KR102617657B1 - Server, method and computer program for providing contents production brokerage service based on ai matching model - Google Patents

Abstract

The present invention relates to a brokerage service that matches content production clients and content creators based on an AI matching model. The purpose of the present invention is to provide a brokerage service that utilizes an AI matching model to select production companies that best suit the requirements of content production clients. According to the server, method, and computer program according to the present invention, a list of matching recommended producers can be created using an AI matching model, and along with this, client feedback data for the client and producer feedback data for unselected producers are provided. Therefore, producers that best meet the client's requirements can be selected, and suggestions for better matching can be fed back to the client and producers, thereby increasing satisfaction with the brokerage service.

Description

Server, method, and computer program providing content production brokerage service based on AI matching model {SERVER, METHOD AND COMPUTER PROGRAM FOR PROVIDING CONTENTS PRODUCTION BROKERAGE SERVICE BASED ON AI MATCHING MODEL}

The present invention relates to a brokerage service that matches content production clients and content creators based on an AI matching model.

Demand for content production is increasing for various purposes such as advertising, publicity, and profit generation. Since professional manpower and equipment are needed to produce content such as videos or pictorial images, content production for clients is being done through agency companies. However, a problem may be that it is difficult to select the company that best suits the client's specific requirements among multiple companies.

Public Patent Publication No. 10-2021-0105024

The purpose of the present invention is to provide a brokerage service that utilizes an AI matching model to select production companies that best suit the requirements of content production clients.

According to some embodiments of the present invention, a server providing a content creation brokerage service based on an AI matching model, comprising: a memory configured to store instructions; And by executing the above commands: receiving request data on the detailed requirements of the target content from the client terminal and publishing it on the service platform, receiving production applications for the target content and production-related information of producers from producer terminals; , Utilizing the AI matching model to select at least some of the producers based on the detailed requirements and the production-related information to generate a list of recommended manufacturers for matching, and utilizing the AI matching model to match the detailed requirements and the Client feedback data is generated based on the recommended producer list, and the AI matching model is used to provide information on the remaining producers who were not selected by the matching recommended producer list among the producers based on the detailed requirements and the production-related information. a processor configured to generate producer feedback data, provide the matching recommended producer list and the client feedback data to the client terminal, and provide producer feedback data to producer terminals of the remaining producers; A server that provides a content production brokerage service based on an AI matching model, including, may be disclosed.

According to some embodiments of the present invention, in a method of providing a content production brokerage service based on an AI matching model, which is performed by a processor executing instructions stored in a memory, detailed requirements of target content are received from a client terminal. Receiving request data and disclosing it to the service platform; Receiving production applications for the target content and production-related information of producers from producer terminals; Selecting at least some of the producers based on the detailed requirements and the production-related information using an AI matching model to generate a list of recommended matching producers; Generating client feedback data based on the detailed requirements and the matching recommendation producer list using the AI matching model; Using the AI matching model to generate producer feedback data for remaining producers not selected from the matching recommended producer list among the producers based on the detailed requirements and the production-related information; and providing producer feedback data to producer terminals of the remaining producers while providing the matching recommended producer list and the client feedback data to the client terminal. A method of providing a content production brokerage service based on an AI matching model, including, may be disclosed.

According to some embodiments of the present invention, in a computer program recorded on a computer-readable storage medium to implement a method of providing a content creation brokerage service based on an AI matching model, instructions of the computer program execute the method when executed. A computer program configured to perform may be disclosed.

According to the server, method, and computer program according to the present invention, a list of matching recommended producers can be created using an AI matching model, and along with this, client feedback data for the client and producer feedback data for unselected producers are provided. Therefore, producers that best meet the client's requirements can be selected, and suggestions for better matching can be fed back to the client and producers, thereby increasing satisfaction with the brokerage service.

1 is a diagram illustrating a system that provides a content production brokerage service based on an AI matching model according to some embodiments of the present invention.
FIG. 2 is a diagram illustrating elements constituting a server that provides a content production brokerage service based on an AI matching model according to some embodiments of the present invention.
Figure 3 is a diagram illustrating a process in which an AI matching model provides feedback data to clients and producers according to some embodiments of the present invention.
FIG. 4 is a diagram illustrating how an AI matching model according to some embodiments of the present invention is updated based on response data of clients and producers to feedback data.
FIG. 5 is a diagram illustrating steps configuring a method of providing a content production brokerage service based on an AI matching model according to some embodiments of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The description below is only intended to specify embodiments and is not intended to limit or limit the scope of rights according to the present invention. What a person skilled in the art related to the present invention can easily infer from the detailed description and examples of the invention should be construed as falling within the scope of rights according to the present invention. Detailed descriptions of matters widely known to those skilled in the art related to the present invention will be omitted.

The terms used in the present invention are described as general terms widely used in the technical field related to the present invention, but the meaning of the terms used in the present invention is the intention of the technician working in the field, the emergence of new technology, examination standards, or precedents. It may vary depending on etc. Some terms may be arbitrarily selected by the applicant, in which case the meaning of the arbitrarily selected terms will be explained in detail. Terms used in the present invention should be construed not only in their dictionary meaning, but in a meaning that reflects the overall context of the specification.

1 is a diagram illustrating a system that provides a content production brokerage service based on an AI matching model according to some embodiments of the present invention.

Referring to Figure 1, the system 10 that provides a content production brokerage service based on an AI matching model includes a client terminal 100, a server 200 that provides a content production brokerage service based on an AI matching model, and producer terminals ( 300).

The system 10 that provides a content production brokerage service may refer to a brokerage system that matches clients who want to produce content with at least some of the producers based on an AI matching model. The system 10 may be implemented in the form of a computer program or mobile application, and the client terminal 100, server 200, and producer terminals 300 execute a program or app to communicate data on the system 10. You can interact through

The client terminal 100 is a terminal device of a client who wants to produce content, and may be a PC such as a desktop or laptop, or a mobile device such as a smartphone or tablet. Likewise, the producer terminals 300, including the first producer terminal 310 and the second producer terminal 320, may be a PC or a mobile device.

In the system 10, the server 200 may provide a content creation brokerage service using an AI matching model. AI matching model may refer to a model that is learned for content production brokerage services in at least one of various machine learning types. For example, an AI matching model can be learned using successful and unsatisfactory matching cases between clients and producers as learning data, and factors such as cost, period, and quality considered in matching are features of the machine learning model. It can function as

FIG. 2 is a diagram illustrating elements constituting a server that provides a content production brokerage service based on an AI matching model according to some embodiments of the present invention.

Referring to FIG. 2, a server 200 that provides a content creation mediation service based on an AI matching model may include a memory 210 and a processor 220. However, it is not limited to this, and other general-purpose elements may be further included in the server 200 that provides content creation brokerage services.

The memory 210 may have a structure for storing various commands, computer programs, or data processed by the server 200 that provides a content creation brokerage service. For example, the memory 210 is non-volatile memory such as ROM, PROM, EPROM, EEPROM, flash memory, PRAM, MRAM, RRAM, FRAM, etc., or volatile memory such as DRAM, SRAM, SDRAM, PRAM, RRAM, and FeRAM. It may be implemented in the form of HDD, SSD, SD, Micro-SD, etc., or a combination thereof.

The processor 220 may have a structure for performing processing processes required for the operation of the server 200 that provides a content creation brokerage service. The processor 220 may be implemented as an array of multiple logic gates or a general-purpose microprocessor for processing various operations, and may be comprised of a single processor or a plurality of processors. For example, the processor 220 may be implemented in the form of at least one of a microprocessor, CPU, GPU, and AP.

The processor 220 may be configured to receive request data regarding detailed requirements of target content from the client terminal 100 and disclose it to the service platform by executing instructions stored in the memory 210.

For example, target content may be promotional video content for an organization or company, and detailed requirements may include production cost, delivery date, quality, etc. When request data including these is received by the server 200, the request data may be made public on the service platform of the system 10. For example, request data may be uploaded to a web page of the system 10 or a related tab of an app and disclosed to creators who wish to be matched.

The processor 220 may be configured to receive production requests for target content and producers' production-related information from the producer terminals 300 by executing instructions stored in the memory 210.

Producers can check the request data disclosed on the service platform through the producer terminals 300 and apply for content production. In addition, producers can provide the specifications of themselves or the production company they belong to as production-related information to the server 200.

The processor 220 executes instructions stored in the memory 210 to select at least some of the manufacturers based on detailed requirements and production-related information using an AI matching model to generate a list of recommended manufacturers. It can be.

In order to select the most suitable producer for the client among the producers who received production applications, the AI matching model can compare and review the client's detailed requirements and the producer's production-related information. The criteria for selecting at least some of the producers may be adjusted by model parameters of the AI matching model. For example, the initial model parameters may be set to produce results similar to the results of comparison/examination confirmed in successful matching cases, and the model parameters may be updated in the direction intended by the system 10 through a feedback process. You can.

The processor 220 may be configured to generate client feedback data based on detailed requirements and a matching recommended producer list using an AI matching model by executing instructions stored in the memory 210.

Client feedback data may refer to data that suggests adjusting detailed requirements so that the client can receive a more suitable match. Here, a matching recommended producer list can be considered, and for example, if the producers selected in the list are excessively biased toward specific requirements or have relatively low ratings, an adjustment method to prevent this can be fed back.

By executing commands stored in the memory 210, the processor 220 utilizes an AI matching model to select the remaining producers that have not been selected as a matching recommended producer list among the producers based on detailed requirements and production-related information. Can be configured to generate producer feedback data.

The remaining producers who were not selected for the matching recommended producer list were excluded from the list despite receiving production applications, so producer feedback data regarding the reasons for not being selected for the list can be provided. For example, based on detailed requirements and production-related information, feedback can be given on which item had the greatest mismatch.

The processor 220 is configured to provide a matching recommendation producer list and client feedback data to the client terminal 100 by executing instructions stored in the memory 210 and provide producer feedback data to the producer terminals of the remaining producers. You can.

In this way, the client can check the matching recommendation and at the same time review supplementary content to improve the matching, and the remaining producers who do not belong to the matching list will analyze the cause of their failure to match and use this when using the service (10) in the future. You can refer to it.

According to some embodiments, the detailed requirements may include content field requirements, production cost requirements, production period requirements, production quality requirements, production experience requirements, and production workforce size requirements, and production-related information may include professional field information and production experience information. , may include production rating information, production cost information, production period information, personnel size information, equipment ownership information, and partner company information.

The detailed requirements and production-related information exemplified in this way can be considered in the process of the AI matching model generating a list of matching recommended producers. Meanwhile, if there are additional factors that can be considered for matching between the client and the producer other than the exemplified items, they may also be included in the detailed requirements and production-related information.

According to some embodiments, the AI matching model may be configured to quantify detailed requirements and production-related information and select at least some of the producers based on similarity values between the numbers, and producers belonging to the matching recommended producer list are Sorting may be possible based on each of the detailed requirements.

The AI matching model can be used to derive results by quantifying the factors to be considered in order to create a list of matching recommendation creators. For example, the client's production cost requirements, production period requirements, etc., and the producer's production cost information, production period information, etc. can be mapped into n-dimensional vectors, and the similarity value between elements is determined based on the distance between the corresponding vectors. can be calculated. In this way, at least some of the producers can be selected by comprehensively considering similarity values corresponding to multiple factors such as cost, period, and quality. Meanwhile, when two or more producers are selected, the client can sort and check the producers in the matching recommended producer list based on cost, period, quality, etc.

According to some embodiments, the client feedback data may include suggestions for adjustments to detailed requirements, and the AI matching model may include production rating information that exceeds the standard rating among the remaining producers not selected in the matching recommended producer list. It can be configured to determine adjustment suggestions based on production-related information from highly rated producers, and the producer feedback data includes two or more detailed requirements and production-related information corresponding to the bottom two or more similarity values among the similarity values between the figures. It may include combinations of .

For example, client feedback data may suggest adjusting production time requirements. Meanwhile, if there is an excellent producer with a high rating among the remaining producers not selected in the list, the AI matching model may suggest adjusting the detailed requirements of the client so that the excellent producer can be included in the list when reselected. Meanwhile, the standard of high ratings is only an example, and feedback may be provided in the direction of re-recommending producers with large scale or high quality among the remaining producers. Specifically, when selecting detailed requirements that the client considers top priority, if the best producer of the requirements is excluded from the list, feedback can be provided in the direction of including them again.

In the case of producer feedback data, for example, it is possible to inform what the bottom two of the distance-based similarity values between n-dimensional vectors are. For example, if it is notified that the combination of (production cost requirements, production cost information) and (production period requirements, production period information) are at the lowest and next lowest level based on similarity, the producer may indicate which production-related information is not in the list. You can find out what is the biggest cause.

According to some embodiments, the producer feedback data may further include matching strategy data, and the AI matching model calculates the contribution for each requirement indicating the degree of contribution of each detailed requirement in the process of generating the matching recommendation producer list, and Based on contribution, it may be configured to generate matching strategy data regarding the relative complementary proportion of production-related information held by each remaining producer not selected in the matching recommended producer list.

For example, if, among the detailed requirements, the weight of contribution of the production experience requirement, production cost requirement, and production period requirement when creating a list of matching recommended producers is 0.5, 0.2, or 0.3, 50/20 will be given to the remaining unselected producers. With a ratio of /30, matching strategy data can be generated that suggests supplementing production experience, production cost, and production period. Meanwhile, the contribution and weight values can be calculated based on an n-dimensional vector by an AI matching model.

According to some embodiments, the processor 220 executes instructions stored in the memory 210 to provide detailed requirements for the client feedback data based on the client response data for the client feedback data and the producer response data for the producer feedback data. It may be further configured to determine the adequacy of each production-related information of the producer feedback data and adjust the parameters of the AI matching model based on the adequacy of each detailed requirement and the adequacy of each production-related information.

The client evaluates the client feedback data and the matching recommended producer list and provides client response data in the form of positive/negative or a 1 to 5 point scale for each detailed requirement such as cost/duration/experience to the server 200. This can be done, and the producer can also provide producer response data to the server 200 for each piece of production-related information in a similar manner. Based on this, the server 200 can adjust the direction in which the AI matching model outputs the results through parameter updates. For example, if the client replies that the result is negative in terms of cost, the server 200 can adjust the parameters of the AI matching model to reflect the cost aspect with a higher weight.

Figure 3 is a diagram illustrating a process in which an AI matching model provides feedback data to clients and producers according to some embodiments of the present invention.

Referring to FIG. 3, in the system 10 providing a content production brokerage service, the server 200 can interact with the client terminal 100 and the producer terminals 310 and 320 using the AI matching model 250. there is.

The client terminal 100 and the producer terminals 310 and 320 can provide request data and production applications to the server 200, and based on these, the AI matching model 250 selects some of the producers and recommends matching. You can create a list of producers. The server 200 may notify the selected producer terminal 320 that it has been selected as a matching recommended producer and provide the list to the client terminal 100.

The AI matching model 250 can additionally generate client feedback data after generating a list of matching recommended producers, and can also generate producer feedback data for producers that were not selected in the list. The server 200 may provide client feedback data along with a matching recommended producer list to the client terminal 100, and may provide producer feedback data to the unselected producer terminal 310.

FIG. 4 is a diagram illustrating how an AI matching model according to some embodiments of the present invention is updated based on response data of clients and producers to feedback data.

Referring to FIG. 4, in the system 10 providing a content production brokerage service, the server 200 creates an AI matching model 250 based on response data provided from the client terminal 100 and the unselected producer terminal 310. can be updated.

The client can provide client response data to the server 200 as his or her own feedback on the client feedback data, and similarly, producers who were not selected can provide producer response data to the server 200. The server 200 may change the detailed tendency of the AI matching model 250 to produce results by adjusting the model parameters of the AI matching model 250 based on the client response data and producer response data.

FIG. 5 is a diagram illustrating steps configuring a method of providing a content production brokerage service based on an AI matching model according to some embodiments of the present invention.

Referring to FIG. 5, a method 500 of providing a content creation brokerage service based on an AI matching model may include steps 510 to 560. However, the present invention is not limited to this, and some steps may be omitted or general-purpose steps may be added, and the order in which the steps of the method 500 for providing a content production brokerage service are performed may be changed.

The method 500 of providing a content production brokerage service based on an AI matching model may consist of steps processed in time series in the server 200 that provides a content production brokerage service based on an AI matching model. Therefore, even if the content is omitted below, the content described above with respect to the server 200 can be equally applied to the method 500.

Steps 510 to 560 of the method 500 for providing a content production brokerage service based on an AI matching model may be performed by the processor 220 executing instructions stored in the memory 210.

In step 510, the server 200, which provides a content production brokerage service based on an AI matching model, may receive request data regarding detailed requirements of the target content from the client terminal and disclose it to the service platform.

In step 520, the server 200, which provides a content production brokerage service based on an AI matching model, may receive production requests for target content and production-related information from creators from creator terminals.

In step 530, the server 200, which provides a content production brokerage service based on an AI matching model, selects at least some of the creators based on detailed requirements and production-related information using the AI matching model and recommends matching. You can create a list of producers.

In step 540, the server 200, which provides a content production brokerage service based on an AI matching model, may utilize the AI matching model to generate client feedback data based on detailed requirements and a list of matching recommended creators.

In step 550, the server 200, which provides a content production brokerage service based on an AI matching model, selects a list of recommended creators among creators based on detailed requirements and production-related information using the AI matching model. Producer feedback data can be generated for the remaining producers.

In step 560, the server 200, which provides a content production brokerage service based on an AI matching model, provides a matching recommended producer list and client feedback data to the client terminal and provides producer feedback data to the producer terminals of the remaining producers. can do.

Meanwhile, the method 500 of providing a content production brokerage service based on an AI matching model may be implemented in the form of a computer program stored in a computer-readable storage medium. That is, the computer program may include instructions for implementing the method 500 for providing a content creation brokerage service, and the instructions of the computer program may be stored in a computer-readable storage medium. Computer programs may include mobile applications.

For example, computer-readable storage media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and floptical disks. It may include magneto-optical media, such as ROM, RAM, flash memory, and hardware devices specifically configured to store and execute computer program instructions. Computer program instructions may include machine code created by a compiler and high-level language code that can be executed by a computer using an interpreter.

Although the embodiments of the present invention have been described in detail above, the scope of rights according to the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention described in the following claims can also be made according to the present invention. It should be construed as being included in the scope of rights pursuant to.

Claims (10)

In a server that provides a content production brokerage service based on an AI matching model,
a memory configured to store instructions; and
By executing the above commands:
Request data regarding detailed requirements of target content is received from the client terminal and disclosed on the service platform,
Receiving production applications for the target content and production-related information from producers from producer terminals,
Using an AI matching model, select at least some of the producers based on the detailed requirements and the production-related information to generate a list of recommended matching producers,
Using the AI matching model, client feedback data is generated based on the detailed requirements and the matching recommendation producer list,
Utilizing the AI matching model to generate producer feedback data for the remaining producers not selected by the matching recommended producer list among the producers based on the detailed requirements and the production-related information,
a processor configured to provide the matching recommended producer list and the client feedback data to the client terminal and provide producer feedback data to the producer terminals of the remaining producers; Including,
The production-related information includes professional field information, production experience information, production rating information, production cost information, production period information, staff size information, equipment ownership information, and partner company information,
The client feedback data includes suggestions for adjustments to the detailed requirements,
The AI matching model is configured to determine the adjustment suggestions based on production-related information of highly rated producers whose production rating information exceeds a standard rating among the remaining producers not selected by the matching recommended producer list,
If there is an excellent producer with a high rating among the remaining producers not selected in the matching recommended producer list, the AI matching model proposes to adjust the detailed requirements so that the excellent producer belongs to the matching recommended producer list when reselected. composed,
The AI matching model uses the client feedback data in the direction of including the best producer in the matching recommended producer list when the best producer that meets the detailed requirements that the client considers top priority is excluded from the matching recommended producer list. configured to create,
A server that provides content production brokerage services based on AI matching model. According to paragraph 1,
The above detailed requirements include content field requirements, production cost requirements, production period requirements, production quality requirements, production experience requirements, and production workforce size requirements,
The AI matching model is configured to quantify the detailed requirements and the production-related information and select at least some of the manufacturers based on similarity values between the numbers,
A server that provides a content production brokerage service based on an AI matching model, where producers belonging to the matching recommendation producer list can be sorted based on each of the detailed requirements. According to paragraph 2,
The producer feedback data includes combinations of two or more detailed requirements and production-related information corresponding to the lower two or more similarity values among the similarity values between the figures. A server that provides a content production brokerage service based on an AI matching model. . According to paragraph 1,
The producer feedback data further includes matching strategy data,
The AI matching model calculates a contribution rate for each requirement indicating the degree of contribution of each of the detailed requirements in the process of generating the matching recommended producer list, and based on the contribution rate for each requirement, each remaining producer not selected in the matching recommended producer list A server that provides a content production brokerage service based on an AI matching model, configured to generate the matching strategy data regarding the relative complement proportion of production-related information. According to paragraph 1,
The processor, by executing the instructions:
Based on the client response data to the client feedback data and the producer response data to the producer feedback data, determine the adequacy of the client feedback data for each detailed requirement and the adequacy of the producer feedback data for each production-related information,
A server that provides a content production brokerage service based on an AI matching model, further configured to adjust parameters of the AI matching model based on the adequacy for each detailed requirement and the adequacy for each production-related information. In a method of providing a content production brokerage service based on an AI matching model, which is performed by a processor executing instructions stored in memory,
Receiving request data on detailed requirements of target content from the client terminal and disclosing it to the service platform;
Receiving production applications for the target content and production-related information of producers from producer terminals;
Selecting at least some of the producers based on the detailed requirements and the production-related information using an AI matching model to generate a list of recommended matching producers;
Generating client feedback data based on the detailed requirements and the matching recommendation producer list using the AI matching model;
Using the AI matching model to generate producer feedback data for remaining producers not selected from the matching recommendation producer list among the producers based on the detailed requirements and the production-related information; and
providing producer feedback data to producer terminals of the remaining producers while providing the matching recommended producer list and the client feedback data to the client terminal; Including,
The production-related information includes professional field information, production experience information, production rating information, production cost information, production period information, staff size information, equipment ownership information, and partner company information,
The client feedback data includes suggestions for adjustments to the detailed requirements,
The AI matching model is configured to determine the adjustment suggestions based on production-related information of highly rated producers whose production rating information exceeds a standard rating among the remaining producers not selected by the matching recommended producer list,
If there is an excellent producer with a high rating among the remaining producers not selected in the matching recommended producer list, the AI matching model proposes to adjust the detailed requirements so that the excellent producer belongs to the matching recommended producer list when reselected. composed,
The AI matching model uses the client feedback data in the direction of including the best producer in the matching recommended producer list when the best producer that meets the detailed requirements considered by the client is excluded from the matching recommended producer list. configured to create,
A method of providing content production brokerage services based on AI matching model. According to clause 6,
The above detailed requirements include content field requirements, production cost requirements, production period requirements, production quality requirements, production experience requirements, and production workforce size requirements,
The AI matching model is configured to quantify the detailed requirements and the production-related information and select at least some of the manufacturers based on similarity values between the numbers,
A method of providing a content production brokerage service based on an AI matching model in which producers belonging to the matching recommended producer list can be sorted based on each of the detailed requirements. In clause 7,
The producer feedback data includes combinations of two or more detailed requirements and production-related information corresponding to the lower two or more similarity values among the similarity values between the figures. A method of providing a content production brokerage service based on an AI matching model. . According to clause 6,
The producer feedback data further includes matching strategy data,
The AI matching model calculates a contribution rate for each requirement indicating the degree of contribution of each of the detailed requirements in the process of generating the matching recommended producer list, and based on the contribution rate for each requirement, each remaining producer not selected in the matching recommended producer list A method of providing a content production brokerage service based on an AI matching model, configured to generate the matching strategy data regarding the relative complement weight of production-related information. According to clause 6,
determining the adequacy of the client feedback data for each detailed requirement and the adequacy of the producer feedback data for each production-related information based on the client response data to the client feedback data and the producer response data to the producer feedback data; and
adjusting parameters of the AI matching model based on adequacy for each detailed requirement and adequacy for each production-related information; A method of providing a content production brokerage service based on an AI matching model, further comprising: