KR20220095694A - AI model connection service system using open API and service method thereof - Google Patents

Abstract

The AI model linkage service system using Open API disclosed in the embodiment of the present invention includes a model link module distribution unit and an open API link unit. The model link module distribution unit receives the prediction model and the link module, stores the received prediction model and the link module in a storage, and loads the stored prediction model and link module to the distribution engine that distributes to the AI model hub. The open API linkage unit searches for model information related to the essential prediction information received through the Open API (API) through the AI model linkage management unit, generates related parameters for input processing of the essential prediction information, and the prediction essential information For the transmission of , the related parameters and the model information are linked with the corresponding model link module of the AI model hub, and the prediction of the model information is executed through the linked model link module, and the result of the prediction result information that has been executed provided through the transmitter.

Description

AI model connection service system using open API and service method thereof

The present invention relates to the field of artificial intelligence (AI) model service, and more particularly, to an AI model linkage service system and service method using an open API.

Currently, AI model developers who develop AI models are mostly uploading AI models through large AI portal companies that provide AI services. In such a case, the AI model developer is subordinated to a large-scale portal company that provides AI services, so there is a problem in the reliability of the AI service or the profit structure according to the cost of development. In addition, AI service providers have to develop software to provide AI services, as well as search for AI model developers or develop AI models themselves.

The technical problem to be solved by the present invention is to provide an AI model linkage service system and service method using Open API that allows an AI model developer and an AI service provider to be easily linked.

According to an embodiment of the present invention for achieving the above technical problem, an AI model linkage service system using Open API includes a model linkage module distribution unit and an open API linker unit. The model link module distribution unit receives the prediction model and the link module, stores the received prediction model and the link module in storage, and distributes the stored prediction model and link module to the AI model hub and the AI model link unit, respectively. load into the engine. The open API linkage unit searches for model information related to the essential prediction information received through the Open API (API) through the AI model linkage management unit, generates relevant parameters for input processing of the essential prediction information, and the prediction essential For information transmission, the related parameters and the model information are linked with a corresponding model link module of the AI model hub, the model information is predicted through the linked model link module, and the prediction result information that has been executed provided through the transmitter.

According to an embodiment of the present invention, an AI model developer and an AI service provider are easily linked to each other through an open API, so that a service using the AI model can be smoothly provided to consumers. Accordingly, the profits of AI model developers and AI service providers can be maximized. In the end, AI model developers do not need to separately develop software that provides AI services, and even if only AI models are developed, services using the AI models can be provided to consumers, and AI service providers do not develop various AI models separately. AI services can be provided.

1 is a conceptual block diagram of an AI model linkage service system using Open AI according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating the operation of the module distribution unit of FIG. 1 .
3 is a flowchart illustrating a part of the operation of the open API linker of FIG. 1 .

The above objects, other objects, features and advantages of the present invention will be easily understood through the following preferred embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided so that the disclosed content may be more thorough and complete, and the spirit of the present invention may be sufficiently conveyed to those skilled in the art, without any intention other than to provide convenience of understanding.

Reference throughout this detailed description to “one embodiment” or “an embodiment” means that a particular feature structure, or characteristic described in connection with the embodiment may be included in at least one embodiment disclosed herein. Thus, the appearances of the phrases "in an embodiment" or "in an embodiment" or "according to an embodiment" (or other constructions having a similar meaning) in various places throughout this specification are all necessarily identical. It may not refer to an embodiment. Moreover, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. As used herein in this regard, the word “exemplary” means “to provide an illustration, illustration, or illustration.” Any embodiment described herein as “exemplary” should not necessarily be construed as preferred or advantageous over other embodiments. Also, depending on the context of this specification, a singular term may include its plural forms, and a plural term may include its singular forms. It should be noted that the various drawings shown and discussed herein (including component diagrams) are for illustrative purposes only and are not drawn to scale.

The terminology used herein is for the purpose of describing particular exemplary embodiments only, and is not intended to limit the claimed invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly dictates otherwise. do. The terms “comprise” and/or “comprising,” when used in the specification, specify the presence of specified features, integers, steps, operations, elements, and/or components, but include one or more other It will be further understood that this does not exclude the presence or addition of features, integers, steps, operations, elements, and/or components, and/or groups thereof. As used herein, terms such as "first", "second", etc. are used as labels of preceding nouns, and unless explicitly defined so, in any type of order (eg, spatial, temporal, logical etc.) is not implied. Also, the same reference numbers may be used throughout two or more drawings to refer to parts, components, blocks, circuits, units, or modules having the same or similar function. However, this use is only for the sake of simplification of the city and ease of discussion. This does not mean that the configuration or structural details of such components or units are the same across all embodiments, or that these commonly referenced parts/modules are the only way to implement the guidelines of the specific embodiments disclosed herein. doesn't mean that

Unless defined otherwise, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the related art, and should not be interpreted in an idealized or overly formal sense unless explicitly defined herein. This will make more sense.

As used herein, the term “module” refers to any combination of software, firmware, and/or hardware configured to provide the functionality described herein in connection with a module. The term “software,” as applied to any implementation described herein, may be implemented as a software package, code, and/or an instruction set or instructions. The term "hardware" as applied to any implementation described herein, for example, individually or in any combination, includes hardwired circuitry, programmable circuitry, state machine circuitry, and/or firmware that stores instructions to be executed by the programmable circuit. Modules, collectively or individually, may be implemented as integrated circuits, system-on-a-chip (SoC), etc., but may be implemented as circuitry forming part of a larger system, including but not limited to.

Each embodiment described and illustrated herein may also include a complementary embodiment thereof, and detailed inference operations and prediction operations of the AI module will not be described in detail so as not to obscure the gist of the present invention.

1 is a conceptual block diagram of an AI model linkage service system using Open AI according to an embodiment of the present invention.

Referring to FIG. 1 , the AI model linkage service system using Open API includes a model linkage module distribution unit 100 and an open API linker unit.

The model link module distribution unit 100 may include a model receiving module 110 , a model storage module 120 , and a model loading module 130 .

The open API linkage unit includes an information receiving and transmitting unit 200 , an AI model linkage management unit 300 , an AI model linkage unit 400 , and an AI model hub 500 .

The information receiving and transmitting unit 200 may include a prediction required information receiving module 210 , a prediction essential information transmitting module 220 , a prediction result information transmitting module 230 , and a prediction result information receiving module 240 . have.

The AI model linkage management unit 300 includes a reception module 310 , an information search module 320 , an input processing module 330 , a transmission processing module 340 , a branch processing module 350 , and a result reception processing module 350 . , a result delivery processing module 360 may be included.

The AI model linkage unit 400 may include a plurality of linkage modules 401-1 to 401-N.

The AI model hub 500 may include a health prediction model 510 , a health age prediction model 520 , an equipment failure prediction model 530 , a weather prediction model 540 , and other models 550 . .

The model receiving module 110 of the model linkage module distribution unit 100 may receive the prediction model and linkage module developed by the company A from the AI model development terminal 10 . Here, company A may be an AI model developer. The above company A is dedicated to the development of the AI model without the need to separately develop software that provides AI services.

The communication protocol between the model receiving module 110 and the AI model development terminal 10 may be HTTP. However, the above communication protocol is only an exemplary method, and in other cases, the following communication protocols may be used. The protocols are Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSM), North American Digital Communications (NADC), Extended Time Division Multiple Access (E-TDMA), Wideband CDMA (WCDMA), CDMA2000, Wi-Fi , Municipal Wi-Fi (Muni Wi-Fi), Bluetooth, Digital Enhanced Cordless Telecommunications (DECT), Wireless Universal Serial Bus (Wireless USB), Fast low-latency access with seamless handoff Orthogonal Frequency Division Multiplexing (Flash-OFDM), IEEE 802.20, General Packet Radio Service (GPRS), iBurst, Wireless Broadband (WiBro), WiMAX, WiMAX-Advanced, Universal Mobile Telecommunication Service - Time Division Duplex (UMTS-TDD), High Speed Packet Access (HSPA), Evolution Data Optimized ( EVDO), Long Term Evolution - Advanced (LTE Advanced), Multichannel Multipoint Distribution Service (MMDS), and the like.

The predictive model may be a model generated using a deep learning engine. The generated prediction model can be linked using a dynamic linkage code such as java or Python.

The link module is automatically deployed on the web using an operation management program. The association module may be automatically associated with the Open API module. Therefore, it is a form of linking the AI prediction model through the open API and receiving the result obtained from the prediction model through the open API.

The model storage module 120 of the model link module distribution unit 100 stores the prediction model and the link module received through the model receiving module 110 in a memory or storage.

The model loading module 130 of the model linkage module distribution unit 100 is a distribution engine that distributes the stored prediction model and linkage module to the AI model hub 500 and the AI model linkage unit 400, respectively. load Here, the distribution engine may be a JVM engine when the linked module is a jar file. The JVM is an abbreviation of Java Virtual Machine, and serves to convert Java bytecodes into OS-specific codes and execute them. In other words, Java bytecode is required to operate on the JVM. Java byte code refers to code that is converted by a Java compiler from Java code written by a developer. Since the JVM converts and executes OS-specific code, it has a characteristic that is dependent on a specific platform. After all, this means that Java is independent of the operating system because it is executed by the JVM in Java.

The information receiving and transmitting unit 200 of the open API linkage unit may be connected to the model use service terminal 20 of company B. Here, company B is an AI service provider. Therefore, AI service providers can provide various AI services to consumers without developing various AI models separately.

The prediction essential information receiving module 210 of the information receiving and transmitting unit 200 receives the prediction essential information from the model use service terminal 20 . The prediction essential information transmission module 220 of the information receiving and transmitting unit 200 transmits the received prediction essential information to the AI model linkage management unit 300 . The prediction result information transfer module 230 of the information receiving and transmitting unit 200 transmits the prediction result information predicted through the AI model to the model use service terminal 20 . The prediction result information receiving module 230 of the information receiving and transmitting unit 200 receives the prediction result information predicted through the AI model from the result transfer processing module 370 of the AI model linkage management unit 300, and the prediction result It is transmitted to the information transfer module 230 .

The receiving module 310 of the AI model linkage management unit 300 receives the prediction essential information from the prediction essential information delivery module 220 of the information receiving and transmitting unit 200 . The information search module 320 of the AI model linkage management unit 300 searches for model information related to the prediction essential information received through the reception module 310 . After all, the model information is information received through the information receiving and transmitting unit 200 that is an open API. The input processing module 330 of the AI model linkage management unit 300 generates related parameters for input processing of the prediction essential information. The transmission processing module 340 of the AI model connection management unit 300 associates the related parameters and the model information with a corresponding model connection module of the AI model hub for transmission of the prediction essential information. In this case, model branching processing needs to be performed in order to link the related parameters and the model information with the corresponding model link module of the AI model hub. The branch processing module 350 of the AI model linkage management unit 300 performs the model branch processing. The result reception processing module 350 of the AI model linkage management unit 300 receives prediction result information that has been predicted through the AI model. The received prediction result information is transmitted to the result transfer processing module 370 of the AI model linkage management unit 300 .

The result transfer processing module 360 of the AI model linkage management unit 300 transmits the received prediction result information to the prediction result information receiving module 240 .

The plurality of linkage modules 401-1 to 401-N of the AI model linkage unit 400 are linkage modules loaded by the model loading module 130, and may include linkage modules for various models. have.

The AI model hub 500 includes a health prediction model 510, a healthy age prediction model 520, an equipment failure prediction model 530, a weather prediction model 540, and other models 550 of the plurality of linkages. It may be provided corresponding to the modules 401-1 to 401-N. The health prediction model 510 , the healthy age prediction model 520 , the equipment failure prediction model 530 , the weather prediction model 540 , and other models 550 are models loaded by the model loading module 130 . admit.

For example, the health prediction model 510 may perform prediction of health model information through the model A linkage module 401-1. The prediction result information on which prediction execution is completed is provided to the result reception processing module 360 .

FIG. 2 is a flowchart illustrating the operation of the module distribution unit of FIG. 1 .

Referring to FIG. 2 , in operation S101 , the model receiving module 110 of the module distribution unit 100 receives a predictive model and a linkage module. The prediction model and link module is an AI prediction model and AI link module, and is a model and module provided by an AI model developer.

In operation S102, the model storage module 120 of the module distribution unit 100 stores the received prediction model and the associated module in a memory or storage. In operation S103, the model loading module 130 of the module distribution unit 100 distributes the stored prediction model and the associated module. For example, when the health prediction model made by Company A and the model A link module are distributed, the health prediction model 510 is present in the AI model hub 500 and the A model linkage unit 400 is linked to the AI model link unit 400 . A module 401-1 is present.

3 is a flowchart illustrating a part of the operation of the open API linker of FIG. 1 .

Referring to FIG. 3 , in operation S201 , the receiving module 310 of the AI model linkage management unit 300 receives essential prediction information required for prediction from the prediction essential information delivery module 220 . For example, the prediction essential information may be information such as model information, activity amount, blood pressure, blood sugar, and the like.

In operation S202, the information search module 320 of the AI model linkage management unit 300 searches for model information.

In operation S203, the input processing module 330 of the AI model linkage management unit 300 inputs and processes prediction information.

In operation S204, the transmission processing module 310 of the AI model linkage management unit 300 performs prediction information transmission processing.

In operation S205, the branch processing module 350 of the AI model linkage management unit 300 performs model branch processing.

In operation S206, the result reception processing module 360 of the AI model linkage management unit 300 receives and processes the prediction result. For example, in relation to predicting healthy age, the prediction result obtained through the predictive model is "Your healthy age is 35." may be the result data.

In operation S207, the result transfer processing module 370 of the AI model linkage management unit 300 transfers the prediction result.

Although specific terms have been used herein, they are only used for the purpose of describing the present invention and are not used to limit the meaning or the scope of the present invention described in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. For example, if the matter is different, the detailed operation of the module distribution unit or the detailed operation of the open API linkage unit may be changed or added or subtracted without departing from the technical spirit of the present invention.

100: module distribution unit
200: information receiving and transmitting unit
300: AI model linkage management unit
400: AI model linkage
500: AI Model Hub

Claims (6)

Model linkage that receives the prediction model and link module, stores the received prediction model and link module in storage, and loads the stored prediction model and link module to the distribution engine that distributes the stored prediction model and link module to the AI model hub and the AI model link unit, respectively module distribution department; and
Search for model information related to essential prediction information received through Open API (API) through the AI model linkage management unit, generate relevant parameters for input processing of the essential prediction information, and transmit the essential prediction information Linking the related parameters and the model information with a corresponding model link module of the AI model hub, executing the prediction of the model information through the linked model link module, and providing the completed prediction result information through the transmission unit A.I model linkage service system using Open API including an open API linkage. The system of claim 1 , wherein the model link module distribution unit receives the prediction model and link module from an AI model development company. The system of claim 1, wherein the result transmitting unit provides the information on the prediction result that has been executed to an AI service company through the open AI service system. According to claim 1, wherein the distribution engine for distributing the stored linkage module to the AI model hub is a JVM engine, AI model linkage service system using Open API. The open API of claim 1, wherein the open API linker further executes model branching to link the related parameters and the model information with a corresponding model link module of the AI model hub when the prediction essential information is transmitted. AI model linkage service system using In the AI model link service method using Open AI (API):
A model linkage module for receiving a prediction model and a linkage module, storing the received prediction model and linkage module in storage, and loading the stored prediction model and linkage module into a distribution engine that distributes the stored predictive model and linkage module to an AI model hub and an AI model linker, respectively deployment phase; and
The model information related to the essential prediction information received through the open API is retrieved through the AI model linkage management unit, the related parameters are generated for input processing of the essential prediction information, and the related parameters are transmitted for the transmission of the essential prediction information. Linking the model information and the model information with the corresponding model linkage module of the AI model hub, executing the prediction of the model information through the linked model linkage module, and providing the executed prediction result information through the transmission unit Open API linkage A system comprising steps.

Images