# US 2021/0082403 A1 · Expediting interaction with a digital assistant by predicting user responses

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0082403 A1
- Document ID: US20210082403A1
- Status: Published application
- Kind: A1
- Application number: 17/103,098
- Filed: 2020-11-24
- Published: 2021-03-18
- Earliest claimed: 2018-12-06
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Vipul AGARWAL; Rahul Kumar JHA; Soumya BATRA; Karthik TANGIRALA; Mohammad MAKARECHIAN; Imed ZITOUNI
- Web page: https://patentgrep.com/patent/US20210082403A1

## CPC

- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L 15/07: to the speaker
- G06F 16/3349: Reuse of stored results of previous queries
- 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)
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/225: {Feedback of the input speech}
- 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

A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system, comprising:
a processor; and
a memory coupled to the processor and storing instructions that, when executed by the processor, perform operations, comprising:
receiving a natural language system prompt generated by a digital assistant;
generating a predicted response based, at least in part, on contextual information associated with the system prompt, the predicted response including a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on a record entry in a data store, the record entry comprising:
a previously-generated system prompt;
contextual information describing a circumstance in which the previously-generated system prompt was issued; and
a previously-encountered response to the previously-generated system prompt; and
selecting a dialogue action from a plurality of dialogue actions based, at least in part, on:
a confidence value associated with the predicted response, the confidence value describing a confidence level associated with the predicted response; and
a dialogue action in which the predicted response is provided to the digital assistant as a proxy response to the system prompt.

### Claim 22 (depends on 21)

The system of claim 21, further comprising instructions for selecting the dialogue action when a confidence value associated with the dialogue action is above a threshold value.

### Claim 23 (depends on 21)

The system of claim 21, wherein the dialogue action expedites an interaction between the individual and the digital assistant by automatically providing the dialog action as the proxy response to the system prompt.

### Claim 24 (depends on 21)

The system of claim 21, wherein the contextual information includes a received query that caused generation of the previously-generated system prompt.

### Claim 25 (depends on 21)

The system of claim 21, wherein the contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

### Claim 26 (depends on 21)

The system of claim 21, wherein the contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

### Claim 27 (depends on 21)

The system of claim 21, further comprising instructions for providing a confirmation prompt to the individual, the confirmation prompt being based, at least in part, on providing the predicted response as the proxy response to the system prompt.

### Claim 28

A method, comprising:
receiving a natural language system prompt generated by a digital assistant;
generating a predicted response based, at least in part, on contextual information associated with the system prompt, the predicted response including a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on a record entry in a data store, the record entry comprising:
a previously-generated system prompt;
contextual information describing a circumstance in which the previously-generated system prompt was issued; and
a previously-encountered response to the previously-generated system prompt; and
selecting a dialogue action from a plurality of dialogue actions based, at least in part, on:
a confidence value associated with the predicted response, the confidence value describing a confidence level associated with the predicted response; and
a dialogue action in which the predicted response is provided to the digital assistant as a proxy response to the system prompt.

### Claim 29 (depends on 28)

The method of claim 28, further comprising selecting the dialogue action when a confidence value associated with the dialogue action is above a threshold value.

### Claim 30 (depends on 28)

The method of claim 28, wherein the dialogue action expedites an interaction between the individual and the digital assistant by automatically providing the dialog action as the proxy response to the system prompt.

### Claim 31 (depends on 28)

The method of claim 28, wherein the contextual information includes a received query that caused generation of the previously-generated system prompt.

### Claim 32 (depends on 28)

The method of claim 28, wherein the contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

### Claim 33 (depends on 28)

The method of claim 28, wherein the contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

### Claim 34 (depends on 28)

The method of claim 28, further comprising providing a confirmation prompt to an individual, the confirmation prompt being based, at least in part, on providing the predicted response as the proxy response to the system prompt.

### Claim 35

A method, comprising:
receiving a natural language system prompt generated by a digital assistant;
generating a predicted response based, at least in part, on contextual information associated with the system prompt, the predicted response including a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on a record entry in a data store, the record entry comprising one or more of:
a previously-generated system prompt;
contextual information describing a circumstance in which the previously-generated system prompt was issued; or
a previously-encountered response to the previously-generated system prompt; and
selecting a dialogue action from a plurality of dialogue actions based, at least in part, on
a confidence value associated with the predicted response, the confidence value describing a confidence level associated with the predicted response.

### Claim 36 (depends on 35)

The method of claim 35, further comprising selecting the dialog action from the plurality of dialogue actions based, at least in part, on a dialogue action in which the predicted response is provided to the digital assistant as a proxy response to the system prompt.

### Claim 37 (depends on 36)

The method of claim 36, further comprising providing a confirmation prompt to an individual, the confirmation prompt being based, at least in part, on providing the predicted response as the proxy response to the system prompt.

### Claim 38 (depends on 35)

The method of claim 35, wherein the contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

### Claim 39 (depends on 35)

The method of claim 35, wherein the contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

### Claim 40 (depends on 35)

The method of claim 35, wherein the contextual information includes a received query that caused generation of the previously-generated system prompt.
