KR20230079306A - Method and System for intermediating project - Google Patents

Abstract

The present invention relates to a method and system for brokering a cloud-based incremental intelligence-enhancing deep learning project by collaboration between an expert device and a system, and more specifically, statistics from project participant recruitment announcements announced by project organizations and project results received by project participants. And by generating statistics and probability DB and machine learning DB by probability calculation and machine learning, project participants suitable for the new project participation recruitment announcement are found among project participants by statistics and probability prediction model and machine learning inference model. and the project organization, project participants are quickly delivered with project information suitable for them, and project organizations have the effect of quickly finding project participants suitable for the project they have planned.

Description

Project intermediary system and method {Method and System for intermediating project}

The present invention relates to a method and system for highly intelligent project mediation by gradually improving intelligence on a cloud basis through collaboration between an expert device and a system.

A project refers to a set of tasks such as research, business, test, experiment, test, etc. that are performed to achieve a certain goal within a certain period of time. A project can be carried out in a way that fulfills various requirements under certain constraints such as a fixed period, allocated amount, and input manpower. As an example, a project may include a clinical research project. In relation to the progress of the clinical research project, an app is provided that allows clinical trial project participants to read recruitment notices and participate in the clinical trial project.

However, clinical trial project participants have a serious problem of wasting time because they have to read recruitment announcements one by one to find a project suitable for them, and carefully review and understand the contents of the recruitment announcement.

In addition, since the project organization (or project announcer) that recruits clinical trial participants must wait without a deadline until the clinical trial project participant applies for participation, it is difficult to proceed with the clinical trial project at the desired time, or it is difficult to recruit participants. Failure to do so has resulted in premature termination of the project.

As an example, according to the thesis of '2016 Clinical Trial Recruitment Improvement Plan Study: From the Sponsor's Perspective_Yang Yeong-hwan', 35.3% experienced early termination of the project due to failure or delay in the recruitment of subjects, and the clinical trial did not proceed as scheduled. Non-progression was found in 41.2%. In addition, according to overseas research data IBM Global Business Services, it is reported that more than 75% of clinical trial projects failed to recruit participants within the set deadline. As described above, recruiting project participants within the specified deadline is acting as an important issue enough to determine the success or failure of a project.

According to the above-mentioned problem recognition, the clinical trial information integrated server provides a questionnaire to the clinical trial project participant terminal, compares and judges the eligibility questionnaire among the questionnaires prepared by the clinical trial project participant, and notifies the eligibility to the clinical trial project participant terminal. A pilot project information matching method has been developed. (Refer to KR Publication Patent Publication 2018-0133301) However, in this conventional method, a medical questionnaire is generated and provided to the clinical trial project participant terminal, and the eligibility questionnaire is compared and judged among the clinical trial project participant questionnaires to determine eligibility to the clinical trial project participant terminal. There is a drawback that it is difficult to use in reality because it includes a cumbersome process of notification.

Korea Patent Registration No. 10-1961144 (2019.03.22.)

The present invention has been proposed to solve the problems of the prior art as described above, and more specifically, by comparing and analyzing the contents of the recruitment announcement of the project organization and the project participation history of the project participant, detecting a suitable project participant, and determining the degree of suitability. It is an object of the present invention to provide a project mediation method and system that enables project participants to easily and quickly perform recruitment by providing project organizations and project participant terminals.

The project mediation system for achieving the above object is a project agency device that posts project announcement contents through a website, collects the project announcement contents from the project agency apparatus, configures a project DB, and proceeds with the project in the project DB. Extracts and stores key project information related to, collects project participant information from project participant devices related to participants who will participate in the project, or collects project results from previously participated project performance from the project organization device to obtain project participant key information , and while selecting a target based on statistical and probability calculations and predictions for the project key information and the project participant key information, an inference model based on machine learning is applied to the project key information and the project participant key information to target the target After selecting a final target by selecting a final target by performing inspection and correction on the selected target, the project brokerage device for providing information on the final target to at least one of the project institution device and the project participant device, the project A project participant device that registers as a participant in the mediation device and, upon receiving new project recommendation information from the project mediation device, transmits a new project participation acceptance message to the project mediation device according to a user input, and an expert who performs the inspection and correction. and a payment server supporting a payment service of at least one of cost processing of the project agency device, cost processing of the project participant device, and fee deduction of the project brokerage device in relation to the device and the recruitment of project participants. to be

The project mediation device according to an embodiment of the present invention includes a crawler that collects project participation recruitment notification contents from a website operated by a project institution device, a data management cloud server that receives data collected by the crawler and stores it in a project DB, Project participant key information DB for storing key information of participants to participate in the project, statistics and probability prediction module for performing statistical and probability calculations and predictions on the key project information, project participant key information stored in the project participant key information DB A primary target selection module for selecting a primary target by the statistics and probability prediction module as a target, a machine learning inference module for performing machine learning inference on the main project information, the primary target among the main information of the project participants Secondary subject selection module that selects the second subjects from the rest except for the project participants selected as, Inspection to check whether the contents of the first and second subject selection are correct, and to correct them correctly if they are incorrect and a correction module, a final target selection and notification module for selecting a final target by combining the primary target and the secondary target, and notifying project participants and project institutions of the selection result.

In addition, the project mediation device includes the participant's age, gender, height, weight, disease history, family history, blood type, address, location, career, education, field of expertise, field of interest, self-introduction information, and qualification related to the project participant device. Member login and information management module that supports the input and management of at least one of information, project progress history and results, hobbies, specialties, preferences, and food, clothing and shelter information, and supports confirmation of the subject selection result history, the contents of the above project participant recruitment announcement and corresponding An information collection module for receiving project participant information actually participating in clinical trials from the project institution device and storing it in a project participant DB, and extracting key project participant information from the project participant DB and storing the project participant key information DB in the project participant key information DB. An information extraction module, a statistics and probability calculation module for generating a statistics and probability DB by calculating statistics and probability from the main information DB of the project participants, and a machine learning module for generating a machine learning DB by machine learning from the main information DB of the project participants. may consist of

The project mediation method according to an embodiment of the present invention calculates and predicts statistics and probabilities for key project information stored in advance based on key project participant information pre-stored in relation to project participant devices and announcements provided by project institution devices. After selecting the first target person, the second target person is selected based on machine learning for the main project participant information and the project participant key information except for the first participant in the project participant key information. providing results of the selection of the first and second subjects to an expert device, and performing inspection and correction by the expert device, selecting a final subject based on the inspection and correction; and providing the final target selection information to at least one of the project institution device and the project participant device.

In addition, the project brokerage method, by crawling the contents of the new project participation recruitment announcement posted on the website operated by the project organization device to create a project DB, and extracting the project main information from the project DB key project information DB generating a step of updating the results of the inspection and correction to the main information of the project participant, generating a statistics and probability DB by calculating statistics and probability based on the updated main information of the project participant, and generating the main information of the updated project participant At least one step of generating a machine learning DB by machine learning based on the information may be further included.

In addition, the project mediation method includes the step of deducting a fee according to an agreement with the project participant device through a payment server and paying a cost to the project participant device participating in the project according to the compensation information described in the project main information can include more.

*Finally, the project mediation method may further include paying a certain fee to the project mediation device whenever the project participant device participates in a project through a payment server.

The project mediation method and system of the present invention described above demonstrates the following useful results.

1) The project organization device learns the results of the previous project and makes a model, and when a new project announcement is issued, the project participant device suitable for the announcement is selected, and the project participant device and the project institution device are notified to proceed with the project. The project can be carried out in a short time without the time delay related to the recruitment of participants.

2) In the project organization device, project participants suitable for the newly announced project contents can be notified quickly, so the overall project planning and operation can be designed in a short period of time.

3) Through project participant information registration, project participants can quickly receive project announcements suitable for them without searching for project information.

4) The performance of the system is guaranteed by inspection and calibration of the expert device, and the accuracy of prediction and inference of the system can be improved by allowing the inspection and calibration results of the expert device to be immediately reflected in the system.

5) Devices of project participants can be notified of selection through various communication interfaces such as SMS, PUSH, SNS (KakaoTalk, Facebook), instance app link, etc. that can be used without the need to install a separate app. there is.

1 is an example of a configuration diagram of a project mediation system according to an embodiment of the present invention.
2 is a diagram showing an example of a method for operating a project brokerage device according to an embodiment of the present invention.
3 is a diagram showing an example of a method of generating and operating a DB of a project brokerage device according to an embodiment of the present invention.
4 is a diagram showing an example of a method of updating and operating a DB of a project brokerage device according to an embodiment of the present invention.
Figure 5 is a diagram showing the signal flow between each component of the project mediation system according to an embodiment of the present invention.
6 is a diagram showing an example of a configuration of a project brokerage device according to an embodiment of the present invention.
7 is a diagram showing an example of a project participant selection method of the project brokerage device according to an embodiment of the present invention.

Hereinafter, preferred embodiments in which the object of the present invention can be realized in detail will be described in detail with reference to the accompanying drawings. In describing the present embodiment, the same name is used for the same configuration, and additional description thereof will be omitted.

1 is an example of a configuration diagram of a project mediation system according to an embodiment of the present invention.

Referring to FIG. 1, the project mediation system 10 of the present invention includes a project agency device 200, a project participant device 300, a project mediation device 100, an expert device 400, and a payment server 500. can do. The project mediation system 10 of the present invention identifies the contents of the project announcement based on cloud-based incremental intelligence enhancement deep learning by system collaboration with the expert device 400, and the project participant device 300 suitable for the contents of the announcement By searching and notifying, rapid progress related to project operation and proper management of project participants can be supported.

The project agency device 200 may design a project, recruit project participant devices 300 through the project brokerage device 100 in relation to the progress of the designed project, and then proceed with the project. For example, when the project is a specific clinical trial, the project institution device 200 provides a clinical trial notification to the project mediation device 100, and through the project mediation device 100, the project participant device suitable for the clinical trial notification ( 300) can be collected. The project agency device 200 includes a storage device for storing the designed project, a communication interface for communicating with the project brokerage device 100, storage of the project and transmission of project notification contents, and a project participant device participating in the project ( 300) may include a processor that performs information management.

As an example, the project agency device 200 may register project notification contents related to the progress of the project 201 on its own website 202 (or web page) after designing the project 201 . The project organization device 200 may allocate and operate each web site 202 to each project 201 . Correspondingly, the project mediation device 100 crawls the new project participation recruitment announcement posted on each website 202 by the crawler 109, and the crawled contents are project DB through the data management cloud server 110. (111).

As another example, the project organization device 200 may access a web site (or web page) provided by the project mediation device 100 and write project notification content on the web site. Project announcements entered through the website include, for example, the purpose of the project (research), the main information of the participants (age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field) , fields of interest, self-introduction information, qualification information, project history and results, hobbies, specialties, preferences, food, clothing and shelter information, etc.), characteristics of drugs for the project, main selection criteria, number of recruits, project (research) method, provided at the time of participation information, foreseeable side effects, application and inquiry information, etc. When the project agency device 200 fills in the project notification content through the website, the project brokerage device 100 can search for and propose a project participant device 300 based on the entered project notification content. there is.

The project institution device 200 may pay expenses related to recruitment of project participant devices 300 through the payment server 500 . For example, the project institution device 200 pays the project participant devices 300 that have participated in the project 1:1 through the payment server 500 and pays the project participant device 300 to the project brokerage device 100. A separate fee may be paid for their recruitment. Alternatively, the project institution device 200 may execute the entire cost related to the recruitment of project participant devices 300 to the project mediation device 100 through the payment server 500 when the participation of the project participants is completed. . In this case, the project brokerage device 100 may provide costs excluding commissions from among the total costs received to each project participant device 300 through the payment server 500 . Here, the payment server in which the project agency device 200 pays the cost to the project mediation device 100 and the payment server in which the project mediation device 100 pays the cost to the project participant devices 300 are payment servers of the same financial company. or may be different financial payment servers. As another example, when the project institution device 200 pays a project related fee to each of the project participant devices 300 participating in the project, the project participant device 300 pays a fee related to the project mediation to the payment server 500. It may be paid separately to the project brokerage device 100 through.

The project participant device 300 receives project participation recommendation information from the project mediation device 100 in relation to the project that the project institution device 200 is in progress, confirms the project announcement, and determines whether or not to participate in the project. It may include participants' terminals. The project participant device 300 may include various electronic devices such as a computing device or a mobile electronic device. The project participant device 300 may access a website operated by the project brokerage device 100, and perform member registration and information entry according to participant manipulation. In this process, the project participant device 300 provides key project participant information (eg, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, field of expertise, field of interest, self-introduction). information, qualification information, project progress history and results, hobbies, specialties, preferences, clothing and shelter information, etc.) or the name of the project 201 of the project agency device 200 may be entered. Project participant main information entered by the project participant device 300 may be used when selecting a project participant. The project participant device 300 may pay a membership fee to the project mediation device 100 through the payment server 500 and receive a project mediation service in relation to the use of project mediation. Alternatively, the project participant device 300 may provide a certain fee to the project brokerage device 100 through the payment server 500 whenever participating in the project 201 . In relation to cost processing, the project participant device 300 may select one of various items provided to the project mediation device 100 (eg, payment of membership fee or fee payment).

The expert device 400 may contribute to the final target selection by providing expert opinions in relation to the selection of participants by the project mediation device 100 . The expert device 400 may provide information about the suitability of project announcement contents and project participant main information. In this regard, the expert device 400 receives the project notification contents, project participant main information, and selection grounds from the project mediation device 100, and the inspection and correction results for the received information are sent to the project mediation device 100. can provide In this regard, the expert device 400 may provide an expert operating environment related to inspection and proofreading, or may build a database of expert knowledge related to inspection and proofreading of the expert. The expert device 400 may generate project participant suitability verification information and correction information for a project based on the established expertise database, and provide the verification and correction information to the project brokerage device 100 . The expertise database may be updated according to project progress results of the project participant devices 300 . In this regard, the project intermediary device 100 or the project institution device 200, with the consent of the project participant device 300, without exposing personal information (eg, providing only body information and results related to the project progress), project Results may be provided to the expert device 400 to assist in updating the expert knowledge database. The expert device 400 may be included as a part of the project mediation device 100, or may be provided and operated as a separate component. The expert device 400 may receive a certain cost from the project mediation device 100 from the payment server 500 according to inspection and correction requested by the project mediation device 100 .

The payment server 500 is at least one of cost payment by the project institution device 200, cost processing by the project intermediary device 100, cost processing by the project participant device 300, and cost processing by the expert device 400. can serve one. The payment server 500 may include a bank server or a card company server operated by at least one financial company. The payment server 500 may support account transfer of the project organization device 200 or the project mediation device 100, for example. In addition, the payment server 500 may support fee processing of the project brokerage device 100 and cost payment of the project participant device 300 . In this regard, the payment server 500 is entrusted with processing costs and costs related to project progress from the project institution device 200, and may pay project participation costs and project brokerage service costs according to project progress. . For example, the payment server 500 receives costs related to the progress of the project 201, project intermediary device 100 information, and project participant device 300 information from the project institution device 200, and the project participant receives the corresponding project When participating in (201), when the project is completed, or during the progress of the project, while paying the project participation cost to the project participant device 300, the related fee may be provided to the project brokerage device 100. In relation to the cost payment of the expert device 400, the payment server 500 acts as an agent for the cost payment of the project brokerage device 100, or when the project agency device 200 designates the expert device 400, the project agency device The cost payment for the expert device 400 of 200 may be substituted.

The project brokerage device 100 manages the project agency device 200 and the project participant devices 300, and when a new project announcement occurs, searches for, selects, and selects suitable project participant devices 300 and processes notification. can do. Explaining this in more detail,

The project mediation device 100 collects the project notification contents presented by the project agency device 200, searches for and selects a project participant device 300 suitable for the project notification content, and then selectively uses the expert device 400. After undergoing inspection and proofreading, final candidates can be selected. The project brokerage device 100 provides project participation recommendation information to the project participant device 300 corresponding to the selected final target person, and depending on whether the project participant device 300 accepts, the project participant device 300 information ( Example: main participant information) may be provided to the project organization device 200 . In this process, the project brokerage device 100 performs statistical and probability calculations and machine learning from project results previously experienced by the project participant device 300 and the contents of the project participant recruitment announcement announced by the project agency device 200. By creating statistics and probability DB and machine learning DB, and finding a project participant device 300 suitable for the new project participation recruitment announcement by statistical and probability prediction model and machine learning inference model, the project participant device 300 and the project institution By notifying the device 200 , the project institution device 200 may support the project participant device 300 to rapidly progress the project.

In this regard, the project brokerage device 100 crawls the new project participation recruitment announcement posted on each website 202 by the crawler 109, and the crawled information is project DB through the data management cloud server 110 (111). The project key information extraction module 113 extracts key project information from the project DB 111 to create a key project information DB 112 . The main project information may include, for example, project (research) purpose, participation target, project drug characteristics, main selection criteria, number of recruits, project (research) method, items to be provided at the time of participation, predictable side effects, applications and inquiries. can

The project intermediary device 100 uses the project participant member login and information management module 120 to personal information (age, gender, height, weight, disease history, family history, blood type) of the participant related to the project participant device 300. , address, location, career, education, field of expertise, field of interest, self-introduction information, qualification information, project progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, etc.) can confirm. In this regard, the project participant member login and information management module 120 provides a website through which the project participant device 300 can access and enter personal information, and can perform personal information storage and management with the consent of the participant. there is. The project participant member login and information management module 120 may store information of the subscribed project participant devices 300 in the project participant DB 102 .

As another example, the project brokerage device 100 may include an information collection module 101 . The information collection module 101 may receive project participant recruitment notification contents and project participant information actually participating in the clinical trial from the project institution device 200 and store them in the project participant DB 102 . The project participant main information extraction module 103 extracts project participant main information from the project participant DB 102 and stores it in the project participant main information DB 104 . The project participant’s main information DB (104) is the name of the clinical trial subject, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, specialty, and interest of the subject in the project participation recruitment notice. , Self-introduction information, qualification information, project progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, selection criteria, etc. are extracted based on rules, and the participant's personal information is stored.

The statistics and probability calculation module 105 performs statistics and probability calculations on key information stored in the project participant key information DB 104 and generates statistics and probability DB 107 as a result of the execution. The statistics and probability calculation module 105 provides a specific index (e.g., age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, interest field) for the main information of the participant. , self-introduction information, qualification information, project progress history and results, hobbies, specialties, preferences, clothing and shelter information), it is possible to perform statistics and probability calculations on the fitness of previous project results. For example, in the statistics and probability DB (107), participant personal information (e.g. disease name: brain tumor, current condition: standard treatment after surgery) middle, etc.) are stored by frequency of occurrence.

The machine learning module 106 performs machine learning on key information stored in the project participant key information DB 104 and creates a machine learning DB 108 based on the performance results. For example, the machine learning module 106 performs data evaluation on main information, extracts attributes of main information based on deep learning, and calculates (or infers) predicted information based on the extracted attributes. can For example, similar age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, qualification information, project history and results, hobbies, specialties, preferences , Based on the project history of the participant who has at least one of food, clothing and shelter information, the suitability for a new project can be inferred through machine learning. As an example, the machine learning DB 108 stores a learning model in which a word extracted from the personal information of a project participant is used as an input value and a word extracted from the name of a clinical trial subject is used as a target value.

The main project information extraction module 113 may extract main project information from the project DB 112 and generate the main project information DB 112 based on the extracted main project information. Key project information stored in the key project information DB 112 may be transmitted to the statistics and probability prediction module 114 and the machine learning inference module 116 . The main project information DB (112) is the name of the clinical trial subject, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional It stores major information such as field, field of interest, self-introduction information, qualification information, project progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, and selection criteria. At this time, a rule-based method of extracting information from the list of sentences included in the announcement is as follows.

"Above the age of 20, male and female under the age of 70" -> Rule: "Over #number# years old, under #number# years old" -> Age: 20~69

"New patients diagnosed with glioblastoma" -> Rule: "+ Patient confirmed with # disease name #" -> Disease name: Glioblastoma

The statistics and probability prediction module 114 performs statistics and probability prediction on the information stored in the statistics and probability DB 107 and the new project key information stored in the project key information DB 112, and the results are presented to the primary target It can be passed to the selection module 115. For example, the statistics and probability prediction module 114 is a clinical trial key information DB (age, gender, height, weight, disease history, family history, blood type, address, location, career, education, specialty field) extracted from the contents of the recruitment announcement for participation in the new project. , field of interest, self-introduction information, qualification information, project history and results, hobbies, specialties, preferences, food, clothing, and shelter information), based on the frequency of occurrence (probability). The first subject selection module 115 may select a first subject having a specified reference value or more among the results predicted by the statistics and probability prediction module 114 and transmit the selected result to the inspection and correction module 118 .

The machine learning inference module 116 performs machine learning based on the machine learning result of the main information of the participants stored in the machine learning DB 108 and the main project information stored in the main project information DB 112, and infers accordingly results can be produced. The machine learning inference module 116 may transfer the calculated inference result to the secondary subject selection module 117 . As an example, the machine learning inference module 116 is used to select a participant suitable for a disease name of a new project from existing member information. In the machine learning inference model, words are vectorized by the Word2vec model and used. The secondary subject selection module 117 may select subjects who satisfy specified conditions as secondary subjects from the transmitted inference result, and transmit the selection result to the inspection and correction module 118 . The secondary subject selection module 117 may select secondary subjects from the remaining project participants except for the project participants selected as the first subjects among the key information of the project participants. Alternatively, the secondary subject selection module 117 may perform secondary subject selection through machine learning independently of the first subject selection.

The inspection and correction module 118 provides the first subject information transmitted by the first subject selection module 115 and the second subject information transmitted by the second subject selection module 117 to the expert device 400, and the expert device Inspection and calibration results may be received from (400). The primary target information is the age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, and qualification information of the participant selected primarily from the main participant information. , Project progress history and results, hobbies, specialties, preferences, and at least one of clothing and shelter information, and may include condition information selected as a primary participant according to statistical and probability calculations for the participant information and key project information. The secondary target information is the age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, qualification information, project of the participant selected from the main participant information. It includes at least one of progress history and results, hobbies, specialties, preferences, and food and clothing information, and may include secondly selected participant condition information based on inference calculated according to machine learning for the participant information and project key information. . The expert device 400 checks whether the content automatically selected by the inspection and correction module 118 is correct, and if it is incorrect, undergoes a correction process of correctly correcting it. For example, the expert device 400 includes the primary subject selection conditions, key project information, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, specialty, and interests of the primary subject. At least one of field, self-introduction information, qualification information, project progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, statistics and probability information is checked to evaluate whether the result is valid as the primary target selection, and the secondary Subject selection conditions, project main information, secondary subject's age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, qualification information, project It is possible to evaluate whether selection as a secondary subject is valid by checking at least one of progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, and reasoning results based on machine learning. The expert device 400 may transmit the first subject inspection and calibration results and the second subject inspection and calibration results to the inspection and correction module 118 . The inspection and correction module 118 may transfer the result received from the expert device 400 to the final subject selection and notification module 119 . In another aspect, the inspection and correction module 118 may accumulate and update information on which the inspection and correction of the expert device 400 is performed as new information in the main project participant information DB 104 . The statistics and probability DB 107 may be updated by the statistics and probability calculation module 105 based on the updated information. In addition, the machine learning DB 108 may be updated by the machine learning module 106 based on the updated information. The statistics and probability prediction module 114 operates by the updated statistics and probability DB 107, and the machine learning inference module 116 operates by the updated machine learning DB 108.

The final target selection and notification module 119 selects the final target by combining both the primary target and the secondary target, and registers SMS, PUSH, SNS (KakaoTalk, Facebook), the selection result is transmitted to the project participant device 300 through the instance app link, and the corresponding result is notified to the project institution device 200. Here, the final target selection and notification module 119 first delivers the results to the project participant device 300, and when the project participant device 300 presents an intention to participate in a new project, the project institution device 200 corresponds to the It can be delivered to the project participant device 300 .

2 is a diagram showing an example of a method for operating a project brokerage device according to an embodiment of the present invention.

Referring to Figures 1 and 2, in relation to the project mediation device operation method according to an embodiment of the present invention, in step 501, the project mediation device 100 is a project 1 to N (201) associated with the website 1 ~ The project DB 111 is created by crawling the contents of the recruitment notification for new project participation posted in N 202 using the crawler 109 . Regarding the crawling operation, the project mediation device 100 may check the web site 202 belonging to the project agency device 200 at regular intervals or in real time to check whether there is a new project announcement. Alternatively, the project mediation device 100 may prepare a website and receive new project notification from the project agency device 200 based on the website.

In step 502, the project mediation device 100 may create a project main information DB (112). In relation to Io, the project brokerage device 100 may generate a project main information DB by extracting main project information from information stored in the project DB 111.

In step 503, the project brokerage device 100 may perform primary target selection based on statistics and probability prediction. To this end, the project brokerage device 100 acquires key project participant information from the project participant key information DB 104 in which the project participant key information is stored, and performs statistics and probability calculations on the project participant key information to obtain statistics and probability. DB 107 can be created. The project brokerage device 100 may perform primary target selection by performing statistical and probability predictions for the information stored in the statistics and probability DB 107 and the main project information DB 112.

In step 504, the project brokerage device 100 may perform secondary target selection using a machine learning DB. In this regard, the project brokerage device 100 may perform machine learning on project participant key information stored in the project participant key information DB 104 and generate a machine learning DB 108 based on the performance results. The project brokerage device 100 may perform secondary target selection based on information stored in the project main information DB 112 and the machine learning DB 108. When selecting the second target, the project mediation device 100 may select the second target from the remaining project participants except for the project participant selected as the first target among the main information of the project participant.

In step 505, the project brokerage device 100 may perform inspection and correction, and select a final target. Regarding inspection and correction, the project brokerage device 100 may form a communication channel with the expert device 400 and transmit first target person selection information and second target person selection information to the expert device 400 . The expert device 400 may include a computing device of an institution having specialized knowledge related to the project announcement content. The expert device 400 may check the received primary target selection information and secondary target selection information, and determine whether the selection is suitable according to the project announcement. Alternatively, the expert device 400 may check whether the selection target does not meet the specific conditions required by the project announcement, and provide a result thereof to the project brokerage device 100 . For example, it is possible to filter subjects having physical information or disease history information that must not participate in a project for which specific announcement content has been presented, and provide the filtering result (filtering reason and exclusion target information) to the project mediation device 100 .

In step 506, the project brokerage device 100 may provide notification content to the final target. The project intermediary device 100 may provide the final target to the project participant device 300 and the project institution device 200 after confirming the inspection and calibration results and selecting the final target. Here, the project mediation device 100 provides project participation recommendation information in preference to the project participant device 300 corresponding to the final target person, and when the project participant device 300 accepts participation, the project participant device that has accepted ( 300) may be provided to the project agency device 200. Alternatively, the project mediation device 100 may provide final target information to the project agency device 200 first, and provide project participation recommendation information only to the project participant devices 300 approved by the project agency device 200. there is.

3 is a diagram showing an example of a method of generating and operating a DB of a project brokerage device according to an embodiment of the present invention.

Referring to Figures 1 and 3, in relation to the project mediation device DB creation and operating method of the present invention, the project mediation device 100 in step 601, may store participant information in the project participant DB (102). In this operation, the project brokerage device 100 may receive project participant recruitment announcement contents and project participant information actually participating in the clinical trial from the project institution device 200, and store the received participant information in the project participant DB 102. there is.

In step 602, the project brokerage device 100 may extract key project participant information from the project participant DB 102 and store the extracted information in the project participant key information DB 104. The main information of the project participants is the name of the clinical trial subject, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, specialty, field of interest, self-introduction information , qualification information, project progress history and results, hobbies, specialties, preferences, food, clothing and shelter information, selection criteria, etc., information extracted based on rules, and the personal information of the participants.

In step 603, the project brokerage device 100 performs statistical and probability calculations on project participant key information stored in the project participant key information DB 104, and generates a statistics and probability DB 107 based on the results. can

In step 604, the project brokerage device 100 may perform machine learning on key project participant information stored in the project participant key information DB 104 and generate a machine learning DB 108 based on the machine learning result. . Meanwhile, although the order of generating the machine learning DB 108 after generating the statistics and probability DB 107 has been disclosed, the present invention is not limited thereto. The project mediation device 100 performs generation of statistics and probability DB 107 after generation of machine learning DB 108, or generation of machine learning DB 108 and generation of statistics and probability DB 107 in parallel. (or simultaneously).

In step 605, the project mediation device 100 operates a statistical and probability prediction model based on the statistics and probability DB 107, and operates a machine learning inference model based on the machine learning DB 108. . Key project information stored in the project key information DB 112 may be used for the operation of the statistical and probability prediction model and the machine learning inference model. The main project information may include, for example, at least the project (research) purpose, participation target, characteristics of the drug for the project, main selection criteria, number of recruits, project (research) method, and predictable side effects.

Through the above-described method, the project mediation device 100 can create and operate statistics, probability DB, and machine learning DB of the cloud-based incremental intelligence enhancement deep learning project mediation system by expert device and system collaboration.

4 is a diagram showing an example of a method of updating and operating a DB of a project brokerage device according to an embodiment of the present invention.

Referring to FIG. 4 , in relation to the DB update operation method of the project mediation device 100 according to an embodiment of the present invention, in step 701, the project mediation device 100 may perform an update of key project participant information. In this regard, the project brokerage device 100 may obtain inspection and correction results for the first subject selection result and the second subject selection result, and update key project participant information based on the inspection and correction results. For example, project participant main information may be updated based on a result of which participant was selected as a final target for a specific project. In the main information of the participant corresponding to the final target, the items selected as the final target of a specific project can be registered and updated.

In step 702, the project intermediary device 100 generates a statistics and probability DB by calculating statistics and probability based on the updated information, or updates the previous statistics and probability DB 107 to generate an updated statistics and probability DB. can do.

In step 703, the project brokerage device 100 may generate a machine learning DB by machine learning based on the updated information, or update the previous machine learning DB 108 to generate an updated machine learning DB. The order of steps 702 and 703 described above may be changed. For example, the project brokerage device 100 may perform update of the statistics and probability DB after first performing the update of the machine learning DB when the update of project participant main information is performed. Alternatively, the project brokerage device 100 may concurrently perform the update of the machine learning DB and the update of the statistics and probability DB in parallel.

In step 704, the project brokerage device 100 operates a statistical and probability prediction model based on the updated statistics and probability DB, and may operate a machine learning inference model based on the updated machine learning DB. In this operation, the project mediation device 100 acquires key project information about a new new project, operates a statistical and probability prediction model based on the key information of the new project and the updated statistics and probability DB, and the new project Machine learning inference model can be operated based on key information and updated machine learning DB.

Based on the above method, the project mediation device 100 of the present invention can perform a new information relearning procedure of the cloud-based incremental intelligence enhancement deep learning project mediation system by expert device and system collaboration.

Figure 5 is a diagram showing the signal flow between each component of the project mediation system according to an embodiment of the present invention.

Referring to FIGS. 1 and 5 , in relation to project mediation, in step 801, the project participant device 300 accesses the project mediation device 100 to input, modify, or query its own information. In this regard, the project brokerage device 100 may create and operate a website that the project participant device 300 can access. In step 803 , the project agency device 200 may provide previous project results to the project mediation device 100 . Here, the project agency device 200 providing the result of the previous project and the project agency device 200 designing and operating a new project may be the same or different. The project result may be provided according to the request of the project agency device 200, or the project agency device 200 designing and operating a new project may provide the previous project result to the project mediation device 100. The project results include contact information (eg, SMS, SNS, phone number, etc.) with the project participant device 300, age, gender, height, weight, disease history, family history, blood type, address, location, career, and education of the project participant. , field of expertise, area of interest, self-introduction information, qualification information, history and results of project progress, hobbies, specialties, preferences, food, clothing and shelter information. Steps 801 and 803 described above may proceed in any order.

The project mediation device 100 builds a project participant DB 102 based on input information of project participants or previous project results, and extracts key participant information from the project participant DB 102 to project participant key information DB 104. ) can be created. The project mediation device 100 may generate a statistics and probability DB 107 and a machine learning DB 108 in steps 805 and 807 based on the project participant main information DB 104 .

Meanwhile, in step 807 , the project agency device 200 may crawl the contents of the new project participation recruitment announcement from the website 202 of the project agency device 200 . The project mediation device 100 builds a project DB 111 based on the new project announcement obtained through crawling, and extracts key project information from the project DB 111 to create a key project information DB 112. can

In step 809, the project mediation device 100 selects the primary target by performing statistics and probability prediction using the key project information stored in the key project information DB 112 and the statistics and probability DB 107. , In step 811, the secondary subject selection may be performed by performing machine learning inference using the main project information stored in the main project information DB 112 and the machine learning DB.

In step 813, the expert device 400 performs inspection and correction on the first target selection information and the second target selection information provided by the project mediation device 100, and the information on the inspection and correction is transferred to the project mediation device. (100) can be provided.

In step 815, the project brokerage device 100 selects a final target based on the inspection and correction information, in step 817, notifies the project participant information to the project agency device 200, and in step 819, to the selected final target. Project recommendation information may be provided to the corresponding project participant device 300 . In step 819, the project mediation device 100 may notify the selection information through SMS, PUSH, SNS (KakaoTalk, Facebook), instance app link related to the project participant device 300.

6 is a diagram showing an example of a configuration of a project brokerage device according to an embodiment of the present invention.

* Referring to FIGS. 1 and 6, the project brokerage device 100 according to an embodiment of the present invention includes a communication circuit 110, a memory 120, an input device 130, a display device 140, and a processor 150 ) may be included.

The communication circuit 110 may support the communication channel formation function of the project brokerage device 100 . The communication circuit 110 may be composed of at least one communication module capable of using various mobile communication networks such as 3G, 4G, and 5G or the Internet network. For example, the communication circuit 110 forms a communication channel with the project agency device 200, and receives the previous project performance result and new project notification from the project agency device 200 in response to the control of the processor 150. can In addition, the communication circuit 110 forms a communication channel with at least one project participant device 300, and participant information (eg, age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, certification information, project history and results, hobbies, specialties, preferences, food, clothing, and shelter information) can be received. In addition, the communication circuit 110 forms a communication channel with the expert device 400 in response to the control of the processor 150, and in response to the control of the processor 150, the expert device 400 provides target selection information. and receive inspection and correction information from the expert device 400 . Alternatively, the communication circuit 110 provides a communication channel through which the expert device 400 can access and check the target person selection information, and the expert device 400 provides the target person selection information posted on the web page of the project intermediary device 100. Inspection and calibration information can be entered. In addition, the communication circuit 110 may form a communication channel with the payment server 500 and transmit/receive payment-related information in response to control of the processor 150 .

The memory 120 may store various applications and data related to the operation of the project brokerage device 100 . For example, the memory 120 includes the project participant DB 102, project participant main information DB 104, project DB 111, project main information DB 112, statistics and probability DB ( 107), machine learning DB 108, and the like. The database included in the memory 120 may be updated according to the addition or deletion of new project participants, and may also be updated according to the creation of a new project and the completion of an ongoing project. In addition, the memory 120 may store inspection and correction information for selected subjects provided by the expert device 400 . The stored inspection and calibration information may be used later to evaluate the expert device 400 .

The input device 130 may support a manager's input necessary for operating the project brokerage device 100 . Alternatively, the input device 130 may provide a hardware interface capable of inputting data. Accordingly, the input device 130 may support manual input of data related to the project participant device 300 or the project institution device 200 or data input through a wired connection to another external storage device.

The display device 140 may provide at least one screen related to the operation of the project intermediary device 100 . The display device 140 may output a screen interface with an external device that has formed a communication channel (eg, a wired or wireless communication channel) through the communication circuit 110 in response to the control of the processor 150 . For example, the display device 140 may be a web page accessed by the project institution device 200, a web page accessed by the project participant device 300, a web page related to the use of the payment server 500, and a web page accessed by the expert device 400. At least one of inspection and correction support web pages may be output. As an example, the display device 140 displays a list of project agency devices 200 supporting project mediation, a list of project participant devices 300 participating in a specific project, and a history of participation in previous projects, according to a manager input. A list of project participant devices 300, a list of at least one expert device 400, and the like may be displayed.

The processor 150 may perform transmission and processing of data related to the operation of the project brokerage device 100 . For example, the processor 150 includes the information collection module 101 described in FIG. 1, the project participant main information extraction module 103, the statistics and probability calculation module 105, the machine learning module 106, and at least one crawler ( 109), data management cloud server module (110), project main information extraction module (113), statistics and probability prediction module (114), primary target selection module (115), machine learning inference module (116), secondary target It may include at least one of a selection module 117, an inspection and correction module 118, a final target selection and notification module 119, and a project participant login and information management module 120. Each of the above-described modules may be implemented with at least one hardware processor or may be configured as a software module executed by one processor. The processor 150 may perform automatic selection and verification of participants suitable for project announcement contents according to an embodiment of the present invention based on the above-described modules, and notify.

Also, the processor 150 may support payment processing between devices (eg, the project institution device 200 , the project participant device 300 , and the expert device 400 ). For example, when the processor 150 is entrusted with payment of expenses to the project participants from the project institution device 200, the account information or payment information that can receive the expenses from the project participant main information of the participants participating in the project. Automatically collects and can perform payment (e.g. account transfer) based on the collected information. In this operation, the processor 150 may guide payment of expenses according to project participation and automatically guide information on related fee deduction. The processor 150 may support payment of expenses related to inspection and calibration of the expert device 400 . For example, the processor 150 calculates costs (e.g., cost calculation based on number of people, cost calculation based on project difficulty, level of urgency) according to predefined rules for inspection and correction of first and second screening subjects. Cost calculation, etc.) may be performed, and the calculated cost may be provided to the expert device 400 . In addition to providing the cost, evaluation scores for inspection and correction provided by the expert device 400 may be provided to the expert device 400 . The evaluation score may be calculated by the project agency device 200 after providing the data selected as the final subject to the project agency device 200 . For example, the evaluation score may be determined by the number of project participant devices 300 excluded by the project institution device 200 from the final person information. The processor 150 may provide a cost discount or increase (eg, incentive) for the expert device 400 based on the evaluation score according to a prior agreement.

7 is a diagram showing an example of a project participant selection method of the project brokerage device according to an embodiment of the present invention.

Referring to FIGS. 6 and 7 , in relation to the project participant selection method of the project mediation device according to an embodiment of the present invention, the processor 150 of the project mediation device 100 performs a statistical and probability-based first target person in step 901 . selection can be performed. In this regard, the memory 120 of the project brokerage device 100 may pre-store the project participant main information DB 104 and the project main information DB 112. Participant key information stored in the project participant key information DB 104 may be obtained by input of the project participant device 300 or may be included in previously performed project results provided by the project organization device 200 . The main project information stored in the project main information DB 112 is collected through crawling of the website 202 operated by the project agency device 200, or the project agency device 200 is the project brokerage device 100 ) can be obtained by passing it to The processor 150 may perform a first target selection through statistical and probability calculations and predictions on the acquired main project information and project participant main information. Alternatively, after the first target person selection, the second target person selection may be performed on the remaining personnel except for the first target person in the project participant information.

Meanwhile, the processor 150 may perform second target selection through machine learning in step 902 while step 901 is performed or before or after step 901 . In this regard, the processor 150 may select a second target by performing machine learning on key project information and participant key information and operating an inference model for machine learning.

The processor 150 may perform verification and correction on the selection result in step 903 . In this regard, the project intermediary device 100 may include an AI (Artificial Intelligence) module capable of performing inspection and correction for the selection result. The AI module may collect expert knowledge related to the project announcement contents and the suitability check of the participant information, and check the suitability result of the participant based on the expert knowledge. Alternatively, the processor 150 of the project mediation device 100 forms a communication channel with the expert device 400 capable of inspecting and correcting the selection result, and cooperates with the expert device 400 to determine the selection result. Inspection and calibration results can be collected.

The processor 150 may perform payment processing for the final recipient in step 904 . In this operation, the processor 150 provides project recommendation information to the project participant device 300 corresponding to the final target, and when receiving an acceptance message from the project participant device 300, the reward described in the project notification content. According to the cost criteria, a certain cost may be provided to the project participant device 300 through the payment server 500 . In this operation, the processor 150 may provide the project participant device 300 with a specified fee participation fee according to a policy defined by the project brokerage device 100 or according to a prior agreement with the project participant device 300. .

Meanwhile, in the above description, it is exemplified that subject selection based on statistics and probability prediction and subject selection through machine learning are performed in parallel, but the present invention is not limited thereto. For example, the project brokerage device 100 of the present invention selects a primary target for performing statistics and probability prediction based on project key information and project participant information, and then, within the primary target, an inference model through machine learning. can be applied to select secondary subjects. Alternatively, the project mediation device 100 of the present invention, based on the project main information and project participant information, applies an inference model through machine learning to select the primary target, and then for the project participants belonging to the primary target Statistical and probabilistic predictions can be performed to select secondary subjects. In addition, the project brokerage device 100 of the present invention may select secondary subjects from the rest of the project participants except for the project participants selected as the first subjects among the key information of the project participants when selecting the second subjects.

Therefore, all project participants selected from either the 'Statistics and Probability Prediction Module' or the 'Machine Learning Inference Module' can be recruited. It has the effect of supplementing the existing content. If a project participant registers project participant information once, they can quickly receive project participation information suitable for them without searching. Regardless of the project field, the present invention proceeds in a way to perform various requirements under certain constraints such as a fixed period, allocated amount, and input manpower for one project, shortening the project period, reducing costs, and inputting Effects can be expected in various project requirements, such as efficient recruitment of manpower.

As described above, according to an embodiment of the present invention, the cloud-based incremental intelligence enhancement deep learning project mediation system by system collaboration with an expert device is the project participant device recruitment announcement announced by the project institution device and the project participant device transferred Statistics and probability DB and machine learning DB are created by statistical and probability calculation and machine learning from the project results experienced in By finding and notifying the corresponding participant device and the project institution device, the project institution device can directly proceed with the project to the project participant device.

In addition, the cloud-based incremental intelligence enhancement deep learning project brokerage system by system collaboration with expert devices of the present invention is a crawler that collects project participation recruitment notices posted on the project agency device website, and the data collected by the crawler is project DB Data management cloud server, project key information extraction module that extracts key project information from project DB and creates key project information DB, statistics and probability that predicts and calculates statistics and probability from key project information DB and statistics and probability DB A prediction module, a primary target selection module that selects the first target by statistical and probability prediction modules for previously secured project participant devices, a machine learning inference module that makes machine learning inference from the main project information DB and machine learning DB, A secondary target selection module that selects secondary targets from the remaining project participant devices except for the project participant devices selected as the primary target among the secured project participant devices, a correction process that checks whether the selected content is correct and corrects it correctly if it is incorrect Inspection and correction module that goes through, all the primary and secondary targets are combined to select the final target, and the selection result is sent to project participant devices and project institution devices through SMS, PUSH, SNS (KakaoTalk, Facebook), and instant app links. Final target selection and notification module to notify, personal information (age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, qualification information , project progress history and results, hobbies, specialties, preferences, food, clothing, and shelter information), member login and information management module to check the subject selection result history, project participant device recruitment notification contents and actual participation in the clinical trial An information collection module that receives project participant device information from project institution devices and stores it in a project participant device DB, and extracts project participant device key information from the project participant device DB and stores the project participant device key information in the project participant device key information DB. Extraction module, statistics and probability calculation module that creates statistics and probability DB by statistical and probability calculation from project participant device key information DB, and machine learning module that creates machine learning DB by machine learning from project participant device key information DB can be configured.

In addition, the cloud-based incremental intelligence enhancement deep learning project mediation method by expert device and system collaboration according to an embodiment of the present invention crawls the contents of the recruitment announcement for new project participation posted on the website provided by the project institution device Creating a DB, extracting key project information from the project DB and creating a key project information DB, selecting a primary target by predicting statistics and probability from the key project information DB and statistics and probability DB, the project It may include the step of selecting the secondary target by the main information DB and the machine learning DB, the step of selecting and notifying the final target by inspecting and correcting the expert device, and the step of providing the notification contents to the device of the project participant or the device of the project institution. .

In addition, in the cloud-based incremental intelligence enhancement deep learning project mediation method by system collaboration with expert devices according to an embodiment of the present invention, project participant device recruitment announcement contents and project participant device information actually participating in the clinical trial are transmitted from the project institution device Step of receiving the data and storing it in the project participant device DB, extracting project participant device key information from the project participant device DB and storing it in the project participant device key information DB, statistics and probability calculations in the project participant device key information DB And generating a probability DB, generating a machine learning DB by machine learning in the main information DB of the project participant device, a statistical and probability prediction model is operated by the statistics and probability DB, and machine learning is performed by the machine learning DB. It may include operating an inference model.

In addition, the cloud-based gradual intelligence enhancement deep learning project mediation method by expert device and system collaboration according to an embodiment of the present invention includes the step of accumulating and updating new information in the main information DB of the project participant device by inspecting and calibrating the expert device , Generating statistics and probability DB by statistical and probability calculation based on updated information, generating machine learning DB by machine learning based on updated information, predicting statistics and probability by the updated statistics and probability DB A step of operating the model and operating the machine learning inference model by the updated machine learning DB may be included.

In addition, in the cloud-based incremental intelligence enhancement deep learning project mediation method by system collaboration with expert devices according to an embodiment of the present invention, the project participant device accesses the project mediation system and inputs, corrects, and inquires its own information , The project organization device transmits the project results (the contents of the project participation recruitment announcement and the information on the project participants who actually participated) to the project mediation system, the project mediation system generates a statistics and probability DB and a machine learning DB based on the project results Step, by crawling the contents of the new project participation recruitment notice from the website of the project institution device, selecting the first target by statistics and probability prediction using statistics and probability DB, and selecting the second target by machine learning inference using machine learning DB Step 2. Inspecting and correcting the data selected by the expert device inspection and correction, and selecting and notifying a final target.

In addition, the present invention may provide other systems, devices, and methods according to various embodiments.

10: Project mediation system
100: project intermediary device
200: project agency device
300: Project participant device
400: expert device
500: payment server

Claims (7)

Project agency device to post project announcements via website;
The project announcement contents are collected from the project agency device to form a project DB, project main information related to the project progress is extracted and stored from the project DB, and project participant information related to the participant to participate in the project is stored from the project participant device. Collects or collects project results according to the performance of projects previously participated by project participants from the project institution device and stores them as key project participant information, and calculates and predicts statistics and probabilities for the project key information and the project participant key information While selecting subjects based on the above, select subjects by applying an inference model based on machine learning to the main project information and the main information of the project participants, select the final subjects by performing inspection and correction on the selected subjects, a project intermediary device that provides information on an end target to at least one of the project organization device and the project participant device;
A project participant device registering as a participant in the project mediation device and, upon receiving new project recommendation information from the project mediation device, transmitting a new project participation acceptance message to the project mediation device according to a user input;
an expert device that performs the inspection and calibration;
In relation to the recruitment of project participants, a payment server supporting at least one payment service of cost processing of the project agency device, cost processing of the project participant device, and fee deduction of the project intermediary device; characterized in that it comprises a A project brokerage system that does. A crawler that collects project participation recruitment notices from the website operated by the project organization device;
A data management cloud server for receiving the data collected by the crawler and storing it in a project DB;
Project participant main information DB for storing the main information of the participants to participate in the project;
Statistics and probability prediction module for performing statistical and probability calculation and prediction for the key project information;
A primary target selection module for selecting a primary target by means of the statistics and probability prediction module for project participant key information stored in the project participant key information DB;
A machine learning reasoning module for performing machine learning reasoning on the project key information;
A secondary target selection module for selecting secondary targets from among the project participants' main information except for the project participants selected as the primary targets;
An inspection and correction module that undergoes a correction process of checking whether the first subject and the second subject selection information are correct and correcting them correctly if they are wrong;
A final candidate selection and notification module for selecting the final target by combining the primary target and the secondary target and notifying the project participants and the project organization of the selection result; Project mediation device comprising a. According to claim 2,
Age, gender, height, weight, disease history, family history, blood type, address, location, career, education, professional field, field of interest, self-introduction information, qualification information, project progress history and results, A member login and information management module that supports input and management of at least one of hobbies, specialties, preferences, food, clothing, and shelter information, and supports confirmation of target selection result history;
an information collection module for receiving the contents of the project participant recruitment announcement and project participant information actually participating in the clinical trial from the project institution device and storing them in a project participant DB;
A project participant main information extraction module for extracting the project participant main information from the project participant DB and storing it in the project participant main information DB;
A statistics and probability calculation module for generating a statistics and probability DB by calculating statistics and probability from the main information DB of the project participants;
Project brokerage device, characterized in that consisting of; machine learning module for generating a machine learning DB by machine learning from the project participant key information DB. Performing first target selection through statistical and probability calculations and predictions on key project information pre-stored in relation to project participant devices and based on announcements provided by project organization devices and project participant key information pre-stored;
After selecting the first target person, performing a second target participant selection based on machine learning for the main project participant information and the project participant main information except for the first project participant main information;
providing results of screening of the first subject and the second subject to an expert device, and performing inspection and correction by the expert device;
Selecting a final target based on the inspection and correction;
Providing the final target selection information to at least one of the project organization device and the project participant device; Project mediation method comprising a. According to claim 4,
generating a project DB by crawling new project participation recruitment announcements posted on a website operated by the project agency device, and extracting key project information from the project DB to create a key project information DB;
The result of the inspection and calibration is updated in the main information of the project participant, statistics and probability DB is created by statistical and probability calculation based on the updated main information of the project participant, and machine learning is based on the updated main information of the project participant. Generating a machine learning DB by; Project brokerage method characterized in that it further comprises at least one step of. According to claim 4,
Through a payment server, deducting a fee according to an agreement with the project participant device and paying the cost to the project participant device participating in the project according to the compensation information described in the project main information; characterized in that it further comprises. How to broker a project to do. According to claim 4,
The project mediation method further comprising: paying a predetermined fee to the project mediation device whenever the project participant device participates in a project through a payment server.

Images