KR102357855B1 - Method, apparatus and program for managing specialist career using structured information generated based on unstructured information - Google Patents

Abstract

A professional career management method is provided. The expert career management method includes the steps of registering an expert (S110), acquiring expert information of the registered expert (S120), and calculating absolute career information of the expert based on the acquired expert information (S130) ), the step of matching the project corresponding to the expert based on the absolute career information of the expert (S140), when the matched project is performed by the expert, the project data calculated according to the execution result of the project obtaining (S150); Updating the absolute career information of the expert based on the project data (S160) and obtaining relative career information based on the updated absolute career information and the project data (S170).

Description

Professional career management method, apparatus and program using structured information generated based on unstructured information

The present invention relates to a professional career management method, apparatus and program using structured information generated based on unstructured information.

In the era of the 4th industrial revolution, it is expected that the depth, speed and scope will be greatly expanded based on hyperconnectivity and superintelligence. As a result, not only various industrial fields are created, but also numerous new fields are generated, such as the fusion of existing and new industrial fields. Therefore, there is a need for a platform where experts in each field can be discovered and recruited and experts in each field can collaborate.

In addition, the period of production activities will be extended due to the extension of life expectancy in the future, and it is necessary to enable each expert to make the relevant field a lifelong “job” rather than simply a job.

In addition, it is desirable to allow experts to act and be treated based on their abilities in each field. However, there were problems such as not being given treatment according to their abilities, and being converted to a managerial position rather than taking advantage of it as experience accumulates.

On the other hand, in order for experts to act and be treated based on their abilities in each field, it is necessary to accurately calculate the career of the expert. However, in the past, it was often impossible to calculate the exact career of an expert. For example, when a plurality of experts perform project A, it is a reality that each of the plurality of experts writes “Project A” in the career field. However, even if a plurality of experts perform project A together, the work content and quality of work performed by each expert will be different, and it is unreasonable for all the experts to have the same experience. That is, there is a problem in that there is no method for distinguishing the careers of experts who have performed only an auxiliary role in the project and those who have performed a practical role in the prior art. Therefore, there is a need for a professional career management method for solving the above-mentioned problem.

On the other hand, blockchain, also called public transaction ledger, is a technology that prevents hacking that can occur when transacting with virtual currency. Whereas existing financial companies keep transaction records on a centralized server, blockchain sends transaction details to all users participating in the transaction and collates them with each transaction to prevent data forgery. have

For example, blockchain is applied to Bitcoin, a representative online virtual currency. Bitcoin transparently records transaction details in a ledger that anyone can view, and multiple computers using Bitcoin verify this record every 10 minutes to prevent hacking. Recently, various coins have been developed and provided to solve the shortcomings of Bitcoin, and with the advent of coins with platform functions, various tokens are functioning as virtual currencies.

In addition, as various distributed applications (DAPPs) using a virtual currency platform are being developed and used, the utilization of blockchain is increasing.

Furthermore, various information such as detailed information of experts managed on the expert platform, work experience, professional field, and project execution history, project execution results and performance information, etc., are at risk of hacking and forgery, and information leaked through hacking When used in the market, trust in the expert platform for expert management may be damaged and the degree of matching may decrease.

Therefore, the development of a technology capable of preventing forgery while maintaining the reliability of such information is required.

On the other hand, MICE is an acronym for corporate meetings, incentive trips, conventions, exhibitions and events. It refers to a promising industry, and in a broad sense, it refers to a convergence industry that includes participant-centered reward tourism and mega-events.

Laid-open Patent Publication No. 10-2010-0026834, published on March 10, 2010

An object to be solved by the present invention is to provide a professional career management method, apparatus and program using structured information generated based on unstructured information.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

The expert management method according to an aspect of the present invention for solving the above-described problems includes the steps of registering an expert (S110), acquiring expert information of the registered expert (S120), and based on the acquired expert information Calculating the absolute career information of the expert (S130), matching the project corresponding to the expert based on the absolute career information of the expert (S140), when the matched project is performed by the expert, acquiring project data calculated according to the project execution result (S150); Updating the absolute career information of the expert based on the project data (S160) and obtaining relative career information based on the updated absolute career information and the project data (S170).

Other specific details of the invention are included in the detailed description and drawings.

According to the disclosed embodiment, by determining actual career information rather than formal career information about an expert, an effect of treating an expert based on true ability and career can be expected.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a diagram illustrating a block chain system according to an embodiment of the present invention.
2 is a system diagram illustrating the operation of a block chain system according to an embodiment of the present invention.
3 is a diagram illustrating a control system of an expert platform for expert career management according to an embodiment of the present invention.
4 is a diagram for explaining a process of propagating valid information on a network of a block chain to nodes on a network of a block chain and recording it in a block chain according to an embodiment of the present invention.
5 is a flowchart illustrating an expert career management method performed in an expert platform according to an embodiment of the present invention.
6 is a flowchart illustrating a method of calculating absolute career information of an expert according to an embodiment of the present invention.
7 is a flowchart illustrating another method of calculating absolute career information of an expert according to an embodiment of the present invention.
8 is a flowchart illustrating a method of updating an expert's absolute career information according to an embodiment of the present invention.
9 is a flowchart illustrating a method of calculating relative career information of an expert according to an embodiment of the present invention.
10 is a flowchart illustrating a method of acquiring relative career information based on a first career score and a second career score according to an embodiment of the present invention.
11 is a flowchart for explaining a method of acquiring career points based on weights according to an embodiment of the present invention.
12 is a flowchart illustrating a method of calculating a career score according to whether project data is a joint work or a combined work according to an embodiment of the present invention.
13 is a block diagram of an apparatus according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium or to reproduce one or more processors. Thus, as an example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or as additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer refers to all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood to include, but is not limited to, smart phones, tablet PCs, desktops, notebooks, and user clients and applications running on each device.

In this specification, the subject of the business and project may be understood as encompassing not only businesses such as individual entrepreneurs or corporations, but also general individuals, and does not limit a specific subject. In an embodiment, the project, project subject, and performing entity may be a government, a local government, a public institution, an association, or the like.

In this specification, the project or project information refers to the government, local government, public institutions, associations, businesses and projects ordered by companies, business and project-related tasks, domestic and international procurement bidding, and other experts It may refer to various projects and business-related tasks.

The type of project may also include various types such as the provision of goods or services, and is not limited to a specific type. For example, a project may be to deliver a specific product, may be to provide research service or professional service service, or may include various tasks in a complex manner.

In the present specification, an expert may be understood to mean any kind of person with a certain expertise in a specific field, and the criterion is not limited thereto. All kinds of experienced, educated, or talented people who can perform work in a specific field can all be referred to as experts, but preferably, it is understood to mean a person with a certain experience in a specific field. can be

Accordingly, experts according to the present disclosure may refer to experts who satisfy the requirements required by a specific group as well as experts of the existing conceptual, conventional, and general standards.

On the other hand, the expert in the present disclosure means a single individual expert, but is not limited thereto. In other words, a specific group itself can be viewed as an expert.

Meanwhile, in this specification, MICE is an acronym for corporate meetings, incentive trips, conventions, exhibitions and events, etc., and in a narrow sense, international conferences and exhibitions. It refers to a promising industry centered around However, in this specification, the meaning of MICE is not limited to the term itself, and may be used in various terms depending on time and region.

For example, in Canada, Meeting, Convention and Incentive Travel is abbreviated as MC&IT, in the United States it is used as ME&I or MEEC (Meetings, Expositions, Events and Conventions), and in Singapore, Business Travel & MICE is abbreviated as BT MICE. As such, various terms are used according to the industrial structure and policies of each country.

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

Each step described in this specification is described as being performed by a computer or a server, but the subject of each step is not limited thereto, and at least a portion of each step may be performed in different devices according to embodiments.

Referring to FIG. 1 , the blockchain holding servers 10 , the management server 20 and the user terminals 30 are shown.

In the disclosed embodiment, each of the user terminals 30 records transaction details based on a preset rule, and the recorded transaction details are recorded in each block and propagated to the blockchain holding servers 10, and each It is stored and managed on the server.

In the disclosed embodiment, the blockchain holding servers 10 mean servers equipped with a blockchain for authenticating and recording transaction information. In an embodiment, transaction information may refer to transaction information based on virtual currency, but may also refer to information about various events performed based on a block chain, and such transaction information is stored in the block chain. is saved

The virtual currency according to the disclosed embodiment is understood as a concept that collectively refers to all kinds of non-real money whose transaction details are managed through a block chain, such as electronic money and cryptocurrency.

The virtual currency according to the disclosed embodiment may be a coin-type virtual currency in which a separate mainnet is built and managed accordingly, or may be a token-type virtual currency utilizing the infrastructure of other coins such as the Ethereum network, not limited

In one embodiment, the virtual currency provided to each of the user terminals 30 is managed by the management server 20 as an already created or issued state, and may be provided according to the transaction details of each of the user terminals 30 . have.

For example, the management server 20 may perform an operation for generating a block for storing the transaction details generated between the user terminals 30 , and may generate the block through Proof Of Work. According to an embodiment, the management server 20 may receive a given virtual currency in return, and distribute it to the user terminals 30 according to the transaction details of the user terminals 30 .

In an embodiment, as transaction details are recorded by each of the user terminals 30 , virtual currency may be generated according to a preset rule and provided to the user terminals 30 , which may be used for mining (mining) virtual currency. ) is expressed as

In general, cryptocurrency mining is performed by one of Proof Of Work (POW), Proof Of Stake (POS), and Proof Of Importance (POI). The above methods are one of the distributed consensus algorithms used to guarantee the reliability of the distributed system.

In the disclosed embodiment, the transaction between the user terminals 30 and the method for providing virtual currency accordingly are performed by a smart contract.

2 is a system diagram illustrating the operation of a block chain system according to an embodiment of the present invention.

Referring to FIG. 2 , the operations of the block chain holding servers 10 , the management server 20 and the user terminal 31 shown in FIG. 1 are illustrated.

The management server 20 shown in FIG. 2 is a server of a communication company through which the user terminal 31 passes to communicate with the block chain holding servers 10 or a local server connected to the user terminal 31, or the user terminal 31 ) may mean a server that manages the blockchain-based service used by the You can also build a system.

What is shown in FIG. 2 is for an example of a configuration used in a general blockchain-based service, and the form of a system utilizing blockchain technology is not limited thereto.

In one embodiment, the user terminal 31 provides information to the management server 20, and the management server 20 sends the information to the block chain holding servers 10 when the information is to be stored in the block chain. You can provide that information. The block chain holding servers 10 may store the corresponding information in the block chain, and in this process, the verification of the block chain-based information may be performed. In this case, only information that has been successfully verified can be recorded in the blockchain.

In addition, when there is information requiring verification, the user terminal 31 may provide the corresponding information to the management server 20 . In this case, the management server 20 can verify it based on the information stored in the block chain. In this process, the management server 20 obtains information for verifying the information from the block chain holding servers 10 . and verification can be performed accordingly. The management server 20 may provide the verification result to the user terminal 31 or provide a service to the user terminal 31 based on the verification result.

Unlike the existing centralized server-based system, this blockchain system provides higher security by providing a decentralized distributed processing system, and has the advantage of providing reliability that cannot be manipulated by a specific subject.

In addition, as it functions as a platform that can provide various blockchain-based applications in recent years, its utilization is expected to increase further.

Each step described in this specification is described as being performed by the server, but the subject of each step is not limited thereto, and at least a portion of each step may be performed in different devices according to embodiments. For example, each step described in this specification may be performed by a computer, cloud, or the like, of course.

3 is a diagram illustrating a control system of an expert platform for expert career management according to an embodiment of the present invention.

Referring to FIG. 3 , the system may include a server 100 for performing an operation of an expert platform for expert career management, a plurality of expert groups 110 , and a block chain network 120 .

For convenience of description, referring to FIG. 3 , the plurality of expert groups 110 will be described as including user terminals of experts included in the plurality of expert groups 110 . In addition, the definition of the server 100 is as described above, but similarly, for convenience of explanation, the server 100 will be described as corresponding to a computer or a cloud.

In an embodiment, the server 100 may mean a computer used to perform a task according to one or more services provided by the offline expert platform, and when the server 100 is an online expert platform, manages the online expert platform It may mean a server that does, but is not limited thereto.

In the disclosed embodiment, the server 100 may register experts according to the registration requests of experts belonging to the plurality of expert groups 110 , and collect expert information on the registered experts. In addition, the server 100 acquires project information that can be performed by experts belonging to the plurality of expert groups 110 , and distributes it to experts belonging to the plurality of expert groups 110 , and various administrative and management for this purpose can do the job.

In an embodiment, the server 100 may calculate career information of the expert from the expert information, and provide a project suitable for the expert based on the calculated career information. The professional career information may include absolute career information and relative career information. In the present specification, absolute career information may mean career information independent of specific criteria. That is, the absolute career information may mean career information or professional evaluation results for all types of information performed by the expert from the past to the present. In addition, the relative career information may mean career information for a specific standard. That is, the relative career information may mean, for example, career information on a project category performed by the expert, information on whether the expert performs the project category, or career information on the position of the project performed by the expert. In this case, the relative career information may be obtained based on the absolute career information. On the other hand, the project position described in this specification may mean a position for dividing the positioning, role and work scope, responsibility scope and evaluation scope of the expert performing the project. That is, the project position described in this specification includes information on the positioning, role and task scope, responsibility scope and evaluation scope of the expert performing the project, or the positioning, role and task scope, and responsibility scope of the expert performing the project and the evaluation range itself.

Meanwhile, absolute career information and relative career information may be provided through various methods. For example, absolute career information and relative career information may be provided as information about an expert. Alternatively, absolute career information and relative career information may be provided in the form of scores calculated based on information on experts. In this case, the score for the absolute career information and the relative career information is obtained by obtaining a career score from each information about the expert, giving a weight or degree of relevance to the obtained career score, It can be obtained in the form of an aggregate.

In another embodiment, the server 100 may collect project data related to a result of a project performed by an expert, and manage the collected project data.

The server 100 may improve the safety and security of information transactions for experts based on the block chain in providing services for managing professional careers. Blockchain is a data distribution processing technology, and refers to a technology in which all users participating in the network distribute and store data such as all transaction details. A blockchain is a distributed P2P (Peer to Peer) of a ledger that utilizes software elements composed of an algorithm in which blocks connected in order in order to secure and maintain integrity negotiate service usage history information using encryption and security technology. ) can mean the system. Here, the distributed P2P system may be a special type of distributed system. In addition, the P2P system allows all nodes in the network to provide resources (processing power, storage space, data or network bandwidth, etc.) to each other without the coordination of a central node. In addition, blockchain can refer to a distributed ledger technology in which the ledger that records usage history information is distributed in a P2P network rather than a central server of a specific institution, and nodes in the network record and manage it jointly.

The blockchain network 120 may include nodes 121 , 122 , 123 , 124 , and 125 . A node can mean a component within the network of a blockchain. Each of the nodes 121 , 122 , 123 , 124 , and 125 may be a server device of individuals joining and participating in the system or server 100 . For example, each of the nodes 121 , 122 , 123 , 124 , and 125 may be a special-purpose computer, a general-purpose computer, a supercomputer, or a mainframe computer. , a personal computer, a smart phone, a tablet PC, etc., but is not limited thereto.

As a result, the server 100 may improve the safety and security of information transactions for experts based on the block chain in providing services for managing professional careers.

Hereinafter, according to the disclosed embodiment, the server 100 manages the plurality of expert groups 110 , receives expert information from the plurality of expert groups 110 , obtains absolute career information for each expert, and project information , and distribute the acquired project information to experts to manage the experts to carry out the project, manage the project data that is the result of the performed project, update absolute career information based on the project data, and update relative career information A method of obtaining , will be described in detail.

4 is a diagram for explaining a process of propagating valid information on a network of a block chain to nodes on a network of a block chain and recording it in a block chain according to an embodiment.

The server 100 may distribute and store expert information necessary for expert management in the block chain network 120 . In this specification, when a specific person produces a specific result in a certain field of work, the expert information may refer to the produced product and information related to the result. Therefore, expert information may include all kinds of information for evaluating each expert's professionalism or acquiring the expert's absolute and relative career information. It may mean information that has a correlation or more with the expertise of a specific professional field of it is not going to be

For example, expert information includes expert background information, expert status information, expert career and history information, expert qualification information, expert area information, expert award information, expert achievement information, expert performance information , expert's activity (advisory, screening, lecture, presentation, award, SNS activity, etc.) information, project information that experts can carry out, expert subscription information, expert contract information, expert's order, participation and execution result information, Project data information related to the results of the expert's project performance, creations, works and copyrights calculated from the expert's project data, the expert's revenue and payment information, the expert's fee information, the expert's evaluation and reputation information, the expert's information use information, etc. may include

According to an embodiment, the background information of the expert may include information necessary to determine the field of expertise and expertise of the expert.

According to an embodiment, the background information of the expert may be divided into structured information and unstructured information. The formal information may refer to information (or quantifiable information) that has already been quantitatively proven to be related to expertise in a specific field of expertise. For example, as described above, objective data that can prove an expert may correspond to structured information. For example, the structured information may include, but is not limited to, a history of working in a company or department in a specific field, a history of participating in a project or task in a specific specialized field, academic background in a specific field, or thesis presentation information.

Furthermore, the unstructured information does not belong to the structured information, but may refer to any kind of history information that is related to a specific specialized field. For example, as described above, history information according to individual efforts may belong to atypical information. For example, the unstructured information may include, but is not limited to, records of activities in online communities or clubs, materials written for personal projects or hobbies, information on taking online educational contents, and the like.

In an embodiment, background information of an expert on a new specialized field in which no formal information is previously stored may be acquired. In this case, since no formal information serving as a standard for evaluation in the relevant specialized field is stored, background information of all experts may be evaluated as unstructured information.

For example, if there is no pre-evaluated or stored information for the relevant specialization, even if there is no information that has been previously evaluated or stored, even if there is information about work or work in a job or department in a specific field of expertise, it will be evaluated like unstructured information to provide information on the relevant field of expertise. It can be used to evaluate the expertise of each expert.

In addition, advisory (committee) activities, review and evaluator activities, lectures and lectures, mentoring activity history, outside history, etc. may be included in the background information of experts, which may belong to structured information or unstructured information. For example, the classification criterion may be whether the correlation with the expertise of a specific specialized field has been previously quantitatively proven and databased, but is not limited thereto.

In addition, data that can verify the morality of the expert may also belong to the background information of the expert. For example, various information such as awareness and reputation of activities in the relevant industry, industry, SNS, rebate, criminal record, fraud record, etc. are utilized Even if all information is not available in reality, if it is information that can be collected and disclosed to the outside, it can be used as background information for experts who are classified as structured or unstructured information.

On the other hand, some of the above-described structured information and unstructured information may be difficult to quantify as data. The case in which it is difficult to quantify data may mean a case in which data quantification is impossible because the standard is not prepared. In this case, it goes without saying that the data, which is difficult to quantify, can be directly input based on the surrounding evaluation and can be quantified through various types of algorithms.

According to an embodiment, the status information of the experts may include the amount of projects that each expert can currently perform, or the number of projects that each expert can participate in, such as the affiliation, affiliation, current project, and other personal circumstances of each expert. It may include information necessary to evaluate, etc.

According to an embodiment, the project data related to the project execution result may mean all data acquired in the course of the project, and not only the meaningful results of the project. For example, a plurality of proposals calculated from a Request For Proposal (RFP) presented in a project bidding process may be project data according to the present invention. Accordingly, not only the adopted proposals but also the proposals not adopted may be project data according to the present invention.

According to an embodiment, the creative work refers to data about a work obtained from project data. In this case, the creative work may refer to data newly created by the project performing entity among project data. However, the present invention is not limited thereto, and it goes without saying that the creative work may refer to data having creativity among data newly created by the project performing subject. A creative work is a different concept from a work that has a copyright, and it goes without saying that a creative work can become a work with copyright only when it is determined that it does not infringe the copyrights of others.

However, the expert management information that can be stored on the block chain is not limited thereto, and may include the above-mentioned information and other types of information necessary for expert management.

According to an embodiment, the server 100 may transmit information to the node 121 of the block chain network 120 .

The server 100 may encrypt the information and transmit the encrypted information to the node 121 on the block chain network 120 . The node 121 may decrypt the encrypted information and verify whether the information is valid based on the decrypted result. As a result of verifying the validity of the information, if the information is not valid, the node 121 may discard the information. According to an embodiment, the validation of information includes a first hash value obtained by applying a hash function to the received information and a second obtained by decrypting the received ciphertext using the public key of the operator of the server 100 This may be performed by comparing hash values, but is not limited thereto.

As a result of verifying the validity of the information, if the information is valid, the node 121 may transmit the information to the node 122 on the blockchain network 120 . Also, the node 121 may write 1212 information to the candidate block. When predetermined transaction information is recorded in the candidate block, the node 121 may generate a valid block by performing proof of work on the candidate block. Also, when the validity of the information is verified in the node 122, the node 122 may generate a valid block by adding the information to the candidate block and performing proof-of-work on the candidate block.

The same operation as in the node 122 may be performed in the node 123 and the node 124 .

When the process of generating a valid block in the node 121 and adding it to the blockchain is described, the node 121 can calculate the root of the Merkle tree for predetermined information. Node 121 can create a hash reference pointing to the previous block header in terms of the block to be added to the blockchain. The node 121 can acquire the required difficulty in the proof of work or constraint conditions of the block to be added to the block chain. The node 121 may check whether the value of the block hash generated by applying the hash function to the root of the Merkle tree, the hash reference pointing to the previous block header, the difficulty, timestamp data and nonce satisfies the constraint condition. The node 121 may perform the proof-of-work on the candidate block by increasing the nonce from 0 to 1 and obtaining the value of the nonce that satisfies the constraint. Node 121 can add a candidate block as a valid block to the blockchain. Also, the node 121 may transmit a valid block to other nodes (122, 123, 124, etc.) on the network of the blockchain.

Each node (122, 123, 124, etc.) on the network of the block chain performs verification on the valid block received from the node 121, and is stored in the block chain held by each node (122, 123, 124, etc.). Valid blocks can be added.

Accordingly, the server 100 can secure the security and reliability of the expert platform by safely protecting information based on the block chain technology.

In addition, various embodiments may be provided based on the block chain.

In the disclosed embodiment, expert information, absolute career information, relative career information, and project information and project data performed by the expert may all be stored in the block chain.

For example, in the step of providing the above-described project information to the experts, the server 100 may perform the step of providing the first project information to the first experts.

In addition, the server 100 may perform a step of storing the first project information in the first block chain, matching and storing the information about the first expert.

In addition, the server 100 may perform a step of storing the information about the first expert in the second block chain, matching and storing the first project information.

In addition, in the step of storing the above-described first project information in the first block chain, the server 100 stores the information obtained by hashing the node on the second block chain in which the first project information is stored in the first block chain. You can perform the steps to save to .

In addition, in the step of storing the above-described information on the first expert in the second block chain, the server 100 stores the information obtained by hashing the node on the first block chain in which the information on the first expert is stored. The step of storing in the second blockchain can be performed.

Through this, the first block chain and the second block chain are linked to each other, and although they are different block chains, they operate like block chains connected to each other through one or more points of contact and can verify each other's information. This allows the two blockchains to verify each other, and if one blockchain fails, the other blockchain is not affected. can provide

In an embodiment, the server 100 may receive a verification request for the first project information.

In this case, the server 100 verifies the first project information based on the block chain, but can double verify the information by using two related block chains.

Also, the server 100 may verify the first project information based on the first project information stored in the second block chain.

Also, the server 100 may obtain a first hash value obtained by hashing the node in which the first project information is stored.

Also, the server 100 may acquire information about the first expert who performed the first project information.

Also, the server 100 may verify the first hash value based on a node on the first block chain in which information about the first expert is stored.

Also, the server 100 may receive a verification request for the first expert.

Also, the server 100 may verify the first expert based on the information about the first expert stored in the first block chain.

Also, the server 100 may obtain a second hash value obtained by hashing the node in which the information on the first expert is stored.

Also, the server 100 may acquire the first project information performed by the first expert.

Also, the server 100 may verify the second hash value based on a node on the second block chain in which the first project information is stored.

The server 100 may return the verification success or not, and may perform the process of evaluating the first project information and the professionalism of the first expert or acquiring absolute career information and relative career information according to the verification success or not, It can also be used for matching between experts and project information.

5 is a flowchart illustrating an expert career management method performed in an expert platform according to an embodiment of the present invention.

In step S110, the server 100 may register an expert.

In step S120, the server 100 may obtain expert information of the registered expert.

In an embodiment, the server 100 may obtain information input from the expert, and may also collect expert information by collecting crawled information about the expert.

For example, the server 100 may acquire an expert's resume or reference, or the expert's input based on a preset format, or freely written information. The information input by the expert may include information about the expert's past project performance and various information that the expert wants to present in the field of expertise.

In an embodiment, the server 100 may collect information related to a corresponding expert through web crawling. For example, the server 100 may collect information about the expert based on the personal information of the expert.

The server 100 may acquire information not input by the expert through crawling, but is not limited thereto. For example, the server 100 verifies the information input by the expert, or receives more information based on the information input by the expert. Crawling may be performed to collect information.

For example, when the corresponding expert inputs information about activities in a specific community site, the server 100 may crawl information about the corresponding expert from the corresponding community site, and in this case, according to an embodiment, Crawling can also be performed using basic information including IDs and nicknames. This can be used to supplement the parts that cannot be submitted by collecting all data directly by the expert, or can be used to verify the information entered by the expert.

In step S130, the server 100 may calculate absolute career information of the expert based on the acquired expert information.

In an embodiment, the server 100 may verify the acquired expert information, and calculate absolute career information of the expert based on the verified expert information. In this case, the verification of expert information may refer to an operation of confirming the authenticity of information directly input from an expert and information obtained through web crawling, etc.

In one embodiment, when the expert information to be verified is information on past project performance input by the expert, the server 100 obtains the source of the project, and requests expert information from the obtained project source. Expert information can be verified by determining whether the expert information input by the expert is the same as the expert information received from the project source.

As another embodiment, when the expert information to be verified is information obtained by crawling, the server 100 obtains category information from the information obtained by crawling, and adds to the category obtained from the verified expert information. Expert information can be verified by comparing corresponding expert information. For example, if the category information is academic background category information, the server 100 may include information on the academic background category included in the information obtained by crawling (for example, graduation from A university) and the educational background category among the verified expert information. Expert information can be verified by comparing corresponding information (eg, B university graduation). If University A and University B are different universities, information obtained by crawling can be excluded from expert information.

As another example, if the category information is performance project category information, the server 100 performs among the information on the performance project category included in the information obtained by crawling (for example, project A execution) and the verified expert information. The expert information can be verified by comparing the information corresponding to the project category (eg, project B). When project A and project B are the same project, the server 100 may obtain information obtained by crawling as verified expert information. Of course, the server 100 may further determine whether the details of the detailed project are the same. If the A project and the B project are different projects, and the two projects cannot be performed at the same time, the server 100 may exclude the information obtained by crawling from the expert information. When project A and project B are different projects, and the two projects can be performed simultaneously, the server 100 may verify expert information by requesting an expert for proof of the authenticity of the information obtained by crawling.

In addition to the above-described embodiment, the server 100 may extract various category information from expert information and verify expert information corresponding to the extracted category information.

* Hereinafter, various embodiments will be described as expert information used or described in the expert platform is verified expert information, unless otherwise specified.

In step S140, the server 100 may match the project corresponding to the expert based on the absolute career information of the expert.

In step S150 , the server 100 may acquire project data calculated according to the project execution result.

In step S160, the server 100 may update the absolute career information of the expert based on the project data.

In step S170, the server 100 may acquire relative career information based on the updated absolute career information and project data.

6 is a flowchart illustrating a method of calculating absolute career information of an expert according to an embodiment of the present invention.

In step S210, the server 100 may classify the expert information into structured information and unstructured information.

As described above, in this specification, expert information may be divided into structured information and unstructured information.

In an embodiment, the structured information may refer to information (or quantifiable information) that has already been quantitatively proven to be correlated with expertise in a specific specialized field. For example, as described above, objective data that can prove an expert may correspond to structured information.

For example, structured information includes history of working at a company or department in a specific field, history of participating in a project or task in a specific field of expertise, academic background or thesis presentation information in a specific field, information on participating projects, awards and qualifications, etc. can, but is not limited thereto.

In an embodiment, the unstructured information does not belong to the structured information, but may refer to any type of information that is related to a specific field of expertise. For example, as described above, information according to individual efforts may belong to unstructured information.

For example, unstructured information may include records of activities in online communities or clubs, personal projects or hobbies, information on online education content, SNS activity information and reputation information, and the like. it is not going to be

In an embodiment, expert information on a new specialized field in which no formal information is previously stored may be acquired. In this case, since no formal information, which is a standard for calculating absolute career information or evaluating professionalism, is stored for the relevant specialized field, all expert information can be evaluated as unstructured information.

For example, if there is no pre-evaluated or stored information for the relevant specialization, even if there is no information that has been previously evaluated or stored, even if there is information about work or work in a job or department in a specific field of expertise, it will be evaluated like unstructured information to provide information on the relevant field of expertise. It can be used to evaluate the expertise of each expert or to acquire the absolute career information of each expert in the relevant field of expertise.

In addition, expert information may include advisory (committee) activities, review and evaluator activities, lectures and lectures, mentoring activities, and outside experiences, which may belong to structured information or unstructured information. For example, the classification criterion may be whether the correlation with the expertise of a specific specialized field has been previously quantitatively proven and databased, but is not limited thereto.

In addition, data that can verify an expert's morality may also belong to expert information. For example, various information such as awareness and reputation of activities in the relevant industry, industry, SNS, etc., whether there is a rebate, criminal record, fraud record, etc. can be utilized. Even if all information is not available in reality, information that can be collected and disclosed to the outside can be used as expert information classified as structured or unstructured information.

On the other hand, some of the above-described structured information and unstructured information may be difficult to quantify as data. The case in which it is difficult to quantify data may mean a case in which data quantification is impossible because the standard is not prepared. In this case, it goes without saying that the data, which is difficult to quantify, can be directly input based on the surrounding evaluation and can be quantified through various types of algorithms.

For example, the expert and each expert information according to the disclosed embodiment may be set in various ways, for example, as experts known by anyone, experts certified by objective data, and non-experts who individually strive to become experts, experts There may be experts who have attained professionalism equivalent to or higher than that of experts, who have been proven by objective data to a certain level, or experts who have increased their expertise by adding individual efforts to it.

Therefore, in order to calculate the absolute career information of these various experts, it is necessary to classify the expert information according to its properties. Hereinafter, an embodiment of classifying this into structured information and unstructured information, and calculating the absolute career information of the expert accordingly will be described in detail.

According to an embodiment, the structured information may refer to information that has already been quantitatively proven to be related to the expertise of a specific field of expertise. For example, as described above, objective data that can prove the absolute career information of the expert may correspond to the formal information.

For example, the structured information may include, but is not limited to, a history of working at a company or department in a specific field, a history of participating in a project or task in a specific specialized field, academic background in a specific field or thesis presentation information, etc.

In addition, advisory (committee) activities, review and evaluator activities, lectures and lectures, mentoring activity history, outside history, etc. may be included in expert information, which may belong to structured information or unstructured information. For example, the classification criterion may be whether the correlation with the expertise of a specific specialized field has been previously quantitatively proven and databased, but is not limited thereto.

In addition, data that can verify an expert's morality may also belong to expert information. For example, various information such as awareness and reputation of activities in the relevant industry, industry, SNS, etc., whether there is a rebate, criminal record, fraud record, etc. can be utilized. In addition, even if all information is not available in reality, any information that can be collected and disclosed to the outside can be used in calculating an expert's career.

According to an embodiment, the unstructured information does not belong to the structured information, but may refer to any type of information that is related to a specific field of expertise. For example, as described above, information according to individual efforts may belong to unstructured information.

For example, the unstructured information may include, but is not limited to, records of activities in online communities or clubs, materials written for personal projects or hobbies, information on taking online educational contents, and the like.

In an embodiment, expert information on a new specialized field in which no formal information is previously stored may be acquired. In this case, since no formal information that is a standard for calculating absolute career information or evaluating professionalism is stored for the relevant specialized field, all expert information can be evaluated as unstructured information.

For example, if there is no pre-evaluated or stored information for the relevant specialization, even if there is no information that has been previously evaluated or stored, even if there is information on work or work in a specific field or department, or information on performing a project or task, it will be evaluated like unstructured information and It can be used to evaluate the expertise of each expert.

In step S220, the server 100 may evaluate the structured information and the unstructured information.

In an embodiment, the server 100 may evaluate each structured information individually, or may comprehensively evaluate a plurality of structured information, and the method is not limited.

In an embodiment, the server 100 may evaluate each unstructured information individually, or may comprehensively evaluate a plurality of unstructured information, and the method is not limited.

In step S230, the server 100 may calculate absolute career information of the expert based on the evaluation result.

In an embodiment, the server 100 may acquire the absolute career information of the expert based on the evaluation result for the structured information and the unstructured information. However, the present invention is not limited thereto, and the server 100 may acquire professionalism evaluation information based on expert information including formal information and unstructured information, and obtain absolute career information of an expert from the acquired professionalism evaluation information. Of course.

In one embodiment, the server 100 evaluates the expert information including each of the structured information and the unstructured information individually, and evaluates the absolute career information or expertise of the expert in a manner that sums the individually evaluated results, A plurality of expert information can be evaluated comprehensively, and the professionalism of each group can be evaluated by grouping some expert information, and absolute career information or expertise of experts can be evaluated by summing up the overall professionalism evaluation results. is not limited

In step S240 , the server 100 may classify expert information corresponding to the history information stored in the database as structured information.

In an embodiment, information on each specialized field and history information corresponding to each specialized field may be stored in advance in the database.

The server 100 may determine, using the database, information already stored in the database as the structured information. In an embodiment, the server 100 may perform a process of matching the information stored in the database with the expert information. For example, since expert information input by an expert or crawled expert information and information previously stored in a database may not exactly match, a process of determining whether the information is structured information may be performed by matching information similar to each other. For example, it may be determined that information stored in the database and information having a matching rate greater than or equal to a predetermined reference value are structured information.

In an embodiment, the server 100 may filter the structured information in the input step by displaying matched database information in the input step by the expert and allowing the expert to directly match the corresponding database information.

In step S250, the server 100 may classify expert information corresponding to the information on the specialized field not stored in the database and the history information not stored in the database as atypical information.

In an embodiment, the server 100 may classify expert information other than the structured information classified based on the database as unstructured information.

In an embodiment, a plurality of databases may be configured hierarchically. For example, information on each specialized field and history information corresponding to each specialized field may be stored in the first database, and expert information corresponding to the information stored in the first database may be classified as structured information.

In addition, information on each specialized field and history information corresponding to each specialized field may be stored in the second database, but expert information corresponding to the information stored in the database is classified as atypical information, and the first database and the first database 2 Information that is not all stored in the database can be classified as unstructured information as well.

In addition, according to an embodiment, expert information corresponding to the information stored in the second database is classified as unstructured information, but the information stored in the second database may be used to evaluate the unstructured information.

That is, the information stored in the second database may correspond to an intermediate stage between the unstructured information and the structured information, but the information stored in the second database may not be evaluated as the structured information. However, this corresponds only to an embodiment, and the configuration of the database and the method of using the database are not limited.

In step S260, the server 100 may evaluate the structured information based on the evaluation information stored in the database.

For example, evaluation information on expert information corresponding to each fixed form information may already be stored in the database, and the server 100 quantitatively calculates a score corresponding to each fixed form information based on the information stored in the database. can do.

For example, in the database, there is information about the degree of experience that can be recognized based on the relationship between specific history information for a specific field of expertise, the period of the history information and the role played by experts in the history information. It can be saved in advance.

The pre-stored information may be input by an expert in the relevant field, or may be determined based on information calculated based on previously collected big data. For example, if there is a lot of reference data for the relevant field, big data can be built using it, and the correlation between each field and history information can be determined by using learning methods such as machine learning, and furthermore, According to the detailed information, it is possible to obtain information that can quantitatively evaluate professionalism.

Such information may be stored in advance in a database and used to evaluate expert information classified as structured information.

In step S270 , the server 100 may estimate absolute career information of the expert in the specialized field from the atypical information by using the model learned to derive the correlation between the history information and the expertise of each specialized field.

The learned model may be a learned model to derive the correlation between specific history information and the expertise of each specialized field, and to estimate the expertise of the corresponding expert from the unstructured information.

In an embodiment, when new unstructured information is acquired with respect to a specific specialization pre-stored in the database, the learned model may estimate a correlation between the unstructured information and the specialization.

In addition, the learned model can estimate the correlation between a new specialized field that is not stored in the database and new unstructured information of the specialized field.

In an embodiment, the learned model may be learned based on information stored in a database. The server 100 may generate various learning data based on the information stored in the database, for example, in the specialized field previously stored in the database, so as to estimate the correlation between the specific field of expertise stored in the database and the new atypical information. It is possible to generate training data including history information previously labeled with respect to the correlation, and train a model based thereon.

As another example, correlation between feature information extracted for a specific field of expertise and feature information extracted with respect to specific history information and each characteristic information so as to estimate the correlation between a specific field of expertise and new atypical information not previously stored in the database You can generate training data with pre-labeled relationships, and train a model based on it.

That is, the server 100 uses a database and a model learned based on the database, classifies the expert's formal and unstructured information, and estimates the expert's absolute career information by evaluating the expert information for each classified information. can do.

7 is a flowchart illustrating another method of calculating absolute career information of an expert according to an embodiment of the present invention.

In step S310, the server 100 may calculate an evaluation result for each expert information.

In step S320, the server 100 may acquire a viewpoint corresponding to each expert information.

For example, the time period may include, but is not limited to, information on the working period, project participation period (including start and end time), online community activity period, thesis presentation time, certificate acquisition time, project execution time, etc. .

In step S330, the server 100 may assign a first weight to the evaluation result calculated based on the period from the time point to the present corresponding to each expert information.

For example, the server 100 may assign a first weight to decrease the evaluation result as the old expert information increases. That is, in the case of old expert information, it may be forgotten over time and the knowledge and sense of the expert may become dull, so a first weight that reduces the evaluation result of the expert information can be given over time. have.

Similarly, the server 100 may give a first weight that increases the evaluation result as the period of each absolute career information is longer, and may give a first weight that increases the evaluation result as the more recent expert information is.

In step S340, the server 100 may calculate the absolute career information of the expert based on the evaluation result to which the first weight is assigned.

In step S350, the server 100 may obtain information on the blank period included in the expert information.

That is, the expert information may include information about the blank period as well as the structured and unstructured information, and one or more of the structured information and the unstructured information may overlap each other.

The blank period may mean a period in which there is no structured information or a period in which both structured information and unstructured information are absent. In addition, the unit of the blank period may be divided into various units such as a minimum of several hours and a maximum of days, weeks, months, years, and the like.

In step S360, the server 100 may sort the structured information, the unstructured information, and the blank period included in the expert information in chronological order.

In step S370, the server 100 may assign a first weight to each of the sorted expert information.

For example, if there is blank information that follows specific expert information, the first weight will be adjusted so that the evaluation result of the expert information decreases during the blank period. On the other hand, even after a long period of time, if a career in the same specialized range is continuously registered after that, the first weight may be set so that the evaluation result does not decrease or increases according to embodiments.

In addition, unstructured information may be placed in the blank period of the structured information. In this case, the unstructured information corresponding to the expert information obtained during the blank period of the structured information is evaluated. It is not regarded as a domain, but can be evaluated as continuous absolute career information. In an embodiment, a blank area less than a preset period may be ignored.

On the other hand, as expert information that can prove expertise in a specific field lasts longer, a higher value may be recognized, and the first weight may also be adjusted accordingly. As the evaluation result of each expert information is higher, the first weight for the previous expert information may also be adjusted in a direction to recognize the high professionalism, but is not limited thereto.

8 is a flowchart illustrating a method of updating an expert's absolute career information according to an embodiment of the present invention.

In step S410, the server 100 may generate feedback on the absolute career information of the expert based on the project data.

The type of feedback is not limited, but information on the difference between the absolute career information estimated for the expert and the absolute career information obtained based on the work processing result may be included in the feedback.

In addition, the server 100 may perform the step of updating the expertise of the expert based on the feedback.

That is, the server 100 may maintain, increase, or decrease the absolute career information of the expert based on the feedback.

In addition, when a change occurs in the absolute career information of the corresponding expert, the server 100 may utilize the absolute career information of the corresponding expert or provide a means for enhancing the absolute career information of the corresponding expert.

For example, according to the absolute career information of the expert, the type of task and project assigned to the expert or the type of task in charge of the corresponding task and project may be changed, and also educational information to increase the expert's expertise may be provided.

In addition, when the professionalism estimation result based on the unstructured information and the actual estimated absolute career information are different, the model can be updated based on this.

In step S420, the server 100 may evaluate the estimation result of the learned model based on the feedback.

For example, the expert's expertise can be estimated from the unstructured information using the model learned as in the above-described method, and this can be evaluated based on the actual work performance result of the expert.

In step S430, the server 100 may update the learned model based on the evaluation information on the estimation result.

The server 100 may update the learned model by using the expert's atypical information and information including the actual work performance result as new learning data or by performing learning by adding it to the existing learning data.

Similarly, based on the estimation result and the feedback thereto, the server 100 may also update the model learned through reinforcement learning.

In operation S440 , when the correlation between the first unstructured information and the first specialization exceeds a preset reference value, the first unstructured information may be stored in the database as structured information on the first specialization.

In step S450 , if the information on the first specialization is not stored in the database, the information on the first specialization may be stored in the database.

That is, even for unstructured information, if references related to the unstructured information are sufficiently accumulated so that the association with a specific field of expertise can be confirmed by more than a preset reference value, by adding the information on the atypical information and the corresponding field of expertise to the database, The atypical information can be registered as structured information.

For example, a specific online community activity may be initially treated as unstructured information, but if the expertise of experts who have been actively active in the online community is proven, the activity information of the online community may be registered as structured information.

In addition, even in the case of a specialized field that is not pre-stored in the database, when one or more unstructured information and a predetermined reference value or more are secured, information on the specialized field and the corresponding unstructured information are registered in the database as structured information. it is possible

9 is a flowchart illustrating a method of calculating relative career information of an expert according to an embodiment of the present invention.

In step S510, the server 100 may acquire the project position of the expert based on the data on the job division of the matched project.

In this case, the data on the division of work is included in the project information, and may mean a table in which the subdivided work for each project is divided. In one embodiment, the server 100 may classify a project into work units, classify work units into work items, and classify work items into detailed items according to data on work division. For example, if the project is for a specific event, the work unit may include program, food and beverage, space creation, operation, invitation, registration, contract, etc., and the work item is program composition, cue sheet, scenario, moderator , performers, BGM, and other confirmation items, etc., and detailed items may be divided into securing contact points for performers, confirmation of costumes, props and number of people, confirmation of waiting space, preparation of other props, rehearsal plan, etc. it is not In this case, one detailed item may be divided into one category. That is, the data obtained by performing one detailed item is composed of one work, and the detailed item can be divided so as not to be composed of a joint work or a combined work. That is, a work obtained by performing one detailed item may be a single work. However, the present invention is not limited thereto, and a work obtained by performing detailed items according to various embodiments of the present invention may be a joint work or a combined work.

Furthermore, the data on the division of work may include a plurality of project positions, and the server 100 classifies the work unit, work item or detailed item performed by each of the plurality of project positions included in the data on the division of work. can For example, the first project position is a position for performing the first work unit, the first work item, or the first sub-item, and the second project position is the second work unit, the second work item, or the second sub-item. It may be a job to perform.

In step S520 , the server 100 may acquire a degree of association between each expert information and a project position based on the project data.

Specifically, the server 100 may determine the degree of association between the project position and the verified expert information obtained from the expert at the time of registration of the expert. Since the expert information obtained during expert registration does not include information on which project position the expert performed in, it is necessary to determine the relationship between each expert information and the project position.

For example, when the expert performs a project according to the first project position to obtain the first project data, the server 100 may determine that the first project data is the project data to be generated by the first project position. have. Accordingly, the server 100 compares the first project data with each of the expert information obtained during expert registration, and among the expert information, expert information similar to the first project data has a high degree of relevance, and information different from the first project data has a low degree of relevance. degree can be given.

In step S530, the server 100 may acquire the relative career information for the project position based on the degree of relevance to each of the expert information and the expert information.

10 is a flowchart illustrating a method of acquiring relative career information based on a first career score and a second career score according to an embodiment of the present invention.

In step S605 , the server 100 may acquire a plurality of project positions based on data on the division of duties of a plurality of projects performed by the server 100 .

In step S610, the server 100 may match the project data obtained by a plurality of experts with a plurality of project positions and a plurality of project positions.

That is, the server 100 may acquire a plurality of project positions for a plurality of projects based on projects performed by all experts registered in the expert platform, and match and store project data performed in each project position By doing so, it is possible to obtain a pair of project data performed by a specific project position.

In step S615 , the server 100 may obtain a plurality of job title clusters by clustering a plurality of matched project titles.

In an embodiment, the server 100 may obtain a plurality of job title clusters by clustering a plurality of project data matched to each of a plurality of project titles. Since a cluster generated by clustering project data is a group of similar projects, the server 100 may determine that a plurality of project positions corresponding to similar projects are similar project positions.

As another embodiment, of course, the server 100 may obtain a plurality of job title clusters by clustering a plurality of project titles themselves. Since project positions performing similar tasks are more likely to include similar words, the server 100 may cluster the project positions themselves to obtain a position cluster.

In another embodiment, the server 100 obtains a plurality of first clusters by clustering a plurality of project positions itself, and a plurality of second clusters by clustering a plurality of project data matched to each of a plurality of project positions Of course, it is also possible to obtain job title clusters based on the obtained plurality of first clusters and the plurality of second clusters. Specifically, the server 100 obtains a center point for each of a plurality of first clusters, obtains a center point for each of a plurality of second clusters, and matches each of a plurality of center points for a plurality of first clusters Determining a center point for a plurality of second clusters, determining a plurality of center points for a plurality of title clusters based on the two matched center points, and performing clustering based on a plurality of center points for a plurality of title clusters Thus, a plurality of title clusters may be obtained through the step of acquiring a plurality of title clusters.

In step S620 , the server 100 may obtain a first central point that is a center point of the first title cluster and a second central point that is a center point of the second title cluster from among the plurality of title clusters.

In step S625 , the server 100 may obtain a first degree of association of the first job cluster with respect to the second job cluster based on the distance between the first central point and the second central point.

In step S630 , the server 100 may acquire a title cluster corresponding to the project position of the expert among the plurality of title clusters.

That is, when the distance between the job clusters is long, the server 100 determines that the relevance of the two job clusters is low, and when the distance between the job clusters is close, the server 100 can determine that the relevance of the two job clusters is high. . The server 100 may determine the value of the first relevance in proportion to the distance between the first central point and the second central point. In this case, the first degree of relevance may be 0 or more and 1 or less.

In one embodiment, the server 100 may obtain two job title clusters with the longest distance between the center points among a plurality of job title clusters, and change the obtained distance between the two clusters to a unit distance (eg, 1). . The server 100 may acquire the distance between any two title clusters among a plurality of title clusters based on the unit distance. The server 100 may obtain a relevance value based on the distance between any two title clusters among a plurality of title clusters obtained based on the unit distance.

For example, when the distance between the first central point and the second central point is obtained as 0.3 based on the unit distance, the server 100 may determine the first relevance to be 0.7 (=1-0.3). That is, since the degree of association between the two title clusters having the longest distance between the center points among the plurality of title clusters should be lower than the degree of association between the other two title clusters, the server 100 has a unit distance of 1, the first central point, and the second The difference value of the distance between the center points may be determined as the first degree of association.

In step S635 , the server 100 may acquire at least one job title cluster corresponding to expert information among a plurality of job title clusters. Specifically, the server 100 may determine whether each of a plurality of pieces of expert information registered by an expert performing a project corresponds to at least one job cluster among a plurality of job title clusters. For example, the first expert information of the expert information may correspond to the first job cluster, and the second expert information of the expert information may correspond to the second job cluster.

In step S640, in the server 100, when the position cluster corresponding to the project position of the expert is the first position cluster, and at least one position cluster corresponding to the expert information is the first position cluster, included in the first position cluster The first career score can be obtained based on expert information.

In step S645, when the position cluster corresponding to the project position of the expert is the first position cluster and the at least one position cluster corresponding to the expert information is the second position cluster, the server 100 includes the second position cluster. A second career score may be obtained based on the expert information and the first degree of relevance.

Specifically, when the project position of the expert performing the project is the project position included in the first position cluster, the server 100 scores a first career score based on the first expert information included in the first position cluster among the expert information. can be obtained. In addition, the server 100 calculates the second career score based on the second expert information included in the second position cluster among the expert information and the first degree of association (the degree of association between the first project position and the second project position) obtained earlier. can be obtained

In this case, the career score may be obtained through various methods. In an embodiment, the career score may be obtained by acquiring each score corresponding to each expert information, and summing the acquired scores. In this case, the first career score is determined as the sum of the respective scores corresponding to each expert information included in the first job cluster, and the second career score is each score corresponding to each expert information included in the second job cluster. It may be determined as a value obtained by multiplying the sum of the scores by the first degree of relevance.

In step S650, the server 100 may obtain relative career information based on at least one of the first career score and the second career score. For example, the relative career information may be a total score obtained by adding the first career score and the second career score.

11 is a flowchart for explaining a method of acquiring career points based on weights according to an embodiment of the present invention.

In step S710 , the server 100 may determine whether a creation corresponding to the project data corresponding to the first job cluster can be registered as a work.

In step S720, when the creation corresponding to the project data can be registered as a work, the server 100 may acquire a second weight for the project data.

In step S730, the server 100 may obtain a first career score based on the expert information and the second weight included in the first job cluster.

In step S740, the server 100 may determine whether the creation corresponding to the project data corresponding to the second position cluster can be registered as a work.

In step S750 , when the creation corresponding to the project data can be registered as a work, the server 100 may acquire a third weight for the project data.

In step S760, the server 100 may obtain a second career score based on the expert information and the third weight included in the second position cluster. In this case, the second weight and the third weight may be greater than one.

Specifically, the server 100 may determine whether the work obtained from the project data is a work that can be registered as a copyright in order to calculate the career score. When the copyright is recognized in the creation corresponding to the project data, the server 100 determines that more effort has been put in than the copyrighted creation, and acquires a second weight and a third weight to increase the career score, It can be reflected in earning experience points.

12 is a flowchart illustrating a method of calculating a career score according to whether project data is a joint work or a combined work according to an embodiment of the present invention.

Specifically, in the case of a work, it can be divided into an individual work created by an individual alone, a joint work jointly created by a plurality of people that cannot be separated, and a combined work jointly created by a plurality of people but can be separated. Accordingly, the server 100 may determine whether the work obtained from the project data is a work that can be registered as a copyright, and further may determine whether the work that can be registered as a copyright is a joint work or a combined work. Furthermore, the server 100 may give different weights to the combined work and the joint work in consideration of the fact that in the case of a combined work, it is a work calculated independently, and in the case of a joint work, it is a work calculated jointly.

Specifically, in step S810, if the project data is data generated by a plurality of experts, the creation corresponding to the project data may determine whether the joint work or the combined work.

In step S820, the server 100 may obtain a 2-1 weight for the project data when the creative work is a joint work, and obtain a 2-2 weight for the project data when the creative work is a combined work. .

In step S830, when the project data is data generated by a plurality of experts, the server 100 may determine whether the creation corresponding to the project data is a joint work or a combined work.

In step S840, the server 100 may obtain a 3-1 weight for the project data when the creative work is a joint work, and obtain a 3-2 weight for the project data when the creative work is a combined work. . In this case, the 2-1 weight may be greater than the 2-2 weight, and the 3-1 weight may be greater than the 3-2 weight.

That is, the server 100 reflects the fact that, in the case of a joint work, the efforts of a plurality of creators are inseparably combined to obtain a new one, and the need for mutual cooperation is inevitably greater than in the case of a combined work. , it is possible to obtain career points by assigning a weight higher in the case of a joint work than in the case of a combined work.

However, the present invention is not limited thereto, and in some cases, the server 100 may obtain a career score by giving a weight in the case of a combined work higher than that in the case of a joint work.

On the other hand, in order to give different weights to a combined work and a joint work, the process of determining whether a creative work is a combined work or a joint work must be preceded. Hereinafter, a method of determining whether a creative work has a copyright and, if it has a copyright, a method of determining whether a work is a joint work or a joint work will be described.

First, the server 100 may acquire at least one creation to be registered as a work among the acquired project data.

In an embodiment, the server 100 may determine data that satisfies the requirements of a work among project data to obtain data that satisfies the requirements as a creation. Specifically, the server 100 may acquire data that includes human thoughts or emotions and whose creativity is recognized as a creation.

In an embodiment of the method of determining a creation, the server 100 may acquire data generated by an expert among project data. For example, the server 100 is the data provided from the registration subject of the project among the project data (for example, documents, images, videos, drawings, drawings, graphics, etc., project-related materials, including project-related forms, projects and Data can be obtained excluding related background data, etc.).

In another embodiment, the server 100 may analyze the data generated by the expert to determine the degree of creativity. For example, when the data generated by the expert is text data, the server 100 may determine the degree of creativity based on the weight of emotion-related words in the text data and the connection relationship between emotion-related words. For example, the server 100 forms and stores emotion-related words in a database, and may determine a ratio of text data generated by experts including emotion-related words stored in the database. When the text data generated by the expert contains more than a preset ratio of words related to emotion, the server 100 may determine that the data is a creation.

In another embodiment, the server 100 may obtain all sentences included in the text data, and determine emotion information for each of the plurality of acquired sentences. For example, the server 100 may quantify the emotion information of the corresponding sentence based on the connection relationship between the word for emotion and the word for emotion included in the sentence. The server 100 may determine the text data as a creation when the sentence in which the emotion information is digitized is equal to or greater than a preset value.

In another embodiment, when the data generated by the expert is image data or image data, the server 100 may determine the data as a creation. In general, images or videos will often express human thoughts or emotions, which are the requirements of a work.

When the creation is obtained, the server 100 may determine the creator of each of the at least one creation, and determine whether the at least one creation is the same as the previously registered work.

That is, not all of the acquired creations can be registered as copyrights due to their relationship with other works, so the server 100 may determine whether the acquired creations are the same as the previously registered works.

When the at least one creative work is not the same as the previously registered work, the server 100 may register the copyright for at least one work.

When the creator is a single creator, the server 100 judges a creation created by a single creator as the creation of a single creator, and when the creator is a plurality of creators, whether the creation created by a plurality of creators is a joint creation or a combined creation It can be judged whether

Hereinafter, a method for judging a joint creation and a combined creation will be described in detail.

First, the server 100 may acquire the work content of the project corresponding to the creation. The server 100 may acquire a plurality of category information for the work performed by each of the plurality of creators.

In this case, since the detailed item may be composed of one category, the server 100 may obtain a plurality of category information for the work performed by each of the plurality of creators who performed the work unit or the work item.

The server 100 may acquire a degree of association between a plurality of acquired categories. The server 100 may determine the creative work as a joint work when the obtained relevance is equal to or greater than a preset value. The server 100 may determine the creative work as a combined work when the obtained relevance is less than a preset value.

That is, the more closely the plurality of categories are related to each other, the higher the probability that the creative work is a joint work.

Therefore, when the degree of relevance is greater than or equal to a preset value, the server 100 may determine that the creation is inseparable, and may determine the creation as a joint work. It can be judged as separable, and the creation can be judged as a combined work.

Meanwhile, the degree of association between a plurality of categories may be obtained through various methods.

In one embodiment, the server 100 may obtain a plurality of result data for the work performed by each of the plurality of creators. In this case, the plurality of result data may refer to data performed by a plurality of creators (or a person in charge, an expert) according to assigned tasks. That is, the result data generated by one creator may constitute one work, a plurality of works, or a part of one work.

The server 100 may obtain a plurality of clusters by clustering a plurality of creations. That is, the server 100 may group a plurality of creations to group creations of a similar category. In this case, of course, the server 100 may cluster not only the creative work, but also the work created from the creative work, and the sub-work for the work.

The server 100 may label the plurality of clusters with a plurality of category information for each of the plurality of clusters. That is, the server 100 may label a category on the cluster by determining the characteristics of each of the plurality of clusters. In this case, the category may be based on the expression method of the creation, such as image, audio, and text categories, and may include language, music, play, art, architecture, photography, image, figure, computer program categories and the above-mentioned language, music, play, It may be about the form of a work, such as art, architecture, photography, video, graphics, derivative works and compilation works produced from computer programs.

The server 100 may determine which cluster each of the plurality of result data is included in among a plurality of clusters corresponding to the plurality of category information. That is, the server 100 may determine whether the result data belongs to which category by determining whether the result data is included in which cluster.

The server 100 may obtain a degree of association based on distances between a plurality of clusters corresponding to each of a plurality of result data. For example, when the first result data is included in the first cluster and the second result data is included in the second cluster, the server 100 obtains a distance between the first cluster and the second cluster, and the obtained distance According to this, the degree of correlation can be judged. If the distance is far, the relevance will be low, and if the distance is close, the relevance will be high. Meanwhile, according to an embodiment, the server 100 may determine the degree of relevance of a plurality of result data using not only the distance between clusters but also the distance between the result data. As another embodiment, when the first result data and the second result data exist in the same cluster, the server 100 may determine the degree of relevance between the first result data and the second result data as the maximum value that can be determined. In this case, the work for the first result data and the second result data may be determined as a joint work.

13 is a block diagram of an apparatus according to an embodiment.

The processor 102 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus, etc.) for transmitting and receiving signals to and from other components. .

The processor 102 according to an embodiment performs the method described with reference to FIGS. 1 to 12 by executing one or more instructions stored in the memory 104 .

For example, the processor 102 acquires new training data by executing one or more instructions stored in the memory, and performs a test on the acquired new training data using the learned model, and the test result, labeling Extracting the first learning data in which the obtained information is obtained with an accuracy greater than or equal to a predetermined first reference value, deleting the extracted first learning data from the new learning data, and removing the new learning data from which the extracted learning data is deleted It is possible to re-train the learned model using

On the other hand, the processor 102 is a RAM (Random Access Memory, not shown) and ROM (Read-Only Memory: ROM) for temporarily and/or permanently storing signals (or data) processed inside the processor 102 . , not shown) may be further included. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, a RAM, and a ROM.

The memory 104 may store programs (one or more instructions) for processing and controlling the processor 102 . Programs stored in the memory 104 may be divided into a plurality of modules according to functions.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software components, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , may be implemented in a programming or scripting language such as Java, assembler, or the like. Functional aspects may be implemented in an algorithm running on one or more processors.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100 : server
110: a plurality of expert groups

Claims (1)

In the professional career management method performed by the server,
Registering an expert (S110);
obtaining expert information of the registered expert (S120);
calculating absolute career information of the expert based on the obtained expert information (S130);
matching the project corresponding to the expert based on the absolute career information of the expert (S140);
When the matched project is performed by the expert, obtaining project data calculated according to the execution result of the project (S150);
updating the absolute career information of the expert based on the project data (S160); and
obtaining relative career information based on the updated absolute career information and the project data (S170); including,
The step of obtaining the relative career information (S170),
Acquiring the project position of the expert based on the data on the division of work of the project matched in the S160 (S510);
based on the project data, obtaining a degree of association between each of the expert information and the project position (S520); and
Acquiring relative career information for the project position based on the degree of relevance to each of the expert information and the expert information (S530);
The step of obtaining the degree of association (S520) is,
obtaining a plurality of project positions based on data on the division of duties of a plurality of projects performed by the server (S605);
Matching the project data obtained by a plurality of experts having the plurality of project positions and the plurality of project positions (S610);
obtaining a plurality of job title clusters by clustering the matched plurality of project titles (S615);
obtaining a first central point that is a center point of a first title cluster and a second central point that is a center point of a second title cluster among the plurality of title clusters (S620); and
obtaining a first degree of association of the first job cluster with respect to the second job cluster based on the distance between the first central point and the second central point (S625); including,
The step of obtaining the relative career information (S530),
obtaining a position cluster corresponding to the project position of the expert among the plurality of position clusters (S630);
obtaining at least one job title cluster corresponding to the expert information among the plurality of job title clusters (S635);
When the position cluster corresponding to the project position of the expert is the first position cluster, and at least one position cluster corresponding to the expert information is the first position cluster, based on the expert information included in the first position cluster obtaining a first career score as (S640);
When the position cluster corresponding to the project position of the expert is the first position cluster, and at least one position cluster corresponding to the expert information is the second position cluster, the expert information included in the second position cluster and the second position cluster 1 step of obtaining a second career score based on the degree of relevance (S645); and
obtaining the relative career information based on at least one of the first career score and the second career score (S650); including,
The first degree of relevance is characterized in that 0 or more and 1 or less,
The step of obtaining the first career score (S640) is,
determining whether the creation corresponding to the project data can be registered as a work (S710);
If the creation corresponding to the project data can be registered as a work, obtaining a second weight for the project data (S720); and
obtaining the first career score based on the expert information and the second weight included in the first job cluster (S730); including,
The step of obtaining the second career score (S645) is,
determining whether the creation corresponding to the project data can be registered as a work (S740);
If the creation corresponding to the project data can be registered as a work, obtaining a third weight for the project data (S750); and
obtaining the second career score based on the expert information and the third weight included in the second job cluster (S760); including,
The second weight and the third weight are characterized in that the value is greater than 1,
The step of determining whether the creation corresponding to the project data can be registered as a work (S710),
obtaining the business contents of the project;
obtaining a plurality of category information for the work performed by each of a plurality of creators;
obtaining a degree of association between the obtained plurality of categories;
determining the creative work as a joint work when the degree of association is greater than or equal to a preset value; and
When the degree of relevance is less than a preset value, determining the creative work as a combined work; including,
The absolute career information means career information unrelated to a specific standard, the relative career information means career information for the specific standard, and the specific standard is a standard related to a project category performed by the expert, the project It is characterized in that the category is at least one of a criterion for whether the expert has performed it, a criterion for a position of the project performed by the expert,
Calculating the absolute career information of the expert (S130),
classifying the expert information into structured information and unstructured information (S210);
evaluating the structured information and the unstructured information (S220); and
calculating absolute career information of the expert based on the evaluation result (S230); including,
The step of classifying the expert information into structured information and unstructured information (S210) is,
Classifying expert information corresponding to the history information stored in the database into structured information based on a pre-stored database (S240); and
classifying the expert information corresponding to the information on the specialized field not stored in the database and the history information not stored in the database into the atypical information (S250); including,
The step of evaluating the structured information and the unstructured information (S220),
evaluating the structured information based on the evaluation information stored in the database (S260); and
estimating absolute career information from the atypical information using a model learned to derive a correlation between history information and expertise in each specialized field (S270); characterized in that it comprises;
Calculating the absolute career information of the expert (S130),
calculating an evaluation result for each of the expert information (S310);
obtaining a viewpoint corresponding to each of the expert information (S320);
assigning a first weight to the calculated evaluation result based on a period from a time point corresponding to each of the expert information to the present (S330); and
calculating absolute career information of the expert based on the evaluation result to which the first weight is assigned (S340); including,
The step of giving the first weight (S330) is,
obtaining information on a blank period included in the expert information (S350);
arranging the structured information, the unstructured information, and the blank period included in the expert information in chronological order (S360); and
assigning a first weight to each of the sorted expert information, wherein the first weight is adjusted according to an evaluation result of one or more pieces of expert information located temporally behind each of the expert information (S370); characterized in that it comprises,
The step of updating the absolute career information of the expert based on the project data (S160),
generating feedback on the absolute career information of the expert based on the project data (S410);
evaluating an estimation result of the learned model based on the feedback (S420); and
updating the learned model based on the evaluation information on the estimation result (S430); further comprising,
Updating the learned model (S430) is,
When the association between the first unstructured information and the first specialization exceeds a preset reference value according to a result of updating the learned model, the first unstructured information is stored in the database as structured information about the first specialization step (S440); and
If the information on the first specialization is not stored in the database, storing the information on the first specialization in the database (S450); further comprising,
The learned model is learned based on learning data generated by the server, including history information that is pre-stored in the database with pre-labeled relevance to the specialized field, or generated by the server. It is learned based on the learning data that has been previously labeled with the correlation between the feature information extracted for the specialized field, the feature information extracted with respect to the specific history information, and each feature information,
The absolute career information is estimated by evaluating, by the server, expert information for each information classified by classifying formal and unstructured information of experts using the database and the learned model. How to manage your professional career.

Images