# US 2026/0073151 A1 · Multi-dimensional entity generation from natural language input

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

- Number: US 2026/0073151 A1
- Document ID: US20260073151A1
- Status: Published application
- Kind: A1
- Application number: 19/392,500
- Filed: 2025-11-18
- Published: 2026-03-12
- Earliest claimed: 2022-12-19
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Samuel Edward SCHILLACE; Umesh MADAN; Devis LUCATO
- Web page: https://patentgrep.com/patent/US20260073151A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 16/56: having vectorial format
- G06F 30/12: characterised by design entry means specially adapted for CAD, e.g. graphical user interfaces [GUI] specially adapted for CAD
- G06F 40/186: Templates
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0475: Generative networks
- G06N 3/048: Activation functions
- G06N 3/0499: Feedforward networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Aspects of the present disclosure relate to systems and methods for creating a multi-dimensional entity (MDE) based on natural language (NL) input. A user may provide NL input into an application. One or more skills may be identified for the NL input, each of which has an associated prompt template. For example, a skill is associated with a computer-aided design and/or three-dimensional manufacturing application and/or file format, thereby enabling the generation of output associated with such applications and/or file formats. In examples, a skill chain may be generated that includes one or more skills with which to generate MDE output accordingly.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform a set of operations, the set of operations comprising:
populating, for each skill of a skill chain and based on received natural language input comprising a description of a multidimensional entity, a corresponding prompt template for the skill;
processing the respective populated prompt template for each skill to generate respective machine learning model output;
generating, based on the machine learning model output for the skill chain, the multi-dimensional entity output; and
providing, to the computing device, the generated multi-dimensional entity output.

### Claim 22 (depends on 21)

The system of claim 21, wherein each skill of the skill chain is associated with at least a portion of the received natural language input.

### Claim 23 (depends on 21)

The system of claim 21, wherein at least one skill of the skill chain is associated with a target application or a target data format for the multi-dimensional entity output.

### Claim 24 (depends on 23)

The system of claim 23, wherein the natural language input comprises a target output indication of the target application or the target data format.

### Claim 25 (depends on 21)

The system of claim 21, wherein:
a first skill of the skill chain is associated with a first model subpart of the multi-dimensional entity; and
a second skill of the skill chain is associated with a second model subpart of the multi-dimensional entity.

### Claim 26 (depends on 25)

The system of claim 25, wherein a third skill of the skill chain processes model output of the first skill and model output of the second skill to combine the model outputs, thereby generating the multi-dimensional entity output.

### Claim 27 (depends on 21)

The system of claim 21, wherein the generated multi-dimensional entity output includes at least one of:
instructions to render the multi-dimensional entity in a virtual environment; or instructions to fabricate a physical representation of the multi-dimensional entity.

### Claim 28

A method for generating a multi-dimensional entity according to a natural language input, the method comprising:
generating, using a machine learning model, a skill chain to generate a multi-dimensional entity based on a natural language request, the generating comprising generating a prompt based at least in part on the natural language request, thereby causing the machine learning model to generate the skill chain based on the prompt;
processing, for each skill in the skill chain and using a machine learning model, a populated prompt template for the skill to generate model output for the skill;
combining the model output for each skill of the skill chain to generate the multi-dimensional entity output; and
generating, based on the multi-dimensional entity output, a display of the multi-dimensional entity.

### Claim 29 (depends on 28)

The method of claim 28, wherein:
the natural language request comprises an indication of an existing multi-dimensional entity in a first format; and
the skill chain comprises a skill associated with a second format that is different than the first format.

### Claim 30 (depends on 29)

The method of claim 29, wherein a skill of the skill chain obtains comprising data for the existing multi-dimensional entity in the first format.

### Claim 31 (depends on 29)

The method of claim 29, wherein the prompt further comprises a target indication for the second format.

### Claim 32 (depends on 31)

The method of claim 31, wherein the target indication indicates at least one of a target application or a target data format for the multi-dimensional entity output.

### Claim 33 (depends on 28)

The method of claim 28, wherein each skill of the skill chain is associated with at least a portion of the user input.

### Claim 34

A method for generating a multi-dimensional entity according to a natural language input, the method comprising:
populating, for each skill of a skill chain and based on the natural language input comprising a description of a multidimensional entity, a corresponding prompt template for the skill;
processing the respective populated prompt template for each skill to generate respective machine learning model output;
generating, based on the machine learning model output for the skill chain, the multi-dimensional entity output; and
providing, to the computing device, the generated multi-dimensional entity output.

### Claim 35 (depends on 34)

The method of claim 34, wherein each skill of the skill chain is associated with at least a portion of the received natural language input.

### Claim 36 (depends on 34)

The method of claim 34, wherein at least one skill of the skill chain is associated with a target application or a target data format for the multi-dimensional entity output.

### Claim 37 (depends on 36)

The method of claim 36, wherein the natural language input comprises a target output indication of the target application or the target data format.

### Claim 38 (depends on 34)

The method of claim 34, wherein:
a first skill of the skill chain is associated with a first model subpart of the multi-dimensional entity; and
a second skill of the skill chain is associated with a second model subpart of the multi-dimensional entity.

### Claim 39 (depends on 38)

The method of claim 38, wherein a third skill of the skill chain processes model output of the first skill and model output of the second skill to combine the model outputs, thereby generating the multi-dimensional entity output.

### Claim 40 (depends on 34)

The method of claim 34, wherein the generated multi-dimensional entity output includes at least one of:
instructions to render the multi-dimensional entity in a virtual environment; or
instructions to fabricate a physical representation of the multi-dimensional entity.
