KR102506640B1 - Method, device and system for matching a custom contract broker for customer-to-business contracts - Google Patents

Abstract

According to one embodiment, provided is a device, which obtains basic information of a user, including the user's age, the user's gender, the user's occupation, the user's region, the user's child composition, the user's hobbies, and the user's preferences, from a user's user terminal, obtains user's additional information including the user's MBTI from the user terminal, firstly screens a broker similar to the user's basic information in a broker database, secondly screens the firstly screened broker using the user's additional information, and thirdly selects the secondly screened broker using brokerage history.

Description

METHOD, DEVICE AND SYSTEM FOR MATCHING A CUSTOM CONTRACT BROKER FOR CUSTOMER-TO-BUSINESS CONTRACTS}

The embodiments below relate to a method, apparatus, and system for matching a customer-specific contract broker for a customer-to-business contract.

For contracts between customers and companies, contract brokers working for companies have increased the number of contracts between customers and companies.

However, conventionally, a customer would match a broker with the contract he/she wants and a broker with the contract history, or the customer would use the broker's career and education, data showing successful professional competence in the field, customer reviews, broker reviews, and broker's service request data. The method of matching brokers and customers by browsing was mainly used.

However, it was confirmed that the formation of a consensus between the individual and the broker is important for the brokerage success rate.

Therefore, the present invention utilizes personal information and personal information of an intermediary to first select an intermediary so that the rapport between the individual and the intermediary is advantageous, and then proceeds to the secondary selection using the intermediary history, so that the intermediary satisfaction is improved. It has the advantage of being able to match brokers who can be high.

Korean Registered Patent No. 10-2176108 Korean Registered Patent No. 10-2075029 Korean Registered Patent No. 10-2375733 Korean Patent Publication No. 10-2022-0127563

Embodiments seek to match a custom contract broker.

The embodiments attempt to first select a customer-customized contract broker based on rapport formation between the customer and the contract broker.

The embodiments attempt to secondaryly select a customer-customized contract broker based on additional information of the customer and the contract broker.

The customer-customized contract broker matching method for contracts between customers and companies includes the user's age, the user's gender, the user's occupation, the user's region, the user's child composition, the user's hobbies, and the user's preference from the user's user terminal. obtaining user's basic information; obtaining additional information of a user including an MBTI of the user from the user terminal; A primary selection step of selecting a broker similar to the basic information of the user in the broker database; a second screening step of re-selecting brokers selected through the first screening step using the additional information of the user; and a third selection step of re-selecting the broker selected through the second selection step using the brokerage history.

In the primary screening step, a first score is assigned according to the similarity with the user's age, a second score is assigned according to the similarity with the user's children, and a second score is assigned according to the user's similarity with the user's region. A score of 3 is assigned, a fourth score is assigned according to the degree of similarity with the user's hobby, a fifth score is assigned according to the degree of similarity with the symbol including the user's preferred style and preferred color, and the first score is given. Through the sum of the fifth to fifth scores, a broker with a preset score or higher is selected to form a rapport between the user and the broker.

The secondary screening step includes an operation of identifying an MBTI that is compatible with the MBTI of the user and selecting a broker having the MBTI.

The tertiary screening step includes obtaining a rating of the preferred broker from the user terminal and selecting a broker having the preferred broker rating from a contract broker evaluation system, wherein the contract broker evaluation system determines from the broker terminal of the broker. Acquired academic background of the broker, qualification of the broker, personal information of the broker including the career period of the broker, number of contracts of the broker extracted from the history of the broker, and contract information of the broker including contract maintenance rate of the broker , and a system for evaluating the broker by setting a rating of the broker based on the existing rating information of the broker, wherein the step of setting the rating of the broker is based on the basic information of the broker, the broker's educational background is Generating a basic score of the broker, which is set higher as the broker's qualifications are higher, the broker's career period is longer, based on the broker's contract information, as the broker's number of contracts increases, the broker's Generating the broker's contract score, which is set higher as the contract retention rate increases, calculating the broker's evaluation score as the sum of the broker's basic score and the broker's contract score, calculating the broker's evaluation score Based on the broker's evaluation grade, based on the broker's evaluation grade and the broker's existing rating information, the broker's evaluation grade and the ratings for the last N times among the previous grades are all preset criteria. Checking whether the rating is higher than the rating, setting a weight based on the confirmation, and setting the rating of the broker by applying the weight to the evaluation rating of the broker.

The tertiary screening step may include obtaining a broker's history from a broker database, and based on the broker's history, information of users whose contract conclusion period is earlier than a preset threshold period among users who have contracted with the broker by performing the brokerage. Extracting and generating first target information of the broker, Based on the history of the broker, the broker extracts user information of users whose satisfaction is greater than a preset target value among users who have contracted with the broker by performing the brokerage, Generating second target information of the broker, generating a first input signal based on the basic information of the user, the additional information of the user, the first target information of the broker, and the second target information of the broker , generating a first output signal by applying the first input signal to a first artificial neural network, generating a matching score corresponding to the user and the broker based on the first output signal, and the matching and selecting an intermediary to mediate the user's contract using the score.

In the customer-customized contract broker matching method for a contract between a customer and a company, when the user and the broker are matched, among the contracts brokered by the broker matched with the user, a contract in which the number of brokerages is greater than a preset threshold is selected as a recommended contract, , Transmitting a guide message for the recommendation contract to the broker terminal based on the review of the recommendation contract; Further comprising, the step of transmitting a guide message for the recommendation contract to the broker terminal based on the review of the recommendation contract includes extracting text information of the review data of the recommendation contract and extracting keywords; Setting a keyword mentioned more than a preset standard number of times from the extracted keyword as a main keyword, classifying the main keyword as a positive keyword or a negative keyword, calculating a positive rate, which is a ratio occupied by the positive keyword among the keywords. , Calculating a negative ratio that is a ratio occupied by the negative keyword among the keywords, comparing the negative ratio with a first reference value and a second reference value set in advance, and when the negative ratio is lower than the first reference value, the recommendation Transmitting a guide message recommending continued mediation of the contract to the broker terminal, when the negative ratio is higher than the first reference value and lower than the second reference value, sorting the negative keywords in the order in which the negative keywords are extracted in large numbers and generating an improvement point of the recommendation contract based on the sorted negative keywords, and transmitting a guide message about the negative keyword and the improvement point to the broker terminal, and when the negative ratio is higher than the second reference value. , Sending a guide message recommending not recommending the recommendation contract to the broker terminal.

An apparatus according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

Embodiments may match a custom contract broker.

Embodiments may primarily select a customer-customized contract broker based on rapport formation between the customer and the contract broker.

Embodiments may secondaryly select a customer-customized contract broker based on additional information of the customer and the contract broker.

Embodiments may tertiarily select a customer-customized contract broker based on the history information of the contract broker.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of matching a user with a user-customized contract broker according to an embodiment.
3 is a flowchart illustrating a process of selecting an intermediary similar to a user to form a rapport according to an embodiment.
4 is a diagram for explaining a process of selecting a broker through a brokerage history according to an embodiment.
5 is a flowchart illustrating a process of setting a broker's rating according to an embodiment.
6 is a flowchart illustrating a process of matching a user and an intermediary through an artificial neural network according to an embodiment.
7 is a flowchart illustrating a process of transmitting a guide message according to an indefinite ratio to an intermediary terminal according to an embodiment.
8 is an exemplary diagram of a configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to Figure 1, the system according to an embodiment may include a user terminal 100, a broker terminal 300 and a device 200 capable of communicating with each other through a communication network.

First, a communication network may be configured regardless of its communication mode, such as wired or wireless, and may be implemented in various forms so that communication between servers and communication between servers and terminals is performed.

The user terminal 100 is a terminal used by a user who wants to sign a contract with a company through an intermediary, and may be a desktop computer, a laptop computer, a tablet computer, a smart phone, and the like.

The broker terminal 300 is a terminal used by a broker to mediate a contract between a user and a company, and may be a desktop computer, a laptop computer, a tablet computer, a smart phone, and the like.

Each of the user terminal 100 and the intermediary terminal 300 may be configured to perform all or part of an arithmetic function, a storage/reference function, an input/output function, and a control function of a typical computer. The user terminal 100 and the broker terminal 300 may be configured to communicate with the device 200 by wire or wireless.

The user terminal 100 and the intermediary terminal 300 are each connected to a website operated by a service provider or organization using the device 200, or a service provider using the device 200. Applications developed and distributed by organizations may be installed. Each of the user terminal 100 and the broker terminal 300 may be linked with the device 200 through a web site or application.

Hereinafter, for convenience of explanation, only one user terminal 100 and one intermediary terminal 300 are shown in FIG. 1 and the following description, but the number of terminals may vary according to embodiments. As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

The device 200 may be a server owned by a person or organization that provides services using the device 200, may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 200 may be configured to perform all or some of the arithmetic function, storage/reference function, input/output function, and control function of a normal computer. The device 200 may include at least one artificial neural network that performs an inference function. The device 200 may be configured to communicate with the user terminal 100 and the broker terminal 300 by wire or wireless.

The device 200 obtains basic information of the user, including the user's age, the user's gender, the user's occupation, the user's region, the user's children, the user's hobbies, and the user's preferences, from the user terminal 100 of the user. and acquires the user's additional information including the user's MBTI from the user terminal 100, primarily selects a broker similar to the user's basic information in the broker database, and primarily selects the broker using the user's additional information. is selected again in the second round, and the broker selected in the second round can be selected again in the third round using the brokerage history.

2 is a flowchart illustrating a process of matching a user with a user-customized contract broker according to an embodiment.

Referring to FIG. 2 , first in step S201, the device 200 receives the user's age, the user's gender, the user's occupation, the user's region, the user's children, the user's hobbies, and the user from the user's user terminal 100. Basic information of the user including the preferred style and preferred color of the user may be acquired.

Specifically, the device 200 transmits the user's age, the user's gender, the user's occupation, the user's region, and the user through the user terminal 100 possessed by the user who intends to sign a contract with the company through a broker that mediates the contract. It is possible to obtain basic information of the user including the configuration of the child, the user's hobbies, the user's preferred style and preferred color.

For example, the device 200 is configured as a first user terminal of a first user who wants to sign a contract with a company through an intermediary, the age of the first user is 30, the gender of the first user is female, and the occupation of the first user is 30 years old. Basic information of the first user including teachers, Seoul as the first user's region, none as the user's children, hiking as the user's hobby, and casual as the user's preferred style may be obtained.

In step S202 , the device 200 may obtain user additional information including the user's MBTI from the user terminal 100 .

For example, the apparatus 200 may obtain additional information of the first user including the ISFP as the MBTI of the first user from the first user terminal.

In step S203, the device 200 may perform a primary screening for selecting a broker similar to the user's basic information in the broker database.

Specifically, the device 200 may include a broker database including information about the broker or communicate with the broker database by wire or wireless, and the broker database includes information related to the broker obtained from a terminal of the broker possessed by the broker. It may be stored, and broker-related information includes the broker's name, contact information, age, gender, region, marital status, child composition, hobbies, preferred style, preferred color, education, career, qualifications, MBTI, disposition, and lifestyle. Also, in the broker database, the broker's history, which is information related to the history of the broker's brokerage of contracts, may be stored.

That is, the apparatus 200 may obtain broker-related information through the broker database, and select a broker similar to the user's basic information by comparing the user's basic information and the broker-related information. A detailed description in this regard will be referred to through FIG. 3 .

In step S204, the device 200 may perform secondary screening to re-select brokers selected through the primary screening using the user's additional information.

Specifically, the device 200 may obtain additional information of the user including the user's MBTI from the user terminal, and based on the user's MBTI, identify an MBTI that is compatible with the user's MBTI and select a broker having the corresponding MBTI. can be selected At this time, the method of confirming the MBTI with good compatibility can be obtained with the data accumulated through the brokerage history, and when the user and the broker who have each MBTI are matched, the most contract speed, satisfaction, and communication are analyzed. And it can be confirmed, and through the confirmation, it is possible to select a broker having an MBTI that is most compatible with the user's MBTI.

Specifically, the apparatus 200 may acquire broker-related information through a broker database, compare the user's additional information and the broker-related information, and select a broker that is compatible with the user's additional information.

In step S205, the device 200 may perform a third screening for re-selecting brokers selected through the second screening using the brokerage history.

Specifically, the apparatus 200 may include an intermediary rating system. The apparatus 200 may generate a broker rating through the history of the broker through the broker evaluation system, and select a broker corresponding to the user through the broker rating. A detailed description in this regard will be referred to through FIGS. 4 and 5 .

For this reason, while the method of matching an existing customer with a broker is a method of matching a desired contract, which is a customer, with a broker having the contract history, the device 200 utilizes the user's basic information and the broker's basic information to match the user and the broker. Brokers are first selected so that the rapport of brokers is advantageous, brokers are selected secondly so that the compatibility between users and brokers is good, and brokers are selected thirdly using the brokerage history to find brokers who can have high brokerage satisfaction. can match

3 is a flowchart illustrating a process of selecting an intermediary similar to a user to form a rapport according to an embodiment.

Referring to FIG. 3 , first, in step S301, the device 200 may assign a first score according to the degree of similarity with the user's age.

Specifically, the device 200 may obtain basic information of the user from the user terminal 100, extract the user's age included in the basic information of the user, and the device 200 may use the broker database. Information related to the broker can be obtained, and the age of the broker included in the information related to the broker can be extracted.

The apparatus 200 may compare the age of the user and the age of the broker, and assign a higher first score as the age difference between the user's age and the broker's age decreases, and the first score increases as the age difference between the user's age and the broker increases. can be given small. In addition, the device 200 may assign a preset first value as the first score when the age difference between the user's age and the broker's age is within the first range, and the age difference between the user's age and the broker's age is within the first range. If not included, a second value preset as the first score may be assigned. In this case, the first range, the first value, and the second value are preset values and may vary according to embodiments.

For example, when the age of the first user obtained from the terminal of the first user is 30 years old, the age of the first broker is 32 years old, and the age of the second broker is 40 years old, the device 200 displays the age of the first user. As a result of comparing the age of 30 years old and the age of the first broker, 32 years old, it is thought that the similarity is large, so 10 points can be given as the first score corresponding to the first broker, and the age of the first user 30 years old and the first broker As a result of comparing the age of the two brokers, 40 years old, it is determined that the degree of similarity is small, and 5 points may be given as the first score corresponding to the second broker.

In step S302, the device 200 may assign a second score according to the degree of similarity with the configuration of the user's children.

Specifically, the device 200 may obtain basic information of the user from the user terminal 100, extract the configuration of the user's children included in the user's basic information, and the device 200 may retrieve the broker database. Through this, information related to the broker can be obtained, and the composition of the broker's children included in the information related to the broker can be extracted.

The device 200 compares the user's child structure and the broker's child structure, and the smaller the difference between the user's child structure and the broker's child structure, the higher the second score may be assigned, and the user's child structure and the broker's child structure. The larger the difference in configuration, the smaller the second score may be assigned. In addition, the device 200 may assign a preset third value as the second score when the difference between the user's children and the broker's children is within the second range, and the user's children and the broker's children If the difference is not within the second range, a preset fourth value may be assigned as the second score. In this case, the second range, the third value, and the fourth value are preset values and may vary according to embodiments.

For example, if the number of children of the first user obtained from the terminal of the first user is non-existent, the number of children of the first broker is absent, and the number of children of the second broker is 2, the device 200 provides 1 As a result of comparing the no child constituents of the user and the no child constituents of the first broker, the similarity is considered high, so 10 points can be given as the second score corresponding to the first broker, and the first user's child constituent As a result of comparing no person and two children of the second broker, it is determined that the degree of similarity is small, and 5 points can be given as the second score corresponding to the second broker.

In step S303, the device 200 may assign a third score according to the degree of similarity with the user's region.

Specifically, the device 200 may obtain basic information of the user from the user terminal 100, extract the user's area included in the basic information of the user, and the device 200 may use the broker database. Information related to the broker can be obtained, and the region of the broker included in the information related to the broker can be extracted.

The apparatus 200 may compare the user's region and the broker's region, and assign a higher third score as the difference between the user's region and the broker's region is smaller, and the larger the difference between the user's region and the broker's region, the higher the third score. 3 points may be awarded. In addition, the apparatus 200 may assign a preset fifth value as the third score when the difference between the user's region and the broker's region is within the third range, and the difference between the user's region and the broker's region is the third score. If it is not included in the range, a sixth value preset as the third score may be assigned. In this case, the third range, the fifth value, and the sixth value are preset values and may vary according to embodiments.

For example, when the first user's region obtained from the first user's terminal is Seoul, the first broker's region is Suwon-si, Gyeonggi-do, and the second broker's region is Seoul, the device 200 determines the first user's As a result of comparing Seoul, the region, and Suwon, the region of the first broker, the similarity is considered small, so 7 points can be given as the third score corresponding to the first broker, and Seoul, the region of the first user, and Suwon, the region of the second broker As a result of comparing Seoul, a local person in , it is judged that the degree of similarity is high, and 10 points can be given as the third score corresponding to the second broker.

In step S304, the device 200 may assign a fourth score according to the degree of similarity with the user's hobbies.

Specifically, the device 200 may obtain basic information of the user from the user terminal 100, extract the user's hobbies included in the basic information of the user, and the device 200 may use the broker database. Information related to the broker can be obtained, and hobbies of the broker included in the information related to the broker can be extracted.

The device 200 compares the user's hobby and the broker's hobby, and may assign a higher fourth score when the user's hobby and the broker's hobby are of the same genre, and when the user's hobby and the broker's hobby are different genres, the fourth score is higher. A small score may be awarded. In addition, the device 200 may assign a seventh value as the fourth score when the user's hobby and the broker's hobby are the same, and set the eighth value as the fourth score when the user's hobby and the broker's hobby are different. can be granted In this case, the seventh value and the eighth value are preset values and may vary according to embodiments.

For example, when the first user's hobby obtained from the terminal of the first user is mountain climbing, the first broker's hobby is mountain climbing, and the second broker's hobby is reading books, the device 200 displays the first user's hobby. As a result of comparing mountain climbing, which is the hobby of the first user, and mountain climbing, which is the hobby of the first broker, it is thought that the degree of similarity is high, and 10 points can be given as the fourth score corresponding to the first broker, and the first user's hobby mountain climbing and the second broker's As a result of comparing reading as a hobby, it is determined that the degree of similarity is small, and 2 points may be given as a fourth score corresponding to the second broker.

In step S305, the device 200 may assign a fifth score according to the degree of similarity with the symbol including the user's preferred style and preferred color.

Specifically, the device 200 may obtain basic information of the user from the user terminal 100, extract the user's preference included in the basic information of the user, and the device 200 may use the broker database. It is possible to obtain information related to the broker, and to extract the broker's taste included in the information related to the broker. In this case, the symbol may include the user's preferred style and the user's preferred color.

The device 200 compares the user's preference and the broker's preference, and when the user's preference and the broker's preference match, the fifth score may be given a large value, and when the user's preference and the broker's preference are different, the fifth score can be given small. In addition, the device 200 may assign a ninth value as the fifth score when the user's preference and the broker's preference match, and a tenth value as the fifth score when the user's preference and the broker's preference are different. can be granted. In this case, the ninth value and the tenth value are preset values and may vary according to embodiments.

For example, when the preferred style of the first user obtained from the terminal of the first user is casual, the preferred style of the first broker is casual, and the preferred style of the second broker is formal, the device 200 sets the first As a result of comparing casual, which is the user's preferred style, with casual, which is the preferred style of the first broker, it is considered that the similarity is high, and 10 points can be given as the fifth score corresponding to the first broker, and the preferred style of the first user is casual. As a result of comparing casual and formal, which are the preferred styles of the second broker, it is determined that the degree of similarity is small, and thus 2 points may be given as a fifth score corresponding to the second broker.

In step S306, the apparatus 200 may select a broker whose sum of the first score, the second score, the third score, the fourth score, and the fifth score is greater than or equal to a preset score. Here, the preset score is a preset value and may vary according to embodiments.

In addition, the apparatus 200 generates a score corresponding to the broker by summing the first to fifth scores, and selects a broker whose score corresponding to the broker is equal to or higher than a preset score, thereby forming a rapport between the user and the broker. can make this happen.

According to an embodiment, the highest scores of each of the first score, the second score, the third score, the fourth score, and the fifth score may be all set to the same score, but the highest score may be set differently according to user settings. there is. For example, the highest scores of the first score, the second score, the third score, the fourth score, and the fifth score may all be equally set to 10 points, and the highest score of the first score is 15 points, and the second score is 15 points. The highest score of the scores may be set to 10 points, the highest score of the third score to 5 points, the highest score to the fourth score to 8 points, and the highest score to the fifth score to 7 points.

For example, the first score corresponding to the first broker is given as 10 points, the second score is given as 10 points, the third score is given as 7 points, the fourth score is given as 10 points, the fifth score is given as 10 points, and the second score is given as 10 points. If the first score corresponding to the broker is 5 points, the second score is 5 points, the third score is 10 points, the fourth score is 2 points, the fifth score is given 2 points, and the preset score is 35 points; Apparatus 200 may calculate 47 points as a score corresponding to the first intermediary, and may calculate 24 points as a score corresponding to the second intermediary. In addition, the apparatus 200 may first select the first broker by confirming that the score corresponding to the first broker, 47 points, is greater than the preset score, 35 points, and the score corresponding to the second broker, 24 points, is set in advance. By confirming that the set score is greater than 35 points, the second broker may not be primarily selected.

4 is a diagram for explaining a process of selecting a broker through a brokerage history according to an embodiment.

Referring to FIG. 4 , first, in step S401 , the device 200 may obtain a rating of a preferred broker from the user terminal 100 .

In detail, the device 200 may obtain the grade of the preferred broker preferred by the user among the grades A to E from the user terminal 100 . At this time, brokers of higher quality may be included as grade A goes, and brokers of lower quality may be included as grade E increases. In addition, the user can pay a higher brokerage commission as the A grade goes, and the user can pay a lower commission as the E grade goes.

In step S402, the device 200 may select a broker that matches the rating of the preferred broker from the broker evaluation system.

Specifically, the broker evaluation system is based on the broker's personal information, including the broker's academic background, broker's qualifications, and the broker's career period, as well as the broker's contract information, including the broker's number of contracts and the broker's contract retention rate, and the broker's existing rating information. As a system for evaluating the broker by setting the rating of the broker on the basis, the broker evaluation system may be included in the device 200 . Here, the personal information of the broker may be information acquired from the broker terminal of the broker, and the broker's contract information and the broker's existing rating information may be information stored by being matched with the broker's brokerage history.

5 is a flowchart illustrating a process of setting a broker's rating according to an embodiment.

Referring to Figure 5, first, in step S501, the device 200 based on the basic information of the broker, the higher the broker's educational background, the higher the broker's qualifications, the longer the broker's career period, the higher the broker's basic points can be generated.

Specifically, the device 200 may obtain the broker's personal information, including the broker's academic background, the broker's license, and the broker's career period, from the broker terminal 300, based on the broker's personal information, the broker's educational background. The higher the broker's license, the longer the broker's career period, the higher the broker's basic score.

In step S502 , the apparatus 200 may generate a broker contract score that is set higher as the broker's contract retention rate increases as the number of broker contracts increases based on the broker's contract information.

Specifically, the device 200 may obtain broker contract information including the number of broker contracts and the broker contract retention rate stored in the broker database, and based on the broker contract information, the higher the broker contract number, the higher the broker contract information. The broker's contract score, which is set higher as the broker's contract retention rate is higher, can be created.

In step S503, the device 200 may calculate the broker's evaluation score as the sum of the broker's basic score and the broker's contract score.

In step S504, the device 200 may generate an evaluation grade of the broker based on the evaluation score of the broker.

Specifically, the device 200 may include data in which the evaluation score and the evaluation grade are matched, and may generate an evaluation grade matched with the broker's evaluation score as the broker's evaluation grade.

In step S505, the device 200 checks whether or not the broker's evaluation grade and the previous grades among the broker's evaluation grades and previous grades are equal to or greater than a reference value, based on the broker's evaluation grade and the broker's existing grade information. Based on this, weights can be set. Here, the broker's existing rating information is information for confirming what grade the broker was previously, and may be matched with the broker and stored in the broker database. In addition, the N times and the reference value are preset values and may vary according to embodiments.

Specifically, the apparatus 200 checks whether all of the broker's evaluation grades and previous grades of the broker's ratings for the last N times are higher than the reference grade, based on the broker's evaluation grade and the broker's existing rating information, and confirms Based on this, weights can be set.

For example, if the evaluation grade of the first intermediary is B, the grades of the first intermediary for three times are B, A, and A, and the reference value is C, the device 200 first It is confirmed that the middleman's middleman's evaluation grade and the last three grades among the previous grades are all higher than the C grade, which is the standard grade, and the weight can be set based on the confirmation.

For example, if the first broker's evaluation grade is B, the first broker's grades for three times are D, B, and C, and the reference value is B, the device 200 sets the first Among the broker's evaluation grades and previous grades of the broker, among the grades for the last three times, it is confirmed that there is a grade lower than the C grade, which is the reference value, and the weight may not be set based on the confirmation.

In step S506, the apparatus 200 may set the middleman's grade by applying a weight to the broker's evaluation grade.

6 is a flowchart illustrating a process of matching a user and an intermediary through an artificial neural network according to an embodiment.

Referring to Figure 6, first, in step S601, the device 200 may obtain the mediation history of the broker from the broker database. Here, the mediation history may store basic information of the user, user information including additional information, contract conclusion time, and user satisfaction in correspondence with the user for whom the mediator performed mediation.

In step S602, the device 200 extracts user information of users whose contract conclusion period is earlier than the critical period among users who contracted through the brokerage by performing the brokerage based on the brokerage history, and generates the broker's first target information. can do. Here, the threshold period is a preset period and may vary according to embodiments.

In step S603, the apparatus 200 may generate second target information of the broker by extracting user information of users whose satisfaction is greater than the target value among users who have contracted with the broker by performing the brokerage based on the broker's brokerage history. there is. Here, the target value is a preset value and may vary according to embodiments.

In step S604, the apparatus 200 may generate a first input signal based on the user's basic information, the user's additional information, the broker's first target information, and the broker's second target information.

Specifically, the apparatus 200 may perform a process of pre-processing the user's basic information, the user's additional information, the broker's first target information, and the broker's second target information. The preprocessed user's basic information, user's additional information, broker's first target information, and broker's second target information are either used as inputs to the first artificial neural network or undergo normal processing to remove unnecessary information. A first input signal may be generated.

In step S605, the device 200 may generate a first output signal by applying the first input signal to the first artificial neural network.

The first artificial neural network is an artificial intelligence model that outputs a matching score between the user and the broker according to the user's basic information, the user's additional information, the broker's first target information, and the broker's second target information. , additional information of the training user, first target information of the training broker, second target information of the training broker, first output signals, and training scores. Here, the training scores are scores corresponding to basic information of the training user, additional information of the training user, first target information of the training broker, and second target information of the training broker, respectively, and the first output signals are the training user The basic information of the training user, the additional information of the training user, the first target information of the training broker, and the second target information of the training broker are output signals generated by applying the first artificial neural network, and the first artificial neural network is the first output signal. It is learned by minimizing training errors generated based on differences in signals and training scores.

The first artificial neural network may be an artificial neural network that is learned according to reinforcement learning. The first artificial neural network may be a Q-Network, a Depp Q-Network (DQN), or a relational network (RL) structure suitable for outputting abstract inference through reinforcement learning. The first artificial neural network learned through reinforcement learning may be updated and optimized by reflecting evaluations on various rewards. For example, the first reward increases as the matching score between the user and the broker is selected as an appropriate score according to the user's basic information, the user's additional information, the broker's first target information, and the broker's second target information. The second reward is rewarded when a matching score between the user and the broker is not selected according to the user's basic information, the user's additional information, the broker's first target information, and the broker's second target information. value may increase.

In step S606, the device 200 may generate matching scores corresponding to the user and the broker based on the first output signal. In this case, the score may be a real value between 0 and 1.

In step S607, the device 200 may select an intermediary to mediate the user's contract using the matching score.

For example, if the scores of broker A to broker D are 0.8, 0.2, 0.4, and 0.6, respectively, the device 200 may select broker A with the highest score of 0.8 as the broker to broker the user's contract. .

7 is a flowchart illustrating a process of transmitting a guide message according to an indefinite ratio to an intermediary terminal according to an embodiment.

When the device 200 selects a broker to broker a contract between a user and a user, among the contracts brokered by the broker, a contract with a brokerage frequency greater than a preset threshold is selected as a recommended contract, and the recommendation contract is recommended based on the review of the recommended contract. A guide message for the contract may be transmitted to the broker terminal 300 . Here, the threshold value is a preset value and may vary according to embodiments.

Referring to FIG. 7 , first, in step S701, the device 200 may extract text information of review data of a recommendation contract and extract keywords.

Specifically, the broker database may include a review written by a user who has entered into a corresponding contract for a contract brokered by the broker, and the device 200 obtains a review corresponding to a contract selected as a recommended contract through the broker database. text information can be extracted through the review of the acquired recommendation contract, and keywords can be extracted through the text information.

In step S702, the device 200 may set a keyword mentioned more than a predetermined standard number of times from the extracted keyword as a main keyword. In this case, the reference number of times may be set differently according to embodiments.

In step S703, the device 200 may classify the main keyword as a positive keyword or a negative keyword.

In step S704, the device 200 may calculate a positive rate and a negative rate. In this case, the positive rate may mean a rate occupied by positive keywords among keywords, and the negative rate may mean a rate occupied by negative keywords among keywords.

In step S705, the device 200 may compare the negative ratio with a preset first reference value. In this case, the first reference value may be set differently according to embodiments.

As a result of comparing the negative ratio with the preset first reference value in step S705, if the negative ratio is lower than the first reference value, in step S706, the device 200 sends a guide message recommending continued brokerage of the recommendation contract to the broker terminal 300. can be sent to

As a result of comparing the negative ratio with the preset first reference value in step S705, if the negative ratio is not lower than the first reference value, the apparatus 200 may compare the negative ratio with the preset second reference value in step S707. At this time, the second reference value may be set differently according to the embodiment.

As a result of comparing the negative ratio with the preset second reference value in step S707, if the negative ratio is higher than the first reference value and lower than the second reference value, in step S708, the device 200 sends a guide message about the negative keyword and improvement points to the broker terminal. (300).

According to an embodiment, the apparatus 200 may sort the negative keywords in the order in which many negative keywords are extracted, and generate improvement points of the retained recommendation contract based on the sorted negative keywords.

For example, if the negative keywords are 'weak durability' and 'expensive', the device 200 sorts the negative keywords in the order in which many negative keywords are extracted, and determines 'durability improvement' and 'price improvement' based on the negative keywords. Improvements in recommendation contracts can be created.

As a result of comparing the negative ratio with the preset second reference value in step S707, if the negative ratio is higher than the second reference value, in step S709, the device 200 sends a guide message recommending not to recommend a recommendation contract to the broker terminal (300 ) can be transmitted.

According to one embodiment, the apparatus 200 compares the negative ratio with the preset second reference value, and if the negative ratio is higher than the second reference value, the guide message recommending not to recommend the corresponding recommendation contract is sent to the broker terminal (300 ), and a guide message recommending changing the broker recommendation contract selected by the broker to the recommendation contract instead of the corresponding recommendation contract may be transmitted to the broker terminal 300 .

8 is an exemplary diagram of a configuration of a device according to an embodiment.

Device 200 according to an embodiment includes a processor 210 and a memory 220 . The processor 210 may include at least one device described above with reference to FIGS. 1 to 7 or may perform at least one method described above with reference to FIGS. 1 to 7 . Individuals or organizations using the device 200 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 7 .

The memory 220 may store information related to the methods described above or may store a program in which the methods described below are implemented. Memory 220 may be volatile memory or non-volatile memory.

The processor 210 may execute a program and control the device 200 . Program codes executed by the processor 210 may be stored in the memory 220 . The device 200 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data through wired/wireless communication.

Apparatus 200 may be used to train an artificial neural network or to use a trained artificial neural network. The memory 220 may include a learning or learned artificial neural network. The processor 210 may learn or execute an artificial neural network algorithm stored in the memory 220 . The device 200 for learning the artificial neural network and the device 200 using the learned artificial neural network may be the same or separate.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (3)

A method for matching a customer-customized contract broker for a contract between a customer and a business, performed by a device, comprising:
Obtaining basic information of the user, including the user's age, the user's gender, the user's occupation, the user's region, the user's child composition, the user's hobby, and the user's preference, from the user's user terminal;
obtaining additional information of a user including an MBTI of the user from the user terminal;
A primary selection step of selecting a broker similar to the basic information of the user in the broker database;
a second screening step of re-selecting brokers selected through the first screening step using the additional information of the user; and
A third screening step of re-selecting the broker selected through the second screening step using the brokerage history;
In the first screening step,
A first score is given according to the degree of similarity with the user's age;
A second score is given according to the degree of similarity with the configuration of the user's children;
A third score is given according to the degree of similarity with the user's region;
A fourth score is given according to the degree of similarity with the user's hobby,
A fifth score is given according to the degree of similarity with the symbol including the user's preferred style and preferred color;
By summing the first to fifth scores and selecting a broker with a preset score or higher, a rapport between the user and the broker is formed,
In the second selection step,
Checking an MBTI that is compatible with the user's MBTI and selecting a broker having the MBTI;
In the third selection step,
Obtaining a rating of a preferred broker from the user terminal;
Selecting a broker of the rating of the preferred broker from a broker evaluation system;
The broker evaluation system
Personal information of the broker, including the broker's academic background, the broker's license, and the broker's career period obtained from the broker's terminal;
The number of contracts of the broker extracted from the broker's history, the broker's contract information including the broker's contract retention rate, and
A system for evaluating the broker by setting the rank of the broker based on the existing rating information of the broker,
The step of setting the rating of the broker is
Based on the basic information of the broker, generating a basic score of the broker, which is set higher as the broker's educational background increases, as the broker's licenses increase, and as the broker's career period increases;
Based on the contract information of the broker, generating a contract score of the broker, which is set higher as the number of contracts of the broker increases and the contract retention rate of the broker increases;
Calculating an evaluation score of the broker as the sum of the base score of the broker and the contract score of the broker;
Generating an evaluation grade of the broker based on the evaluation score of the broker;
Based on the evaluation grade of the broker and the existing grade information of the broker, it is checked whether the evaluation grade of the broker and the grades for the last N times among the previous grades are all equal to or greater than a preset reference grade, and based on the confirmation setting weights;
Setting the rating of the broker by applying the weight to the evaluation rating of the broker,
A custom contract broker matching method for customer-to-business contracts. delete delete

Images