KR102177604B1 - Apparatus and method for predicting salary - Google Patents

Abstract

It provides an apparatus and method for predicting annual salary. A method for predicting an annual salary is an apparatus for predicting an annual salary performed by a computing device, the method comprising: receiving first salary calculation data for a user; Calculating a first predicted annual salary of the user based on the first annual salary calculation data; Receiving a second annual salary calculation data different from the first annual salary calculation data; And after calculating the user's first predicted annual salary, calculating a second predicted annual salary of the user based on the first annual salary calculation data and the second annual salary calculation data.

Description

Apparatus and method for predicting salary}

The present invention relates to an apparatus and method for predicting annual salary.

Many people have questions about whether the level of pay they are currently receiving is suitable for their job skills or experience. Also, job-seekers who want to get a job for the first time in their lives do not know how much salary they should prepare for employment due to lack of information. Recruitment-related services currently on the market are just platform services that connect consumers and suppliers in the job market, and only a few services provide salary information by industry or job.

In the case of a service that provides annual salary information by industry or job, since it provides only the average annual salary information for a specific industry and specific job, the job seeker can only know the average annual salary level of the target job market, based on individual circumstances. It is not possible to know the appropriate salary level calculated.

Therefore, it is necessary to predict an individual's optimal annual salary level based on a variety of individual situational information so that job-seekers are prepared for employment correctly, and that employees can check whether they are assessed with fair market value. have.

The problem to be solved by the present invention is to provide an apparatus and method for predicting annual salary.

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

In order to achieve the above object, one aspect of the annual salary prediction method of the present invention is a method of predicting an annual salary performed by a computing device, the method comprising: receiving first salary calculation data for a user; Calculating a first predicted annual salary of the user based on the first annual salary calculation data; Receiving a second annual salary calculation data different from the first annual salary calculation data; And after calculating the user's first predicted annual salary, calculating a second predicted annual salary of the user based on the first annual salary calculation data and the second annual salary calculation data.

After calculating the first predicted salary, the step of presenting a first predicted salary and a first reliability level of the first predicted salary to the user together. A second reliability higher than the first reliability when providing the second annual salary calculation data between the step of presenting the first predicted annual salary and the first reliability to the user together and receiving the second annual salary calculation data It further includes informing the user that the second predicted annual salary of may be provided.

Each of the first annual salary calculation data and the second annual salary calculation data includes any one of basic information about the user, self-development, work experience, job aptitude, and industry information, and basic information about the user, self-development , Work experience or job aptitude is input by a user through a user terminal, and the industry information is collected by accessing an external database.

In the calculating of the first predicted annual salary or the calculating of the second predicted annual salary, a predicted annual salary is calculated using a plurality of machine learning algorithms, and a plurality of predicted annual salaries are calculated using the plurality of machine learning algorithms. The predicted annual salary of the machine learning algorithm representing the smallest error is calculated as the final predicted annual salary by comparing with the previously measured annual salary.

Comparing the calculated first predicted annual salary or the second predicted annual salary with the actual salary of the user and recommending a subsequent operation of the user, wherein the step of recommending the subsequent operation of the user may include: It includes providing employment information when the actual salary is greater than the actual salary, and providing capability improvement information to improve the individual's ability in the industry when the predicted annual salary is less than the actual salary.

In addition, in order to achieve the above other object, one side of the computer-readable storage medium of the present invention stores instructions of a computer program for implementing the above-described salary prediction method.

In order to achieve the above another problem, one aspect of the annual salary prediction apparatus of the present invention, a communication module; Processor; And a memory, wherein the memory includes, by the processor, receiving first annual salary calculation data for the user, calculating a first predicted annual salary of the user based on the first annual salary calculation data, and the first annual salary After receiving the second annual salary calculation data different from the calculation data, and calculating the first predicted annual salary of the user, the second predicted annual salary of the user is calculated based on the first annual salary calculation data and the second annual salary calculation data To save the instructions.

Details of other embodiments are included in the detailed description and drawings.

1 is a diagram illustrating an annual salary prediction system to which an annual salary prediction apparatus according to some embodiments of the present invention is applied.
2 is a block diagram of an apparatus for predicting annual salary according to some embodiments of the present invention.
3 is a flowchart illustrating an annual salary prediction method according to some embodiments of the present invention.
4 is an annual salary graph for explaining the relationship between the predicted salary and the actual salary.
5 and 6 are views showing an example of application of the annual salary graph of FIG. 4.
7 is a diagram illustrating an operation of the predicted annual salary calculator illustrated in FIG. 2.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments to be posted below, but may be implemented in a variety of different forms, and only these embodiments make the posting of the present invention complete, and common knowledge in the technical field to which the present invention pertains. It is provided to completely inform the scope of the invention to those who have it, and the invention is only defined by the scope of the claims. The same reference numerals refer to the same components throughout the specification.

Although the first, second, etc. are used to describe various elements, components and/or sections, of course, these elements, components and/or sections are not limited by these terms. These terms are only used to distinguish one element, component or section from another element, component or section. Therefore, it goes without saying that the first element, the first element, or the first section mentioned below may be a second element, a second element, or a second section within the technical scope of the present invention.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used in the specification, "comprises" and/or "comprising" refers to the presence of one or more other components, steps, actions and/or elements, and/or elements, steps, actions and/or elements mentioned. Or does not exclude additions.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

In the present specification, "configured to (configured to)" is changed according to the situation, for example, hardware or software, "suitable for," "having the ability to," "... ," "made to," "can do," or "designed to" can be used interchangeably. In some situations, the expression "a device configured to" may mean that the device "can" along with other devices or parts. For example, the phrase “a processor configured (or configured) to perform A, B, and C” means a dedicated processor (eg, an embedded processor) for performing the operation, or by executing one or more software programs stored in a memory device. , May mean a general-purpose processor (eg, CPU or application processor) capable of performing corresponding operations.

The annual salary prediction method according to some embodiments of the present invention is performed by an annual salary prediction apparatus, and the annual salary prediction apparatus is implemented as a computing device. The computing device may be implemented by, for example, at least one server (eg, a web server, an application server, a database server, a communication server, a terminal server, etc.), but is not limited thereto.

Alternatively, the computing device may be implemented as a centrally managed data storage environment or a distributed data storage environment.

In another embodiment, the computing device is, for example, a desktop PC, laptop PC, netbook computer, workstation, PDA, portable multimedia player (PMP), smart phone, tablet PC, mobile phone, video phone, e-book reader, MP3 It may include at least one of a player, a medical device, a camera, or a wearable device. Here, the wearable device is an accessory type (e.g., watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-devices (HMD)), fabrics or clothing integrated (e.g., electronic clothing). ), body-attached (for example, a skin pad or tattoo), or a bio-implantable circuit In some embodiments, the computing device is, for example, a television, a digital video disk (DVD) Player, audio, refrigerator, air conditioner, vacuum cleaner, oven, microwave, washing machine, air purifier, set-top box, home automation control panel, security control panel, media box (e.g. Samsung HomeSync ^TM , Apple TV ^TM , or Google TV) ^TM ), a game console (eg, Xbox ^TM , PlayStation ^TM ), an electronic dictionary, an electronic key, a camcorder, or an electronic frame.

In another embodiment, the computing device includes various medical devices (e.g., various portable medical devices (such as a blood glucose meter, heart rate meter, blood pressure meter, or body temperature meter), magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), etc.), CT (computed tomography), camera, or ultrasound), navigation device, global navigation satellite system (GNSS), event data recorder (EDR), flight data recorder (FDR), automobile infotainment device, marine electronic equipment (E.g., navigation devices for ships, gyro compasses, etc.), avionics, security devices, vehicle head units, industrial or home robots, drones, ATMs in financial institutions, point of sale (POS) in stores of sales), or IoT devices (eg, light bulbs, various sensors, sprinkler devices, fire alarms, temperature controllers, street lights, toasters, exercise equipment, hot water tanks, heaters, boilers, etc.). According to some embodiments, the computing device may be a piece of furniture, a building/structure or a vehicle, an electronic board, an electronic signature receiving device, a projector, or various measuring devices (e.g., water, electricity, Gas, or a radio wave measuring device, etc.). In various embodiments, the computing device may be flexible or may be a combination of two or more of the various devices described above. The computing device according to the embodiment of the present document is not limited to the above-described devices. In this document, the term user may refer to a person using a computing device or a device (eg, an artificial intelligence computing device) using a computing device. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and in the description with reference to the accompanying drawings, identical or corresponding components are assigned the same reference numerals and duplicated Description will be omitted.

1 is a diagram showing an annual salary prediction system.

Referring to FIG. 1, an annual salary prediction system 10 includes an annual salary prediction apparatus 100 and a user terminal 200.

The annual salary prediction device 100 calculates a predicted salary using annual salary calculation data for a user (for example, self-development, work experience, job aptitude, industry information, etc.), and calculates the calculated predicted salary from the user terminal 200. Plays the role of sending to ). Here, the salary calculation data may be received from the user terminal 200 or may be collected separately. That is, the annual salary prediction apparatus 100 receives at least a part of the salary calculation data (eg, self-development information, work experience, job aptitude, etc.) from the user terminal 200. The annual salary prediction apparatus 100 may receive some (eg, industry information) from a source other than the user terminal 200 (eg, an internal/external database).

The calculated predicted annual salary may be stored in the annual salary predicting apparatus 100, and the annual salary predicting apparatus 100 may calculate a predicted annual salary for another user after referring to the stored predicted information.

The user terminal 200 transmits the annual salary calculation data input from the user to the salary predictor 100 and outputs the predicted salary received from the salary predictor 100.

The user terminal 200 may be a portable terminal such as a laptop, a tablet, a smartphone, a wearable device, or the like, and may be a fixed terminal such as a personal computer (PC), a home appliance, or a medical device, but is not limited thereto. Each user terminal 200 may be used by different users, but is not limited thereto.

Meanwhile, the user terminal 200 may be an individual user or a corporate user. For example, an individual user may input annual salary calculation data through the user terminal 200, and the individual user may be provided with a predicted annual salary calculated by the annual salary prediction apparatus 100. Alternatively, an individual user may input annual salary calculation data through the user terminal 200, but a corporate user may be provided with a predicted annual salary calculated by the annual salary prediction apparatus 100. Alternatively, an individual user may input annual salary calculation data such as self-development matters, work experience, job aptitude, etc., a corporate user inputs annual salary calculation data such as connection information, and the annual salary prediction device 100 may calculate a predicted annual salary. have.

The annual salary prediction apparatus 100 may provide a graphic user interface (GUI) for access and data input through the user terminal 200. For example, a graphic user interface may be implemented with HTML5 that operates flexibly on a portable terminal and the Internet, but this is an example, and a graphic user interface may be implemented with a separate interface platform. FIG. 2 shows some implementations of the present invention. A block diagram of an apparatus for predicting annual salary according to an example.

Referring to FIG. 2, the annual salary prediction apparatus 100 includes a communication unit 110, a first storage unit 121, a second storage unit 122, a control unit 130, a data collection unit 140, and a predicted annual salary calculation unit. It is configured to include 150, a cost input determination unit 160 and a diagnosis unit 170.

The communication unit 110 receives annual salary calculation data from the user terminal 200 and transmits the predicted salary to the user terminal 200. To this end, a communication channel may be configured between the communication unit 110 and the user terminal 200. In addition, when a plurality of user terminals 200 are included in the annual salary prediction system 10, the communication unit 110 may configure a separate communication channel for each user terminal 200, but is not limited thereto.

The communication channel may include both wired and wireless methods. In particular, wireless communication is, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM Cellular communication using at least one of (Global System for Mobile Communications) and the like may be included. Or, the wireless communication, WiFi (wireless fidelity), LiFi (light fidelity), Bluetooth, Bluetooth low power (BLE), Zigbee (Zigbee), NFC (near field communication), magnetic secure transmission (Magnetic Secure Transmission), radio frequency ( RF), or a body area network (BAN). Alternatively, wireless communication may include GNSS. The GNSS may be, for example, a Global Positioning System (GPS), a Global Navigation Satellite System (Glonass), a Beidou Navigation Satellite System (hereinafter “Beidou”), or Galileo, the European global satellite-based navigation system. Wired communication is, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard232), power line communication, or POTS (plain old telephone service), computer network (for example, LAN or WAN) and the like.

The first storage unit 121 serves to store the predicted annual salary calculated by the predicted annual salary calculation unit 150. The predicted annual salary calculation unit 150 may calculate predicted annual salaries for different users. The first storage unit 121 may store predicted annual salaries for different users calculated by the predicted annual salary calculator 150. The prediction information may be stored together with the annual salary calculation data used to calculate the corresponding prediction information.

The second storage unit 122 serves to store annual salary calculation data collected through a network other than a network used for communication with the user terminal 200 (hereinafter, referred to as an external network). For example, information on various industries may be collected through an external network and stored in the second storage unit 122.

In addition, the first storage unit 121 or the second storage unit 122 stores instructions for performing the annual salary prediction method according to some embodiments of the present invention. That is, the first storage unit 121 or the second storage unit 122 is a memory, and the processor receives the first annual salary calculation data for the user, and calculates the user’s first predicted annual salary based on the first annual salary calculation data. After calculating, receiving data for calculating the second annual salary that is different from the data for calculating the first annual salary, and calculating the first predicted annual salary of the user, the second predicted annual salary of the user is based on the first annual salary calculation data and the second annual salary calculation data. It is possible to store the instructions, yielding.

2 shows that the first storage unit 121 and the second storage unit 122 are separately provided, but the first storage unit 121 and the second storage unit 122 are provided in one physical storage unit. Can be included. Alternatively, at least one of the first storage unit 121 and the second storage unit 122 may not be directly connected to the annual salary prediction apparatus 100, but may be connected through a network. For example, a separate storage server (not shown) may store data in the first storage unit 121 or the second storage unit 122, and transmit and receive data through a network with the annual salary prediction device 100. . Hereinafter, a description will be made mainly on that the first storage unit 121 and the second storage unit 122 are separately provided in the annual salary prediction apparatus 100.

The data collection unit 140 accesses an external network and collects information about the industry (hereinafter, referred to as industry information). For example, industry information may include at least one of supply and demand status, trend and issue by industry and job. Here, the status of supply and demand by industry and job may be employment status by industry and job. For example, the number of required and active showhosts in the shopping industry may be included in the supply and demand status of each industry and job. Trends represent items recognized as representative in the industry. For example, a trend might include the prevalence of long padding in the winter clothing industry. An issue represents a recent event in the industry and is recognized as being able to affect the industry. For example, in an industry that manufactures winter heating equipment, incidents of fires caused by heating equipment may be included in the issue.

The data collection unit 140 may access an external network (or an external database) and continuously collect industry information. Also, the data collection unit 140 may replace the existing industry information with the latest industry information when there is a difference between the previously collected industry information and the recently collected industry information.

The predicted annual salary calculation unit 150 serves to calculate a predicted annual salary for a user. The predicted annual salary calculation unit 150 may receive the annual salary calculation data for the user step by step, and apply the annual salary prediction result of the previous stage to the annual salary prediction of the subsequent stage to calculate the predicted annual salary step by step. When first-stage annual salary calculation data (hereinafter referred to as first-stage data) is input, the predicted annual salary calculation unit 150 may calculate the first-stage predicted annual salary by referring to the first-stage data and stored data. Subsequently, when the second-stage annual salary calculation data (hereinafter referred to as second-stage data) is input, the predicted annual salary calculation unit 150 may calculate the second-stage predicted annual salary by applying the second-stage data and stored data to the first-stage predicted annual salary. have. Proceeding to a later step, the predicted annual salary calculator 150 may repeat the above process.

The predicted annual salary for each step calculated by the predicted annual salary calculator 150 may be transmitted to the user terminal 200 through the communication unit 110. That is, when the first-stage predicted salary is calculated, the communication unit 110 may transmit the first-stage predicted salary. Subsequently, when the second-stage predicted salary is calculated, the communication unit 110 may transmit the second-stage predicted salary. The reception of stage 2 data may be included between the transmission of the stage 1 predicted salary and the transmission of the stage 2 predicted salary. However, according to some embodiments of the present invention, data of a plurality of stages may be collectively received, and then the predicted annual salary of each stage may be collectively transmitted.

In the present invention, the salary calculation data may include at least one of basic information on a user, self-development, work experience, job aptitude, and industry information.

Basic information may include gender, age, military qualifications, college graduate, major and credits. In addition, if the user is an experienced person, basic information may include the business type of the company that has been or is currently employed, the job at each company, the final annual salary at each company, and the final education at the time of joining each company.

Self-development items may include qualifications acquired, work-related awards, language skills, and work-related job skills.

Work experience may include the length of work for each job experience, the size of the company that has or is employed, the number of employees in each company, and the average year of service for each company.

Job aptitude includes information to determine how well the business type to be employed and performing the job in the job suits the employer's job style. For example, personality, sincerity, activity, and communication ability may be included in job aptitude, and results of Myers-Briggs Type Indicator (MBTI) may be included in job aptitude. Depending on which job aptitude test item is added, the input item may be changed. In particular, in the apparatus and method for predicting annual salary according to some embodiments of the present invention, job aptitude is used as one of important data for predicting annual salary. It is judged that the better the job aptitude is, the higher the likelihood of a higher performance will be, and the higher the annual salary.

Industry information may include at least one of supply and demand status, trend and issue by industry and job. Since the industry information has been described above, detailed descriptions will be omitted.

The cost input determination unit 160 determines whether to input an annual salary calculation cost for predicting an annual salary. Meanwhile, the predicted annual salary calculation unit 150 may calculate the predicted annual salary in stages, and the annual salary calculation cost may be generated for each stage. Accordingly, the cost input determination unit 160 may determine whether to input the annual salary calculation cost for predicting the annual salary in each step. In calculating the predicted annual salary for each step, the predicted annual salary calculation unit 150 may determine whether to calculate the predicted annual salary by referring to whether or not the annual salary calculation cost is input in the corresponding step.

A user who wants to search for prediction information using the user terminal 200 may pay the annual salary calculation cost for each step using the user terminal 200 or using a separate means. The cost input determination unit 160 may determine whether an annual salary calculation cost is input, and transmit the result to the predicted annual salary calculation unit 150.

The predicted annual salary calculation unit 150 may calculate the predicted annual salary step by step, and the annual salary calculation cost may be incurred for only some of them. For example, an annual salary calculation cost may be generated only after a specific step, and the predicted annual salary may be calculated by the predicted annual salary calculator 150 for free before the corresponding step.

The diagnosis unit 170 compares the predicted annual salary calculated by the predicted annual salary calculation unit 150 with the actual annual salary of the user and recommends a subsequent operation of the user. For example, if the predicted annual salary is greater than the actual annual salary, the diagnostic unit 170 provides employment information to the user, and if the predicted annual salary is less than the actual annual salary, the diagnostic unit 170 has the ability to improve personal ability in the industry. Enhancement information can be provided to the user.

Employment information and ability improvement information can be calculated by referring to data on calculating the annual salary of others corresponding to the actual salary. As described above, a user who wants to inquire the predicted annual salary can input basic information. Here, the basic information includes information on a company in which the user has or is currently employed. The diagnosis unit 170 may calculate the employment information of the current user by referring to basic information of each user who has previously inquired the predicted salary. In addition, a user who wants to inquire the predicted annual salary can input self-development information. Self-development items may include qualifications acquired, work-related awards, language skills, and work-related job skills. The diagnosis unit 170 may calculate the current user's ability improvement information by referring to the self-development items of each user who previously inquired the predicted salary. In addition, the diagnosis unit 170 may calculate employment information and ability improvement information of the current user by referring to information collected by the data collection unit 140 as well as information input from a previous user. Alternatively, the diagnosis unit 170 may recommend a user's subsequent operation using an annual salary graph, as described later. The diagnosis result by the diagnosis unit 170 may be transmitted to the user terminal 200 through the communication unit 110.

The control unit 130 includes a communication unit 110, a first storage unit 121, a second storage unit 122, a data collection unit 140, a predicted annual salary calculation unit 150, a cost input determination unit 160, and a diagnosis. Overall control of the unit 170 is performed.

Meanwhile, in the present specification, "~ unit" (or "module") includes a unit composed of hardware, software, or firmware, and is interchangeably compatible with terms such as logic, logic blocks, parts, or circuits. Can be used. The “~ unit” (or “module”) may be an integrally configured component or a minimum unit that performs one or more functions, or a part thereof. The "~ unit" (or "module") may be implemented mechanically or electronically, for example, known or future development, application-specific integrated circuit (ASIC) chips, FPGAs (field -programmable gate arrays), or programmable logic devices. At least a part of a device (eg, modules or their functions) or a method (eg, operations) according to various embodiments may be a computer-readable storage medium (eg, the first storage unit 121) in the form of a program module. It may be implemented as a command stored in the second storage unit 122. When a command is executed by a processor (e.g., the control unit 130, the data collection unit 140, the predicted annual salary calculation unit 150, the cost input determination unit 160, the diagnosis unit 170, etc.), the processor It can perform the corresponding function. Computer-readable recording media include hard disks, floppy disks, magnetic media (e.g. magnetic tape), optical recording media (e.g. CD-ROM, DVD, magnetic-optical media (e.g., floppy disk)), internal memory, It may include EEPROM, PRAM, RRAM, Flash memory, etc. Instructions may include code generated by a compiler or code that can be executed by an interpreter Module or program module according to various embodiments has the above-described configuration At least one or more of the elements may be included, some may be omitted, or other elements may be further included. Operations performed by a module, a program module, or other elements according to various embodiments may be sequentially and parallelly performed. , Iteratively or heuristically executed, at least some operations may be executed in a different order, omitted, or other operations may be added.

3 is a flowchart illustrating an annual salary prediction method according to some embodiments of the present invention.

Referring to FIG. 3, the predicted annual salary may be calculated step by step. In order to calculate the estimated annual salary for each step, the information input for each step may be different.

Basic information may be input to calculate the first stage predicted annual salary 310. The predicted annual salary calculation unit 150 may calculate the first stage predicted annual salary 310 by referring to the input basic information. An exemplary equation for calculating the first stage predicted annual salary 310 is as follows.

[Equation 1]

는 1 단계 예측 연봉(310)을 나타내고,

는 해당 업종 및 직무에서의 기본 연봉을 나타내고,

~

는 항목별 가중치를 나타내며,

은 1 단계 예측 연봉(310)을 산출함에 있어서 발생할 수 있는 오차를 보상하기 위한 보상 값을 나타낸다.

,

~

및

은 예측 연봉 산출부(150)에 의한 1 단계 예측 연봉(310)의 산출 결과가 누적되면서 갱신될 수 있다.here,

Represents the first-stage predicted annual salary 310,

Represents the basic annual salary in the relevant industry and job,

~

Represents the weight of each item,

Denotes a compensation value for compensating for an error that may occur in calculating the first-stage predicted annual salary 310.

,

~

And

May be updated as a result of calculating the first-stage predicted annual salary 310 by the predicted annual salary calculator 150 is accumulated.

In order to calculate the second-stage predicted annual salary 320, personal development matters and work experience may be input. The predicted annual salary calculation unit 150 may calculate the second predicted annual salary 320 by adding the detailed salary calculated according to the input self-development information and work experience to the first stage predicted annual salary 310. An exemplary equation for calculating the second-stage predicted annual salary 320 is as follows.

[Equation 2]

는 2 단계 예측 연봉(320)을 나타내고,

는 1 단계 예측 연봉(310)을 나타내고,

~

는 항목별 가중치를 나타내며,

은 2 단계 예측 연봉(320)을 산출함에 있어서 발생할 수 있는 오차를 보상하기 위한 보상 값을 나타낸다.

~

및

은 예측 연봉 산출부(150)에 의한 2 단계 예측 연봉(320)의 산출 결과가 누적되면서 갱신될 수 있다. 2 단계 예측 연봉(320)의 신뢰도는 1단계 예측 연봉(310)의 신뢰도보다 개선된다. here,

Represents the two-stage predicted annual salary 320,

Represents the first-stage predicted annual salary 310,

~

Represents the weight of each item,

Represents a compensation value for compensating for an error that may occur in calculating the second-stage predicted annual salary 320.

~

And

May be updated as the calculation result of the second-stage predicted annual salary 320 by the predicted annual salary calculator 150 is accumulated. The reliability of the second-stage predicted salary 320 is improved than that of the first-stage predicted salary 310.

Job aptitude may be input to calculate the three-step predicted annual salary 330. The predicted annual salary calculator 150 may calculate the third predicted annual salary 330 by adding the detailed salary calculated according to the input job aptitude to the second predicted annual salary 320. An exemplary equation for calculating the three-step predicted annual salary 330 is as follows.

[Equation 3]

는 3 단계 예측 연봉(330)을 나타내고,

는 2 단계 예측 연봉(320)을 나타내고,

~

는 항목별 가중치를 나타내며,

은 3 단계 예측 연봉(330)을 산출함에 있어서 발생할 수 있는 오차를 보상하기 위한 보상 값을 나타낸다.

~

및

은 예측 연봉 산출부(150)에 의한 3 단계 예측 연봉(330)의 산출 결과가 누적되면서 갱신될 수 있다. 3 단계 예측 연봉(330)의 신뢰도는 2단계 예측 연봉(320)의 신뢰도보다 개선된다.here,

Represents the three-stage predicted annual salary 330,

Represents the two-stage predicted annual salary 320,

~

Represents the weight of each item,

Denotes a compensation value for compensating for an error that may occur in calculating the 3-step predicted annual salary 330.

~

And

May be updated as the calculation result of the three-step predicted annual salary 330 by the predicted annual salary calculator 150 is accumulated. The reliability of the three-stage predicted salary 330 is improved than that of the second-stage predicted salary 320.

Industry information may be input to calculate the fourth-stage predicted annual salary 340. The four-step annual salary forecast reflects the status of social supply and demand for the business type and job area to be supported (or turnover), industry type and job popularity or trend information according to social issues, and reference check information through acquaintances. It is a step of realistically adjusting the three-stage predicted salary 330 by reflecting. For example, the social demand of big data analysts has recently increased, but if the supply manpower is insufficient, the estimated annual salary can be increased by assigning a certain weight, and the evaluation or recommendation score for the user is high or If it is low, the final estimated annual salary can be appropriately increased or decreased. However, since the evaluation/recommendation information through the reference person is optional, the user may not input it.

The predicted annual salary calculation unit 150 may calculate the fourth stage predicted annual salary 340 by adding the detailed annual salary according to the inputted industry information to the third stage predicted annual salary 330. An exemplary equation for calculating the four-step predicted annual salary 340 is as follows.

[Equation 4]

는 4 단계 예측 연봉(340)을 나타내고,

는 3 단계 예측 연봉(330)을 나타내고,

~

는 항목별 가중치를 나타내며,

은 4 단계 예측 연봉(340)을 산출함에 있어서 발생할 수 있는 오차를 보상하기 위한 보상 값을 나타낸다. 또한, 참조인 추천 점수는 사용자를 취업에 추천한 추천자에 의하여 부여된 점부로서, 이는 사용자에 의하여 입력될 수 있다.

~

및

은 예측 연봉 산출부(150)에 의한 4 단계 예측 연봉(340)의 산출 결과가 누적되면서 갱신될 수 있다. 4 단계 예측 연봉(340)의 신뢰도는 3단계 예측 연봉(330)의 신뢰도보다 개선된다.here,

Represents the four-stage predicted annual salary 340,

Represents the three-stage predicted annual salary 330,

~

Represents the weight of each item,

Denotes a compensation value for compensating for an error that may occur in calculating the 4-step predicted annual salary 340. In addition, the reference score is a point assigned by a recommender who recommends the user for employment, which may be input by the user.

~

And

May be updated as the result of the calculation of the four-step predicted annual salary 340 by the predicted annual salary calculator 150 is accumulated. The reliability of the four-stage predicted annual salary 340 is improved than that of the three-stage predicted annual salary 330.

In the annual salary prediction method according to some embodiments of the present invention, the predicted salary 310 to 340 may be changed according to the amount or type of inputted salary calculation data. In particular, as the annual salary calculation data are inputted in stages, the optimal predicted annual salary (310 to 340) is calculated based only on the input annual salary calculation data. In other words, even if all necessary annual salary calculation data are not entered (i.e., basic information, self-development information, work experience, job aptitude, industry information, etc. are not all entered), even with only the input annual salary calculation data (for example, , When only basic information, self-development matters, and work experience are input), the predicted salary (for example, the second-stage predicted salary 320) is estimated.

In addition, as the predicted annual salary is calculated step by step (310 to 340), the reliability (or accuracy) of the predicted annual salary may gradually increase. For example, the reliability of the first-stage predicted salary 310 is about 60%, the reliability of the second-stage predicted salary 320 is about 70%, and the reliability of the third-stage predicted salary 330 is about 80%, and 4 The reliability of the step prediction annual salary 340 may be about 90% or more. As various user-related information is used more, the reliability of the predicted annual salary 310 to 340 for each step may gradually increase.

While presenting the predicted annual salary of the current stage to the user (eg, the predicted annual salary of the first stage), the reliability (eg, about 60%) can be presented at the same time. In addition, by inputting additional information, users can be informed that they can estimate the predicted annual salary with higher reliability (for example, "If you enter the self-development and work experience required for the second-stage predicted salary, about 70% You can tell that you can check the predicted salary with the above reliability.) In this way, it is possible to induce a user to pay a cost in order to receive a predicted annual salary of higher reliability (accuracy).

Subsequently, evaluation/diagnosis may be performed based on the predicted annual salary calculated for each step. In the case of current workers, the gap is analyzed based on the current salary and the predicted salary calculated through the salary prediction device 100, and recommends a suitable job or a new job, or adds consulting for career development. You can also offer services. Alternatively, in the case of a job seeker without work experience, a similar supplementary service may be presented by analyzing the difference based on the desired salary and the estimated salary calculated through the salary prediction apparatus 100. A more detailed description of this will be described later with reference to FIGS. 4 to 6.

Meanwhile, in FIG. 3, for convenience of explanation, it has been described that the data for calculating annual salary are input in the order of basic information, self-development items and work experience, job aptitude, and industry information, but the present invention is not limited thereto. For example, data for calculating annual salary may be input in the order of basic information, job aptitude, industry information, self-development information, and work experience.

4 is an annual salary graph for explaining the relationship between the predicted salary and the actual salary. 5 and 6 are views showing an example of application of the annual salary graph of FIG. 4.

Referring to FIG. 4, an annual salary graph 400 may represent a process relationship between a predicted salary and an actual salary. For example, if the predicted annual salary calculated by the predicted annual salary calculation unit 150 and the actual annual salary that the user is actually paid are on the annual salary graph 400, the user may be considered to be receiving a fair annual salary. have.

The graph plane may be divided into two areas A1 and A2 by the annual salary graph 400. Hereinafter, an area close to the predicted annual salary axis based on the annual salary graph 400 is referred to as a first area A1, and an area close to the actual salary axis is referred to as a second area A2.

Depending on which region of the first region A1 and the second region A2 is mapped to the intersection of the predicted annual salary calculated by the predicted annual salary calculation unit 150 and the actual annual salary that the user is actually paid, the diagnosis unit 170 ) Can provide different diagnostic results.

Referring to FIG. 5, an intersection point P1 between the predicted annual salary ES and the actual annual salary RS1 may be mapped to the first area A1.

It can be understood that the fact that the intersection point P1 of the predicted salary ES and the actual salary RS1 is mapped to the first area A1 is that the user is being paid less than the actual value of the user. Accordingly, the diagnosis unit 170 may provide employment information. That is, the predicted annual salary of the user is ES, and the actual annual salary is RS1, and the diagnosis unit 170 provides information on a company that provides RS2, which is an actual annual salary corresponding to the ES, by referring to the annual salary graph 400. Employment information can be calculated by referring to other people's basic information.

Referring to FIG. 6, an intersection point P2 between the predicted annual salary ES1 and the actual annual salary RS may be mapped to the second area A2.

It can be understood that the fact that the intersection point P2 of the predicted salary ES1 and the actual salary RS is mapped to the second area A2 is that the user is receiving a higher salary than the actual value of the user. Accordingly, the diagnosis unit 170 may provide capability improvement information. That is, the predicted annual salary of the user is ES1, and the actual annual salary is RS, and the diagnosis unit 170 provides the ability improvement information to achieve ES2, which is a predicted annual salary corresponding to RS, by referring to the annual salary graph 400. The ability improvement information may be calculated by referring to basic information of another person.

7 is a diagram illustrating an operation of the predicted annual salary calculation unit shown in FIG. 2.

Referring to FIG. 7, the predicted annual salary calculation unit 150 may calculate a predicted annual salary using a plurality of machine learning algorithms 510 to 540.

The plurality of machine learning algorithms 510 to 540 may include a multilinear regression algorithm, a multilayer perceptron algorithm, a regression tree algorithm, and a model tree algorithm.

The multiple linear regression algorithm is an algorithm that models the 　linear 　 correlation relationship between the dependent variable and two or more independent variables or explanatory variables, and estimates the regression model by least squares method.

Multilayer Perceptron Algorithm is a machine learning algorithm that can be used for both numerical and categorical predictions as a model having a hierarchical structure as at least one hidden layer exists between an input layer that receives an independent variable and an output layer that outputs a dependent variable. The multilayer perceptron algorithm is a kind of nonlinear regression model and works by nonlinearizing the values of each layer and passing them to the next layer.

The Regression Tree Algorithm is an algorithm modified so that the Decision Tree algorithm that performs classification prediction can be used for numerical prediction. Like a general decision tree, data is classified using the division and conquer method, but the classification is not performed at the terminal node, but numerical prediction is performed based on the average value of the corresponding node.

The model tree algorithm, like the regression tree algorithm, is one of the decision tree algorithms that can predict numerical values. Unlike the regression tree algorithm that performs numerical prediction based on the average value at each terminal node, the model tree algorithm includes a separate multiple linear regression model for numerical prediction at each terminal node.

The predicted annual salary calculation unit 150 compares a plurality of predicted annual salaries calculated by using a plurality of machine learning algorithms 510 to 540 with an actual measured annual salary in the past, and calculates the predicted annual salary of a machine learning algorithm representing the smallest error. It can be calculated as the final estimated salary.

When the annual salary calculation data is input, the predicted annual salary calculation unit 150 may calculate a plurality of predicted annual salaries using a plurality of machine learning algorithms 510 to 540. The plurality of predicted annual salaries calculated in this way may be compared with an actual measured annual salary (hereinafter, referred to as an existing measured annual salary). For example, the annual salary calculation data similar to the input annual salary calculation data is used and compared with the previously calculated annual salary calculation. Thus, the predicted annual salary calculation unit 150 may calculate a predicted annual salary that is most similar to the existing measured annual salary among the plurality of predicted annual salaries as the final predicted annual salary.

A mean square error (MSE) according to the following equation may be used to compare the current estimated salary and the existing measured salary.

[Equation 5]

은 예측 연봉을 나타내며,

는 i번째 기존 측정 연봉을 나타낸다.Here, MSE represents the average squared error between the estimated annual salary and the existing measurement annual salary, n represents the number of existing measurement annual salaries,

Represents the estimated annual salary,

Represents the i-th existing measured annual salary.

According to Equation 5 above, an average square error with a plurality of existing measured annual salaries is calculated for each of the plurality of predicted annual salaries, and the predicted annual salary calculation unit 150 uses the predicted annual salary having the smallest average square error as the final predicted annual salary. Can be calculated.

Although the embodiments of the present invention have been described with reference to the above and the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can implement the present invention in other specific forms without changing the technical spirit or essential features. You can understand that there is. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting.

10: annual salary prediction system 100: annual salary prediction device
110: communication unit 121: first storage unit
122: second storage unit 130: control unit
140: data collection unit 150: predicted annual salary calculation unit
160: cost input determination unit 170: diagnosis unit
200: user terminal 400: salary graph

Claims (6)

In the annual salary prediction method performed by a computing device,
Receiving data for calculating a first annual salary for a user;
Calculating a first predicted annual salary of the user based on the first annual salary calculation data;
After calculating the first predicted annual salary, presenting a first predicted annual salary and a first reliability level of the first predicted annual salary to a user;
Notifying a user that if a second annual salary calculation data different from the first annual salary calculation data is provided, a second predicted annual salary having a second reliability higher than the first reliability may be provided;
Receiving the second annual salary calculation data; And
Calculating a second predicted annual salary of the user based on the first annual salary calculation data and the second annual salary calculation data;
Including the step of providing the second predicted annual salary to the user,
Each of the data for calculating the first annual salary and the data for calculating the second annual salary includes any one of basic information about a user, self-development, work experience, job aptitude, and industry information,
Basic information, self-development, work experience or job aptitude for the user is entered by the user through the user terminal,
The industry information is collected by accessing an external database, an annual salary prediction method. delete delete delete The method of claim 1,
In the calculating of the first predicted annual salary or the calculating of the second predicted annual salary, a predicted annual salary is calculated using a plurality of machine learning algorithms,
The annual salary prediction method of comparing a plurality of predicted salaries calculated by using the plurality of machine learning algorithms with previously measured salaries to calculate a predicted salary of a machine learning algorithm indicating the smallest error as a final predicted salary. The method of claim 1,
Comparing the calculated first predicted annual salary or the second predicted annual salary with the actual annual salary of the user, and recommending a subsequent operation of the user,
The step of recommending the user's follow-up operation includes providing employment information when the predicted annual salary is greater than the actual annual salary,
A method of predicting an annual salary comprising providing competency improvement information to improve an individual's ability in the industry when the predicted salary is less than the actual salary.

Images