# US 12,008,992 B2 · Generating dialog responses from dialog response frame based on device capabilities > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,992 B2 - Document ID: US12008992B2 - Status: Granted - Kind: B2 - Application number: 17/414,331 - Filed: 2020-01-10 - Published: 2022-02-17 - Granted: 2024-06-11 - Earliest claimed: 2019-01-23 - Assignees: Sony Group Corporation - Applicants: Sony Group Corporation - Inventors: Junki Ohmura - Web page: https://patentgrep.com/patent/US12008992B2 ## CPC - G06F 40/186: Templates - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G06F 3/16: Sound input; Sound output (speech processing G10L) - G06F 40/35: Discourse or dialogue representation - G06F 40/56: Natural language generation - G10L 13/08: Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination - G10L 15/01: Assessment or evaluation of speech recognition systems - G10L 13/00: Speech synthesis; Text to speech systems - G10L 2015/223: {Execution procedure of a spoken command} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract An information processing apparatus acquires a capability for each of agent devices that each output a dialog response, generates the dialog response corresponding to the capability, based on a general-purpose dialog response frame, and deploys the dialog response to each of the agent devices. The capability indicates a combination of interfaces available for each of the agent devices. The apparatus applies to the general-purpose dialog response frame a conversion template including plural templates that convert values of parameters of the general-purpose dialog response frame into converted forms in accordance with the combination of interfaces available for each of the agent devices, and generate the dialog response for each of the agent devices, using the converted forms converted from the values of the parameters of the general-purpose dialog response frame. ## Claims ### Claim 1 An information processing apparatus comprising: circuitry configured to acquire a capability for each of agent devices that each output a dialog response, the capability indicating a combination of interfaces available for each of the agent devices; generate the dialog response corresponding to the capability based on a general-purpose dialog response frame at a time of generation of the dialog response, and deploy the dialog response to each of the agent devices, wherein the circuitry is further configured to apply to the general-purpose dialog response frame a conversion template including plural templates that convert values of parameters of the general-purpose dialog response frame into converted forms in accordance with the combination of interfaces available for each of the agent devices, and generate the dialog response for each of the agent devices, by using the converted forms that were converted from the values of the parameters of the general-purpose dialog response frame. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the capability includes interface information regarding the combination of interfaces for each of the agent devices and capability information regarding ability of the interfaces. ### Claim 3 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to convert the dialog response corresponding to the capability into the dialog response corresponding to another capability. ### Claim 4 (depends on 3) The information processing apparatus according to claim 3, wherein the circuitry is further configured to convert the dialog response by using a rule-based conversion algorithm or a machine learning-based conversion algorithm. ### Claim 5 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to select one or more interfaces from among the combination of interfaces on the basis of context information regarding context about a user of the agent devices, and generate the dialog response corresponding to the interfaces that were selected. ### Claim 6 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to select one or more interfaces from among the combination of interfaces corresponding to accessibility, and generate the dialog response corresponding to the interfaces that were selected. ### Claim 7 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to include additional information in the dialog response. ### Claim 8 An information processing method by an information processing apparatus, the information processing method comprising: acquiring a capability for each of agent devices that each output a dialog response, the capability indicating a combination of interfaces available for each of the agent devices; generating the dialog response corresponding to the capability based on a general-purpose dialog response frame at a time of generation of the dialog response; and deploying the dialog response to each of the agent devices, wherein the method further comprises applying to the general-purpose dialog response frame a conversion template including plural templates that convert values of parameters of the general-purpose dialog response frame into converted forms in accordance with the combination of interfaces available for each of the agent devices, and generating the dialog response for each of the agent devices, by using the converted folnis that were converted from the values of the parameters of the general-purpose dialog response frame.