Personalization-based talent skill recommendation system

Abstract

The invention discloses a personalized talent skill recommendation system, which relates to the technical field of post recommendation and comprises a recruiter data module, a post data module, a feature construction module, a habit effect module, a post matching module, a personalized module, a recommendation module and a coming and going cost module. The system has the advantages that the feature vectors of the recruiters and the posts are constructed through the feature construction module, the characteristics of the recruiters and the posts can be known more accurately, the post matching accuracy is improved, the habit effect module analyzes the influence of the habits of the employees on the employment cycle in the past, reference can be provided for the recruiters and enterprises, and the employment period is improved. According to the method, the situation in work can be better predicted and adapted, the matching quality of the recruiter and the post can be improved, the recommended post can better meet the expectation of the recruiter, and the recruiter can comprehensively consider the cost factor and make a more reasonable decision when selecting the post.

Description

Technical Field

[0001] The present invention relates to the technical field of job recommendation, and in particular to a talent skill recommendation system based on personalization. Background Art

[0002] With the rapid development of the global economy, various industries are constantly upgrading and transforming. Emerging industries such as artificial intelligence, big data, and new energy are booming, and traditional industries are also undergoing transformation under the wave of digitalization and intelligence. These changes in industries have had a huge impact on the skill requirements of talents, and more accurate talent skill job matching is needed to meet the needs of industrial development. The mobility of the labor market is constantly increasing, and the flow of talents is more frequent. On the one hand, job seekers' expectations for their own career development are constantly increasing, and they are eager to find positions that are highly matched with their own skills and interests. On the other hand, in order to stand out in the fierce market competition, companies are becoming more and more strict in selecting talents and have higher requirements for the accuracy of job matching.

[0003] The general talent skill recommendation systems on the market only match based on simple resume keywords or basic job descriptions. It is difficult to accurately find the most suitable match. It does not fully consider comprehensive factors such as the recruiter's expectations for the job and the job's adaptability to the recruiter, resulting in low matching quality. For this reason, we propose a personalized talent skill recommendation system. Summary of the invention

[0004] The purpose of the present invention is to provide a talent skill recommendation system based on personalization.

[0005] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a personalized talent skill recommendation system, comprising a recruiter data module and a job data module, wherein the recruiter data module can collect basic information of recruiters, and the job data module can analyze job demand information in the current market, and further comprises a feature construction module, a habit performance module, a job matching module, a personalization module and a recommendation module;

[0006] The feature construction module establishes an extraction unit and constructs the feature vectors of the recruiter and the position based on the extraction unit information, the basic information of the recruiter and the position requirement information;

[0007] The habit effectiveness module obtains the employment information of previous positions, thereby obtaining the information of previous employees, and analyzes the skill habits of the previous employees and the employment cycle information during the employment period, and analyzes the impact of the different habits of previous employees on the employment cycle information;

[0008] The job matching module uses collaborative filtering recommendation information and content-based recommendation information to analyze the match between recruiters and jobs;

[0009] The personalized module extracts the personalized needs of recruiters and establishes an external expansion unit. Recruiters can edit the information in the external expansion unit independently, so that the recommended job information better meets the needs of recruiters;

[0010] The recommendation module generates a job recommendation list based on matching ranking, and establishes a recruiter feedback unit to collect recruiters' opinions on the job recommendation list.

[0011] As a further solution of the present invention, it also includes a travel cost module, which has a distance cost unit, a time cost unit and a vacation cost unit. The distance cost unit and the vacation cost unit are used to calculate the travel cost of the recruiter during employment.

[0012] As a further solution of the present invention: when the feature construction module constructs the feature vectors of the recruiter and the position, the extraction unit will perform feature extraction on the recruiter's information, and at the same time, the extraction unit has basic extraction functions and advanced extraction functions set up inside, wherein the feature extraction types in the basic extraction function are the recruiter's skill keyword information, work experience years information, project experience type information and work location information, as well as the skill keyword information, work experience years information, project experience type information and work location information required for the position, wherein the information in the advanced extraction function needs to be edited independently by both the recruiter and the administrator.

[0013] As a further solution of the present invention: the habit performance module can extract various job requirement information, thereby retrieving the previous employment status of various jobs, thereby obtaining the employment information of previous employees when they were employed and the habit information of previous employees, and analyzing the habit information suitable for employment in various jobs, thereby analyzing the impact of different habits of previous employees on the employment cycle information, wherein the employment cycle information refers to the learning cycle, adaptation cycle and proficiency cycle of previous employees during the period of the job.

[0014] As a further solution of the present invention: the job matching module can receive information processed by the feature building module and obtain the influence of different habits on the employment cycle information, wherein the content-based recommendation information can analyze the item information of the recruiter's past habits, and then extract the employment feature information therefrom, and then analyze the item information associated with various job information, and then extract the job feature information therefrom, so as to determine the job information related to the employment feature information;

[0015] The collaborative filtering recommendation information includes recruiter collaborative filtering and item collaborative filtering;

[0016] Recruiter collaborative filtering is to make recommendations based on the similarity between recruiters, find other recruiters who are related to the interests of the target recruiter, and recommend their favorite items to the target recruiter;

[0017] Item collaborative filtering recommends items based on the similarity between items, finding other items related to the items that the target recruiter likes and recommending them;

[0018] Then, the matching degree between the recruiter and the position is comprehensively analyzed based on the collaborative filtering recommendation information and the content-based recommendation information;

[0019] The convolutional neural network in deep learning is used to perform deep feature encoding on the job description text and the recruiter's resume text to improve the matching accuracy.

[0020] As a further solution of the present invention, the personalized module can extract different habit information of the recruiter, and at the same time set a personalized input function, through which the recruiter can input his or her desired conditions into the personalized module, and then the personalized module will convert the desired conditions into habit information, and set the different habit information suitable for the position as J Z =J1, J2, J3, ..., J D , let the habit information of the employee be Y Z =Y1, Y2, Y3, ..., Y G , let the habit information matching the position be X P , let D be the number of different habit information suitable for the job;

[0021] X P =J Z ∩Y Z =(J1, J2, J3, ..., J D )∩(Y1, Y2, Y3,…,Y G

[0022] According to the above formula, the habit information that matches the position can be calculated, and then the number of habit information that matches the position can be analyzed. Suppose the number of habit information that matches the position is G S , let the custom matching value of the position be X 匹 ;

[0023]

[0024] According to the above formula, the habit matching value of the position can be calculated.

[0025] As a further solution of the present invention: the recommendation module can receive information processed by the personalization module, so as to obtain the habitual matching value information of the position and the matching degree information between the recruiter and the position, and then draw a recommendation list according to the habitual matching value and the matching degree information between the recruiter and the position, and display the recommendation list to the recruiter.

[0026] As a further solution of the present invention: the distance cost unit in the travel cost module accesses the recruiter data module and the recommendation module to obtain the location information of the recruiter and the location information of the recommended positions in the recommendation list, and then obtains the distance between the location information of the recruiter and the location information of the recommended positions in the recommendation list, and connects with the traffic software to calculate the traffic cost, and the recruiter can modify the location information of the recruiter and display the traffic time;

[0027] The vacation cost unit can obtain the vacation information of the position, so as to analyze the economic loss caused by the vacation to the recruiter and calculate the vacation cost;

[0028] Then, the travel costs of the recruiter during employment are comprehensively calculated based on transportation costs and vacation costs, and the travel costs are displayed.

[0029] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0030] 1. The present invention constructs feature vectors of recruiters and positions through feature construction modules, which helps to more accurately understand the characteristics of recruiters and positions, thereby improving the accuracy of position matching. The habit effectiveness module analyzes the impact of the habits of previous employees on the employment cycle, which can provide references for recruiters and enterprises, better predict and adapt to work situations, and improve the matching quality of recruiters and positions, so that the recommended positions are more in line with the expectations of recruiters, so that recruiters can comprehensively consider cost factors when selecting positions and make more reasonable decisions;

[0031] 2. The present invention can better meet personalized needs through the feature construction module, and can find out habits suitable for different positions by using the habit performance module, which can provide reference for recruiters and enterprises, and help improve employees' adaptability and work efficiency in their positions. The position matching module can combine collaborative filtering recommendation information and content-based recommendation information for comprehensive analysis, and can consider the matching degree between recruiters and positions from multiple angles, thereby improving the accuracy and reliability of recommendations;

[0032] 3. The present invention can extract different habit information of recruiters through the personalization module, so as to more accurately calculate the habit information that matches the position and the habit matching value of the position. The recommendation module helps recruiters to have a more comprehensive understanding of the positions that suit them, thereby improving the efficiency and satisfaction of recruitment. The transaction cost module can enable recruiters to have a clearer understanding of the actual transaction cost of the position, which helps recruiters to comprehensively consider various cost factors of the position, so that recruiters can more comprehensively evaluate the cost-effectiveness of the position and make more wise choices. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Schematic diagram of the system flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0035] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0036] Embodiment 1:

[0037] Therefore, in order to effectively solve the above problems, this application proposes a talent skill recommendation system based on personalization, as shown in the accompanying drawings of the specification. Figure 1 As shown, it includes a recruiter data module and a job data module. The recruiter data module can collect basic information of recruiters, and the job data module can analyze the job demand information in the current market. It also includes a feature construction module, a habit effect module, a job matching module, a personalization module and a recommendation module.

[0038] You can also collect information about the recruiter's part-time experience in different industries, the short-term project cooperation he / she has participated in, and the honors and certificates he / she has obtained in his / her professional field;

[0039] We also add descriptions of soft factors such as the cultural characteristics and team atmosphere of the company where the position is located, because these factors also have an important impact on the job matching and job satisfaction of the recruiter;

[0040] By combining big data analysis with predictions from industry experts, we can predict the changing trend of market job demand in the future and provide recruiters with more forward-looking job information.

[0041] The feature construction module establishes an extraction unit and constructs the feature vectors of the recruiter and the position based on the extraction unit information, the basic information of the recruiter and the position requirement information;

[0042] The habit effectiveness module obtains the employment information of previous positions, thereby obtaining the information of previous employees, and analyzes the skill habits of previous employees and the employment cycle information during the employment period, and analyzes the impact of different habits of previous employees on the employment cycle information;

[0043] The job matching module uses collaborative filtering recommendation information and content-based recommendation information to analyze the match between recruiters and jobs;

[0044] The personalized module extracts the personalized needs of recruiters and establishes an external expansion unit. Recruiters can edit the information in the external expansion unit independently, so that the recommended job information better meets the needs of recruiters;

[0045] The recommendation module generates a job recommendation list based on the matching degree, and establishes a recruiter feedback unit to collect recruiters' opinions on the job recommendation list;

[0046] It also includes a travel cost module, which has a distance cost unit, a time cost unit and a vacation cost unit. The distance cost unit and the vacation cost unit are used to calculate the travel cost of the recruiter during employment.

[0047] Specific workflow: Collect basic information of recruiters, analyze job demand information in the current market, construct feature vectors of recruiters and jobs based on extracted unit information, basic information of recruiters and job demand information, analyze the skill habits of previous job seekers and job cycle information during employment, analyze the impact of different habits of previous job seekers on job cycle information, calculate the matching degree between recruiters and jobs, insert personalized needs of recruiters, generate job recommendation list, collect recruiters' opinions on the job recommendation list, and calculate the recruiters' communication cost;

[0048] Furthermore, constructing feature vectors of recruiters and positions through the feature construction module helps to understand the characteristics of recruiters and positions more accurately, thereby improving the accuracy of job matching. The habit effectiveness module analyzes the impact of previous employees' habits on the employment cycle, which can provide reference for recruiters and companies, better predict and adapt to work situations, and improve the matching quality of recruiters and positions, making the recommended positions more in line with the expectations of recruiters, allowing recruiters to comprehensively consider cost factors when choosing positions and make more reasonable decisions.

[0049] Embodiment 2:

[0050] Based on the first embodiment, as shown in the accompanying drawings of the specification Figure 1As shown, when the feature construction module constructs the feature vectors of the recruiter and the position, the extraction unit will extract features from the recruiter's information. At the same time, the extraction unit has a basic extraction function and an advanced extraction function. The basic extraction function includes the recruiter's skill keyword information, work experience years information, project experience type information, and work location information, as well as the skill keyword information, work experience years information, project experience type information, and work location information required for the position. The information in the advanced extraction function needs to be edited by both the recruiter and the administrator.

[0051] Establish a feature weight assessment mechanism to assign different weights to each feature according to the importance of different industries and different job types. For example, for technical R&D positions, the weight of professional skills may be higher, while for management positions, the weight of leadership and communication skills may be greater;

[0052] Dynamic feature elements can be added by analyzing the learning curve and the speed of adapting to new tasks in different working environments in the past. For the position feature vector, the scalability feature of the position is added, that is, the possible changes in responsibilities and the direction of skill extension of the position in the future business expansion process;

[0053] The habit effectiveness module can extract various job demand information, and retrieve the previous employment status of various jobs, so as to obtain the employment information of previous employees when they were employed and the habit information of previous employees, and analyze the habit information suitable for employment in various jobs, so as to analyze the impact of different habits of previous employees on the employment cycle information, where the employment cycle information refers to the learning cycle, adaptation cycle and proficiency cycle of previous employees during the period of employment in the job;

[0054] Use data mining technology to analyze the impact of factors that may have been overlooked in previous job seekers' information on the job search cycle, such as the impact of the degree of match between the job seeker's career values ​​and the value provided by the position on the job search cycle;

[0055] The job matching module can receive the information processed by the feature building module and obtain the impact of different habits on the employment cycle information. The content-based recommendation information can analyze the item information of the recruiter's past habits and then extract the employment feature information from it. At this time, the item information associated with various job information is analyzed and then the job feature information is extracted from it, so as to determine the job information related to the employment feature information.

[0056] The collaborative filtering recommendation information includes recruiter collaborative filtering and item collaborative filtering;

[0057] Recruiter collaborative filtering is to make recommendations based on the similarity between recruiters, find other recruiters who are related to the interests of the target recruiter, and recommend their favorite items to the target recruiter;

[0058] Item collaborative filtering recommends items based on the similarity between items, finding other items related to the items that the target recruiter likes and recommending them;

[0059] Then, the matching degree between the recruiter and the position is comprehensively analyzed based on the collaborative filtering recommendation information and the content-based recommendation information;

[0060] Use the convolutional neural network in deep learning to perform deep feature encoding on job description text and recruiter resume text to improve matching accuracy;

[0061] Specific workflow: Extract features from recruiters’ information. Recruiters and administrators can edit the information in the advanced extraction function. Then retrieve the previous employment status of various positions, obtain the employment information of previous employees and the habit information of previous employees, analyze the impact of different habits of previous employees on the employment cycle information, conduct a comprehensive analysis of the matching degree between recruiters and positions based on collaborative filtering recommendation information and content-based recommendation information, and use the convolutional neural network in deep learning to perform deep feature encoding on the job description text and the recruiter resume text;

[0062] Furthermore, the feature construction module can better meet personalized needs, and the habit effectiveness module can find out the habits suitable for different positions, providing reference for recruiters and enterprises, which helps to improve employees' adaptability and work efficiency in their positions. The position matching module can combine collaborative filtering recommendation information and content-based recommendation information for comprehensive analysis, and can consider the matching degree between recruiters and positions from multiple angles, thereby improving the accuracy and reliability of recommendations.

[0063] Embodiment three:

[0064] Based on the second embodiment, as shown in the accompanying drawings of the specification Figure 1 As shown in the figure, the personalized module can extract different habit information of recruiters, and set a personalized typing function at the same time. Recruiters can type their expected conditions into the personalized module through the personalized typing function. At this time, the personalized module will convert the expected conditions into habit information. Let the different habit information suitable for the position be J Z =J1, J2, J3, ..., J D , let the habit information of the employee be Y Z =Y1, Y2, Y3, ..., Y G , let the habit information matching the position be X P , let D be the number of different habit information suitable for the job;

[0065] X P =J Z∩Y Z =(J1, J2, J3, ..., J D )∩(Y1, Y2, Y3,…,Y G )

[0066] According to the above formula, the habit information that matches the position can be calculated, and then the number of habit information that matches the position can be analyzed. Suppose the number of habit information that matches the position is G S , let the custom matching value of the position be X 匹 ;

[0067]

[0068] According to the above formula, the habit matching value of the position can be calculated;

[0069] The external expansion unit can also include personalized options such as training opportunities for positions, mentoring conditions, international dispatch opportunities, etc. to meet the diverse needs of recruiters;

[0070] Provides a priority setting function for personalized needs. Recruiters can set different weights for different personalized needs according to their preferences. The platform will make comprehensive considerations based on the weights when recommending positions.

[0071] The recommendation module can receive the information processed by the personalization module, thereby obtaining the custom matching value information of the position and the matching degree information between the recruiter and the position, and then draw a recommendation list based on the custom matching value and the matching degree information between the recruiter and the position, and display the recommendation list to the recruiter;

[0072] The distance cost unit in the travel cost module will access the recruiter data module and the recommendation module to obtain the location information of the recruiter and the location information of the recommended positions in the recommendation list, and then obtain the distance between the recruiter's location information and the location information of the recommended positions in the recommendation list, and connect with the traffic software to calculate the traffic cost. The recruiter can modify the recruiter's location information and display the travel time.

[0073] The vacation cost unit can obtain the vacation information of the position, so as to analyze the economic loss caused by the vacation to the recruiter and calculate the vacation cost;

[0074] Then, the travel costs of the recruiter during employment are calculated comprehensively based on the transportation costs and vacation costs, and the travel costs are displayed;

[0075] In addition to considering geographical distance, we also consider the impact of factors such as traffic convenience and traffic congestion on distance costs. For example, we can obtain real-time traffic information through data connection with the transportation department and calculate the actual time cost of recruiters traveling to the job location at different time periods.

[0076] In addition to working hours, the impact of factors such as overtime and flexibility of working hours on time costs are also considered. For example, for positions that require frequent overtime, the additional time cost can be calculated based on the length and frequency of overtime.

[0077] Specific workflow: Extract different habit information of recruiters, set up personalized input function, recruiters input their expected conditions into the personalized module through the personalized input function, the personalized module will convert the expected conditions into habit information, analyze the number of habit information matching the position, calculate the habit matching value of the position, draw a recommendation list, and show the recommendation list to the recruiters;

[0078] Then, the location information of the recruiter and the location information of the recommended positions in the recommendation list are obtained, and the distance between the location information of the recruiter and the location information of the recommended positions in the recommendation list is obtained, and the transportation cost is calculated by connecting with the transportation software, and the vacation information of the positions is obtained, and the vacation cost is calculated, and the travel cost of the recruiter during employment is comprehensively calculated;

[0079] Furthermore, the personalization module can extract different habit information of recruiters, so as to more accurately calculate the habit information that matches the position and the habit matching value of the position. The recommendation module helps recruiters to have a more comprehensive understanding of the positions that suit them, thereby improving the efficiency and satisfaction of recruitment. The transaction cost module can enable recruiters to have a clearer understanding of the actual transaction cost of the position, which helps recruiters to comprehensively consider various cost factors of the position, so that recruiters can more comprehensively evaluate the cost-effectiveness of the position and make more wise choices.

[0080] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A personalized talent skill recommendation system includes a recruiter data module and a job data module. The recruiter data module can collect basic information of recruiters, and the job data module can analyze job demand information in the current market. The system is characterized by: It also includes feature building module, habit performance module, job matching module, personalization module and recommendation module; The feature construction module establishes an extraction unit and constructs the feature vectors of the recruiter and the position based on the extraction unit information, the basic information of the recruiter and the position requirement information; The habit effectiveness module obtains the employment information of previous positions, thereby obtaining the information of previous employees, and analyzes the skill habits of the previous employees and the employment cycle information during the employment period, and analyzes the impact of the different habits of previous employees on the employment cycle information; The job matching module uses collaborative filtering recommendation information and content-based recommendation information to analyze the match between recruiters and jobs; The personalized module extracts the personalized needs of recruiters and establishes an external expansion unit. Recruiters can edit the information in the external expansion unit independently, so that the recommended job information better meets the needs of recruiters; The recommendation module generates a job recommendation list based on matching ranking, and establishes a recruiter feedback unit to collect recruiters' opinions on the job recommendation list.

2. The personalized talent skill recommendation system according to claim 1 is characterized by: It also includes a travel cost module, which has a distance cost unit, a time cost unit and a vacation cost unit. The distance cost unit and the vacation cost unit are used to calculate the travel cost of the recruiter during employment.

3. The personalized talent skill recommendation system according to claim 2 is characterized by: When the feature construction module constructs the feature vectors of the recruiter and the position, the extraction unit will perform feature extraction on the recruiter's information. At the same time, the extraction unit has basic extraction functions and advanced extraction functions set up inside. The feature extraction types in the basic extraction function include the recruiter's skill keyword information, work experience years information, project experience type information and work location information, as well as the skill keyword information, work experience years information, project experience type information and work location information required for the position. The information in the advanced extraction function needs to be edited independently by both the recruiter and the administrator.

4. The personalized talent skill recommendation system according to claim 1 is characterized in that: The habit effectiveness module can extract various job requirement information, thereby retrieving the previous employment status of various jobs, thereby obtaining the employment information of previous employees when they were employed and the habit information of previous employees, and analyzing the habit information suitable for employment in various jobs, thereby analyzing the impact of the different habits of previous employees on the employment cycle information, wherein the employment cycle information refers to the learning cycle, adaptation cycle and proficiency cycle of previous employees during the period of the job.

5. The personalized talent skill recommendation system according to claim 3 is characterized by: The job matching module can receive information processed by the feature building module and obtain the influence of different habits on the employment cycle information, wherein the content-based recommendation information can analyze the item information of the recruiter's past habits, and then extract the employment feature information therefrom, and then analyze the item information associated with various job information, and then extract the job feature information therefrom, so as to determine the job information related to the employment feature information; The collaborative filtering recommendation information includes recruiter collaborative filtering and item collaborative filtering; Recruiter collaborative filtering is to make recommendations based on the similarity between recruiters, find other recruiters who are related to the interests of the target recruiter, and recommend their favorite items to the target recruiter; Item collaborative filtering recommends items based on the similarity between items, finding other items related to the items that the target recruiter likes and recommending them; Then, the matching degree between the recruiter and the position is comprehensively analyzed based on the collaborative filtering recommendation information and the content-based recommendation information; The convolutional neural network in deep learning is used to perform deep feature encoding on the job description text and the recruiter's resume text to improve the matching accuracy.

6. The personalized talent skill recommendation system according to claim 5 is characterized by: The personalized module can extract different habit information of recruiters, and set a personalized input function at the same time. Recruiters can input their desired conditions into the personalized module through the personalized input function. At this time, the personalized module will convert the desired conditions into habit information. Let the different habit information suitable for the position be J Z =J1, J2, J3, ..., J D , let the habit information of the employee be Y Z =Y1, Y2, Y3, ..., Y G , let the habit information matching the position be X P , let D be the number of different habit information suitable for the job; <h2 style=";text-align:left;direction:ltr">X<h2 style=";text-align:left;direction:ltr"> P <h2 style=";text-align:left;direction:ltr"> =J<h2 style=";text-align:left;direction:ltr"> Z <h2 style=";text-align:left;direction:ltr"> ∩Y<h2 style=";text-align:left;direction:ltr"> Z <h2 style=";text-align:left;direction:ltr"> (J1, J2, J3,……, J)<h2 style=";text-align:left;direction:ltr"> D <h2 style=";text-align:left;direction:ltr"> )∩(Y1、Y2、Y3、……、Y<h2 style=";text-align:left;direction:ltr"> G According to the above formula, the habit information that matches the position can be calculated, and then the number of habit information that matches the position can be analyzed. Suppose the number of habit information that matches the position is G S , let the custom matching value of the position be X 匹 ; According to the above formula, the habit matching value of the position can be calculated.

7. The personalized talent skill recommendation system according to claim 6 is characterized by: The recommendation module can receive information processed by the personalization module to obtain the customary matching value information of the position and the matching degree information between the recruiter and the position, and then draw a recommendation list based on the customary matching value and the matching degree information between the recruiter and the position, and display the recommendation list to the recruiter.

8. The personalized talent skill recommendation system according to claim 2 is characterized by: The distance cost unit in the travel cost module will access the recruiter data module and the recommendation module to obtain the location information of the recruiter and the location information of the recommended positions in the recommendation list, and then obtain the distance between the recruiter's location information and the location information of the recommended positions in the recommendation list, and connect with the traffic software to calculate the traffic cost, and the recruiter can modify the recruiter's location information and display the traffic time; The vacation cost unit can obtain the vacation information of the position, so as to analyze the economic loss caused by the vacation to the recruiter and calculate the vacation cost; Then, the travel costs of the recruiter during employment are comprehensively calculated based on transportation costs and vacation costs, and the travel costs are displayed.

Images