# US 2025/0165379 A1 · Action sequence generation for intelligent software testing

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

- Number: US 2025/0165379 A1
- Document ID: US20250165379A1
- Status: Published application
- Kind: A1
- Application number: 18/517,223
- Filed: 2023-11-22
- Published: 2025-05-22
- Earliest claimed: 2023-11-22
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: William Tigard BAKER; Swamy V.P.L.N. NALLAMALLI; Dallas Allen WARREN; Aaron Edward DIETRICH; Piyush GUPTA; Robert M. FRIES
- Web page: https://patentgrep.com/patent/US20250165379A1

## CPC

- G06F 11/3684: {for test design, e.g. generating new test cases}
- G06F 8/51: Source to source
- G06F 11/3688: {for test execution, e.g. scheduling of test suites}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system and method for providing automated action sequence generation. An action sequence generated utilizes a natural language processing system to automatically generate a sequence of actions that a software testing tool can exercise on a software under test based on identified natural language instructions that describe the actions. For instance, the natural language processing system identifies cues describing action instructions and converts the instructions into the software testing tool's programming language-specific language for executing actions in a sequence (i.e., an action sequence). The software testing tool can then replay action sequences and perform specific actions requested by or otherwise relevant to the customer.

## Claims

### Claim 1

A method, comprising:
receiving natural language content describing interactions with software under test;
identifying, using a natural language processing system (NLPS), natural language instructions in the natural language content based on the interactions;
converting the natural language instructions into programming language-specific instructions that, when executed by a software testing tool, perform testing of the software under test, where the programming language-specific instructions are formatted in a programming language-specific language of the software testing tool; and
storing the programming language-specific instructions as a sequence of actions for testing the software under test.

### Claim 2 (depends on 1)

The method of claim 1, wherein identifying the natural language instructions comprises:
generating a prompt for the NLPS, wherein the prompt includes the natural language content and a request for the NLPS to identify actions that can be performed against the software under test; and
providing the prompt as input to the NLPS.

### Claim 3 (depends on 2)

The method of claim 2, further comprising, including, in the prompt, at least one of:
examples of the actions that can be performed against the software under test; or
natural language metadata that describe the actions that can be performed against the software under test.

### Claim 4 (depends on 2)

The method of claim 2, wherein the prompt further includes a request to convert the identified natural language instructions into the programming language-specific instructions.

### Claim 5 (depends on 2)

The method of claim 2, wherein the prompt further includes examples of the programming language-specific instructions that correspond to the natural language instructions.

### Claim 6 (depends on 2)

The method of claim 2, wherein:
generating the prompt comprises generating a first prompt; and
converting the identified natural language instructions into the programming language-specific instructions comprises:
providing the first prompt as a first input into a first NLPS, where the first NLPS is an external NLPS;
in response to the first input, receiving a first output from the first NLPS, wherein the first output includes identified natural language instructions;
generating a second prompt;
including, in the second prompt, the identified natural language instructions and a request to convert the identified natural language instructions into the programming language-specific instructions;
providing the second prompt as a second input for a second NLPS; and
in response to the second input, receiving a second output from the second NLPS, wherein the second output includes the programming language-specific instructions.

### Claim 7 (depends on 1)

The method of claim 1, wherein the NLPS is trained on training data including recorded actions performed against the software under test, the training data comprising:
respective programming language-specific instructions for each recorded action; and
natural language metadata describing the recorded action.

### Claim 8 (depends on 1)

The method of claim 1, wherein receiving the natural language content comprises at least one of:
receiving a code update submission corresponding to a change made to source code of the software under test;
receiving a comment included in the source code;
receiving manually-authored instructions for testing the software under test;
a design document for the software under test; or
receiving a project management specification for the software under test.

### Claim 9 (depends on 1)

The method of claim 1, wherein receiving the natural language content comprises receiving a message via a messaging interface.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
performing the sequence of actions against the software under test; and
receiving action telemetry data recorded about each action in the sequence of actions performed against the software under test, the action telemetry data including:
respective programming language-specific instructions for each recorded action; and
natural language metadata describing each recorded action.

### Claim 11 (depends on 10)

The method of claim 10, further comprising using the action telemetry data as training data for the NLPS.

### Claim 12

A computing system, comprising: a processing system; and
memory storing instructions that, when executed, cause the computing system to perform operations comprising:
receiving natural language content from a natural language source describing testing a software under test;
identifying, in the natural language content, natural language instructions that describe actions that can be performed against the software under test;
converting the identified natural language instructions into programming language-specific instructions that a software testing tool can perform against the software under test in a sequence; and
storing the programming language-specific instructions as an action sequence.

### Claim 13 (depends on 12)

The computing system of claim 12, wherein the natural language source includes at least one of: a message;
a code update submission corresponding to a change made to source code of the software under test;
a comment included in the source code;
manually-authored instructions for testing the software under test;
a project management specification for the software under test; or
a design document.

### Claim 14 (depends on 12)

The computing system of claim 12, wherein identifying the natural language instructions that describe actions that can be performed against the software under test comprises generating an input for a natural language processing system (NLPS), wherein the input includes the natural language content and a request for the NLPS to identify the natural language instructions describing the actions that can be performed against the software under test.

### Claim 15 (depends on 14)

The computing system of claim 14, wherein the input further comprises:
examples of the actions that can be performed against the software under test; and
natural language metadata that describe the actions.

### Claim 16 (depends on 15)

The computing system of claim 15, wherein the input further comprises:
a request to convert the identified natural language instructions into the programming language-specific instructions; and
example programming language-specific instructions that correspond to the natural language metadata.

### Claim 17 (depends on 14)

The computing system of claim 14, the operations further comprising:
providing the input to the NLPS;
in response to the input, receiving an output from the NLPS, wherein the output includes the identified natural language instructions; and
converting the identified natural language instructions into the programming language-specific instructions.

### Claim 18 (depends on 12)

The computing system of claim 12, further comprising:
receiving, in response to executing the programming language-specific instructions against the software under test, action telemetry data recorded for each action in the action sequence, the action telemetry data including:
respective programming language-specific instructions for each recorded action; and
natural language metadata describing each recorded action; and
training the NLPS to identify the natural language instructions that describe the actions that can be performed against the software under test using training data including the action telemetry data.

### Claim 19

A software testing tool, comprising:
a processing system; and
memory storing instructions that, when executed, cause the software testing tool to:
receive natural language content describing interactions with a software under test;
identify, using natural language processing, natural language instructions in the natural language content based on the described interactions; and
convert the natural language instructions into programming language-specific instructions that, when executed in an action sequence, perform testing of the software under test.

### Claim 20 (depends on 19)

The software testing tool of claim 19, wherein identifying the natural language instructions and converting the natural language instructions into the programming language-specific instructions is based on training data including recorded actions performed against the software under test, the training data comprising: respective programming language-specific instructions for each recorded action; and
natural language metadata describing each recorded action.
