# US 2026/0244934 A1 · Method And Apparatus For Transforming Artificial Intelligence Model Between Framework And Intermediate Representation

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

- Number: US 2026/0244934 A1
- Document ID: US20260244934A1
- Status: Published application
- Kind: A1
- Application number: 19/349,051
- Filed: 2025-10-03
- Published: 2026-08-20
- Earliest claimed: 2025-02-20
- Assignees: Nota, Inc.
- Applicants: Nota, Inc.
- Inventors: Huiseong GIM; Donggeun KIM; Shinkook CHOI
- Web page: https://patentgrep.com/patent/US20260244934A1

## CPC

- G06F 16/904: Browsing; Visualisation therefor (for navigating the web G06F16/954; browsing optimisation for the web G06F16/957)
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/048: Activation functions
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N 3/10: Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N 3/105: {Shells for specifying net layout}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/025: Extracting rules from data
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one embodiment, a method for transforming an artificial model between a framework and an intermediate representation, performed by a computing device, is disclosed. The method may comprise: receiving target model operator information regarding target model operators executable in a target framework; determining a target module corresponding to each of the target model operators from the target model operator information, based on an execution-based analysis method using execution of a test artificial intelligence model, or an embedding-based analysis method using embedding transformation between a model operator and an atomic operator independent of a framework; and generating a target mapping table for the target framework by mapping each of the target model operators and the determined target module, and wherein the target module, as the intermediate representation of the target model operator, is composed of a combination of one or more nodes corresponding to the atomic operator.

## Claims

### Claim 1

A method for transforming an artificial model between a framework and an intermediate representation, performed by a computing device, comprising:
receiving target model operator information regarding target model operators executable in a target framework;
determining a target module corresponding to each of the target model operators from the target model operator information, based on an execution-based analysis method using execution of a test artificial intelligence model, or an embedding-based analysis method using embedding transformation between a model operator and an atomic operator independent of a framework; and
generating a target mapping table for the target framework by mapping each of the target model operators and the determined target module, and
wherein the target module, as the intermediate representation of the target model operator, is composed of a combination of one or more nodes corresponding to the atomic operator.

### Claim 2 (depends on 1)

The method of claim 1, wherein
when the target framework is a first framework, the target module is determined based on a first execution-based analysis method of tracing atomic operators called during execution of the test artificial intelligence model, and
when the target framework is a second framework, the target module is determined based on a second execution-based analysis method of comparing execution results of the test artificial intelligence model or based on the embedding-based analysis method.

### Claim 3 (depends on 2)

The method of claim 2, wherein
the first framework corresponds to a framework supporting a function of converting model operators included in the test artificial intelligence model into an intermediate representation structure expressed in units of atomic operators, and
the second framework corresponds to a framework not supporting a function of converting model operators included in the test artificial intelligence model into an intermediate representation structure expressed in units of atomic operators.

### Claim 4 (depends on 2)

The method of claim 2, wherein
when the target framework is the second framework, the determining the target module is performed after generating a first mapping table for the first framework.

### Claim 5 (depends on 2)

The method of claim 2, wherein when the target framework is the second framework, the target module is determined based on:
generating a candidate mapping table corresponding to the target framework based on the second execution-based analysis method or the embedding-based analysis method, the candidate mapping table corresponding to a table in which one or more candidate modules are mapped to one target model operator; and
determining the target module corresponding to each of the target model operators by comparing execution results of each of the target model operators and execution results of each of the one or more candidate modules mapped in the candidate mapping table, and
wherein the generating the candidate mapping table is performed using a plurality of first modules predetermined for the first framework.

### Claim 6 (depends on 2)

The method of claim 2, wherein when the target framework is the first framework, the determining the target module comprises:
generating a first test artificial intelligence model including the target model operators;
converting the target model operators included in the first test artificial intelligence model into a first intermediate representation structure expressed in units of atomic operators by executing the first test artificial intelligence model;
identifying, based on the target model operator information, a combination of atomic operators corresponding to each of the target model operators and an execution order thereof in the first intermediate representation structure; and
determining the target module corresponding to each of the target model operators based on the identified combination of atomic operators and the execution order.

### Claim 7 (depends on 2)

The method of claim 2, wherein when the target framework is the second framework, the determining the target module comprises:
generating a second test artificial intelligence model including the target model operators; and
determining the target module corresponding to each of the target model operators included in the second test artificial intelligence model, based on execution results of first input data for the second test artificial intelligence model and execution results of the first input data for a plurality of pre-stored candidate modules, and
wherein the plurality of pre-stored candidate modules correspond to a plurality of first modules predetermined for the first framework.

### Claim 8 (depends on 7)

The method of claim 7, wherein
the second test artificial intelligence model consists of a single first target model operator, and
the determining the target module based on execution results of the first input data for the second test artificial intelligence model and execution results of the first input data for the plurality of pre-stored candidate modules comprises:
generating an error between execution results of the first input data for the first target model operator and execution results of the first input data for the plurality of pre-stored candidate modules;
identifying one or more candidate modules among the plurality of pre-stored candidate modules in which the error is less than or equal to a threshold error; and
determining the target module corresponding to the first target model operator among the identified one or more candidate modules, by comparing execution results of second input data for the first target model operator and execution results of the second input data for the identified one or more candidate modules.

### Claim 9 (depends on 7)

The method of claim 7, wherein the determining the target module based on execution results of the first input data for the second test artificial intelligence model and execution results of the first input data for the plurality of pre-stored candidate modules comprises:
generating an error between execution results of the first input data for the second test artificial intelligence model and execution results of the first input data for candidate module combinations composed of the plurality of pre-stored candidate modules;
identifying one or more candidate module combinations in which the error is less than or equal to a threshold error among the candidate module combinations; and
determining the target module corresponding to each of the target model operators included in the second test artificial intelligence model within the identified one or more candidate module combinations, by comparing execution results of third input data for each of the target model operators and execution results of the third input data for each of the candidate modules included in the identified one or more candidate module combinations.

### Claim 10 (depends on 7)

The method of claim 7, wherein
the second test artificial intelligence model includes a second target model operator and a third target model operator, the third target model operator receiving an output value of the second target model operator, and
the determining the target module based on execution results of the first input data for the second test artificial intelligence model and execution results of the first input data for the plurality of pre-stored candidate modules comprises:
generating a first error between a first intermediate execution result of the second target model operator for the first input data and execution results of the first input data for the plurality of pre-stored candidate modules;
identifying one or more first candidate modules among the plurality of pre-stored candidate modules in which the first error is less than or equal to a threshold error;
generating a second error between a second intermediate execution result output by the third target model operator using the first intermediate execution result as input and execution results output by the plurality of pre-stored candidate modules using the first intermediate execution result as input;
identifying one or more second candidate modules among the plurality of pre-stored candidate modules in which the second error is less than or equal to the threshold error; and
determining the target module corresponding to each of the second target model operator and the third target model operator, based on the identified one or more first candidate modules and the identified one or more second candidate modules.

### Claim 11 (depends on 1)

The method of claim 1, wherein the determining the target module comprises:
generating a target model operator embedding vector corresponding to each of the target model operators based on the target model operator information;
generating an atomic operator embedding vector corresponding to each of atomic operators based on information regarding the atomic operators; and
determining the target module corresponding to each of the target model operators based on a vector similarity between the target model operator embedding vector and the atomic operator embedding vector.

### Claim 12 (depends on 11)

The method of claim 11, wherein
the target model operator embedding vector is generated by performing a filtering process of deleting tokens corresponding to predefined stopwords or selecting tokens corresponding to predefined keywords for a plurality of target model operator tokens obtained by tokenizing the target model operator information corresponding to each of the target model operators, and
the atomic operator embedding vector is generated by performing a filtering process of deleting tokens corresponding to the predefined stopwords or selecting tokens corresponding to the predefined keywords for a plurality of atomic operator tokens obtained by tokenizing the information regarding the atomic operators.

### Claim 13 (depends on 11)

The method of claim 11, wherein the determining the target module based on the vector similarity comprises:
determining one or more candidate atomic operators corresponding to one or more atomic operator embedding vectors in which the vector similarity with the target model operator embedding vector corresponding to a fourth target model operator is greater than or equal to a threshold vector similarity;
identifying one or more candidate modules including the one or more candidate atomic operators among a plurality of pre-stored candidate modules; and
determining the target module corresponding to the fourth target model operator among the identified one or more candidate modules by comparing execution results of fourth input data for the fourth target model operator and execution results of the fourth input data for the identified one or more candidate modules, and
wherein the plurality of pre-stored candidate modules correspond to a plurality of first modules predetermined for the first framework.

### Claim 14 (depends on 1)

The method of claim 1, wherein
the target model operator information includes identification information, description information, input/output information, and implementation code of each of the target model operators,
the description information is information in which a description of each of the target model operators is written in natural language text, and
the input/output information includes data type, shape, and order information of input values and output values of each of the target model operators.

### Claim 15 (depends on 1)

The method of claim 1, wherein
the receiving the target model operator information comprises receiving the target model operator information by version of the target framework,
the target mapping table includes the version-based target mapping table for the target framework, and
the method further comprises:
generating modification information including a modification between the target model operator information on a first version of the target framework and the target model operator information on a second version of the target framework;
determining a modified module corresponding to a modified model operator, in which the target model operator information has been modified, among the target model operators, from the modification information based on the execution-based analysis method or the embedding-based analysis method; and
generating the target mapping table of the second version by mapping the modified model operator and the determined modified module.

### Claim 16 (depends on 1)

The method of claim 1, wherein
the target mapping table includes version information of the framework, identification information of the target model operator, input/output information of the target model operator, identification information of one or more nodes included in the target module mapped to the target model operator, input/output information of the one or more nodes, and an execution order of each node.

### Claim 17 (depends on 1)

The method of claim 1, wherein
the intermediate representation has a hierarchical structure including nodes independent of the framework and modules dependent on the framework, and
one or more nodes constitute a single module within the hierarchical structure.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
determining a target model operator corresponding to each of atomic operators based on a mapping relation between each of the target model operators and the determined target module; and
generating a target reverse mapping table by mapping each of the atomic operators and the determined target model operator.

### Claim 19

A non-transitory computer-readable medium storing a computer program that, when executed by a computing device, allows the computing device to perform operations for transforming an artificial model between a framework and an intermediate representation, the operations comprising:
receiving target model operator information regarding target model operators executable in a target framework;
determining a target module corresponding to each of the target model operators from the target model operator information, based on an execution-based analysis method using execution of a test artificial intelligence model, or an embedding-based analysis method using embedding transformation between a model operator and an atomic operator independent of a framework; and
generating a target mapping table for the target framework by mapping each of the target model operators and the determined target module, and
wherein the target module, as the intermediate representation of the target model operator, is composed of a combination of one or more nodes corresponding to the atomic operator.

### Claim 20

A computing device for transforming an artificial model between a framework and an intermediate representation, comprising a processor including at least one core,
wherein the processor is configured to:
receive target model operator information regarding target model operators executable in a target framework;
determine a target module corresponding to each of the target model operators from the target model operator information, based on an execution-based analysis method using execution of a test artificial intelligence model, or an embedding-based analysis method using embedding transformation between a model operator and an atomic operator independent of a framework; and
generate a target mapping table for the target framework by mapping each of the target model operators and the determined target module, and
wherein the target module, as the intermediate representation of the target model operator, is composed of a combination of one or more nodes corresponding to the atomic operator.
