KR20210062547A - Npu adaptable network platform for artificial intelligent contents service - Google Patents

Abstract

Disclosed is a user terminal equipped with an NPU adaptive edge framework supporting AI content installation and execution according to one embodiment of the present invention. In the user terminal according to one embodiment of the present invention, the NPU adaptive edge framework comprises: an application manager that manages an AI application; a content installer manager that downloads and installs AI content from a content server; and an OS platform comprising an AI content edge engine, an NPU driver, and a sensor driver that executes the AI content and accelerates a first NPU provided in the user terminal. Therefore, the present invention is capable of allowing for efficient AI recognition/deduction functions to be accelerated.

Description

NPU adaptive network platform for AI content service {NPU ADAPTABLE NETWORK PLATFORM FOR ARTIFICIAL INTELLIGENT CONTENTS SERVICE}

The present invention relates to a network platform for AI content services, and more particularly, to an NPU adaptive network platform for AI content distribution, installation, and execution.

Neural Processing Unit (NPU) is a processor that learns and processes information like our brain, and is connected to countless neurons and synapses to send and receive signals, similar to human brain neurons. Because it is working, it is called an AI chip because it incorporates artificial intelligence that can learn and judge by itself. With the advent of these NPUs, it is possible to accelerate AI recognition and reasoning functions with low power and high efficiency in mobile terminals.

In particular, for general images and videos, the need for various types of AI recognition processes is increasing. Since the GPU is more efficient in the learning process using machine learning technology, but the NPU is more efficient in the recognition process, the importance of the NPU in developing a service or application applied to an already created learning model is increasing. Therefore, most chipset manufacturers are starting to develop NPU as a next-generation SoC (systen on chip) and will continue to increase in the future.

Currently, machine learning-based learning technology is generalized, but the development of artificial intelligence devices that directly service terminals by applying algorithms (learning models) are not meeting the needs of the market, and NPU chipsets appear in the market in various ways. However, there is not enough content to use it. In addition, compared to high camera performance, devices and services to which AI technology is applied are also limited.

In particular, due to the NPU dependency and data monopoly of the algorithm, there is no terminal platform that can test various learning models, and there is a lack of learning data that can use the NPU.

An object of the present invention for solving the above problem is to provide a user terminal capable of supporting the installation and execution of AI content desired by the user without being dependent on the NPU.

Another object of the present invention for solving the above problem is to provide a method for distributing AI content without being dependent on a test platform of a terminal.

The present invention for achieving the above object is a user terminal equipped with an NPU adaptive edge framework that supports installation and execution of AI content, wherein the NPU adaptive edge framework includes an application manager for managing AI applications, and contents. An OS platform including a content installation manager for downloading and installing AI content from a server, an AI content edge engine for executing the AI content and accelerating the first NPU provided in the user terminal, an NPU driver, and a sensor driver. It provides a user terminal including.

Here, the AI content includes a learning model and an environment parameter, and the learning model is provided in a hardware-independent intermediate expression form or an execution code form supported by a specific NPU, and the environment parameter corresponds to the environment of the user terminal. The library and resources, and when the learning model is in the form of an intermediate expression, includes information on a conversion server where a cloud compiler to be converted into an execution code is located, and the content installation manager receives a list of downloadable AI contents from the content server, and selects It characterized in that it comprises a content downloader for downloading AI content and a cloud request unit for converting the learning model into an executable code that can be supported by the first NPU by requesting a cloud compiler on the conversion server.

In addition, wherein the AI content includes a learning model and an environment parameter, the learning model is provided in a hardware-independent intermediate expression form or an execution code form supported by a specific NPU, and the content installation manager displays the learning model. A local compiler that converts to a first local executable code supported by the first NPU and conversion information including the first NPU information and the user terminal information to the environment parameter are added to the content server, and the content It characterized in that it further comprises an authentication requesting unit for requesting the server to authenticate the first local execution code.

In addition, here, the environment parameter includes information on a peer terminal having a second local execution code that can be supported by the first NPU when the learning model is in the form of an intermediate expression, and the content installation manager And a peer communication unit configured to request the peer terminal to receive the second local execution code.

In addition, the peer communication unit is characterized in that when there is a request from a third peer terminal, the first local execution code is transmitted to the third peer terminal, and the transmission information is transmitted to a content server.

In addition, the second local execution code is an execution code converted by a local compiler of the peer terminal, and transmission information of the local execution code between peer terminals is calculated based on a billing policy of the content server.

In addition, the AI content edge engine is characterized in that it includes a model executor for decoding and inferring the downloaded AI content, and a content service protocol for controlling communication between the NPU driver and the model execution period.

In an AI content distribution method for distributing AI content in an AI content production studio, the present invention for achieving the other object is the step of generating AI content including a learning model and environment parameters learned using a machine learning tool. And uploading the AI content to a content server, wherein the learning model is a hardware-independent intermediate expression form or an execution code form converted according to a specific NPU, and the environment parameter is a library corresponding to the environment of the user terminal. And a conversion server information including a resource, and in which a cloud compiler to convert the learning model into an execution code is located when the learning model is in the form of an intermediate expression.

Here, when the learning model is in the form of an intermediate expression, the method further comprises authenticating the converted local execution code by a local compiler of the user terminal, wherein the authenticating step is performed in the local execution code from the user terminal or the content server. Upon receiving an authentication request for the content server, the local execution code is authenticated based on an authentication policy of the content server, and authentication information of the local execution code is added to the environment parameter and uploaded to the content server.

In addition, here, the local execution code that has obtained the authentication is transmitted in a P2P method between user terminals based on the information of the environment parameter, and the transmission information of the local execution code is calculated based on the charging policy of the content server. It is characterized.

When using a user terminal equipped with the NPU adaptive AI contents service edge framework for installing and executing AI contents of the present invention, by downloading various AI contents, converting them into execution codes suitable for the NPU provided in the terminal, and executing or testing them. , It can accelerate the efficient AI recognition/inference function. In addition, AI content creators have the advantage of distributing self-produced AI content through the NPU adaptive network platform and testing it on terminals in various environments.

1 is a conceptual diagram of an NPU adaptive network platform supporting an AI content service according to an embodiment of the present invention.
2 is a conceptual diagram of an NPU adaptive edge platform supporting installation and execution of AI content according to an embodiment of the present invention.
3 is a block diagram showing an NPU adaptive edge framework supporting installation and execution of AI content according to an embodiment of the present invention.
4 is a flowchart illustrating a process of installing AI content in a terminal equipped with an NPU adaptive edge framework supporting installation and execution of AI content according to an embodiment of the present invention.
5 is a flowchart illustrating a process of producing and distributing AI content in a content production studio according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the present invention. In describing each drawing, similar reference numerals have been used for similar elements.

Terms such as first, second, A, and B may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. It should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as "comprise" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof does not preclude in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms as defined in a commonly used dictionary should be construed as a meaning consistent with the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in the present application.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a conceptual diagram of an NPU adaptive network platform supporting an AI content service according to an embodiment of the present invention.

Referring to FIG. 1, in the NPU adaptive network platform according to an embodiment of the present invention, a content creator uploads various types of AI content produced to a content server 30 through a content production studio 20, and a user It is possible to provide a service platform in which AI content can be downloaded and installed on the user terminal 10 anytime, anywhere.

In addition, referring to FIG. 1, the NPU adaptive network platform according to an embodiment of the present invention distributes content learned through machine learning and converts the distributed content to be accelerated according to the environment of the user terminal. It may be a subscriber-based web service that provides an edge computing environment.

That is, the content production studio 20 develops and uploads AI content, builds the machine learning result into content that can be executed by an application provided in the user terminal 10, and builds a GUI-based UX (graphic coding in the form of a sequence diagram). ) Can be provided. In this case, the AI content may include a learning model and an environment parameter, and the learning model may be in the form of an intermediate representation independent of hardware, or may be in the form of an execution code converted to be supported by a specific NPU in a production studio. In this case, the learning model may include an application having an independent user interface, or may operate in connection with an open recognition application.

In addition, referring to FIG. 1, when the downloaded AI content is in the form of an intermediate expression, an edge computing environment that can be directly converted into an executable code in the user terminal 10 is provided. That is, for example, the user terminal 10 converts the AI content downloaded through the cloud compiler on the conversion server 40 into an execution code suitable for the NPU provided in the terminal 10 or is installed in the peer terminal 11 You can receive the code. In addition, the user terminals 10 and 10 may be equipped with an edge (EDGE) computing environment (NPU, sensors, applications, etc.) capable of testing AI recognition services using various AI contents.

2 is a conceptual diagram of an NPU adaptive edge platform supporting installation and execution of AI content according to an embodiment of the present invention.

Referring to FIG. 2, the NPU adaptive edge platform 100 according to an embodiment of the present invention supports a device-independent installation environment of AI content downloaded from the content server 30.

In the NPU adaptive edge platform 100 of the present invention, when the learning model included in the downloaded AI content is in the form of an intermediate expression, an environment that can be converted into an execution code suitable for the NPU 101 provided in the user terminal 10 It is equipped with. For example, the learning model may be converted into an executable code that can be supported by the NPU 101 using a cloud compiler of the conversion server 40 or a local compiler provided in the terminal 10. Alternatively, the converted execution code may be transmitted from the peer terminal 11 having the same environment. More details regarding the conversion of the learning model into execution code will be described later.

3 is a block diagram showing an NPU adaptive edge framework supporting installation and execution of AI content according to an embodiment of the present invention.

Referring to FIG. 3, the NPU adaptive edge framework according to an embodiment of the present invention may be provided as a framework independent of the hardware platform 150 of the terminal. In addition, the NPU adaptive AI content service edge framework according to an embodiment of the present invention executes an application manager 110 for managing an application, AI content, and accelerates the NPU 101 provided in the user terminal 10. It may be composed of an AI content edge engine 130 and an OS platform 140 including an NPU driver and a sensor driver.

As described above, the AI content may include a learning model and environment parameters, and the learning model may be provided in the form of a hardware-independent intermediate expression or an execution code supported by a specific NPU, and the environment parameter is the user terminal 10 ) May include libraries and resources including installation information and execution information corresponding to the environment of).

In addition, when the learning model is in the form of an intermediate expression, the NPU 101 provided in the terminal 10 is supported by the conversion server 40 information or the NPU 101 in which the cloud compiler to be converted into a supportable executable code is located. It may include information on the peer terminal 11 having possible executable code. More details on code conversion by the cloud compiler and the peer terminal will be described later.

The content installation manager 120 receives a list of downloadable AI content from the content server 30, and converts the content downloader 121 for downloading the selected AI content and the learning model included in the AI content to the cloud on the server 40. It may include a cloud request unit 122 that requests the compiler and converts it into an executable code that can be supported by the NPU 101 provided in the terminal 10. The cloud compiler may include a web compiler, and since code conversion using the cloud compiler is a known technology, detailed descriptions are omitted.

In addition, the content installation manager 120 includes a local compiler 125 that can convert the learning model included in the downloaded AI content into a first local executable code that can be supported by the NPU 101 provided in the terminal 10. , It may also include an authentication requesting unit 123 for requesting authentication for the first local execution code.

At this time, the authentication request unit 123 adds conversion information including NPU 101 information and information of the user terminal 10 (eg, identification information of the user terminal, physical address, network address, etc.) to the environment parameter. Thus, it is uploaded to the content server 30 and may request the content server 30 to authenticate the first local execution code.

The authentication information is registered in the content server 30, and the authenticated execution code can be directly transmitted between peer terminals, and can be settled according to the server's billing policy.

In addition, the content installation manager 120 requests a second local execution code from the peer terminal 11 having a second local execution code that can be supported by the NPU 11 provided in the terminal 10 by referring to the environment parameter. It may include a peer communication unit 124 for receiving. In this case, the second local execution code provided in the peer terminal 11 may be an execution code converted by a local compiler of the peer terminal 11.

The content installation manager 120 may select a method of converting AI content (using a cloud compiler, using a local compiler, or requesting a peer terminal) according to the environment of the terminal.

When there is a request from the third peer terminal, the peer communication unit 124 transmits the first local execution code converted by the terminal 10 to the third peer terminal, and transmits the transmission information to the content server 30. May be. At this time, transmission information of the local execution code between the peer terminals 10 and 11 may be calculated based on the charging policy of the content server 30.

For example, when the first local execution code converted by the user terminal 10 is transmitted to a third peer terminal, a portion of the AI content usage fee charged to the third peer terminal may be applied to the user terminal 10 by a coupon or It can be given in the form of points or the like. Conversely, a portion of the AI content usage fee imposed on the user terminal 10 may be given as a point to the peer terminal 11 that has transmitted the second local execution code to the user terminal 10.

The AI content edge engine 130 may include a model executor 131 that decodes and infers the downloaded AI content, and a content service protocol 132 for controlling communication between the NPU driver 141 and the model executor 131. have.

For example, the AI content edge engine 130 integrates parts supported through different SDKs for different NPU companies, and can use a vast amount of AI content produced for different NPUs.

Hereinafter, a process of installing AI content in a terminal according to an embodiment of the present invention will be described.

4 is a flow chart showing a process of installing AI content in a terminal equipped with an NPU adaptive edge framework that supports installation and execution of AI content according to an embodiment of the present invention.

Referring to FIG. 4, the process of installing AI content in a terminal equipped with an NPU adaptive edge framework according to an embodiment of the present invention includes displaying a list of downloadable AI contents (S110) and downloading AI contents ( S120), the execution code conversion step using a local compiler (S130) and the converted code authentication request step (S140), the execution code conversion step using a cloud compiler (S150), the execution code receiving step from the peer terminal (S160), AI content It may be configured to include a terminal installation step (S170).

Hereinafter, each step of the process of installing AI content in a terminal according to an embodiment of the present invention will be described in more detail.

First, the user can inquire downloadable AI content through the content downloader installed in the user terminal (S110). In this case, the content downloader may be basically installed in the terminal or an application downloaded from the market. In addition, the AI content searched through the content downloader may include only AI content supported by the NPU provided in the user terminal, or may include a learning model in the form of an intermediate expression independent of the NPU. In addition, AI content may include learning models and environment parameters learned using deep learning tools.

In the case of AI content that includes a learning model in the form of intermediate representation, a means to convert it into an executable code may be provided in the AI content inquiry list. For example, it can be converted through the cloud compiler of the server, or the execution code can be transmitted from the peer terminal, and if there is a local compiler in the terminal, it can be converted by itself. The environment parameter may include the address of the server where the cloud compiler is located or information on the peer terminal having the certified execution code. Information on various conversion means may be provided for the same AI content.

The content downloader may download AI content suitable for the environment of the terminal (S120). If, if the AI content in the form of an executable code supported by the NPU provided in the terminal can be installed in the user terminal (S170) without going through a separate conversion. Or, if it is in the form of an intermediate code and a local compiler is provided in the terminal, the terminal may convert the learning model included in the downloaded AI content using the local compiler into the first local execution code that can be supported by the NPU provided in the terminal. (S130).

At this time, the terminal provides conversion information including NPU information related to the first local execution code and information of the user terminal (eg, identification information of the user terminal, physical address, network address, etc.) in the environment parameter included in the AI content. In addition, it is uploaded to the content server, and authentication for the first local execution code may be requested from the content server (S140). Authentication information is registered in the content server, and the authenticated execution code can be directly transmitted between peer terminals, and can be settled according to the server's billing policy. For example, part of the fee paid by the terminal downloading the AI content may be paid to the peer terminal that transmitted the execution code.

If the AI content is in the form of an intermediate expression, but there is no local compiler in the terminal, the terminal executes the learning model included in the AI content downloaded using the cloud compiler on the conversion server 40 that can be supported by the NPU provided in the terminal. It can be converted into a code (S150).

Alternatively, the terminal may receive the second local execution code by requesting a peer terminal having a second local execution code supported by the NPU provided in the terminal with reference to the environment parameter (S160). In this case, the second local execution code provided in the peer terminal is an execution code converted by a local compiler of the peer terminal, and may be a code certified by a content server or a content production studio.

The AI content converted through the above process may be installed in the user terminal (S170).

Hereinafter, the process of producing and distributing AI content will be described.

5 is a flowchart illustrating a process of producing and distributing AI content in a content production studio according to an embodiment of the present invention.

5, the process of producing and distributing AI content according to an embodiment of the present invention includes a recognition application selection step (S210), a learning model generation step (S220), a learning model conversion step (S230), and an AI content production step. It may be configured to include (S240), content upload step (S250) and local execution code authentication step (S260).

Hereinafter, a process of producing and distributing AI content in a content production studio will be described in more detail with reference to FIG. 5.

First, the content creation studio selects a recognition application to which the AI content is to be applied (S210). The recognition application may refer to an application that receives various signals through various sensors (eg, a camera, a sound sensor, a gravity sensor, a fire sensor, etc.) and operates based on the received signal. In addition, the recognition application may be an application that is preinstalled in a user terminal for downloading AI content or an application that is downloaded together with AI content.

The content production studio may mean a terminal used by various subjects that create and distribute learning models through deep learning and big data analysis, such as schools, research institutes, companies, and individuals.

Next, a learning model to be used in the selected recognition application may be generated (S220). The learning model may be a model generated by machine learning through big data analysis. Big data analysis and machine learning are known methods, so detailed descriptions are omitted. The learning model can be created in the form of a device-independent intermediate expression. Alternatively, it may be in the form of an executable code that is not supported by the NPU and is produced according to the OS of the terminal.

Next, the generated learning model may be converted into an execution code supported by a specific NPU (S230). In this step, a plurality of executable codes converted to fit a plurality of various NPUs may be generated. Alternatively, this step (S230) may be omitted.

Next, it is possible to produce AI content including the learning model and environment parameters generated in the previous step (S240). At this time, the learning model may be provided in the form of a hardware-independent intermediate expression or an execution code supported by a specific NPU as described above, and the environment parameter is a library including installation information and execution information corresponding to the environment of the user terminal. And resources.

In addition, when the learning model is in the form of an intermediate expression, the environment parameter includes information on the conversion server where the cloud compiler to be converted into an NPU-supportable execution code provided in the terminal is located, or information on a peer terminal having an execution code that can be supported by the NPU. can do. However, the information of the peer terminal may not be generated during the content production stage.

Next, the AI content produced including the learning model and environment parameters may be uploaded to the server (S250).

Next, when the learning model is in the form of an intermediate expression, the local execution code converted by the local compiler of the user terminal may be authenticated (S260). For example, when a user terminal makes a request for authentication for a local executable code to the content server, the content server may transmit the authentication request content to the content production studio.

The content production studio receiving the requested content may authenticate the local execution code based on the authentication policy of the content server, add authentication information of the local execution code to the environment parameter, and upload it to the content server. On the other hand, authentication of the local execution code may be performed directly in the content server. This may vary depending on the content server's authentication policy. Such authentication information may be initialized when content is updated to ensure content integrity.

In addition, the local execution code that has obtained authentication is transmitted in a P2P manner between user terminals based on the information of the environment parameter, and transmission information of the local execution code may be calculated based on the charging policy of the content server.

As described above, using a user terminal equipped with an NPU adaptive AI contents service edge framework for installing and executing AI contents of the present invention, various AI contents are downloaded and converted into an execution code suitable for the NPU provided in the terminal. By running or testing, you can accelerate efficient AI recognition/inference capabilities. In addition, AI content creators have the advantage of distributing self-produced AI content through the NPU adaptive network platform of the present invention and testing it on terminals in various environments.

Meanwhile, the device according to an embodiment of the present invention may be provided in the form of an application driven by a user terminal. In this case, the user terminal may include various computing devices including a smart phone, a tablet PC, a laptop computer, a desktop computer, and a PDA.

Meanwhile, the method of the present invention described above can be produced as a program code to be executed on a computer and stored in a computer-readable medium, and a program for executing the method of the present invention is produced as an application and stored on a recording medium. Can be. The recording medium may include a computer, a mobile terminal, a hard disk such as a server, a memory, an auxiliary memory, or a movable storage medium such as a compact disk.

Further, the method and apparatus of the present invention described so far can be implemented by a computer program in practice, and can be stored in a computer-readable recording medium when executed in a computer. Computer-readable recording media include all types of recording media in which programs and data are stored so that they can be read by a computer system, including ROM, RAM, CD, DVD-ROM, magnetic tape, floppy disk, and optical data storage devices. Also, it may be implemented in the form of transmission through the Internet. That is, such a medium may be distributed over a computer system connected through a network, and computer-readable codes may be stored and executed in a distributed manner.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the following claims. You will understand that you can do it.

Claims (10)

In a user terminal equipped with an NPU adaptive edge framework supporting AI content installation and execution, the NPU adaptive edge framework
An application manager to manage AI applications,
A content installation manager for downloading and installing AI content from a content server,
An AI content edge engine for executing the AI content and accelerating the first NPU provided in the user terminal;
User terminal including the OS platform including the NPU driver and sensor driver. The method according to claim 1
The AI content includes a learning model and an environment parameter, and the learning model is provided in a hardware-independent intermediate expression form or an execution code form supported by a specific NPU,
The environmental parameters include library and resources corresponding to the environment of the user terminal, and conversion server information in which a cloud compiler to be converted into an execution code is located when the learning model is in an intermediate expression form,
The content installation manager
A content downloader for receiving a list of downloadable AI content from the content server, and downloading the selected AI content, and
And a cloud requesting unit configured to request a cloud compiler on the conversion server to convert the learning model into an executable code that can be supported by the first NPU. The method according to claim 1 or 2,
The AI content includes a learning model and an environment parameter, and the learning model is provided in a hardware-independent intermediate expression form or an execution code form supported by a specific NPU,
The content installation manager
A local compiler that converts the learning model into a first local executable code supported by the first NPU;
An authentication request unit for adding conversion information including the first NPU information and the user terminal information to the environment parameter and uploading it to the content server, and requesting the content server to authenticate the first local execution code. Terminal comprising a. The method of claim 3,
The environment parameter includes information on a peer terminal having a second local execution code that can be supported by the first NPU when the learning model is an intermediate expression type,
The content installation manager
And a peer communication unit configured to request the peer terminal to receive the second local execution code. The method of claim 4,
And the peer communication unit, upon request from a third peer terminal, transmits the first local execution code to the third peer terminal and transmits the transmission information to a content server. The method of claim 5,
The second local execution code is an execution code converted by a local compiler of the peer terminal, and transmission information of the local execution code between peer terminals is calculated based on a charging policy of the content server. The method according to claim 1,
The AI content edge engine
A model runner that decodes and infers the downloaded AI content,
And a content service protocol for controlling communication between the NPU driver and the model execution period. In the AI content distribution method for distributing AI content in an AI content production studio,
Generating AI content including learning models and environment parameters learned using machine learning tools, and
Including the step of uploading the AI content to a content server,
The learning model is a hardware-independent intermediate expression form or an execution code form converted to a specific NPU,
The environment parameter includes a library and a resource corresponding to the environment of the user terminal, and further includes conversion server information in which a cloud compiler to convert the learning model into an execution code is located when the learning model is an intermediate expression type. AI content distribution method. The method of claim 8,
If the learning model is an intermediate expression form, further comprising the step of authenticating the converted local execution code in a local compiler of the user terminal,
In the authenticating step, upon receiving an authentication request for the local execution code from the user terminal or the content server, the local execution code is authenticated based on an authentication policy of the content server, and the local execution code is used in the environment parameter. AI content distribution method, characterized in that uploading to the content server by adding the authentication information of. The method of claim 9,
The local execution code that has obtained the authentication is transmitted in a P2P manner between user terminals based on the information of the environment parameter, and the transmission information of the local execution code is settled based on the charging policy of the content server. How to distribute AI content.

Images