KR101972554B1 - Agency matching method, apparatus and program - Google Patents

Abstract

Disclosed is an agency matching method performed by a computer comprising the steps of: obtaining task information from a task registration subject; obtaining local information and task content included in the task information; obtaining information on one or more agencies corresponding to the local information; determining an agency of the one or more agencies that matches the task content; and transmitting information on the determined agency to the task registration subject.

Description

[0001] AGENCY MATCHING METHOD, APPARATUS AND PROGRAM [0002]

The present invention relates to an agency matching method, apparatus and program.

Block Chain is a data distribution processing technology that distributes and stores all data to be managed by all users participating in the network. Distributed Ledger Technology (DLT) 'or' Public Transaction Book 'in that it is a technology that all participants of a network share, not a transaction entity or a specific institution that holds transaction information. . A block chain is a chain of blocks that contain transactional content.

The block chain is the core concept of de-centralization, which is aimed at P2P (peer-to-peer) transactions, away from the existing financial system that guarantees and manages all transactions in financial institutions. P2P refers to a communication network that connects personal computers without a server or client, and each connected computer acts as a server and a client and shares information.

In the existing financial system, financial companies have stored transaction records in a central server. In the block chain based on P2P method, transaction information is linked in blocks and then all the participants share it.

Virtual currency is also called electronic currency or cryptography, and refers to money that is not traded in bank notes or coins and is traded online. Virtual currencies are valued according to rules set by the original inventor, unlike the general currency issued by governments or central banks. In addition, due to the decentralization feature, government and central banks do not manage transaction details and are distributed based on block chain technology.

MICE is a term preceded by English words such as meetings, incentive trips, conventions, exhibitions and events. In the narrow sense, MICE is a promising industry with international conferences and exhibitions as its main axis. , And the broader concept is the mixed-use industry including participant-oriented reward tourism and mega events.

Registered Patent Publication No. 10-0339055, Registered May 21, 2002

An object of the present invention is to provide an agency matching method, an apparatus, and a program.

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

According to an aspect of the present invention, there is provided an agency matching method comprising: obtaining task information from a task registration subject (S101); acquiring local information and task content included in the task information (S102 (S103) of acquiring one or more agency information corresponding to the local information, determining an agency matching one of the one or more agencies among the agencies (S104), and transmitting the determined agency information to the subject registering entity (S105).

The step S104 may include obtaining information about the one or more agencies from the block chain (S106), and determining an agency matching the contents of the task based on the information obtained in the step S106 (S107).

In addition, the step (S105) includes the steps of acquiring the contract information of the task registration subject and the determined agency (S108), acquiring performance information of the task according to the contract (S109) And recording the performance information in the block chain (S110).

The step (S109) includes the steps of acquiring (S111) at least one performing entity that has performed the task, acquiring information about the at least one performing entity from the block chain (S112) And acquiring task performance information of the performing entity (S113).

The step (S113) may further include a step (S114) of obtaining the execution result of the task from the task registration subject, a step (S115) of obtaining the execution result of the task from the determined agency, (Step S116) of obtaining the execution result of the task, a step S117 of cross-validating the execution result of the task obtained in the steps S114, S115, and S116, , Virtual money is paid as the compensation for information to the task registering entity, the determined agency and the at least one performing entity, and a credit score of the task registering entity, the determined agency, and the one or more performing subjects is awarded If the cross validation fails, judges an object to which the erroneous information is uploaded based on the information recorded in the block chain, (S119), wherein the step (S107) includes the step of: (a) obtaining a score of a reliability point of an object to which the information has been uploaded, (S121) selecting one or more first agencies having reliability scores of the one or more agencies equal to or greater than a predetermined reference value, calculating a score of fitness for the task of the one or more agencies (S122) of acquiring information about a task performing entity, calculating an average of the reliability scores of the connected subject performing tasks for each of the selected one or more first agencies (S123) Selecting one or more second agencies having a set reference value or more (S124), selecting one or more second agencies (S125) calculating a final reliability score based on an average of the reliability scores of the connected subject-performing subjects and a reliability score of the one or more second agencies, and calculating (S125), for each of the one or more second agencies, Determining a priority based on the final reliability score (S126), and determining an agency (S127) matching the task content based on the priority.

The step (S107) may include extracting one or more parameters from the content of the task (S128), extracting one or more parameters from the information obtained in the step (S106) (S129) And inputting the parameter extracted in step S129 into the artificial intelligence model to evaluate the fitness between the task and the at least one agency (S130) and determining an agency matching the task content based on the fitness S131).

In addition, the step (S106) includes the step (S132) of obtaining information on a result of the task mediated by the one or more agencies from the block chain, wherein the step (S132) (S134) of acquiring agency evaluation information of a subject performing the task, and evaluating the content of the task of each task and the subject performing the task (S135). In the step S107 ) May include evaluating the one or more agencies based on the information obtained in the step S132 (S136).

In addition, the step S136 may include a step S137 of obtaining information on a first language used by the subject registering entity, a step S138 of obtaining information on a second language corresponding to the local information, (S140) of obtaining a test document prepared in the first language and a predetermined second language translation of the test document by quantitatively evaluating the first language utilization capability of the at least one agency (S139) (S141) of obtaining a translation obtained by mechanically translating the document into the second language (S141), comparing the predetermined translated translation with the translated machine translation (S142), and comparing the first language and the second language Calculating a translation rate of a second language (S143), weighting the first language utilization ability based on the translation rate (S144), and calculating the weighted first language utilization ability (S145) of reflecting on one or more agency evaluations.

An apparatus according to one aspect of the present invention for solving the above-mentioned problems includes a memory for storing one or more instructions and a processor for executing the one or more instructions stored in the memory, the processor executing the one or more instructions Acquiring task information from a task registration subject, acquiring local information and task content included in the task information, acquiring one or more agency information corresponding to the local information, A step of determining an agency matching the task content, and a step of transmitting the determined agency information to the task registration subject.

According to an aspect of the present invention, there is provided a computer program stored in a computer-readable recording medium for performing an agency matching method according to the disclosed embodiments in combination with a computer.

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

According to the disclosed embodiment, it is possible to evaluate an agency that links a company registering an assignment with a subject performing a task, and provide a service that can recommend an agency suitable for the enterprise.

Particularly, in the global MICE industry, there is an advantage that an overseas company can automatically receive an agency recommendation through a system according to the disclosed embodiment without directly searching and evaluating an agency of the target country.

In addition, the information on the agency and the information on the subject of the task can be managed by a block chain to guarantee its safety. Since agency recommendation is performed by examining various parameters using an artificial intelligence model, There is an advantage.

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

1 is a diagram illustrating an agency matching system in accordance with one embodiment.
2 is a block chain system according to one embodiment.
FIG. 3 is a diagram illustrating an agency matching method according to an embodiment.
4 is a flow diagram illustrating a method for determining an agency in accordance with one embodiment.
5 is a flowchart illustrating a method for managing contract and task performance information according to one embodiment.
FIG. 6 is a flowchart illustrating a method for acquiring task performing entity information according to an embodiment.
7 is a flow diagram illustrating a method for verifying information and providing a confidence score in accordance with one embodiment.
FIG. 8 is a flowchart illustrating a method of matching an agency using an artificial intelligence model according to an embodiment.
9 is a flow diagram illustrating a method for evaluating an agency in accordance with one embodiment.
10 is a flow diagram illustrating a method for utilizing an agency based on language capabilities in accordance with one embodiment.
11 is a configuration diagram of an apparatus according to an embodiment.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. It should be understood, however, that the invention is not limited to the disclosed embodiments, but may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, Is provided to fully convey the scope of the present invention to a technician, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms " comprises " and / or " comprising " used in the specification do not exclude the presence or addition of one or more other elements in addition to the stated element. Like reference numerals refer to like elements throughout the specification and " and / or " include each and every combination of one or more of the elements mentioned. Although " first ", " second " and the like are used to describe various components, it is needless to say that these components are not limited by these terms. These terms are used only to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical scope of the present invention.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense that is commonly understood by one of ordinary skill in the art to which this invention belongs. In addition, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

As used herein, the term "part" or "module" refers to a hardware component, such as a software, FPGA, or ASIC, and a "component" or "module" performs certain roles. However, " part " or " module " is not meant to be limited to software or hardware. A " module " or " module " may be configured to reside on an addressable storage medium and configured to play back one or more processors. Thus, by way of example, " a " or " module " is intended to encompass all types of elements, such as software components, object oriented software components, class components and task components, Microcode, circuitry, data, databases, data structures, tables, arrays, and variables, as used herein. Or " modules " may be combined with a smaller number of components and " parts " or " modules " Can be further separated.

In this specification, a computer means all kinds of hardware devices including at least one processor, and may be understood as meaning a software configuration that operates in the corresponding hardware device according to the embodiment. For example, a computing device may be understood to include, but is not limited to, a smart phone, a tablet PC, a desktop, a notebook, and a user client and application running on each device.

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

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least some of the steps may be performed in different apparatuses according to the embodiment.

1 is a diagram illustrating an agency matching system in accordance with one embodiment.

Referring to FIG. 1, the system includes a registration subject 10, one or more agencies 20, and one or more task performing subjects 30.

In the present specification, the task is understood to include, but is not limited to, the tasks necessary for carrying out the MICE event. For example, the type of the task may include various kinds such as in-kind, service, and the like, and is not limited to a specific kind. For example, the assignment may be for the delivery of a specific product, or for research services or professional services.

The subject of registration of the assignment may include, but is not limited to, a public enterprise, a private enterprise, an individual, etc., other than the government.

In this specification, the task performing entity may mean a company (applicant) performing the task bidding, but is not limited thereto. In this specification, the term " business entity " is understood to mean not only a business entity such as an individual business entity or a corporation but also a general person, and does not limit the specific object.

In the present specification, the agency recommends an execution subject 30 suitable for the task requested by the registration subject 10 between the subject of registration 10 and the subject 30 of the assignment, and performs contract and post- And the like, but is not limited thereto.

In one embodiment, the subject of registration 10 of the assignment may refer to a company that wishes to host a global MICE event in a particular country. In this case, the subject 30 of the task may be a performing entity of a specific country to which the MICE event is to be hosted, and the agency 20 should be able to link the performing subjects 30 of the corresponding country with the registration subject 10 do. The agency (20) may be a corporation of a country, but may be a global corporation including a branch in the country.

Since the subject registration entity 10 lacks information on the country concerned and there may be a problem in communication of the language in some cases, it is possible to obtain reliable information through the agency 20 and to perform the contract according to local laws and market conditions You may request a proxy.

However, there are many cases in which there is insufficient information for carrying out the evaluation of the agency 20 that provides the information on the task execution subject 30, and the agency 20 is evaluated, and the task registration subject 10 and the registration It is required to develop a technique which can recommend an agency 20 suitable for the task of making a request.

In the present specification, it is possible to recommend and mediate the subject 30 that is suitable for the subject registration subject 10, and to provide information on the agency 20 that is highly evaluated in contract and post-processing .

2 is a block chain system according to one embodiment.

Referring to FIG. 2, a management server 100, block-chain holding servers 200, and user terminals 300 are shown.

In the disclosed embodiment, each of the user terminals 300 transmits information to at least one of the management server 100 or the block chain holding servers 200, and the transmitted information is propagated to the block chain holding servers 200 And stored and managed on each server.

In the disclosed embodiment, the block-chain holding servers 200 are provided with information on task registration subjects and agencies, information on task execution subjects, task information, task performance information, bidding information, selection information, matching information, And a block chain for authenticating and recording information about the server.

Each of the user terminals 300 transmits / receives information necessary for using the agency matching service according to the disclosed embodiment to / from the management server 100. In one embodiment, each of the user terminals 300 may correspond to a task performing entity, a registration entity, and an agency.

The management server 100 can use the information stored in the block chain holding servers 200 to acquire, store and verify information necessary for platform operation.

The virtual money according to the disclosed embodiment is understood as a concept of collecting all kinds of non-real money in which transaction details are managed through block chains such as electronic money and password.

The virtual money according to the disclosed embodiment may be a virtual money in the form of a coin or a virtual money in the form of a token which utilizes the infrastructure of another coin such as the Ethernet network, It is not limited.

In one embodiment, the task matching service according to the disclosed embodiment may be serviced as a form utilizing an infrastructure of an existing block chain platform such as Ethernet, or may be serviced using a proprietary infrastructure when a main net is developed in the future.

In one embodiment, the virtual currency in accordance with the disclosed embodiment is paid as a reward for the use of the service according to the disclosed embodiment, can be utilized for transactions between users, and can be paid to users who have a stake in the initial ICO have.

In one embodiment, the virtual money paid for each of the user terminals 300 is managed by the management server 100 as already created or issued, and can be paid according to the activity of each of the user terminals 300 .

For example, the management server 100 may perform an operation for generating a block storing information and activity details of the user terminals 300, and may generate a block through a proof of work. According to the embodiment, the management server 100 can receive the virtual money generated in exchange for it and distribute it to the user terminals 300. [

As another example, the management server 100 may manage already issued virtual currency, and may issue additional virtual currency as the case may be. The management server 100 can verify the information stored in the block chain holding servers 200, determine the integrity thereof, and pay the virtual money according to the activity to the user terminals 300 based thereon.

In one embodiment, the management server 100 may verify the information directly or through an external verification server.

In another embodiment, as information is recorded by each of the user terminals 300, virtual money may be generated and paid to the user terminals 300 according to predetermined rules, and the virtual money may be mined (mined) .

In general, the extraction of virtual money is performed by one of the following methods: Proof Of Work, Proof Of Stake, and Proof Of Importance. The above methods are one of the distributed sum algorithms used to guarantee the reliability of the distributed system.

In the disclosed embodiment, the transactions between the user terminals 300 and the corresponding virtual money payment method are performed by a Smart Contract. According to the embodiment, the task contract according to the agency matching can also be performed by the smart contract, and at least part or all of the compensation according to the performance of the task may be paid through the virtual currency.

In the embodiment shown in FIG. 2, the first user terminal 310 may send and receive necessary information to the management server 100 providing the agency matching service according to the disclosed embodiment.

Hereinafter, each of the steps is described as being performed by a computer, but the computer may correspond to the management server 100 shown in FIG. 2 and may correspond to other subjects. Depending on the embodiment, the subject performing each step is not limited thereto, and all or part of each step may be performed by another subject.

FIG. 3 is a diagram illustrating an agency matching method according to an embodiment.

In step S101, the computer performs a step of obtaining task information from the task registration subject.

In step S102, the computer performs the step of acquiring the local information and the contents of the task included in the task information.

For example, the local information may include, but is not limited to, information about the country or city in which the task will be performed.

In step S103, the computer performs step of acquiring one or more agency information corresponding to the regional information.

For example, the computer may obtain information about one or more agencies that are affiliated with, or able to connect to, subjects in the region. The information about the agency may be obtained from a predetermined list or from a list that is searched based on a particular search condition or filter.

In one embodiment, the agency information may be information input directly from each agency, or may be information obtained based on the big data collected from the results of existing tasks, etc., by the computer.

The agency information can be updated at predetermined intervals, or whenever a change occurs in the agency information. For example, if changes occur such as changes in the organizational structure of the agency, addition of the history of the tasks performed, capital changes, or changes in the area, the updated information needs to be updated. The update of the information can be confirmed and updated at predetermined intervals, or when the change occurs, the change may be updated by the agency's application.

In the case of information collection based on Big Data, it may be difficult to identify changes immediately. Therefore, it is better for the agency to update the changes directly when the change occurs, and the computer may be able to provide benefits to the agency that enters the changes directly, or to penalize agencies that do not enter changes for more than a predetermined period of time. The method of updating the information of the agency can be induced using the method, and the method is not limited.

In one embodiment, the agency may enter different information for each assignment. For example, depending on the nature of the assignment, you can enter information by highlighting the characteristics of each agency that is specific to it, or you can enter information based on the resources that the agency can actually put into each task You can also type.

If there is updated and up-to-date information about each agency, the computer obtains the most up-to-date information first and, if there is updated information specific to each task or field, it can obtain it as well. When the information specialized for each task or field is updated, the selection probability can be increased, so that information input by each agency can be induced.

In step S104, the computer performs a step of determining an agency that matches the content of the task among the one or more agencies.

The computer selects one or more agencies suitable for the content of the task, and can determine the agency based on the agency evaluation information, and a specific method will be described later.

In step S105, the computer performs the step of transmitting the determined agency information to the subject registration subject.

According to the embodiment, the contract may be performed in a smart contract manner in which the contract is automatically executed according to a predetermined contract condition when the agency information satisfies the predetermined condition But is not limited thereto.

That is, the computer provides only the information for the agency selection and contract to the subject registration subject, and the final selection and contract can be performed by the subject registration subject.

However, according to the embodiment, the contract between the agency and the subject registration subject satisfying the preset condition may be automatically performed by the computer, and according to the embodiment, when the contract is executed, information on the contracted agency, And then the contract may be executed by the computer through the simple settlement of the subject registration subject.

In one embodiment, when a contract between a task registering entity and an agency is performed, the agency may select one or more connectable task execution subjects to perform tasks. According to the embodiment, the agency manages and supervises the task execution by the task execution subject, and mediates the exchange of opinions and the task execution between the task registration subject and the task execution subject.

In one embodiment, the contract between the task registering entity and the agency may be performed on a task basis, but a contract may be performed in a manner of assigning a plurality of tasks or a whole task. In this case, the agency can select a task performing entity for each task, and assign the task to the selected task performing entity so that the task can be performed.

The authority granted to an agency may be different according to the contents of the contract. Depending on the embodiment, various rights such as the operation of the overall task, the assignment of the task performing subject, and the contract with each task performing entity may be given. Do not. In addition, each authority can provide information to the subject registration authority after the agency directly exercises the authority to post-report, permission to exercise with the consent of the subject registration authority, , And rights that can not be directly exercised.

These rights are determined according to the content of the contract, and the contents of the contract are recorded in a block chain to prevent forgery and falsification. When an agency exercises its authority, the computer checks whether it is within the scope of the authority of the agency based on the contents of the contract stored in the block chain, and then stops the agency from performing any action other than the authority, can do.

4 is a flow diagram illustrating a method for determining an agency in accordance with one embodiment.

In the above-described step S104, the computer may perform step S106 of obtaining information on the one or more agencies from the block chain.

In the above-described step S106, the computer can perform the step S107 of determining an agency matching the subject matter based on the obtained information.

In one embodiment, the block chain stores information about one or more registrants and information about one or more agencies, stores the information when a contract between a registrant and an agency is performed, and stores the result of the assignment .

Based on the information stored in the block chain, the computer verifies the information on the subject registration agent and the agency, and can determine the agency matching the subject contents based on the verified information.

5 is a flowchart illustrating a method for managing contract and task performance information according to one embodiment.

In the above-described step S105, the computer can perform the step S108 of obtaining the contract information of the task registration subject and the determined agency.

In addition, the computer may perform step S109 of acquiring performance information of the task according to the agreement.

In addition, the computer may perform step S110 of recording the acquired contract information and performance information in the block chain.

In one embodiment, the performance information of the task may include quantitative and qualitative evaluation information on the outcome of performance of the task.

FIG. 6 is a flowchart illustrating a method for acquiring task performing entity information according to an embodiment.

In the above-described step S109, the computer may perform the step S111 of obtaining one or more pieces of performing entity information that have performed the above-described tasks.

In addition, the computer may perform step S112 of obtaining information on the at least one performing entity from the block chain.

In addition, the computer may perform step S113 of acquiring task performance information of the at least one performing entity.

7 is a flow diagram illustrating a method for verifying information and providing a confidence score in accordance with one embodiment.

In the above-described step S113, the computer may perform step S114 of obtaining the execution result of the task from the task registration subject.

In addition, the computer may perform step S115 of obtaining the result of performing the task from the determined agency.

In addition, the computer may perform the step of obtaining a result of performing the task from the at least one performing entity (S116).

In addition, the computer may perform step S117 of cross-verifying the execution results of the tasks obtained in steps S114, S115, and S116.

In one embodiment, the computer may verify the accuracy of the information by cross-verifying the performance of the task received from each subject, and may re-verify the information based on the information stored in the block chain, according to an embodiment.

In addition, when the cross validation is successful, the computer provides virtual money as compensation for information to the task registering entity, the determined agency, and the at least one performing entity, and the virtual registration server, the determined agency, A step S118 of assigning a point of interest to the trustworthiness score of the performing entity may be performed.

If the cross validation is unsuccessful, the computer determines an object to which the erroneous information has been uploaded based on the information recorded in the block chain, and gives a penalty point to the reliability point of the uploaded erroneous information (S119 ). ≪ / RTI >

That is, if the verification through cross validation fails, the authenticity of each information can be evaluated based on the reliable information stored in the block chain. Even when the same information is not stored in the block chain, the related background information can be obtained and the authenticity of the information can be evaluated from this. Users who have uploaded the wrong information can deduct credibility scores.

In one embodiment, in this case, the user who uploaded the correct information may be given a credit score, and may be provided to confirm each other's uploaded information in the cross validation step according to the embodiment. In this case, additional information may be added to the reliability score if the information is provided on the wrong information.

In one embodiment, a credibility score may be utilized when matching a task enrollment entity with an agency. The reliability score may be used to assign a point of interest or weight in matching, to be used as a minimum criterion requirement, or to be used to classify each task, registrant, agency and performer.

In the above-described step S107, the computer may calculate the fitness score for each of the one or more agencies based on the information obtained in the step S106 and the contents of the task (S120) .

In addition, the computer may perform the step (S121) of selecting one or more first agencies whose reliability score among the one or more agencies is equal to or greater than a preset reference value.

In addition, the computer may perform the step S122 of acquiring information on the task performing entity connected to each of the selected one or more first agencies.

In addition, the computer may perform the step S123 of calculating an average of the reliability scores of the connected subject performing subjects for each of the selected one or more first agencies.

In addition, the computer may perform the step (S124) of selecting one or more second agencies having an average of the reliability scores equal to or greater than a preset reference value.

Further, the computer performs a step (S125) of calculating, for each of the one or more second agencies, a final reliability score based on the average of the reliability scores of the connected subject performing agents and the reliability scores of the one or more second agencies can do.

In other words, the reliability of the agency itself is also subject to evaluation, but the reliability of the subject that is linked to the agency or brokered by the agency is also subject to evaluation.

The computer may also perform, for each of the one or more second agencies, determining priority (S126) based on the fitness score and the final confidence score.

Further, the computer may perform the step S127 of determining an agency matching the subject matter based on the priority.

That is, the computer selects an agency suitable for the contents of the task, and the agency with the highest reliability can be selected first.

FIG. 8 is a flowchart illustrating a method of matching an agency using an artificial intelligence model according to an embodiment.

In the above-described step S107, the computer may perform the step S128 of extracting one or more parameters from the contents of the above-described subject matter.

Further, the computer may perform the step S129 of extracting one or more parameters from the information obtained in the step S106.

In addition, the computer may perform step S130 of inputting the parameters extracted in step S128 and step S129 into the artificial intelligence model to evaluate the fitness between the task and the one or more agencies.

Further, the computer may perform the step S131 of determining an agency matching the contents of the task based on the fitness.

The fitness can be evaluated in a variety of ways, and in one embodiment, the computer can determine the fitness and match the challenges based on the likelihood or performance of contract success for each task in each agency.

For example, satisfying the qualifications included in each task information may not be successful (i.e., selectable) for the task information. Therefore, the computer analyzes and compares the contents of the agency information and the respective task information, thereby calculating the probability that the agency succeeds in contracting the respective task information.

Various artificial intelligence models can be used to calculate the probability. For example, as learned models based on machine learning, an artificial intelligence model capable of inputting agency information and task information and outputting probability based thereon can be utilized.

In one embodiment, the artificial intelligence model can extract parameters for calculating the selection probability from each agency information and task information through natural language processing. The computer can input the extracted parameters into the artificial intelligence model, thereby obtaining the probability as an output to the artificial intelligence model. The artificial intelligence model can be learned by using the big data including the information on the agency that has completed the task and the task information corresponding to each task information as the learning data. Depending on the embodiment, the learned model may include parameters obtained by preprocessing the big data.

In another embodiment, a model capable of extracting parameters may be separately learned and utilized. After the computer guesses the parameters and provides the results of the estimation to the agency, the agent inputs the parameters selected by the agency into the artificial intelligence model, May be calculated.

For example, if the bidding for each task information is successful based on the resource information of the agency, the computer judges whether the agency has a resource capable of performing the task task, Can be evaluated.

In one embodiment, the resource may be a resource of an agency including an agent of an agency capable of managing and managing an agent, and may be a resource or an infrastructure Quot; means a resource of the performing entity which means that the resource is sufficient.

In one embodiment, the resources of the agency may be understood as the sum of the resources of the entire performing entity connected to the agency. In addition, entities associated with agencies can be classified into disciplines and classes. For example, among the performing entities connected to the agency, the executing entity related to tourism, the executing entity related to the reservation of the place, the executing entity related to the event proceeding, and the executing entity related to the research service may be included. Also, the rating can be calculated based on the evaluation information of each performing entity for each field.

The agency's resources may be understood as sector-specific and grade-specific resources, in which case the agency's resources may be understood as the sum of the resources of the entity and the performer of the required field according to the task information.

In one embodiment, the computer may determine whether duplicate bids and duplicate bids of the performing entities to be associated with the agency or agency are to be determined. For example, the computer can determine how many times the resources of the agency will provide task information to the subject.

Further, the computer can calculate the expansion resource of the agency based on the resource information of the agency and the multiple bid multiplier. For example, the computer can multiply the resource information of the agency by a multiple number of bids to calculate the expansion resources of the agency.

In one embodiment, the computer may provide the executing entity with a number of pieces of task information that the agency can support based on the magnified resource. For example, when the multiple bid multiplication is three times, the computer can match the assignment information of the amount corresponding to three times the resources of the agency with the agency, and deliver the matched information to the agency and the assignment register.

In one embodiment, the computer provides the task information based on the enlarged resource, and when the required resource of the single task information exceeds the resource of the performing subject, the task information may not be provided to the agency and the task registration subject . That is, the computer can provide the task information that requests resources less than the resources of the agency, but provides the task information of the number that makes the required resources of the task information less than the extended resources of the agency.

9 is a flow diagram illustrating a method for evaluating an agency in accordance with one embodiment.

In the above-described step S106, the computer may perform step S132 of obtaining information on the result of the task mediated by the one or more agencies from the block chain.

In the above-described step S132, the computer can perform the step S133 of obtaining the agency evaluation information of the subject registration subject.

Further, the computer may perform step S134 of acquiring agency evaluation information of the subject performing the task.

In addition, the computer can perform the step S135 of evaluating the fitness between each task and the subject performing the task.

In the above-described step S107, the computer may perform the step S136 of evaluating the one or more agencies based on the information obtained in the step S132.

That is, the computer can request the subject registration agent and the subject to evaluate the agency as an intermediary according to the result of the task execution, and obtain the evaluation information. The evaluation information can be cross-checked with each other, but the evaluation information may be different depending on the subject, so that it can be utilized only as reference data. Computers can pay virtual money to each entity in return for uploading information.

The evaluation information of the agency can be utilized to determine the priority of the agency together with the reliability score described above.

According to the embodiment described above, the criteria for evaluating the agency include the agency's goodness of fit and the reliability of the agency.

The criterion for judging the fitness of an agency can be set in various ways and may be judged on the basis of the correlation between the contents of the task and the characteristics of the agency as described above and may be judged based on the competence of the agency itself.

The correlation between the contents of the task and the characteristics of the agency can be evaluated based on various big data and the correlation between the contents of the task and the agency can be derived based on the artificial intelligence model as described above, Based on the information collected while providing the service, the AI model can be continuously learned and updated.

The correlation between the task content and the agency's characteristics can be assessed based on various parameters. For example, when evaluating an agency based on some typical parameters, such as the agency's ability to address the field of the assignment, a large agency that has a lot of resources in all areas may always be highly valued.

Therefore, according to the disclosed embodiment, the computer sets various parameters, and assigns weights to the parameters in accordance with the characteristics of the subjects and the contents of the tasks, thereby making it possible to recommend an agency suitable for the contents of the task.

For example, a specific task enrollment entity may prefer an agency that has previously collaborated with. When such information is collected, the computer can confirm whether or not the work has been collaborative with the subject registration authority, and assign a weight to the information so that the agent having cooperation experience with the subject registration subject can be given a benefit.

Further, the computer can confirm the information on the agencies having the staff having the history of working in the agency that collaborated with the subject registering entity based on the Big Data, and more specifically, the agent who has participated in the task of the subject registering subject You can check the information about the agencies and give the information to the information.

For example, if the task enrollee has worked with agency A, but all of company A's employees have left the company and are currently employed by company B, the weight may be adjusted so that company B has a higher price than company A , The weighting may be adjusted so that the higher value is given to A, nevertheless, depending on the embodiment, the system of each agency and the data of existing tasks may be considered more important.

The setting of these weights may be adjusted according to the intention of each subject registration person, and the selection of the agency according to the weight setting by the computer and the continuous learning and learning by the artificial intelligence model based on the result of the task execution of the selected agency It may be updated. Reinforcement learning may be used for such weight resetting, but is not limited thereto.

The above-described embodiment is presented by way of example. In addition, weights for various parameters can be set and updated so that the artificial intelligence model can be learned so as to recommend an agent suitable for each task content and subject registration subject.

10 is a flow diagram illustrating a method for utilizing an agency based on language capabilities in accordance with one embodiment.

In the above-described step S136, the computer may perform the step S137 of acquiring the information on the first language used by the subject registration subject.

In addition, the computer may perform step S138 of obtaining information on a second language corresponding to the local information.

In addition, the computer may perform step S139 of quantitatively evaluating the first language utilization capability of the one or more agencies.

In other words, if a foreign company wants to ask for a task in a particular country, and if it uses different languages, one of the major competencies of an agency can be language communication skills. Therefore, the computer can acquire information about the language used by the company, which is the subject of registration, and the language of the region in which the task is to be performed, and can quantitatively evaluate the agency's ability to use the language. For example, the computer can assess each agency's ability to use the first language, using quantitative assessment criteria, such as the number of employees who can use the first language in each agency.

In addition, the computer may perform step S140 of acquiring a test document written in the first language and a predetermined second language translation of the test document.

For example, test documents and translations may be test documents that have already been translated by a person and whose content is verified.

In addition, the computer may perform step S141 of obtaining a translation obtained by mechanically translating the test document into the second language. The tool used for machine translation is not limited, and various tools may be used together to obtain a machine translation according to an embodiment.

Further, the computer may perform the step S142 of comparing the predetermined translation with the machine translation.

Further, the computer may calculate the translation rate of the first language and the second language (S143) based on the comparison result.

In addition, the computer may perform the step (S145) of reflecting the weighted first language utilization capability to the one or more agency evaluations.

For example, Korean and Japanese have a high translation rate, but Korean and Chinese have a relatively low translation rate, and other languages that are not widely used in Korea may have a lower translation rate.

In addition, the computer may perform step S144 of weighting the first language utilizing ability based on the translation rate. For languages with high translation rates, the ability to mediate and manage projects rather than ability to use language as an agency's ability can be considered more important. Accordingly, the computer can determine a weight to be given to the language ability based on the translation rate between the first language and the second language, and can evaluate the agency according to the determined weight.

For example, in languages with extremely low translation rates, the agency's ability to use language may be the most important criterion.

11 is a configuration diagram of an apparatus according to an embodiment.

The processor 102 may include one or more cores (not shown) and a connection path (e.g., a bus, etc.) to transmit and receive signals to and / or from a graphics processing unit (not shown) .

The processor 102 in accordance with one embodiment performs the methods described herein by executing one or more instructions stored in the memory 104. [

For example, the processor 102 acquires the task information from the task registration subject by executing one or more instructions stored in the memory, acquires the local information and the task content included in the task information, Acquires the above agency information, determines an agency among the one or more agencies that matches the contents of the assignment, and transmits the determined agency information to the subject registration body.

The processor 102 may include a random access memory (RAM) (not shown) and a read-only memory (ROM) for temporarily and / or permanently storing signals (or data) , Not shown). In addition, the processor 102 may be implemented as a system-on-chip (SoC) including at least one of a graphics processing unit, a RAM, and a ROM.

The memory 104 may store programs (one or more instructions) for processing and control of 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 the embodiments of the present invention may be embodied directly in hardware, in software modules executed in hardware, or in a combination of both. The software module may be a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD- May reside in any form of computer readable recording medium known in the art to which the invention pertains.

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

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. Therefore, it should be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

10: Assignment subject
20: Agency
30: Subject to perform the task

Claims (10)

A method for agency matching performed by a computer,
Acquiring task information from a task registration subject (S101);
Acquiring local information and task contents included in the task information (S102);
Obtaining one or more agency information corresponding to the local information (S103);
Determining (S104) an agency among the one or more agencies that matches the content of the assignment; And
Transmitting the determined agency information to the subject registering entity (S105); Lt; / RTI >
The step (S104)
Obtaining information on the one or more agencies from the block chain (S106); And
Determining (S107) an agency matching the subject matter based on the information obtained in the step (S106); Lt; / RTI >
The step (S106)
Acquiring information on a result of the task mediated by the one or more agencies from the block chain (S132); , ≪ / RTI &
The step (S132)
A step (S133) of acquiring agency evaluation information of a subject registration subject;
Acquiring agency evaluation information of a subject performing the task (S134); And
A step of evaluating a fitness between each task and a subject performing the task (S135); Lt; / RTI >
The step (S107)
Evaluating the one or more agencies based on the information obtained in the step S132 (S136); Lt; / RTI >
The step (S136)
Acquiring information on a first language used by the subject registering step (S137);
Acquiring information on a second language corresponding to the local information (S138);
Quantitatively evaluating the first language utilization capability of the at least one agency (S 139);
Obtaining a test document written in the first language and a predetermined second language translation of the test document (S140);
Obtaining a translation obtained by mechanically translating the test document into the second language (S 141);
(S142) comparing the predetermined translation with the machine translation;
Calculating a translation rate of the first language and the second language based on the comparison result (S 143);
Weighting the first language utilization ability based on the translation rate (S144); And
Reflecting the weighted first language utilization capability to the one or more agency evaluations (S145); / RTI >
Agency matching method. delete The method according to claim 1,
The step (S105)
(S108) acquiring contract information of the task registration subject and the determined agency;
Acquiring performance information of the task according to the contract (S109); And
Recording the acquired contract information and performance information in the block chain (S110); ≪ / RTI >
Agency matching method. The method of claim 3,
The step (S109)
(S111) of acquiring one or more performing subject information that has performed the task;
Obtaining information about the at least one performing entity from the block chain (S112); And
Acquiring task performance information of the at least one performing entity (S113); / RTI >
Agency matching method. ◈ Claim 5 is abandoned due to the registration fee. 5. The method of claim 4,
The step (S113)
Obtaining a result of performing the task from the task registering entity (S114);
Acquiring an execution result of the task from the determined agency (S115);
Acquiring an execution result of the task from the at least one performing entity (S116);
(S117) cross-verifying the execution results of the tasks obtained in the steps (S114), (S115) and (S116);
And a step of providing virtual money as compensation for information to the task registration subject, the determined agency, and the at least one performing subject when the cross validation is successful, and determining the reliability of the subject registration subject, the determined agency, Adding a point to the score (S118); And
(S119), when the cross validation is unsuccessful, determining an object to which the erroneous information is uploaded based on the information recorded in the block chain, and adding a penalty point to the reliability point of the uploaded erroneous information; Lt; / RTI >
The step (S107)
Calculating (S120) a fitness score for each of the one or more agencies based on the information obtained in the step (S106) and the contents of the task;
Selecting (S121) at least one first agency in which the reliability score among the at least one agency is equal to or greater than a preset reference value;
Acquiring information on a task performing entity connected to the selected one or more first agencies (S122);
Calculating (S123) an average of reliability scores of the connected subject performing subjects for each of the selected one or more first agencies;
Selecting one or more second agencies having an average of the reliability scores equal to or greater than a preset reference value (S124);
(S125) calculating, for each of the one or more second agencies, a final reliability score based on an average of the reliability scores of the connected subject performing agents and a reliability score of the one or more second agencies;
Determining (S126), for each of the one or more second agencies, a priority based on the goodness score and the final confidence score; And
Determining an agency matching the task content based on the priority (S127); / RTI >
Agency matching method. ◈ Claim 6 is abandoned due to the registration fee. The method according to claim 1,
The step (S107)
Extracting one or more parameters from the content of the task (S128);
Extracting one or more parameters from the information obtained in the step S106 (S129);
A step (S130) of inputting the parameters extracted in the step (S128) and the step (S129) into the artificial intelligence model to evaluate the fitness between the task and the one or more agencies; And
Determining an agency matching the content of the task based on the goodness of fit (S131); / RTI >
Agency matching method. delete delete A memory for storing one or more instructions; And
And a processor executing the one or more instructions stored in the memory,
The processor executing the one or more instructions,
12. An apparatus for performing the method of claim 1. A computer program stored in a computer readable recording medium in combination with a computer which is hardware and which is capable of performing the method of claim 1. Description:

Images