WO2022092448A1

WO2022092448A1 - Deep learning solution providing method performed by deep learning platform providing device for providing deep learning solution platform

Info

Publication number: WO2022092448A1
Application number: PCT/KR2021/001360
Authority: WO
Inventors: 여승기
Original assignee: 주식회사 디에스랩글로벌
Priority date: 2020-10-29
Filing date: 2021-02-02
Publication date: 2022-05-05
Also published as: KR102313181B1

Abstract

A deep learning solution providing method according to an embodiment of the present invention may comprise the steps of: collecting, from a user terminal, input information including tabular data to be analyzed or predicted, a training scheme of a deep learning model, and a training type of the deep learning model; collecting, from the user terminal, pre-processing information including whether pre-processing according to a column of the tabular data is performed, whether to be used for training of the deep learning model, and a pre-processing scheme; and training a plurality of pre-prepared deep learning models on the basis of the collected input information and pre-processing information, and providing training result information including a training state, accuracy, an error rate, and similarity for each of the plurality of deep learning models according to the result of the training.

Description

A method of providing a deep learning solution performed by a deep learning platform providing device that provides a deep learning solution platform

The present invention relates to a deep learning solution providing method performed by a deep learning platform providing apparatus that provides a deep learning solution platform. In more detail, the step of collecting input information including tabular data to be analyzed or predicted from the user terminal, the learning method of the deep learning model and the learning form of the deep learning model, the column of table data from the user terminal A step of collecting pre-processing information including whether pre-processing according to It relates to a method for providing a deep learning solution, comprising the step of providing learning result information including a learning state, accuracy, error rate, and similarity of each of a plurality of deep learning models according to the learned result.

Recently, with the rapid development of processors and memories, artificial intelligence (AI) technology has been developed and is in the spotlight, and services using artificial intelligence technology are being widely developed in various fields.

In particular, deep learning technology is drawing attention in the field of artificial intelligence technology, and it is showing excellent results in various fields such as data analysis, image recognition, and natural language processing. Deep learning is a field of machine learning, and it is a technique to express data in a form that a computer can process, such as a vector or graph, and build a model that learns it. That is, for a specific learning goal, such as recognizing a face or expression, deep learning focuses on building better representation methods and efficient models for learning, and many of the representation methods in deep learning are inspired by neuroscience. It is based on information processing and communication patterns of the nervous system.

In the early days, the development of artificial intelligence algorithms was somewhat closed based on individual capabilities based on R language and Python language, and performance evaluation has been evaluated and verified by individual standards. Therefore, there was a limitation in that artificial intelligence had to be continuously managed and controlled by humans in order to maintain the expected performance and operate stably. And, in order to meet the unit requirements, the existing AI algorithm has been developed in a somewhat personalized way by an analyst after design and development verification in a personal development environment, and understanding and improvement of performance that changes depending on the environment, etc. There were also difficulties in proceeding with the process.

Recently, the development of algorithms of open source-based deep learning techniques has increased and a large number of deep learning algorithms are being developed. For this purpose, it is very difficult to check the suitability of the deep learning learning results.

Accordingly, it is required to develop a technology for a deep learning solution platform that can acquire a deep learning model to derive a result that a user wants to predict or analyze if there is only data for learning the deep learning model.

The present invention is to solve the above-described problems, and provides a deep learning model generation method in which even unskilled people related to deep learning can obtain a deep learning model to obtain a result to be predicted or analyzed only by input of learning data. The purpose is to want to.

As an embodiment of the present invention, a method for providing a deep learning solution performed by an apparatus for providing a deep learning platform that provides a platform for providing a deep learning solution may be provided.

A method for providing a deep learning solution according to an embodiment of the present invention collects input information including tabular data to be analyzed or predicted from a user terminal, a learning method of a deep learning model, and a learning form of the deep learning model step, collecting pre-processing information including whether pre-processing according to the column of table data from the user terminal, whether it is used for learning of a deep learning model, and a pre-processing method, and collecting the pre-prepared plurality of deep learning models It may include learning based on the input information and pre-processing information, and providing learning result information including a learning state, accuracy, error rate, and similarity of a plurality of deep learning models for each deep learning model according to the learned result.

According to the deep learning solution providing method performed by the deep learning platform providing device that provides the platform for providing the deep learning solution of the present invention, even an unskilled person related to deep learning can predict or analyze results by only inputting learning data. It has the effect of acquiring a deep learning model.

1 is a flowchart of a method for providing a deep learning solution performed by an apparatus for providing a deep learning platform that provides a platform for providing a deep learning solution according to an embodiment of the present invention.

2 is an exemplary diagram illustrating a user interface window for collecting input information in a method for providing a deep learning solution according to an embodiment of the present invention.

3 is an exemplary diagram illustrating a user interface window for collecting pre-processing information in a method for providing a deep learning solution according to an embodiment of the present invention.

4 is an exemplary diagram illustrating a state of providing a learning result information user interface in a method for providing a deep learning solution according to an embodiment of the present invention.

5 is an exemplary diagram illustrating a user interface for providing prescriptive analysis result information in a method for providing a deep learning solution according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Terms used in this specification will be briefly described, and the present invention will be described in detail.

The terms used in the present invention have been selected as currently widely used general terms as possible while considering the functions in the present invention, but these may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

In the entire specification, when a part "includes" a certain element, this means that other elements may be further included, rather than excluding other elements, unless otherwise stated. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. . In addition, throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being connected "with another element in the middle".

1 is a flowchart of a method for providing a deep learning solution performed by an apparatus for providing a deep learning platform that provides a platform for providing a platform for providing a deep learning solution according to an embodiment of the present invention, and FIG. 2 is a flowchart according to an embodiment of the present invention In the method for providing a deep learning solution, it is an exemplary view for showing a user interface window for collecting input information, and FIG. 3 is a method for providing a deep learning solution according to an embodiment of the present invention, for collecting pre-processing information It is an exemplary view for showing a user interface window, and FIG. 4 is an exemplary view showing a state of providing a learning result information user interface in a method for providing a deep learning solution according to an embodiment of the present invention. 5 is an exemplary diagram illustrating a user interface for providing prescriptive analysis result information in a method for providing a deep learning solution according to an embodiment of the present invention. Hereinafter, the present invention will be described in detail with reference to the above drawings.

As an embodiment of the present invention, a deep learning solution providing method performed by a deep learning platform providing apparatus providing a platform (hereinafter, deep learning solution platform) for providing a deep learning solution may be provided.

A method for providing a deep learning solution according to an embodiment of the present invention collects input information including tabular data to be analyzed or predicted from a user terminal, a learning method of a deep learning model, and a learning form of the deep learning model step (S100), collecting pre-processing information including whether the table data is pre-processed by column from the user terminal, whether it is used for learning a deep learning model, and a pre-processing method (S200) and a plurality of deep learning models prepared in advance learning based on the collected input information and pre-processing information, and providing learning result information including the learning state, accuracy, error rate, and similarity of each of a plurality of deep learning models according to the learned result (S300) may include

Hereinafter, each process ( S100 - S300 ) of the method for providing a deep learning solution according to an embodiment of the present invention will be described.

First, a step (S100) of collecting input information including tabular data to be analyzed or predicted from a user terminal, a learning method of a deep learning model, and a learning form of the deep learning model (S100) may be performed.

Input information according to one disclosure may include table data that is a target of analysis or prediction using a deep learning model. The table data may be data based on a tabular form including at least one or more cells generated by rows and columns. The table data may be in the form of spreadsheet data, CSV (comma-separated value), Excel, HTML (HyperTextMarkup Language), XML (Extensible markup language), PDF (Portable Document Format), etc. there is.

Table data according to one disclosure is data of a column to be analyzed or predicted (hereinafter, an analysis target column) and data of at least one column (hereinafter, a related column) expected to be related to the data of the analysis target column may include Hereinafter, the column of the table data may include the analysis target column and at least one or more related columns. The analysis target column may be determined by the analysis target column determination signal collected from the user terminal, the analysis target column is determined from among the table data by the analysis target column determination signal, and the remaining columns of the table data except for the analysis target column are It may be determined by an associated column.

Input information according to one disclosure may include information about a learning method of a deep learning model. The learning method may include information for learning to proceed according to a learning method preferred by a user based on information on learning speed, information on accuracy of learning, information on error rate of learning, and the like.

Input information according to one disclosure may include information about a learning form of the deep learning model. The learning form may include learning form information such as binary classification, multi-class classification, regression, prediction, segmentation, and detection. That is, the learning form information may be input and collected by the user so that the learning result appears according to the user's preferred learning form.

The deep learning solution platform according to one disclosure may receive information from the user terminal by using the input information user interface 100 of FIG. 2 in order to collect input information from the user terminal. In more detail, the table data can be collected from the user terminal through the table data input block 110 , and information about the learning method can be collected from the user terminal through the learning method input block 120 . Similarly, the information on the learning form may be collected from the user terminal through the learning form input block 130 in the input information user interface 100 .

According to one disclosure, the input information may further include other types of data as well as structured data such as the aforementioned table data. For example, the input information may include time series data, image data, natural language data, voice data, etc., and may receive various data as described above and analyze or predict it using a deep learning model.

Next, a step (S200) of collecting pre-processing information including whether the table data is pre-processed for each column, whether it is used for learning a deep learning model, and a pre-processing method from the user terminal (S200) may be performed.

The pre-processing information according to the disclosure may include information on whether pre-processing is input through a user terminal with respect to whether to perform pre-processing for each column. Since table data of input information is configured in a table form, a column indicating an attribute of data for one column may be included. That is, the information on whether the pre-processing is performed may indicate information on whether to perform the pre-processing for each column of table data. In other words, in S200, the pre-processing may be performed by separately selecting only a column that the user wants to pre-process from among the columns of the input table data. Through the above process, it is possible to obtain a desired learning result by a user by enabling a different selection of pre-processing for each column.

Referring to FIG. 3 , an exemplary diagram of the preprocessing information user interface 200 is shown. That is, the information on whether to perform the pre-processing for each column may be collected from the user terminal through the pre-processing input block 210 for each column of the pre-processing information user interface 200 as shown in FIG. 3 .

The preprocessing information according to the disclosure may include information on whether or not it is used for learning the deep learning model for each column. That is, a column used for learning the deep learning model may be selected by the user. In other words, a learning result desired by the user may be derived by excluding a column necessary for learning from the table data.

Referring to FIG. 3 , an exemplary diagram of the preprocessing information user interface 200 is shown. That is, the information on whether each column is used for learning the deep learning model may be collected from the user terminal through the learning data use input block 220 of the preprocessing information user interface 200 as shown in FIG. 3 .

The pre-processing information according to the disclosure may include information about a pre-processing method. The pre-processing method may include data cleansing, normalization, de-identification, and data replacement. The data cleansing may refer to at least one data operation such as data deduplication, error removal, and invalidation removal. For example, the data cleansing may refer to a data operation of deleting rows having a predetermined value in which the number of data is less than a predetermined number, or deleting rows outside a predetermined ratio of the overall standard distribution. The de-identification may be a data operation of deleting a column in which a predetermined data value occupies a predetermined ratio or more of the total number of data. The data replacement may refer to a data operation of deleting rows having empty values or filling empty values with a predetermined value. The user may select to perform the pre-processing in a method selected by the user from among the pre-processing methods including data cleansing, normalization, de-identification, and data replacement.

In S200 according to an embodiment of the present invention, the user may determine whether to perform pre-processing for each column of table data, and may determine whether to use for learning for each column. In addition, the pre-processing method can be selected by the user. That is, the deep learning model generation method of the present invention can learn the deep learning model by specifying only the columns used for learning among the table data input by the user so that the learning result desired by the user can be derived. In addition, the deep learning model can be trained in the user's desired direction by performing only preprocessing on a specific column.

Finally, a plurality of pre-prepared deep learning models are trained based on the collected input information and pre-processing information, and the learning state, accuracy, error rate and similarity of each of the plurality of deep learning models according to the learned result are included. A step ( S300 ) of providing learning result information may be performed.

In S300 according to an embodiment, learning is performed based on the collected input information and pre-processing information for a plurality of pre-prepared deep learning models ( S310 ) and a plurality of deep learning models according to the results learned in S310 It may include the step of providing learning result information including the learning state, accuracy, error rate, and similarity for each group ( S320 ).

In S310 according to an embodiment, the plurality of pre-prepared deep learning models may include models that have been previously trained based on a pre-prepared database. The plurality of deep learning models may include deep learning models having different structures in which at least one or more neural networks are combined. For example, the deep learning model may include a multi-layer perceptron, a recurrent neural network, a convolutional neural network, a generative adversarial network, etc., as well as a combination of the neural networks or It may have been changed and created. That is, in S310, learning may proceed according to the input information and the pre-processing information for the plurality of deep learning models that have been trained in advance.

In S320 according to an embodiment, the learning result information may include a learning state, accuracy, error rate, and similarity for each of a plurality of deep learning models. The learning state may indicate a learning result for indicating whether learning has been completed or whether learning has failed according to a plurality of deep learning models. The accuracy may indicate the accuracy of a deep learning model that has been trained. The error rate may indicate a rate of errors generated during training of the deep learning model. The similarity (Dice) may represent a sample coefficient for measuring the similarity between the training data and the result data of the deep learning model. The user may select a deep learning model to be used for data analysis or prediction of an analysis target column by the user using the learning result information including the learning state, accuracy, error rate, and similarity. That is, after step S320, user selection information about the deep learning model to be used by the user for analysis or prediction of the data of the analysis target column may be collected from the user terminal (S400). The deep learning model selected by the user by the user selection information may be referred to as a selection model.

4 is an exemplary diagram illustrating a state of providing a learning result information user interface 300 in a method for providing a deep learning solution according to an embodiment of the present invention. Referring to FIG. 4 , each deep learning model may be identified through the model name block 310 of the plurality of deep learning models. In addition, the learning result block 320 for indicating accuracy, error rate, and similarity can be confirmed in the user terminal through the learning result information user interface.

The learning result information according to the start may further include detailed learning information. The detailed learning information may include importance information, detailed analysis information, loss function information, and other information. The detailed analysis information may include statistical information on data for each column. The loss function information may include information about a loss function used for training a deep learning model. The other information may include statistical information used to measure the reliability of the deep learning model.

The importance information according to one disclosure may be information for indicating a degree of association between an analysis target column and at least one or more related columns according to a result learned for each deep learning model. That is, the user can check the most important related column for analyzing or predicting the data of the analysis target column through the importance information. In the importance information, the degree of relevance may be digitized and displayed for each related column. Alternatively, the importance information may be displayed by visualizing the degree of relevance (eg bar graph) for each relevance column. That is, the importance information may be displayed in various ways for the user to determine the correlation between the analysis target column and the related column. In other words, the user can check the most important (most relevant) related column for analysis or prediction of the analysis target column for each deep learning model that has been trained according to the above-described process through the importance information.

According to one disclosure, after the user selection information is collected from the user terminal in the aforementioned S400, an analysis request signal may be collected from the user terminal, and prescriptive analysis result information is transmitted to the user terminal in response to the collected analysis request signal. may be provided (S500). That is, the analysis request signal may be a signal from a user terminal requesting a prescriptive analysis result using the selection model. According to one disclosure, in the learning result information user interface 300 of FIG. 4 , the user may input the user selection information through the analyzing block 331 . In other words, the deep learning solution platform according to the disclosure collects an analysis request signal for the deep learning model selected by the user through the analyzing block 331 among a plurality of deep learning models through the learning result information user interface 300 can do.

Here, prescriptive analytics is one of the business analysis methods that use information to identify phenomena based on given data, predict future events, and decide appropriate actions. It can be an analysis method that presents the best alternative by efficiently allocating limited resources with ideal results. In the deep learning model generating method of the present invention, prescriptive analysis result information may be generated (S510) by deriving an optimal decision using the learning result of the deep learning model. The selection model in which the prescription analysis result information is generated by S510 may be referred to as a prescription analysis model.

Hereinafter, the process ( S510 ) of generating the prescriptive analysis result information will be described in detail. Also, in the following description, n may be a natural number.

First, a final related column among at least one or more related columns may be generated ( S511 ). The final association column may be determined according to a difference in the degree of association. More specifically, if the value of the nth correlation difference satisfies Equation 1 below in a relationship from the first correlation difference to the maximum value among the n−1th correlation difference values (n≥3), among at least one or more association columns From the first association column to the nth association column may be determined as the final association column.

[Equation 1]

Here, d _n is the nth correlation difference, d _x is the maximum value (n≧3) among the values of the n−1th correlation difference from the value of the first correlation difference, and r _f may be a reference ratio.

Here, the reference ratio may be a predetermined value. In addition, the nth association column is the nth association column when the degree of association with the analysis target column is listed in descending order (in descending order) from the greatest value (the value of the degree of association of the first association column) according to the importance information. (from the highest correlation column to the nth highest correlation column) may be referred to. That is, the first association column may be an association column in which the degree of association with the learning result analysis target column of the deep learning model is greater than that of the remaining associated columns except for the first association column. The nth correlation difference may be a value obtained by dividing the absolute value of a difference between the degree of association of the nth association column and the degree of association of the n+1th association column by the degree of association of the n+1th association column as shown in Equation 2 below.

[Equation 2]

Here, v _n may be an nth degree of association.

For reference, the final related column was composed of at least three columns to define the relationship with the column to be analyzed (n≥3).

After the final associated column is determined as in step S511, an approximate expression for analysis or prediction of the data of the analysis target column may be generated as shown in Equation 3 below (S512).

[Equation 3]

Here, J may be the data of the column to be analyzed, p may be the number of final related columns, d ^f _k may be the degree of correlation of the last related column, and a _k may be the final correlation coefficient. (k=1, 2, ..., p)

After the approximate expression is generated as in S512, the final association coefficient can be derived by substituting it into the approximate expression based on the relationship between the data of the final association column and the data of the analysis target column. That is, the input information includes table data, and since the table data includes the data of the last related column and the data of the analysis target column, the final related column data and the analysis target column data are substituted into the approximate expression to obtain the final result. The approximation can be completed by deriving the association coefficient.

Next, prescriptive analysis result information may be provided based on the data value of the analysis target column derived through the approximation equation for arbitrary data for the final related column ( S513 ).

According to one disclosure, the prescriptive analysis result information may be provided like the prescriptive analysis result information user interface 400 of FIG. 5 . Referring to FIG. 5 , the approximation formula is calculated for arbitrary data on 'recent contact period', 'recent contact date (month)', and 'recent contact day (day)' selected as a total of three final related columns. The data of the analysis target column ('charged or not') derived through this is derived and the user can check it.

As the prescriptive analysis result information prepared based on the approximation formula is provided as in the processes of S511 - S513 described above, a solution consisting only of information most relevant to the data to be analyzed or predicted can be presented to the user. That is, the user may determine the data related to the data to be analyzed or predicted directly by the user using the importance information, but if the prescriptive analysis result information according to the above-described processes S511 to S513 is used, analysis or prediction is performed. It can be used as a more efficient problem solution by providing a relationship between the target data and practically related data. In other words, if the prescriptive analysis result information according to the above-described processes S511 - S513 is used, it is possible to reduce errors that may occur when the user determines the importance information according to the deep learning learning result.

According to one disclosure, the user terminal may execute various types of applications, and may display the currently running application by visual or auditory display and provide it to the user. The user terminal may include a display module for visually displaying an application, and may include an input module for receiving a user's input, a communication module, a storage module storing at least one program, and a control module.

The user terminal according to one disclosure may be a mobile terminal such as a smart phone or a tablet PC, and according to an embodiment, a fixed device such as a desktop may also be included. Here, the user terminal includes a mobile phone, a smart phone, a laptop computer, a tablet PC, a wearable device, for example, a watch-type terminal (smart watch), a glasses-type terminal (smart glass) )) may be included.

The user terminal according to the disclosure may download and install various applications by accessing an app store or a play store. Here, the application may be a web browser application that outputs content such as games, news, photos, and videos provided online, or a dedicated application for providing each content.

The user terminal according to one disclosure may be connected to a deep learning platform providing apparatus that provides a deep learning solution platform through a communication network. Here, the communication network may include a wired network and a wireless network. More specifically, the communication network may include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN). The communication network may also include the well-known World Wide Web (WWW). However, the communication network according to the present invention is not limited to the networks listed above, and may include a well-known wireless data network, a well-known telephone network, a well-known wired or wireless television network, and the like. That is, the communication network may be any network method for connecting the user terminal and the deep learning platform providing apparatus.

The apparatus for providing a deep learning platform according to one disclosure may be connected to a user terminal through an application, and may provide a deep learning model and various information related to learning in response to a request of the user terminal.

The apparatus for providing a deep learning platform according to one disclosure may provide a deep learning solution platform.

That is, the deep learning solution providing method of the present invention may be performed by the deep learning platform providing apparatus. In other words, the processor of the apparatus for providing a deep learning platform according to one disclosure receives input information including tabular data to be analyzed or predicted from a user terminal, a learning method of the deep learning model, and a learning form of the deep learning model. and collects preprocessing information including whether the table data is preprocessed by column from the user terminal, whether it is used for learning a deep learning model, and a preprocessing method, and the collection for a plurality of deep learning models prepared in advance It is possible to learn based on the received input information and pre-processing information, and according to the learned result, it is possible to provide learning result information including the learning state, accuracy, error rate, and similarity of each of the plurality of deep learning models.

The apparatus for providing a deep learning platform according to one disclosure may include a memory for storing one or more instructions and a processor for executing one or more instructions stored in the memory.

According to one disclosure, the processor 200, for example, by driving software (eg, a program) to at least one other component (eg, hardware or software component) of the deep learning platform providing apparatus connected to the processor 200 can be controlled, and various data processing and operations can be performed. The processor 200 may load and process commands or data received from other components into a volatile memory, and store the result data in a non-volatile memory. According to an embodiment, the processor operates independently of the main processor (eg, central processing unit or application processor), and additionally or alternatively, uses less power than the main processor, or a secondary processor specialized for a specified function (eg, : graphic processing unit, image signal processor, sensor hub processor, or communication processor). Here, the auxiliary processor may be operated separately from or embedded in the main processor.

According to one disclosure, the memory 300 may store a program for processing and controlling the processor 200 , and may also store data input to or output from the device of the present invention. Programs stored in the memory 300 may be classified into a plurality of modules according to their functions, where the plurality of modules are software, not hardware, and are functionally operated modules. According to one disclosure, programs stored in the memory 300 may be classified into a plurality of modules according to their functions, where the plurality of modules are software, not hardware, and may mean modules that operate functionally.

The processor of the apparatus for providing a deep learning platform according to one disclosure collects input information including tabular data, a learning method of a deep learning model, and a learning form of the deep learning model, from a user terminal to be analyzed or predicted, Collects preprocessing information including whether the table data is preprocessed for each column, whether it is used for learning a deep learning model, and a preprocessing method from the user terminal, and the collected input information for a plurality of deep learning models prepared in advance and learning based on the preprocessing information, and may provide learning result information including a learning state, accuracy, error rate, and similarity of each of the plurality of deep learning models according to the learned result.

According to an embodiment of the present invention, after the prescription analysis result information is generated in step S510, the deep learning platform providing apparatus interworks with the deep learning model transaction brokerage server to mediate the transaction of the prescription analysis model (S600). there is.

More specifically, the deep learning model transaction brokerage server may collect sales information from the user terminal (seller terminal) for the prescription analysis model, and the prescription analysis model requested by the purchaser from the purchaser terminal. Buyer's purchase information may be collected (S610).

In addition, the deep learning model transaction brokerage server searches for sales information of at least one seller terminal that sells a prescription analysis model corresponding to the purchase information of the purchaser, and sales information of the prescription analysis model corresponding to the request information of the purchaser may be transmitted to the purchaser terminal (S620).

In addition, the deep learning model transaction brokerage server may receive the model selection signal of the purchaser from the purchaser terminal, and transmit the model selection signal to the seller terminal corresponding to the purchaser's model selection signal (S630).

Hereinafter, the process of brokering the transaction of the prescription analysis model in conjunction with the deep learning model transaction brokerage server (S610-S630) will be described in more detail.

First, the deep learning model transaction brokerage server may collect sales information from the user terminal (seller terminal) for the prescription analysis model, and purchase information of the purchaser regarding the prescription analysis model requested by the purchaser from the purchaser terminal may be collected (S610).

Next, the deep learning model mediation server searches for sales information of at least one seller terminal that sells a prescription analysis model corresponding to the purchase information of the purchaser, and retrieves sales information of the prescription analysis model corresponding to the request information of the purchaser. It can be transmitted to the purchaser terminal (S620).

Sales information according to the start of work may include a sales amount.

The sales amount according to the start of work may include a model usage amount and a brokerage fee.

The model usage amount according to the start may be determined from the seller setting information collected from the seller terminal. The seller setting information may include desired selling price information of the prescription analysis model determined by the seller.

The brokerage fee according to the initiation may be determined as in Equation 4 below based on the seller learning index.

[Equation 4]

where Wcom is the brokerage fee, f is the reference cost, Q _sell is the seller learning index, q _p is the platform learning factor, N _acc is the seller’s cumulative learning times, and N _tot is the seller’s learnable number of times there is.

The reference cost may be predetermined by the deep learning model transaction brokerage server. The platform learning factor indexes the degree to which the learning of the deep learning model is not completed when the seller terminal learns the deep learning model using the deep learning solution platform during the reference period, and may be predetermined by the deep learning platform providing device. .

The cumulative number of learning may represent the number of times the seller terminal trained the deep learning model using the deep learning solution platform during the reference period. The learnable number represents the number of times that the seller terminal can learn the deep learning model using the deep learning solution platform during the reference period, and the learnable number may be determined by the seller grade. The reference period may be predetermined in the deep learning model transaction brokerage server. The seller rating is the number of times the seller terminal sold the prescription analysis model using the deep learning model transaction brokerage server by the deep learning platform providing device, and the total sales of the prescription analysis model by the seller terminal using the deep learning model transaction brokerage server It may be determined based on the total number of times the seller terminal trained the deep learning model using the deep learning solution platform for the amount and the entire period.

Next, the deep learning model mediation server may receive the model selection signal of the purchaser from the purchaser terminal, and transmit the model selection signal to the seller terminal corresponding to the purchaser's model selection signal (S630).

As an embodiment of the present invention, a computer-readable recording medium in which a program for implementing the above-described method is recorded may be provided.

That is, the above-described method can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable medium. In addition, the structure of the data used in the above-described method may be recorded in a computer-readable medium through various means. A recording medium recording an executable computer program or code for performing various methods of the present invention should not be construed as including temporary objects such as carrier waves or signals. The computer-readable medium may include a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optically readable medium (eg, a CD-ROM, a DVD, etc.).

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

Although preferred embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims are also provided. is within the scope of the That is, the scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims

In the deep learning solution providing method performed by the deep learning platform providing device that provides the deep learning solution platform,

Collecting input information including tabular data to be analyzed or predicted from a user terminal, a learning method of a deep learning model, and a learning form of the deep learning model;

Collecting pre-processing information including whether the table data is pre-processed by column from the user terminal, whether it is used for learning a deep learning model, and a pre-processing method; And

A plurality of pre-prepared deep learning models are trained based on the collected input information and pre-processing information, and the learning result including the learning state, accuracy, error rate and similarity of each of the plurality of deep learning models according to the learned result Including; providing information;

How to provide deep learning solutions.