JP2021022360A - Device and method for planning to place recruitment advertisement, and program therefor - Google Patents

Abstract

To provide a method for planning to place a recruitment advertisement in one or more job sites and predicting effects of the recruitment advertisement.SOLUTION: An advertisement placing device 101 determines past recruitment advertisements whose similarity to a recruitment advertisement to be placed is greater than or equal to a prescribed level, such as a prescribed value (S201). The device then determines a cost of placing, in each job site, the recruitment advertisement to be placed (S202). Then, for the determined one or more past recruitment advertisements and for each job site, the device calculates cost effectiveness based on the placing cost and the number of applicants who have proceeded in screening to an applicant status greater than or equal to a prescribed level, such as passing paper screening (S203).SELECTED DRAWING: Figure 2

Description

The present invention relates to a device, a method and a program for planning the placement of a job advertisement, and more specifically, a device, a method and a program for planning the placement of a job advertisement on one or more job sites. Regarding.

The placement of job advertisements is shifting from paper media to job sites on the Internet. There are various types of job sites, which are affected by the diversification of work styles, and companies are often using multiple job sites at the same time.

Recruiters of companies can decide which recruiting site and how much budget to place an advertisement based on their own experience, and also ask a recruiting agency to advertise media. Selection, creation of advertising manuscript, and placement.

In either case, at present, the recruiting company has not been able to make a judgment based on the data when placing a job advertisement. There is no practical method for making a quantitative judgment as to how much budget should be allocated to which medium and how much recruitment can be expected.

The present invention has been made in view of such problems, and an object thereof is a device, a method, and a program for planning the placement of a job advertisement on one or a plurality of job sites. Is to predict the effect of.

In order to solve such a problem, the first aspect of the present invention is a method for planning the placement of a job advertisement on one or a plurality of job sites, and the past corresponding to the job advertisement to be placed. A step of determining one or more job advertisements, a step of determining the placement cost of the job advertisement scheduled to be placed for each of the one or more job sites, and the past one or more determined for each job site. It is characterized by including a step of calculating cost effectiveness based on the number of applications for which selection has progressed to a predetermined level or higher in a plurality of job advertisements and the placement cost.

Further, in the second aspect of the present invention, in the first aspect, the determination of the past one or more job advertisements corresponding to the job advertisements scheduled to be placed has a similarity with the job advertisements scheduled to be placed. It is characterized in that it is performed on condition that it is above a certain level.

Further, in the third aspect of the present invention, in the second aspect, the degree of similarity between the job advertisement to be posted and the past job advertisement is determined by adding the item related to the job content of the job advertisement to the job advertisement. It is characterized by calculating based on the description of items related to the company information of the recruiting company to be posted.

In addition, a fourth aspect of the present invention is characterized in that, in the third aspect, the company information includes at least one of the year of establishment or the date of establishment, the capital stock, and the number of people.

Further, in the fifth aspect of the present invention, in any one of the first to fourth aspects, the posting time of the job advertisement scheduled to be posted is similar according to the rate of change in the number of accesses or the number of applications to each job site. It is characterized in that the weighting in the degree calculation is different.

Further, in the sixth aspect of the present invention, in any one of the first to fifth aspects, whether or not each application has progressed to the application status of the predetermined level or higher is collected from the one or a plurality of recruiting sites. It is characterized in that the determination is made based on the application status of each application for one or more of the past determined job advertisements.

Further, the seventh aspect of the present invention is characterized in that, in the sixth aspect, the application status of the predetermined level or higher is equal to or higher than the document screening pass.

Eighth aspect of the present invention is a program for causing a computer to execute a method for planning the placement of a job advertisement on one or a plurality of job sites, and the method is a job advertisement to be placed. A step of determining one or more past job advertisements corresponding to the above, a step of determining the placement cost of the one or more job advertisements scheduled to be placed for each of the above one or more job sites, and a step of determining each job site. It is characterized by including a step of calculating cost effectiveness based on the number of applications for which selection has progressed to a predetermined level or higher in the past one or more job advertisements and the placement cost.

A ninth aspect of the present invention is a device for planning the placement of job advertisements on one or more job sites, and determines one or more past job advertisements corresponding to the job advertisements scheduled to be placed. Then, the placement cost of the job advertisement scheduled to be placed for each of the one or more job sites is determined, and for each job site, the application status of the determined past one or more job advertisements is equal to or higher than a predetermined level. It is characterized in that the cost effectiveness is calculated based on the number of applications that have been selected up to and the above-mentioned placement cost.

Further, a tenth aspect of the present invention is a method for placing a job advertisement on one or a plurality of job sites, and a step of determining a past one or a plurality of job advertisements corresponding to the job advertisement to be placed. And the step of determining the placement cost of the job advertisement scheduled to be placed for each of the one or more job sites, and for each job site, the determined level or more in the past one or more job advertisements determined. Based on the step of calculating the cost-effectiveness based on the number of applications that have been selected up to the application status and the advertisement cost, and the cost-effectiveness calculated according to the budget of the advertisement or the desired effect. It is characterized by including a step of determining the placement amount or the placement period of the job advertisement to be posted on each job site.

According to one aspect of the present invention, the number of applications on each job site where selection has progressed to a predetermined level or higher, such as passing document screening, in one or more past job advertisements corresponding to the job advertisements scheduled to be placed. By calculating the cost-effectiveness based on the above and the placement cost for each job site, it is possible to predict the effect of the job advertisement based on the data when placing the job advertisement.

It is a figure which shows the advertising apparatus which concerns on one Embodiment of this invention. It is a figure which shows the flow of effect prediction concerning one Embodiment of this invention. It is a figure which shows an example of the job advertisement which concerns on one Embodiment of this invention. It is a figure which shows an example of the result display of the effect prediction which concerns on one Embodiment of this invention.

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

FIG. 1 shows a system according to an embodiment of the present invention. The system 100 determines the application status of the applicant for the job advertisement posted on the one or more job sites 110 and the placement device 101 for placing the job advertisement on at least one of the one or the plurality of job sites 110. It is provided with a management device 102 for collecting and managing applicants. The job advertisement may be received by the advertising device 101 from the terminal 120 used by the recruiting company, or may be created on the website provided by the advertising device 101. Here, the number of recruiting sites is 3, but in reality, one company may use double-digit number of recruiting sites. Further, the device 101 referred to in the present specification as the "posting device" is a device for planning a posting before posting, and it is conceivable that the actual posting is performed by another device or a person.

The application status of each applicant includes unsupported, document screening, passing document screening, passing the first interview, passing the second interview, unofficial decision, joining the company, and so on. When an application is input from the applicant terminal 130 used by the applicant, the application status may be automatically changed during document selection on the recruiting site 110. Alternatively, the application status may be changed by the recruiting company that has placed the job advertisement by inputting the change on the recruiting site 110. The application status at each of these recruiting sites is collected by the management device 120.

In order for the management device 102 to collect the application status of each applicant from the recruiting site 110 for each recruiting company, it is often necessary to log in to the account of each recruiting company for the recruiting site 110, and in one embodiment, It is assumed that the login information for each recruiting site of each recruiting company is stored in the storage medium or storage device accessible from the storage unit or the management device 102. The login information is generally composed of an ID and a password. Alternatively, in another embodiment, the application status can be referred to by storing the application status collected in some form in the storage unit of the management device 102 or a storage medium or storage device accessible from the management device 102. Good. Here, the login information can be more generally an authentication information, and may be a token, an API key, or the like for authenticating access to the account of each recruiting company on the recruiting site 110.

As an example, the authentication information can be stored by the recruiting company logging in to the website provided by the management device 102 with its own account and setting the recruiting site for collecting information.

The issuing device 101 includes a communication unit 101-1 such as a communication interface, a processing unit 101-2 such as a processor and a CPU, and a storage unit 101-3 including a storage device such as a memory and a hard disk or a storage medium. It can be configured by executing a program to perform processing and may include one or more devices or servers. The program may also include one or more programs and may be recorded on a computer-readable storage medium to be a non-transient program product. The program can be stored in a storage device or storage medium accessible from the storage unit 103 or the device 100, and executed in the processing unit 102. Although not shown, the management device 102 may have the same configuration as the issuing device 101.

In FIG. 1, the system 100 shows the first device 101 and the second device 102 as separate devices, but these may be the same device. Conversely, these may be separate devices and operated by separate companies.

In the advertising device 101, it is necessary to be able to access the past application status collected and managed by the management device 102 in order to predict the effect when the job advertisement is advertised. Hereinafter, the effect prediction of the job advertisement using the application status managed by the management device 102 will be described. However, as described above, when the management device 102 is the same device as the advertising device 101, the advertising device 101 , The application status stored in the storage medium or the storage device accessible from the storage unit 101-3 or the advertising device 101 will be accessed.

First, the advertising device 101 determines past job advertisements having a similarity with a job advertisement scheduled to be placed to a predetermined level such as a predetermined value (S201). Next, the cost of placing the job advertisement to be placed on each job site is determined (S202). Next, for one or more of the determined past job advertisements, the cost-effectiveness is calculated based on the number of applications that have been selected to the application status above a predetermined level and the placement cost for each job site (S203). .. As an example, the cost-effectiveness can be calculated as an individual cost-effectiveness for each of the past job advertisements and as an average value for each job site.

For example, the advertising device 101 sets the above-mentioned predetermined level of similarity according to a numerical value such as 75% or a degree such as B out of five stages A to E, and the similarity with the job advertisement scheduled to be advertised is equal to or higher than the predetermined level. The job advertisement is determined from the past job advertisements stored in the storage unit or the storage medium or the storage device accessible from the storage unit 102. The job advertisement is as shown in FIG. 3, for example, and includes items related to the job content such as job outline, condition outline, and recruitment criteria. The similarity can be calculated based on a predetermined rule, and examples of the rule include a calculation model generated by machine learning.

In calculating the degree of similarity, it is preferable to consider the degree of similarity between the company information of the recruiting company in addition to the degree of similarity between the job contents of the job advertisement itself. The accuracy of the similarity of job advertisements is improved by providing that the company information such as the year of establishment or the date of establishment, capital, number of people, etc. is similar. Even if the job description is similar, such as job type sales, annual income of 6 million yen, and work location Tokyo, for example, the actual job content differs between a company with capital of 10 million yen and a company with 100 billion yen, and the items related to the job offer are described. This is because it is often difficult to clearly distinguish between them.

Since the effect of job advertisements is affected by the timing of placement, it is useful to use similar evaluation parameters for the similarity of job advertisements scheduled to be placed. As an example, ads placed around the same time last year may be rated higher than ads placed at other times. On the other hand, as another example, in the case of an emerging recruiting site that has not been opened for a long time, the number of site accesses or applications in the same period last year and the current number of site accesses or applications are significantly different. It may not be suitable for comparison. Therefore, as an example, if the rate of change in the number of applications is less than the specified value, the advertisement placed in the same period last year will be highly evaluated, and if it is above the specified value, the advertisement placed in the last few months will be highly evaluated. The evaluated similarity calculation can be considered. More generally, it is conceivable that the weighting in the similarity calculation of the posting time will be different depending on the rate of change in the number of accesses or the number of applications to the recruiting site. The unit of change rate includes various units such as month and year.

The placement cost is generally determined for each job site according to the posting period of the job advertisement, etc., and the placement device 101 is a storage medium or storage accessible from the storage unit 101-3 or the placement device 101. It is possible to determine the placement cost of the job advertisement scheduled to be placed by referring to the placement cost data of each job site stored in the device. The advertisement cost data may be stored in the management device 102. In addition, it is conceivable that the placement cost data is manually input for each of the past job advertisements. It is conceivable to calculate the placement cost of each job site based on the placement cost data input for one or more past job advertisements corresponding to the job advertisements scheduled to be placed. There are paid and free recruiting sites, but in the present embodiment, it is preferable that the posting destination is a paid recruiting site that incurs a posting cost.

As shown in FIG. 4, for example, the cost-effectiveness calculation result can be displayed on the display screen of the terminal for the advertiser of the job advertisement. Whether or not to pass the interview after the document screening tends to depend more on the recruitment criteria of the recruiting company than the effectiveness of the recruiting site, and it is a recruiting site that can effectively attract good applicants. It is conceivable to evaluate whether or not there is, based on the number of passing document selections, and in the present embodiment, this is possible by using the application status managed by the management device 102. In this way, it is preferable to use the number of documents that have passed the screening as a standard, but it excludes the possibility of additional or alternative calculation of cost-effectiveness based on other numerical values such as the number of applications, internal constants, and number of employees. It's not a thing.

As described above, by referring to the results of past job advertisements corresponding to the job advertisements scheduled to be placed when considering placement, it is possible to predict the effect of job advertisements for which it has been difficult to make a quantitative judgment. Is possible.

Once the cost-effectiveness of each job site is calculated, the recruiting company can determine based on the data how much budget to allocate to which job site according to the placement budget of the job advertisement. , The advertising device 101 can determine the advertising amount or the advertising period for each recruiting site. Alternatively, it is possible to determine the placement amount or placement period for each recruiting site according to the effect determined by the recruiting company. For example, if the number of applications that pass the document screening is set to 100 or more, the posting device 101 predicts how many postings will be made on each recruiting site, or how long the posting will be to obtain the desired effect. can do. Further, it is conceivable that the recruiting company determines the budget and the effect, and the advertising device 101 determines the advertising amount or the advertising period for each recruiting site.

In the above explanation, the past job advertisements that are similar to the job advertisements scheduled to be placed are judged, but the past job advertisements corresponding to the job advertisements scheduled to be placed are judged based on a standard different from the degree of similarity. Can be considered. As an example, it is a condition that the job type of the job advertisement is the same, or that the place of work is the same. It is also possible to use the job type, work location, etc. as parameters for determining the similarity.

In addition, unless there is a description of "only" such as "based on XX only", "according to XX only", and "in the case of XX only", additional information is provided in this specification. Note that it is assumed that also can be considered. Also, as an example, it should be noted that the description "b in the case of a" does not necessarily mean "always b in the case of a".

Further, just in case, even if some method, program, terminal, device, server or system (hereinafter referred to as “method”) has an aspect of performing an operation different from the operation described in the present specification, each of the present inventions The aspect is intended to be the same operation as any of the operations described in the present specification, and the existence of an operation different from the operation described in the present specification means that the method and the like are described in each of the present inventions. It is added that it is not outside the scope of the aspect.

100 System 101 Advertising device 101-1 Communication unit 101-2 Processing unit 101-3 Storage unit 102 Management device 110 Recruiting site 120 Recruiting company terminal 130 Applicant terminal

Claims (7)

A computer is a way to plan the placement of classified ads on multiple job sites.
Steps to determine multiple past job advertisements corresponding to the job advertisements to be placed, and
A step of determining the placement cost of the job advertisement to be placed for each of the plurality of job sites, and
For each job site, including the step of calculating the cost-effectiveness based on the number of applications that have been selected to the application status above a predetermined level in the past multiple job advertisements judged and the placement cost.
Judgment of the plurality of job advertisements in the past corresponding to the job advertisements scheduled to be posted is performed on the condition that the similarity with the job advertisements scheduled to be posted is at least a certain level.
To calculate the similarity between the job advertisement scheduled to be placed and the past job advertisement, in addition to the description of the item related to the job content of the job advertisement, the establishment year or the establishment date and capital of the recruiting company that publishes the job advertisement. And a method characterized by performing based on the description of items related to company information including at least one of the number of people. A computer is a way to plan the placement of classified ads on multiple job sites.
Steps to determine multiple past job advertisements corresponding to the job advertisements to be placed, and
A step of determining the placement cost of the job advertisement to be placed for each of the plurality of job sites, and
For each job site, including the step of calculating the cost-effectiveness based on the number of applications that have been selected to the application status above a predetermined level in the past multiple job advertisements judged and the placement cost.
Judgment of the plurality of job advertisements in the past corresponding to the job advertisements scheduled to be posted is performed on the condition that the similarity with the job advertisements scheduled to be posted is at least a certain level.
The calculation of the degree of similarity between the job advertisement scheduled to be placed and the past job advertisement includes an evaluation of the degree of similarity at the time of publication. Whether or not each application has progressed to the application status above the predetermined level is based on the application status of each application for the determined past one or more job advertisements collected by the computer from the plurality of job sites. The method according to claim 1 or 2, wherein the determination is made. The method according to claim 3, wherein the application status of the predetermined level or higher is equal to or higher than the document screening. A program for causing a computer to execute a method for planning the placement of job advertisements on multiple job sites.
Steps to determine multiple past job advertisements corresponding to the job advertisements to be placed, and
A step of determining the placement cost of the job advertisement to be placed for each of the plurality of job sites, and
For each job site, including the step of calculating the cost-effectiveness based on the number of applications that have been selected to the application status above a predetermined level in the past multiple job advertisements judged and the placement cost.
A program characterized in that the determination of the plurality of job advertisements in the past corresponding to the job advertisement scheduled to be placed is performed on the condition that the degree of similarity with the job advertisement scheduled to be placed is at least a certain level. It is a system for planning the placement of job advertisements on multiple job sites.
Judge multiple past job advertisements corresponding to the job advertisements scheduled to be placed,
Judging the placement cost for each of the plurality of job sites of the job advertisement scheduled to be placed,
For each job site, the cost-effectiveness is calculated based on the number of applications that have been selected to the application status above a predetermined level in the past multiple job advertisements judged and the placement cost.
A system characterized in that the determination of the plurality of job advertisements in the past corresponding to the job advertisement scheduled to be posted is performed on the condition that the degree of similarity with the job advertisement scheduled to be posted is at least a certain level. It's a way to place job ads on multiple job sites,
Steps to determine multiple past job advertisements corresponding to the job advertisements to be placed, and
A step of determining the placement cost of the job advertisement to be placed for each of the plurality of job sites, and
For each job site, a step to calculate the cost-effectiveness based on the number of applications that have been selected to the application status above a predetermined level in the past multiple job advertisements judged and the placement cost.
Including a step of determining the placement amount or placement period of the job advertisement to be placed on each job site based on the calculated cost-effectiveness according to the budget of the placement or the target effect.
A method characterized in that the determination of the plurality of job advertisements in the past corresponding to the job advertisement scheduled to be posted is performed on the condition that the degree of similarity with the job advertisement scheduled to be posted is at least a certain level.

Images