating private skills 3. Variation Example 4. Components of a Computer <1. System Configuration> (Configuration of the Content-Voice AI Linkage System) FIG. 1 is a block diagram illustrating an example of the configuration of an embodiment of a content-voice AI linkage system applying the present technology. The content-voice AI linkage system (1) is a system for delivering content, and it is possible to use voice AI assistance services in conjunction with the delivered content. In FIG. 1, the content-voice AI linkage system (1) is configured to include a broadcasting transmission system (10), a receiving device (20), a voice user interface device (30), a voice assistance server (40), and a processing server (50). In addition, in the content and voice AI linkage system (1), the receiving de