A method and system for recommending student jobs based on artificial intelligence

Abstract

The present application discloses a method and system for recommending student jobs based on artificial intelligence, which belongs to the field of artificial intelligence technology. The present application obtains student personal learning course information and enterprise recruitment demand information, and simultaneously obtains project information of employees in corresponding jobs, constructs a feature extraction model, imports student personal learning course information, enterprise recruitment demand information and work project information of employees in corresponding jobs into the feature extraction model for corresponding feature extraction, constructs a correlation evaluation model, imports the extracted corresponding features into the correlation evaluation model for evaluation, constructs a student job recommendation model, imports student course comprehensive skill feature vectors, recruitment job comprehensive skill feature vectors and project comprehensive skill feature vectors into the student job recommendation model, generates recommendation results, and provides students with more matching jobs through comprehensive analysis of the courses learned, recruitment jobs and skills required for job development.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically is a method and system for recommending student jobs based on artificial intelligence. Background Art

[0002] With the rapid changes in the education and employment markets, the match between students and companies has become increasingly important. Traditional recruitment methods rely on offline campus job fairs, which are open to all graduates, causing students to spend a lot of time screening suitable positions. Due to the wide variety of positions, students may waste time on irrelevant positions and miss truly suitable opportunities. In addition, different positions have different requirements for students' professional skills, and students cannot fully judge the degree of fit with the position when making choices. In the existing technical job matching process, only the connection between students' grades and positions is considered, while the connection between the implicit characteristics of students' courses and positions is ignored, which leads to the neglect of the connection between courses and job development, causing trouble for students' job hunting and job development.

[0003] This application proposes an artificial intelligence-based student job recommendation method and system, aiming to improve the matching efficiency between students and enterprises and realize intelligent recommendation. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present application proposes a method and system for recommending student jobs based on artificial intelligence. The present application obtains student personal learning course information and enterprise recruitment demand information, and at the same time obtains project information of employees in corresponding jobs, constructs a feature extraction model, imports student personal learning course information, enterprise recruitment demand information and work project information of employees in corresponding jobs into the feature extraction model for corresponding feature extraction, constructs a correlation evaluation model, imports the extracted corresponding features into the correlation evaluation model for evaluation, constructs a student job recommendation model, imports student course comprehensive skill feature vectors, recruitment position comprehensive skill feature vectors and project comprehensive skill feature vectors into the student job recommendation model, generates recommendation results, and provides students with more matching jobs through comprehensive analysis of the courses learned, recruitment positions and skills required for job development, thereby improving the matching degree between students' majors and jobs.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] A method for recommending student jobs based on artificial intelligence, comprising the following specific steps:

[0007] Obtain information about students' personal study courses and corporate recruitment needs, as well as project information about employees in corresponding positions;

[0008] Construct a feature extraction model, import the student's personal learning course information, the company's recruitment demand information and the corresponding job position employee work project information into the feature extraction model to extract the corresponding features;

[0009] Construct a correlation evaluation model, and import the extracted corresponding features into the correlation evaluation model for evaluation;

[0010] Construct a student job recommendation model, import the student course comprehensive skill feature vector, recruitment position comprehensive skill feature vector and project comprehensive skill feature vector into the student job recommendation model, and generate recommendation results.

[0011] It should be specifically explained here that the acquisition of student personal learning course information and enterprise recruitment demand data, and the acquisition of project information of employees for corresponding recruitment positions includes the following specific steps:

[0012] S11. Obtain students’ course information through the school’s student management system and organize students’ personal course information, including courses studied and course scores;

[0013] S12. Obtain recruitment demand information from recruiting companies and organize recruitment position data, including job requirements and job recruitment conditions;

[0014] S13. Obtain the work project information of the employees for the corresponding recruitment positions, including the project names and project published papers.

[0015] It should be specifically explained here that the construction of the feature extraction model, importing the student's personal learning course information, the enterprise's recruitment demand information and the corresponding job position employee work project information into the feature extraction model for corresponding feature extraction includes the following specific steps:

[0016] S21. Build a standardized feature dictionary that contains all the skill features in the course and job descriptions;

[0017] S22. Traverse each course outline of the student, match the course outline content with the standardized skill features in the dictionary, and record the number of occurrences of keywords in the course outline that have the same meaning as the standardized skill features, and construct a skill feature vector for each course. The skill feature vector of the a-th course is: , where c ap represents the pth skill feature of the ath course, and p belongs to any item from 1 to n. If the ath course does not include the pth skill feature, then c ap =0;

[0018] S23, traverse the enterprise recruitment demand information, match the recruitment demand text of each position with the standardized skill features in the feature dictionary, and construct the skill feature vector of the recruitment position, where the skill feature vector of the jth recruitment position is: , where c jp represents the pth skill characteristic of the jth recruitment position, and p belongs to any item from 1 to n. If the jth recruitment position does not include the pth skill characteristic, then c jp =0;

[0019] S24. By traversing the employee's project information, extracting skill keywords, and matching the project information with the standardized skill features in the dictionary, a skill feature vector of the project is constructed, where the skill feature vector of the dth project is: , where c dp represents the pth skill feature of the dth project, and p belongs to any one of 1 to n. If the dth project does not include the pth skill feature, then c dp =0.

[0020] It should be specifically explained here that the construction of the correlation evaluation model and the importation of the extracted corresponding features into the correlation evaluation model for evaluation include the following specific steps:

[0021] S31. Substitute the eigenvector of each course into the course standardized eigenvalue calculation formula to calculate the course standardized eigenvalue, where the standardized eigenvalue calculation formula for the pth skill of the ath course is: , where Za is the standardized score of the a-th course, Tp is the number of keyword occurrences of the p-th skill, and T is the total number of keyword occurrences. The standardized score calculation formula for the a-th course is: , S a,i is the score of the ath course of the i-th student, M a is the average score of the ath course of all students in the i-th student’s major, is the standard deviation of the score of the ath course of the i-th student’s major, where the standard deviation of the score of the ath course of the i-th student’s major is calculated as follows: , G is the number of students in the major of the i-th student;

[0022] S32. Obtain all the skill feature values ​​of course a to generate a course standardized feature vector, where the course standardized feature vector is: ,in, is the standardized feature value of the pth skill of the ath course, and p belongs to any item from 1 to n. Substitute the standardized feature vector of each course into the comprehensive skill feature vector generation formula to generate the comprehensive skill feature vector of the course, where the comprehensive skill feature vector generation formula corresponding to the course is: ,in, is the pth comprehensive skill characteristic value corresponding to the course, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic corresponding to the course is: , where B a is the credits of the ath course, C is the total credits of the courses taken, and N is the number of courses;

[0023] S33. Substitute the feature vector of the recruitment position into the generation formula of the comprehensive skill feature vector corresponding to the recruitment position to generate the comprehensive skill feature vector corresponding to the recruitment position, wherein the generation formula of the comprehensive skill feature vector corresponding to the recruitment position is: ,in, is the pth comprehensive skill characteristic value corresponding to the recruitment position, and p is any one of 1 to n. The calculation formula for the pth comprehensive skill characteristic value corresponding to the recruitment position is: , where k 1 is the number of times a skill appears in semantic analysis, w 1 is the weight of the number of times a skill appears in the semantic analysis, k 2 is the number of times a skill appears in historical data, w 2 is the weight of the number of times a skill appears in historical data;

[0024] S34, substituting the project skill feature vector into the comprehensive skill feature vector generation formula corresponding to the project to generate the project comprehensive skill feature vector, wherein the comprehensive skill feature vector generation formula corresponding to the project is: ,in, is the pth comprehensive skill characteristic value corresponding to the project, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic value corresponding to the project is: , where c dp is the pth skill feature of the dth project, and L is the total number of participating projects;

[0025] S35. Substitute the course comprehensive skill feature vector and the recruitment position comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the recruitment position comprehensive skill. The correlation calculation formula between the course comprehensive skill and the recruitment position comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n;

[0026] S36. Substitute the course comprehensive skill feature vector and the project comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the project comprehensive skill. The correlation calculation formula between the course comprehensive skill and the project comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n.

[0027] It should be specifically explained here that the construction of the student job recommendation model, importing the student course comprehensive skill feature vector, the recruitment position comprehensive skill feature vector and the project comprehensive skill feature vector into the student job recommendation model, and generating the recommendation result includes the following specific steps:

[0028] S41. Substitute the correlation between the course comprehensive skills and the recruitment position comprehensive skills and the correlation between the course comprehensive skills and the project comprehensive skills into the position recommendation calculation formula to calculate the position recommendation degree, where the position recommendation calculation formula is: ,in, is the correlation weight between the comprehensive skills of the course and the comprehensive skills of the recruitment position, is the correlation weight between the course comprehensive skills and the project comprehensive skills, and , sort the required recommendation list, select the top ten with the highest recommendation, and generate a job recommendation list.

[0029] An artificial intelligence-based student job recommendation system is implemented based on the artificial intelligence-based student job recommendation method described above, and specifically includes:

[0030] The data acquisition module is used to obtain students' personal learning course information and corporate recruitment demand information, as well as project information of employees in corresponding positions;

[0031] Feature extraction module, used to extract features of students’ personal learning course information, enterprise recruitment demand information, and corresponding job position employee work project information;

[0032] A correlation evaluation module is used to evaluate the correlation between the corresponding features extracted;

[0033] The job recommendation module is used to calculate the recommendation degree, generate recommendation results, and recommend jobs to students.

[0034] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0035] The processor executes the above-mentioned method for recommending student jobs based on artificial intelligence by calling the computer program stored in the memory.

[0036] A computer-readable storage medium, characterized in that it stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for recommending student jobs based on artificial intelligence.

[0037] Compared with the prior art, the beneficial effects of this application are:

[0038] This application obtains students' personal learning course information and enterprise recruitment demand information, and also obtains project information of employees in corresponding jobs, builds a feature extraction model, imports students' personal learning course information, enterprise recruitment demand information and work project information of employees in corresponding jobs into the feature extraction model for corresponding feature extraction, builds a correlation evaluation model, imports the extracted corresponding features into the correlation evaluation model for evaluation, builds a student job recommendation model, imports students' course comprehensive skill feature vectors, recruitment position comprehensive skill feature vectors and project comprehensive skill feature vectors into the student job recommendation model, generates recommendation results, and provides students with more matching jobs through comprehensive analysis of courses learned, recruitment positions and skills required for job development. Through comprehensive analysis of courses learned, recruitment positions and skills required for job development, students are provided with more matching jobs, thereby improving the matching degree between students' majors and jobs. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of the overall process of an artificial intelligence-based student job recommendation method for this application;

[0040] Figure 2 This is a schematic diagram of the overall framework of an artificial intelligence-based student job recommendation system for this application;

[0041] Figure 3 This application provides a flowchart for calculating the student job recommendation degree based on artificial intelligence. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0043] Example 1

[0044] See also Figure 1-Figure 3 , an embodiment provided by the present application: a method for recommending student jobs based on artificial intelligence, which comprises the following specific steps:

[0045] Obtain information about students' personal study courses and corporate recruitment needs, as well as project information about employees in corresponding positions;

[0046] Construct a feature extraction model, import the student's personal learning course information, the company's recruitment demand information and the corresponding job position employee work project information into the feature extraction model to extract the corresponding features;

[0047] Construct a correlation evaluation model, and import the extracted corresponding features into the correlation evaluation model for evaluation;

[0048] Construct a student job recommendation model, import the student course comprehensive skill feature vector, recruitment position comprehensive skill feature vector and project comprehensive skill feature vector into the student job recommendation model, and generate recommendation results.

[0049] In this embodiment, it should be specifically explained that obtaining the student's personal learning course information and the enterprise's recruitment demand data, and simultaneously obtaining the project information of the corresponding recruitment position employees includes the following specific steps:

[0050] S11. Obtain students’ course information through the school’s student management system and organize students’ personal course information, including courses studied and course scores;

[0051] S12. Obtain recruitment demand information from recruiting companies and organize recruitment position data, including job requirements and job recruitment conditions;

[0052] S13. Obtain the work project information of the employees for the corresponding recruitment positions, including the project names and project published papers.

[0053] In this embodiment, it should be specifically explained that constructing a feature extraction model, importing student personal learning course information, enterprise recruitment demand information and corresponding job position employee work project information into the feature extraction model to extract corresponding features includes the following specific steps:

[0054] S21. Build a standardized feature dictionary that contains all the skill features in the course and job descriptions;

[0055] S22. Traverse each course outline of the student, match the course outline content with the standardized skill features in the dictionary, and record the number of occurrences of keywords in the course outline that have the same meaning as the standardized skill features, and construct a skill feature vector for each course. The skill feature vector of the a-th course is: , where c ap represents the pth skill feature of the ath course, and p belongs to any item from 1 to n. If the ath course does not include the pth skill feature, then c ap =0;

[0056] The following example code describes this step:

[0057] course_skill_vectors = []

[0058] for i, syllabus in enumerate(course_syllabi):

[0059] print(f"Processing syllabus for Course {i+1}")

[0060] skill_vector = {}

[0061] for skill_index, skill_name in enumerate(skill_dictionary):

[0062] c_ap = skill_matrix[i][skill_index]

[0063] if c_ap == 0:

[0064] skill_vector[skill_name] = 0

[0065] else:

[0066] skill_vector[skill_name] = c_ap

[0067] course_skill_vectors.append(skill_vector)

[0068] S23, traverse the enterprise recruitment demand information, match the recruitment demand text of each position with the standardized skill features in the feature dictionary, and construct the skill feature vector of the recruitment position, where the skill feature vector of the jth recruitment position is: , where c jp represents the pth skill characteristic of the jth recruitment position, and p belongs to any item from 1 to n. If the jth recruitment position does not include the pth skill characteristic, then c jp =0;

[0069] The following example code describes this step:

[0070] job_skill_vectors = []

[0071] for i, description in enumerate(job_descriptions):

[0072] print(f"Processing job description for Job {i+1}")

[0073] skill_vector = {}

[0074] for skill_index, skill_name in enumerate(skill_dictionary):

[0075] c_jp = skill_matrix[i][skill_index]

[0076] if c_jp == 0:

[0077] skill_vector[skill_name] = 0

[0078] else:

[0079] skill_vector[skill_name] = c_jp

[0080] job_skill_vectors.append(skill_vector)

[0081] S24. By traversing the employee's project information, extracting skill keywords, and matching the project information with the standardized skill features in the dictionary, a skill feature vector of the project is constructed, where the skill feature vector of the dth project is: , where c dp represents the pth skill feature of the dth project, and p belongs to any one of 1 to n. If the dth project does not include the pth skill feature, then c dp =0.

[0082] The following example code describes this step:

[0083] project_skill_vectors = []

[0084] for i, description in enumerate(project_descriptions):

[0085] print(f"Processing project description for Project {i+1}")

[0086] skill_vector = {}

[0087] for skill_index, skill_name in enumerate(skill_dictionary):

[0088] c_dp = skill_matrix[i][skill_index]

[0089] if c_dp == 0:

[0090] skill_vector[skill_name] = 0

[0091] else:

[0092] skill_vector[skill_name] = c_dp

[0093] project_skill_vectors.append(skill_vector)

[0094] job_development_vectors = []

[0095] In this embodiment, it should be specifically explained that constructing a correlation evaluation model and importing the extracted corresponding features into the correlation evaluation model for evaluation includes the following specific steps:

[0096] S31. Substitute the eigenvector of each course into the course standardized eigenvalue calculation formula to calculate the course standardized eigenvalue, where the standardized eigenvalue calculation formula for the pth skill of the ath course is: , where Za is the standardized score of the a-th course, Tp is the number of keyword occurrences of the p-th skill, and T is the total number of keyword occurrences. It is the proportion of keyword appearance, which is used to assign weights. Skills with more keyword appearances are assigned higher weights. The standardized score calculation formula for course a is: , S a,i is the score of the ath course of the i-th student, M a is the average score of the ath course of all students in the i-th student’s major, is the standard deviation of the score of the ath course of the i-th student’s major, where the standard deviation of the score of the ath course of the i-th student’s major is calculated as follows: , G is the number of students in the major of the i-th student;

[0097] S32. Obtain all the skill feature values ​​of course a to generate a course standardized feature vector, where the course standardized feature vector is: ,in, is the standardized feature value of the pth skill of the ath course, and p belongs to any item from 1 to n. Substitute the standardized feature vector of each course into the comprehensive skill feature vector generation formula to generate the comprehensive skill feature vector of the course, where the comprehensive skill feature vector generation formula corresponding to the course is: ,in, is the pth comprehensive skill characteristic value corresponding to the course, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic corresponding to the course is: , where B a is the credits of course a, C is the total credits of the courses taken, N is the number of courses, Indicates the importance of courses, and weights the importance of each course;

[0098] S33. Substitute the feature vector of the recruitment position into the generation formula of the comprehensive skill feature vector corresponding to the recruitment position to generate the comprehensive skill feature vector corresponding to the recruitment position, wherein the generation formula of the comprehensive skill feature vector corresponding to the recruitment position is: ,in, is the pth comprehensive skill characteristic value corresponding to the recruitment position, and p is any one of 1 to n. The calculation formula for the pth comprehensive skill characteristic value corresponding to the recruitment position is: , where k 1 is the number of times a skill appears in semantic analysis, w 1 is the weight of the number of times a skill appears in the semantic analysis, k 2 is the number of times a skill appears in historical data, w 2 is the weight of the number of times a skill appears in historical data;

[0099] S34, substituting the project skill feature vector into the comprehensive skill feature vector generation formula corresponding to the project to generate the project comprehensive skill feature vector, wherein the comprehensive skill feature vector generation formula corresponding to the project is: ,in, is the pth comprehensive skill characteristic value corresponding to the project, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic value corresponding to the project is: , where c dp is the pth skill feature of the dth project, and L is the total number of participating projects;

[0100] S35. Substitute the course comprehensive skill feature vector and the recruitment position comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the recruitment position comprehensive skill. The correlation calculation formula between the course comprehensive skill and the recruitment position comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n. It represents the cumulative amount of two vectors in the same dimension, which measures the correlation between the course and the job recruitment requirements in each skill. The higher the value, the higher the match between the two in the same skill. To normalize the modulus length, the dot product is divided by the two moduli to obtain a normalized similarity value, which avoids the impact of differences in the score scales of course or job recruitment requirements. The closer the correlation is to 1, the higher the degree of skill matching between the course and the job recruitment requirements.

[0101] S36. Substitute the course comprehensive skill feature vector and the project comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the project comprehensive skill. The correlation calculation formula between the course comprehensive skill and the project comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n.

[0102] In this embodiment, it should be specifically explained that constructing a student job recommendation model, importing the student course comprehensive skill feature vector, recruitment position comprehensive skill feature vector and project comprehensive skill feature vector into the student job recommendation model, and generating a recommendation result includes the following specific steps:

[0103] S41. Substitute the correlation between the course comprehensive skills and the recruitment position comprehensive skills and the correlation between the course comprehensive skills and the project comprehensive skills into the position recommendation calculation formula to calculate the position recommendation degree, where the position recommendation calculation formula is: ,in, is the correlation weight between the comprehensive skills of the course and the comprehensive skills of the recruitment position, is the correlation weight between the course comprehensive skills and the project comprehensive skills, and , sort the required recommendation list, select the top ten with the highest recommendation, and generate a job recommendation list.

[0104] It should be noted here that the weights of the number of skill appearances in the semantic analysis, the weights of the number of skill appearances in the historical data, the weights of the correlation between the comprehensive course skills and the comprehensive skills of the recruitment positions, and the weights of the correlation between the comprehensive course skills and the comprehensive project skills are obtained as follows: 5,000 groups of student personal learning course information and enterprise recruitment demand information are obtained, and at the same time, the project information of employees in the corresponding jobs is obtained, and the information is substituted into the job recommendation calculation formula to calculate the job recommendation degree, the student's job development situation is obtained, and the student's job development situation and the job recommendation degree are substituted into the fitting software, and the weights of the number of skill appearances in the semantic analysis, the weights of the number of skill appearances in the historical data, the weights of the correlation between the comprehensive course skills and the comprehensive skills of the recruitment positions, and the weights of the correlation between the comprehensive course skills and the comprehensive project skills are output, which meet the maximum student job development matching judgment accuracy.

[0105] The benefit of this embodiment is that it obtains students' personal learning course information and enterprise recruitment demand information, and at the same time obtains project information of employees in corresponding jobs, constructs a feature extraction model, imports students' personal learning course information, enterprise recruitment demand information and work project information of employees in corresponding jobs into the feature extraction model for corresponding feature extraction, constructs a correlation evaluation model, imports the extracted corresponding features into the correlation evaluation model for evaluation, constructs a student job recommendation model, imports students' course comprehensive skill feature vectors, recruitment job comprehensive skill feature vectors and project comprehensive skill feature vectors into the student job recommendation model, generates recommendation results, and provides students with more matching jobs through comprehensive analysis of courses learned, recruitment jobs and skills required for job development. Through comprehensive analysis of courses learned, recruitment jobs and skills required for job development, students are provided with more matching jobs, thereby improving the matching degree between students' majors and jobs.

[0106] Example 2

[0107] like Figure 2 As shown, a student job recommendation system based on artificial intelligence is implemented based on the above-mentioned student job recommendation method based on artificial intelligence, and specifically includes a data acquisition module, a feature extraction module, a correlation evaluation module and a job recommendation module. The data acquisition module is used to obtain students' personal learning course information and enterprise recruitment demand information, and at the same time obtain project information of employees in corresponding jobs; the feature extraction module is used to extract features of students' personal learning course information, enterprise recruitment demand information and work project information of employees in corresponding jobs; the correlation evaluation module is used to evaluate the correlation between the corresponding features extracted; the job recommendation module is used to calculate the recommendation degree to generate recommendation results and recommend jobs to students.

[0108] Example 3

[0109] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0110] The processor executes the above-mentioned method for recommending student jobs based on artificial intelligence by calling the computer program stored in the memory.

[0111] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a multimedia image quality evaluation method based on scene recognition provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface for data input and output. This embodiment will not be described in detail here.

[0112] Example 4

[0113] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0114] When the computer program runs on a computer device, the computer device executes the above-mentioned method for recommending student jobs based on artificial intelligence.

[0115] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0116] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0117] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0118] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0119] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one way of division, and there may be other ways of division in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0124] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0125] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A method for recommending student jobs based on artificial intelligence, characterized in that: It includes the following specific steps: Obtain information about students' personal study courses and corporate recruitment needs, as well as project information about employees in corresponding positions; Construct a feature extraction model, import the student's personal learning course information, the company's recruitment demand information and the corresponding job position employee work project information into the feature extraction model to extract the corresponding features; Construct a correlation evaluation model, and import the extracted corresponding features into the correlation evaluation model for evaluation; Construct a student job recommendation model, import the student course comprehensive skill feature vector, recruitment position comprehensive skill feature vector and project comprehensive skill feature vector into the student job recommendation model, and generate recommendation results; The steps of obtaining the student's personal learning course information and the enterprise's recruitment demand information and obtaining the project information of the corresponding job position employees include the following specific steps: S11. Obtain students’ course information through the school’s student management system and organize students’ personal course information; S12. Obtain recruitment demand information from recruiting companies and organize recruitment position data; S13. Obtaining employee work project information for corresponding recruitment positions; The construction of the feature extraction model, importing the student's personal learning course information, the enterprise's recruitment demand information and the corresponding job position employee work project information into the feature extraction model to extract corresponding features includes the following specific steps: S21. Build a standardized feature dictionary that contains all the skill features in the course and job descriptions; S22. Traverse each course outline of the student, match the course outline content with the standardized skill features in the dictionary, and record the number of occurrences of keywords in the course outline that have the same meaning as the standardized skill features, and construct a skill feature vector for each course. The skill feature vector of the ath course is: , where c ap represents the pth skill feature of the ath course, and p belongs to any item from 1 to n. If the ath course does not include the pth skill feature, then c ap =0; S23, traverse the enterprise recruitment demand information, match the recruitment demand text of each position with the standardized skill features in the feature dictionary, and construct the skill feature vector of the recruitment position, where the skill feature vector of the jth recruitment position is: , where c jp represents the pth skill characteristic of the jth recruitment position, and p belongs to any item from 1 to n. If the jth recruitment position does not include the pth skill characteristic, then c jp =0; S24. By traversing the employee's project information, extracting skill keywords, and matching the project information with the standardized skill features in the dictionary, a skill feature vector of the project is constructed, where the skill feature vector of the dth project is: , where c dp represents the pth skill feature of the dth project, and p belongs to any one of 1 to n. If the dth project does not include the pth skill feature, then c dp =0; The construction of the association evaluation model and the importation of the extracted corresponding features into the association evaluation model for evaluation include the following specific steps: S31. Substitute the eigenvector of each course into the course standardized eigenvalue calculation formula to calculate the course standardized eigenvalue, where the standardized eigenvalue calculation formula for the pth skill of the ath course is: , where Za is the standardized score of the a-th course, Tp is the number of keyword occurrences of the p-th skill, and T is the total number of keyword occurrences. The standardized score calculation formula for the a-th course is: , S a,i is the score of the ath course of the i-th student, M a is the average score of the ath course of all students in the i-th student’s major, is the standard deviation of the score of the ath course of the i-th student’s major, where the standard deviation of the score of the ath course of the i-th student’s major is calculated as follows: , G is the number of students in the major of the i-th student; S32. Obtain all skill feature values ​​of the a-th course to generate a standardized feature vector of the course, wherein the standardized feature vector of the a-th course is: ,in, is the standardized feature value of the pth skill of the ath course, and p belongs to any item from 1 to n. Substitute the standardized feature vector of each course into the comprehensive skill feature vector generation formula to generate the comprehensive skill feature vector of the course, where the comprehensive skill feature vector generation formula corresponding to the course is: ,in, is the pth comprehensive skill characteristic value corresponding to the course, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic corresponding to the course is: , where B a is the credits of the ath course, C is the total credits of the courses taken, and N is the number of courses; S33. Substitute the feature vector of the recruitment position into the generation formula of the comprehensive skill feature vector corresponding to the recruitment position to generate the comprehensive skill feature vector corresponding to the recruitment position, wherein the generation formula of the comprehensive skill feature vector corresponding to the recruitment position is: ,in, is the pth comprehensive skill characteristic value corresponding to the recruitment position, and p is any one of 1 to n. The calculation formula for the pth comprehensive skill characteristic value corresponding to the recruitment position is: , where k1 is the number of times a skill appears in semantic analysis, w1 is the weight of the number of times a skill appears in semantic analysis, k2 is the number of times a skill appears in historical data, and w2 is the weight of the number of times a skill appears in historical data; S34, substituting the project skill feature vector into the comprehensive skill feature vector generation formula corresponding to the project to generate the project comprehensive skill feature vector, wherein the comprehensive skill feature vector generation formula corresponding to the project is: ,in, is the pth comprehensive skill characteristic value corresponding to the project, and p belongs to any item from 1 to n. The calculation formula of the pth comprehensive skill characteristic value corresponding to the project is: , where c dp is the pth skill feature of the dth project, and p belongs to any one of 1 to n, and L is the total number of participating projects; S35. Substitute the course comprehensive skill feature vector and the recruitment position comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the recruitment position comprehensive skill. The correlation calculation formula between the course comprehensive skill and the recruitment position comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n; S36. Substitute the course comprehensive skill feature vector and the project comprehensive skill feature vector into the correlation calculation formula to calculate the correlation between the course comprehensive skill and the project comprehensive skill. The correlation calculation formula between the course comprehensive skill and the project comprehensive skill is: , where p is the pth skill feature, and p belongs to any item from 1 to n.

2. The method for recommending student jobs based on artificial intelligence as claimed in claim 1, characterized in that: The construction of the student job recommendation model, importing the student course comprehensive skill feature vector, the recruitment position comprehensive skill feature vector and the project comprehensive skill feature vector into the student job recommendation model, and generating the recommendation result includes the following specific steps: S41. Substitute the correlation between the course comprehensive skills and the recruitment position comprehensive skills and the correlation between the course comprehensive skills and the project comprehensive skills into the position recommendation calculation formula to calculate the position recommendation degree, where the position recommendation calculation formula is: ,in, is the correlation weight between the comprehensive skills of the course and the comprehensive skills of the recruitment position, is the correlation weight between the course comprehensive skills and the project comprehensive skills, and , sort the required recommendation list, select the top ten with the highest recommendation, and generate a job recommendation list.

3. An artificial intelligence-based student job recommendation system, which is implemented based on the artificial intelligence-based student job recommendation method as claimed in any one of claims 1-2, characterized in that: Specifically include: The data acquisition module is used to obtain students' personal learning course information and corporate recruitment demand information, as well as project information of employees in corresponding positions; Feature extraction module, used to extract features of students’ personal learning course information, enterprise recruitment demand information, and work project information of employees in corresponding positions; A correlation evaluation module is used to evaluate the correlation between the corresponding features extracted; The job recommendation module is used to calculate the recommendation degree, generate recommendation results, and recommend jobs to students.

4. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the student job recommendation method based on artificial intelligence as described in any one of claims 1-2 by calling the computer program stored in the memory.

5. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes an artificial intelligence-based student job recommendation method as described in any one of claims 1-2.

Images