# US 11,908,462 B2 · Adaptive interface in a voice-activated network > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,462 B2 - Document ID: US11908462B2 - Status: Granted - Kind: B2 - Application number: 17/699,580 - Filed: 2022-03-21 - Published: 2022-06-30 - Granted: 2024-02-20 - Earliest claimed: 2018-05-11 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Gleb Skobeltsyn; Mihaly Kozsevnyikov; Vladimir Vuskovic - Web page: https://patentgrep.com/patent/US11908462B2 ## CPC - G06F 16/90332: {Natural language query formulation or dialogue systems} - G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning} - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G06F 40/30: Semantic analysis - G10L 15/1822: {Parsing for meaning understanding} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G06F 40/268: Morphological analysis - G06F 40/295: Named entity recognition - G10L 2015/223: {Execution procedure of a spoken command} - G10L 2015/226: {using non-speech characteristics} - 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 The systems and methods of the present disclosure generally relate to a data processing system that can identify and surface alternative requests when presented with ambiguous, unclear, or other requests to which a data processing system may not be able to respond. The data processing system can improve the efficiency of network transmissions to reduce network bandwidth usage and processor utilization by selecting alternative requests that are responsive to the intent of the original request. ## Claims ### Claim 1 A system to generate voice-based interfaces in a networked system, comprising: a data processing system comprising one or more processors to: receive an input audio signal detected by a sensor of a client device; determine a plurality of candidate requests based on past requests received by the data processing system, each of the plurality of candidate requests corresponding to a different semantic meaning of the input audio signal; generate a first action data structure for a first candidate request of the plurality of candidate requests and a second action data structure for a second candidate request of the plurality of candidate requests; select, based on the first candidate request or the first action data structure, a content item provided by a third party content provider; and transmit, to the client device, the first action data structure and the content item for the first candidate request of the plurality of candidate requests based on an interface type of the client device. ### Claim 2 (depends on 1) The system of claim 1, comprising the data processing system to: select the content item based on the first candidate request; and generate the first action data structure with the content item. ### Claim 3 (depends on 1) The system of claim 1, comprising the data processing system to: select the content item based on the first action data structure; and transmit the content item to the client device for output by the client device. ### Claim 4 (depends on 1) The system of claim 1, wherein the content item comprises audio output. ### Claim 5 (depends on 1) The system of claim 1, wherein the interface type indicates at least one of a display format of the client device, a display size of the client device, a display availability of the client device, or a client device type. ### Claim 6 (depends on 1) The system of claim 1, comprising: the data processing system to transmit, to the client device, the second action data structure for the second candidate request to be rendered after the first action data structure. ### Claim 7 (depends on 1) The system of claim 1, comprising the data processing system to: parse the input audio signal to identify a request in the input audio signal; determine a confidence score for a semantic meaning of the request; and select the plurality of candidate requests based on the confidence score being below a predetermined threshold. ### Claim 8 (depends on 1) The system of claim 1, comprising the data processing system to: identify a term in the input audio signal having a plurality of interpretations; and select a number of the plurality of candidate requests based on the term in the input audio signal having the plurality of interpretations. ### Claim 9 (depends on 1) The system of claim 1, comprising the data processing system to: parse the input audio signal to identify a primary request in the input audio signal; determine a response to the primary request; determine a generality score for the response to the primary request in the input audio signal; determine a generality score for a response to each of the plurality of candidate requests; and select a number of the plurality of candidate requests based on a comparison of the generality score for the response to the request in the input audio signal and the generality score for the response to each of the plurality of candidate requests. ### Claim 10 (depends on 1) The system of claim 1, comprising the data processing system to: transmit an audio signal request comprising a prompt; receive a second input audio signal from the client device, the second input audio signal generated in response to the prompt; and select a number of the plurality of candidate requests based the second input audio signal. ### Claim 11 A method of generating voice-based interfaces in a networked system, comprising: receiving, by a data processing system comprising one or more processors, an input audio signal detected by a sensor of a client device; determining, by the data processing system, a plurality of candidate requests based on past requests received by the data processing system, each of the plurality of candidate requests corresponding to a different semantic meaning of the input audio signal; generating, by the data processing system, a first action data structure for a first candidate request of the plurality of candidate requests and a second action data structure for a second candidate request of the plurality of candidate requests; selecting, by the data processing system based on the first candidate request or the first action data structure, a content item provided by a third party content provider; and transmitting, by the data processing system to the client device, the first action data structure and the content item for the first candidate request of the plurality of candidate requests based on an interface type of the client device. ### Claim 12 (depends on 11) The method of claim 11, comprising: selecting the content item based on the first candidate request; and generating the first action data structure with the content item. ### Claim 13 (depends on 11) The method of claim 11, comprising: selecting the content item based on the first action data structure; and transmitting the content item to the client device for output by the client device. ### Claim 14 (depends on 11) The method of claim 11, wherein the content item comprises audio output. ### Claim 15 (depends on 11) The method of claim 11, wherein the interface type indicates at least one of a display format of the client device, a display size of the client device, a display availability of the client device, or a client device type. ### Claim 16 (depends on 11) The method of claim 11, comprising: transmitting, to the client device, the second action data structure for the second candidate request to be rendered after the first action data structure. ### Claim 17 (depends on 11) The method of claim 11, comprising: parsing the input audio signal to identify a request in the input audio signal; determining a confidence score for a semantic meaning of the request; and selecting the plurality of candidate requests based on the confidence score being below a predetermined threshold. ### Claim 18 (depends on 11) The method of claim 11, comprising: identifying a term in the input audio signal having a plurality of interpretations; and selecting a number of the plurality of candidate requests based on the term in the input audio signal having the plurality of interpretations. ### Claim 19 (depends on 11) The method of claim 11, comprising: parsing the input audio signal to identify a primary request in the input audio signal; determining a response to the primary request; determining a generality score for the response to the primary request in the input audio signal; determining a generality score for a response to each of the plurality of candidate requests; and selecting the number of the plurality of candidate requests based on a comparison of the generality score for the response to the request in the input audio signal and the generality score for the response to each of the plurality of candidate requests. ### Claim 20 (depends on 11) The method of claim 11, comprising: transmitting an audio signal request comprising a prompt; receiving a second input audio signal from the client device, the second input audio signal generated in response to the prompt; and selecting a number of the plurality of candidate requests based the second input audio signal.