# US 2021/0343292 A1 · Techniques for converting natural speech to programming code

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

- Number: US 2021/0343292 A1
- Document ID: US20210343292A1
- Status: Published application
- Kind: A1
- Application number: 17/246,220
- Filed: 2021-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-05-04
- Assignees: Lingua Robotica, Inc.
- Applicants: Lingua Robotica, Inc.
- Inventors: Austin COX
- Web page: https://patentgrep.com/patent/US20210343292A1

## CPC

- G06F 40/279: Recognition of textual entities
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 8/31: {Programming languages or programming paradigms}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 40/205: Parsing
- 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

Described herein are a system and techniques for generating programming code from unstructured text (e.g., natural speech). To do this, upon receiving a request for programming code, the system parses unstructured text using natural language processing to identify an entity. The system then identifies a template associated with that entity. The template may also be associated with a particular programming language. Once a template has been selected, a number of parameters associated with the template are identified. The parameters are then matched to data values included in the unstructured text. Once data values have been identified for each of the parameters, the requested programming code is generated using the template and data values.

## Claims

### Claim 1

A method comprising:
receiving a request for programming code from a user, the request including unstructured text data;
identifying, from the unstructured text data, an intended entity;
identifying, from a set of templates, a template associated with the intended entity, the template including a set of parameters;
determining, from the unstructured text data, values for each parameter in the set of parameters; and
generating the programming code by populating each parameter in the set of parameters of the template with its determined value.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining a programming language associated with the request, wherein the template is further associated with the programming language.

### Claim 3 (depends on 2)

The method of claim 2, wherein the programming language is selected by the user.

### Claim 4 (depends on 1)

The method of claim 1, wherein the intended entity is identified from the unstructured text data using one or more natural language processing techniques.

### Claim 5 (depends on 1)

The method of claim 1, wherein receiving the request for programming code from the user comprises receiving an audio request and converting the audio request into a text-based request.

### Claim 6 (depends on 5)

The method of claim 5, wherein the audio request is converted into the text-based request using one or more speech to text techniques.

### Claim 7 (depends on 1)

The method of claim 1, wherein the intended entity is determined based at least in part on a context in which the request has been provided.

### Claim 8

A computing system comprising:
a processor; and
a memory including instructions that, when executed with the processor, cause the computing system to, at least:
receive a request for programming code from a user, the request including unstructured text data;
identify, from the unstructured text data, an intended entity;
identify, from a set of templates, a template associated with the intended entity, the template including a set of parameters;
determine, from the unstructured text data, values for each parameter in the set of parameters; and
generate the programming code by populating each parameter in the set of parameters of the template with its determined value.

### Claim 9 (depends on 8)

The computing system of claim 8, wherein the instructions comprise further instructions that, when executed with the processor, cause the computing system to determine a programming language associated with the request, wherein the template is further associated with the programming language.

### Claim 10 (depends on 9)

The computing system of claim 9, wherein causing the computing system to determine the programming language comprises receiving an input by the user.

### Claim 11 (depends on 8)

The computing system of claim 8, wherein the intended entity is identified from the unstructured text data using one or more natural language processing techniques.

### Claim 12 (depends on 8)

The computing system of claim 8, wherein the instructions to receive the request for programming code from the user comprises receiving an audio request and converting the audio request into a text-based request.

### Claim 13 (depends on 12)

The computing system of claim 12, wherein the audio request is converted into the text-based request using one or more speech to text techniques.

### Claim 14 (depends on 8)

The computing system of claim 8, wherein the intended entity is determined based at least in part on a context in which the request has been provided.

### Claim 15

A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive a request for programming code from a user, the request including unstructured text data;
identify, from the unstructured text data, an intended entity;
identify, from a set of templates, a template associated with the intended entity, the template including a set of parameters;
determine, from the unstructured text data, values for each parameter in the set of parameters; and
generate the programming code by populating each parameter in the set of parameters of the template with its determined value.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions comprise further instructions that, when executed by the one or more processors, cause the one or more processors to determine a programming language associated with the request, wherein the template is further associated with the programming language.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the intended entity is identified from the unstructured text data using one or more natural language processing techniques.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions to receive the request for programming code from the user comprise further instructions to cause the one or more processors to receive an audio request and convert the audio request into a text-based request.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the audio request is converted into the text-based request using one or more speech to text techniques.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the intended entity is determined based at least in part on a context in which the request has been provided.
