A recommendation method for intelligent recommendation system

By modeling and analyzing employment data through an intelligent recommendation system, an employment feature matrix and a path matrix are established, and employment path feature values ​​are calculated. This solves the problems of low efficiency and accuracy in employment recommendation and achieves efficient and accurate employment matching.

CN114861067BActive Publication Date: 2024-11-19HEBEI JILIAN HUMAN RESOURCES SERVICE GRP CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210631162.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-06
Publication Date
2024-11-19
Estimated Expiration
2042-06-06

AI Technical Summary

Technical Problem

Current job recommendations mainly rely on manual aggregation and classification, which is inefficient and lacks accuracy, failing to accurately match job seekers with suitable employers.

Method used

The intelligent recommendation system collects employment data and performs modeling analysis to establish an employment feature matrix and path matrix, calculates employment path feature values, and realizes intelligent employment recommendation.

Benefits of technology

It improves the efficiency and accuracy of job recommendations and reduces the tediousness and error rate of manual operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114861067B_ABST
    Figure CN114861067B_ABST
Patent Text Reader

Abstract

The present invention discloses an intelligent recommendation system and method, which mainly relates to the field of Internet technology. The system includes a storage medium, an employment data initialization module, an employment matrix modeling module, and a path matrix modeling module. The beneficial effects of the present invention are: through modeling and analysis of employment data, employment data is realized, and through feature value comparison, intelligent employment recommendation is realized, thereby improving the efficiency and accuracy of employment recommendation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet, and in particular to a recommendation method of an intelligent recommendation system. Background Art

[0002] With the development of Internet technology and computer and mobile phone terminals, and the promotion and application of the "Internet +" platform, service providers in various fields can actively explore various personalized application services for users through the Internet to meet the needs of recommendations that are more suitable for actual needs.

[0003] However, currently, employment recommendations are mainly completed through manual summary and classification, which has low efficiency and is unable to more accurately recommend the corresponding unemployed persons to suitable employers, resulting in low accuracy of recommendations. Summary of the invention

[0004] The purpose of the present invention is to provide a recommendation method for an intelligent recommendation system, which realizes employment data through modeling and analysis of employment data, and realizes intelligent employment recommendation through feature value comparison, thereby improving the efficiency and accuracy of employment recommendation.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] A recommendation method of an intelligent recommendation system comprises the following steps:

[0007] S1. Collect employment record information and initialize the collected employment data through the employment data initialization module;

[0008] S2. Model the employment data in S1 through the employment matrix modeling module to establish the employment feature matrix Rec j (po, st, hr), where j is the worker number, po represents the worker's job type information, st represents the worker's current work status information, and hr represents the worker's historical work path feature value;

[0009] S3. According to the employment feature matrix in S2. and the latitude and longitude coordinate information of the worker's historical work location, a path feature matrix Rod is established through a path matrix modeling module. i,n j (x i ,y i , va i ), where j represents the worker number information, i represents the number of the worker with number j in the i-th job, n represents the total number of historical jobs of the worker with number j, and x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y iThe ordinate longitude value of the position of the worker numbered j at the i-th work unit, va i The characteristic value of the characteristic point of the employment path of the employing unit where the worker numbered j works for the i-th time;

[0010] S4. Calculate the characteristic value va of the characteristic point of the employment path according to each value in the path characteristic matrix described in S3. i , the calculation formula is as follows:

[0011] va i =((x i -y i ) 2 ) 1 / 2

[0012] where x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i It represents the ordinate longitude value of the position of the employing unit where the worker numbered j is located during the i-th work;

[0013] S5. The historical work path of each worker is depicted according to the location changes of the worker in different employment units, and the employment path characteristic value hr of each worker is calculated according to the characteristic values ​​of the path characteristic points described in S4. The calculation formula is as follows:

[0014]

[0015] Among them, i represents the eigenvalue of the employment path feature point in the path feature matrix, x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i Indicates the vertical coordinate longitude value of the position of the employment unit where the worker numbered j is located during the i-th work; the hr calculation result is saved in the employment feature matrix;

[0016] S6. When there is a need for employment, the currently serving worker or the worker who has resigned is taken as the target worker, all the unemployed workers of the job type are traversed in the employment feature matrix, the employment path characteristic value hr of the unemployed worker is compared with that of the target worker, and the top 10 unemployed workers with the highest similarity of the employment path characteristic value hr are selected to be added to the recommendation list;

[0017] S7. Feedback the recommendation list to the employer;

[0018] Among them, the intelligent recommendation system includes a storage medium, an employment data initialization module, an employment matrix modeling module, and a path matrix modeling module.

[0019] Furthermore, the storage medium is a database.

[0020] Furthermore, the employment data initialization module is used to initialize the employment data.

[0021] Furthermore, the employment matrix modeling module is used to establish an employment feature matrix.

[0022] Furthermore, the path matrix modeling module is used to establish a path feature matrix.

[0023] Furthermore, the collected information in step S1 includes the worker number, the worker's job type information, the worker's current work status, and the longitude and latitude coordinates of the worker's historical work location.

[0024] Compared with the prior art, the beneficial effects of the present invention are:

[0025] The present invention is based on an intelligent recommendation system. By modeling and analyzing the collected employment data, an employment matrix and an employment feature matrix are established to realize the digitization of employment information. By calculating the characteristic values ​​of employment feature points and the characteristic values ​​of employment paths, the employment history characteristic value information is extracted. Through characteristic value comparison, intelligent employment recommendations are realized, which improves the efficiency and accuracy of employment recommendations and avoids the tediousness of manual operations and the occurrence of errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Attached Figure 1 It is a system composition diagram of the present invention.

[0027] Attached Figure 2 It is a working principle diagram of the present invention.

[0028] Numbers shown in the accompanying drawings:

[0029] 1. Employment data initialization module; 2. Employment matrix modeling module; 3. Path matrix modeling module; 4. Database. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the application equally.

[0031] The present invention discloses a recommendation method for an intelligent recommendation system, the main structure of which includes a storage medium, an employment data initialization module 1, an employment matrix modeling module 2, and a path matrix modeling module 3.

[0032] Preferably, the storage medium is a database 4.

[0033] Preferably, the employment data initialization module 1 is used to initialize the employment data.

[0034] Preferably, the employment matrix modeling module 2 is used to establish an employment feature matrix.

[0035] Preferably, the path matrix modeling module 3 is used to establish a path feature matrix.

[0036] Embodiment: An intelligent recommendation method, characterized in that it includes the following steps:

[0037] S1. Collect the worker number, worker type information, worker current work status, longitude and latitude coordinates of the worker's historical work location and other employment record information, and initialize the collected employment data through the employment data initialization module 1;

[0038] S2. Model the employment data in S1 through the employment matrix modeling module 2 to establish an employment feature matrix Rec j (po, st, hr), where j is the worker number, po represents the worker's job type information, st represents the worker's current work status information, and hr represents the worker's historical work path feature value;

[0039] S3. According to the employment feature matrix in S2., and the latitude and longitude coordinate information of the worker's historical work location, the path feature matrix Rod is established through the path matrix modeling module 3. i,n j (x i ,y i , va i ), where j represents the worker number information, i represents the number of the worker with number j in the i-th job, n represents the total number of historical jobs of the worker with number j, and x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i The ordinate longitude value of the position of the worker numbered j at the i-th work unit, va i The characteristic value of the characteristic point of the employment path of the employing unit where the worker numbered j works for the i-th time;

[0040] S4. Calculate the characteristic value va of the characteristic point of the employment path according to each value in the path characteristic matrix described in S3. i , taking the worker numbered j at the i-th work as an example, the calculation formula is as follows:

[0041] va i =((x i -y i ) 2 )1 / 2

[0042] where x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i It represents the ordinate longitude value of the position of the employing unit where the worker numbered j is located during the i-th work;

[0043] S5. The historical work path of each worker can be depicted according to the position changes of the worker in different employment units, and the employment path characteristic value hr of each worker is calculated according to the characteristic values ​​of the path characteristic points described in S4. Taking the calculation of the historical work path of the job numbered j as an example, the calculation formula is as follows:

[0044]

[0045] Among them, i Represents the eigenvalues ​​of the employment path feature points in the path feature matrix. i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i Indicates the vertical coordinate longitude value of the position of the employment unit where the worker numbered j is located during the i-th work; the hr calculation result is saved in the employment feature matrix;

[0046] S6. When there is a need for employment, the currently serving worker or the worker who has resigned is taken as the target worker, all the unemployed workers of the job type are traversed in the employment feature matrix, the employment path characteristic value hr of the unemployed worker is compared with that of the target worker, and the top 10 unemployed workers with the highest similarity of the employment path characteristic value hr are selected to be added to the recommendation list;

[0047] S7. Feedback the recommendation list to the employer.

[0048] The present invention provides a recommendation method for an intelligent recommendation system. By modeling and analyzing employment data, an employment matrix and an employment feature matrix are established to realize employment dataization. By calculating the characteristic values ​​of employment feature points and the characteristic values ​​of employment paths, the characteristic value information of employment history is extracted. By comparing the characteristic values, intelligent employment recommendations are realized, thereby improving the efficiency and accuracy of employment recommendations.

Claims

1. A recommendation method of an intelligent recommendation system, characterized in that: The following steps are involved: S1. Collect employment record information and initialize the collected employment data through the employment data initialization module (1); S2. Model the employment data in S1 through the employment matrix modeling module (2) to establish the employment feature matrix Rec j (po, st, hr), where j is the worker number, po represents the worker's job type information, st represents the worker's current work status information, and hr represents the worker's historical work path feature value; S3. According to the employment feature matrix in S2. and the latitude and longitude coordinate information of the workers' historical work locations, a path feature matrix Rod is established through the path matrix modeling module (3). i,n j (x i ,y i , va i ), where j represents the worker number information, i represents the number of the worker with number j in the i-th job, n represents the total number of historical jobs of the worker with number j, and x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i The ordinate longitude value of the position of the worker numbered j at the i-th work unit, va i The characteristic value of the characteristic point of the employment path of the employing unit where the worker numbered j works for the i-th time; S4. Calculate the characteristic value va of the characteristic point of the employment path according to each value in the path characteristic matrix described in S3. i , the calculation formula is as follows: goes i ((x) i -and i ) 2 ) 1 / 2 where x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i It represents the ordinate longitude value of the position of the employing unit where the worker numbered j is located during the i-th work; S5. The historical work path of each worker is depicted according to the location changes of the worker in different employment units, and the employment path characteristic value hr of each worker is calculated according to the characteristic values ​​of the path characteristic points described in S4. The calculation formula is as follows: Among them, i represents the eigenvalue of the employment path feature point in the path feature matrix, x i The horizontal coordinate latitude value of the position of the worker numbered j in the i-th work unit, y i Indicates the vertical coordinate longitude value of the position of the employment unit where the worker numbered j is located during the i-th work; the hr calculation result is saved in the employment feature matrix; S6. When there is a need for employment, the currently serving worker or the worker who has resigned is taken as the target worker, all the unemployed workers of the job type are traversed in the employment feature matrix, the employment path characteristic value hr of the unemployed worker is compared with that of the target worker, and the top 10 unemployed workers with the highest similarity of the employment path characteristic value hr are selected to be added to the recommendation list; S7. Feedback the recommendation list to the employer; The intelligent recommendation system comprises a storage medium, an employment data initialization module (1), an employment matrix modeling module (2), and a path matrix modeling module (3).

2. The recommendation method of the intelligent recommendation system according to claim 1, characterized in that: The storage medium is a database (4).

3. The recommendation method of the intelligent recommendation system according to claim 1, characterized in that: The employment data initialization module (1) is used to initialize the employment data.

4. The recommendation method of the intelligent recommendation system according to claim 1, characterized in that: The employment matrix modeling module (2) is used to establish an employment feature matrix.

5. The recommendation method of the intelligent recommendation system according to claim 1, characterized in that: The path matrix modeling module (3) is used to establish a path feature matrix.

6. The recommendation method of the intelligent recommendation system according to claim 1, characterized in that: Said The collected information in step S1 includes the worker number, the worker's job type information, the worker's current working status, The latitude and longitude coordinates of the worker's historical work location.

Citation Information

Patent Citations

  • Intelligent human resource screening system and method

    CN110648104A

  • Classifier-based employment recommendation method and system, and readable storage medium

    CN113849740A

  • Working employment data matching system and method and storage medium thereof

    CN114240227A