AI artificial intelligence-based occupational planning auxiliary analysis method and system

Abstract

The invention relates to the technical field of artificial intelligence decision support, in particular to an AI artificial intelligence-based professional planning auxiliary analysis method and system. The method comprises the following steps: collecting user feature data and position feature data, and carrying out standardization processing; constructing a multi-level decision-making structure by using an analytic hierarchy process method, performing quantitative analysis on the users and the occupations by using a pairwise comparison matrix, and performing calculation to obtain feature weights and feature values of the users and the occupations; fusing the user characteristic value and the occupational characteristic value into a decision tree model, calculating the matching similarity between the user and the occupational, and dynamically generating an occupational planning path; and defining a feedback error value based on the user and occupational matching similarity and the user score value, and dynamically adjusting the occupational feature weight. According to the AI artificial intelligence-based occupational planning auxiliary analysis method and system, a dynamic and personalized occupational planning scheme is provided for a user by combining an analytic hierarchy process method and a decision tree model and defining a feedback error value.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence decision support technology, and in particular to a career planning auxiliary analysis method and system based on AI artificial intelligence. Background Art

[0002] The AI-based career planning auxiliary analysis method and system aims to improve the accuracy of career matching and the dynamic adjustment of personalized career planning. By integrating the analytical hierarchical process method with the multi-level decision tree model, it controls the multi-dimensional weight distribution of user characteristics and job characteristics and the generation of dynamic planning paths, thus achieving a dynamic and continuously optimized career planning solution.

[0003] Existing career planning auxiliary analysis methods and systems are usually difficult to accurately capture the complex relationship between users' multi-dimensional characteristics and job requirements. In addition, due to the multi-dimensional nature of user characteristics, insufficient hierarchy when matching job requirements, and the great differences in the impact of various characteristics on the final matching decision, the career matching results are not accurate and personalized enough, and cannot effectively adapt to the changing needs of users in the process of career development. Therefore, a career planning auxiliary analysis method and system based on AI artificial intelligence is provided. Summary of the invention

[0004] The purpose of the present invention is to provide a career planning auxiliary analysis method and system based on AI artificial intelligence, so as to solve the problems raised in the above background technology that the career matching results are not accurate enough, not personalized enough, and cannot effectively adapt to the changing needs of users in the process of career development due to the multi-dimensional characteristics of user characteristics, insufficient hierarchy when matching job requirements, and the great differences in the influence of various characteristics on the final matching decision.

[0005] To achieve the above objectives, the present invention aims to provide a career planning auxiliary analysis method based on AI artificial intelligence, comprising:

[0006] S1. Collect user characteristic data and position characteristic data and perform standardization processing;

[0007] S2. Use the analytical hierarchy process to construct a multi-level decision-making structure, use the pairwise comparison matrix to quantitatively analyze users and occupations, and calculate the characteristic weights and characteristic values ​​of users and occupations;

[0008] S3, integrating the user feature value and the occupation feature value into the decision tree model, calculating the matching similarity between the user and the occupation, and dynamically generating the career planning path;

[0009] S4. Define a feedback error value based on the user and occupation matching similarity and the user rating value, and dynamically adjust the occupation feature weight based on the feedback error value.

[0010] As a further improvement of the technical solution, in S1, user characteristic data and position characteristic data are collected and standardized, and the specific method steps are as follows:

[0011] S1.1. User characteristic data U includes: education, work experience, career interests, skills mastered, current career and salary expectations;

[0012] U=[u1,u2,u3,…,u6];

[0013] Among them, u1 represents education; u2 represents work experience; u3 represents career interest; u4 represents skill mastery; u5 represents current occupation; u6 represents salary expectation;

[0014] Job characteristic data J include:

[0015] J = [j1, j2, j3];

[0016] Among them, j1 represents the salary level of the position; j2 represents the industry type of the position; j3 represents the career development potential;

[0017] S1.2. Standardize the user feature data U and the position feature data J:

[0018] For user feature u in user feature data U i To standardize:

[0019]

[0020] Where i is a subscript, i∈[1,6]; u i is the i-th user feature; is the mean of the i-th user feature; is the standard deviation of the i-th user feature;

[0021] For job feature j in job feature data J k To standardize:

[0022]

[0023] Where k is a subscript, k∈[1,3]; j k is the k-th position feature; is the mean of the k-th position characteristic; is the standard deviation of the k-th position characteristic;

[0024] S1.3, after standardization:

[0025] User feature matrix U′:

[0026] U′=[u′1,u′2,u′3,…,u′6];

[0027] Position feature matrix J′:

[0028] J′=[j′1,j′2,j′3];

[0029] Among them, u′1 represents the standardized academic qualifications; u′2 represents the standardized work experience; u′3 represents the standardized career interests; u′4 represents the standardized skills mastery; u′5 represents the standardized current occupation; u′6 represents the standardized salary expectation; j′1 represents the standardized position salary level; j′2 represents the standardized position industry type; j′3 represents the standardized career development potential.

[0030] As a further improvement of the technical solution, in S2, the analytical hierarchy process method is used to calculate the relative importance weights of user characteristics and job characteristics, so that the weighted characteristic values ​​are used for personalized recommendation of job matching;

[0031] The method uses the analytical hierarchy process to construct a multi-level decision structure, uses a pairwise comparison matrix to perform quantitative analysis on users and occupations, and calculates the characteristic weights and characteristic values ​​of users and occupations. The specific method steps are as follows:

[0032] S2.1. Use the analytical hierarchy process to construct a multi-level decision-making structure:

[0033] Target level: Optimize the matching degree of career planning;

[0034] Criteria layer: user feature matrix U′ and position feature matrix J′;

[0035] S2.2. Use the analytic hierarchy process to construct a user feature pairwise comparison matrix A u , calculate the user feature weight w u And the user characteristic value U * ;

[0036] S2.3. Use the analytic hierarchy process to construct a pairwise comparison matrix of occupational characteristics A j , calculate the occupational feature weight w j and the position characteristic value J * .

[0037] As a further improvement of the technical solution, in S2.2, the user feature pairwise comparison matrix A is constructed using the analysis hierarchy process method u , calculate the user feature weight w u And the user characteristic value U * , the specific steps are as follows:

[0038] S2.2.1. Constructing a six-order user feature pairwise comparison matrix A u :

[0039]

[0040] Among them, A u is the user feature pairwise comparison matrix; a 12 Indicates the importance of the first user feature relative to the second user feature, and so on;

[0041] S2.2.2. Compare the user features into pairs using the matrix A u Perform column normalization:

[0042]

[0043] in, is the user feature pairwise comparison matrix after column normalization; i is the subscript, i∈[1,6];

[0044] S2.2.3 Calculation The mean of each row is used to obtain the user feature weight of the i-th column And add them together to get the user feature weight w u :

[0045]

[0046]

[0047] in, is the feature weight of the user in the i-th column; p is the subscript, p∈[1,6]; w u is the user feature weight;

[0048] S2.2.3. According to the user feature weight w u , weighted calculation to obtain the user characteristic value U * :

[0049]

[0050] Among them, U * is the user characteristic value; u′ i is the i-th standardized user feature.

[0051] As a further improvement of the present technical solution, in S2.3, the occupational characteristic pairwise comparison matrix A is constructed using the analytic hierarchy process method. j , calculate the occupational feature weight w j and the position characteristic value J * , the specific steps are as follows:

[0052] S2.3.1. Constructing a third-order occupational characteristic pairwise comparison matrix A j :

[0053]

[0054] Among them, A j is the pairwise comparison matrix of occupational characteristics; b 12 It indicates the importance of the first occupational characteristic relative to the second occupational characteristic, and so on;

[0055] S2.3.2. Pairwise comparison matrix A of occupational characteristics j Perform column normalization:

[0056]

[0057] in, is the column-normalized occupational characteristic pairwise comparison matrix; k is the subscript, k∈[1,3];

[0058] S2.3.3 Calculation The mean of each row gives the occupational feature weight w of the kth column jk , and add them together to get the occupational characteristic weight w j :

[0059]

[0060] w j =[w j1 ,w j2 w j3 ];

[0061] Among them, w jk is the occupational feature weight w of the kth column jk ; q is a subscript, q∈[1,3]; w j is the occupational characteristic weight;

[0062] S2.3.4. According to the occupational characteristic weight w j , weighted calculation to obtain the position characteristic value J * :

[0063]

[0064] Among them, J * is the position characteristic value; j′ k is the kth standardized occupational characteristic.

[0065] As a further improvement of the technical solution, in S3, the user feature value and the occupation feature value are integrated into the decision tree model, the matching similarity between the user and the occupation is calculated, and the career planning path is dynamically generated. The specific method is as follows:

[0066] S3.1. Constructing the fused user feature value U * and occupational characteristic value J* Multi-level decision tree model;

[0067] S3.2. Based on user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * );

[0068] S3.3. Based on the matching similarity between users and occupations, a career planning path is dynamically generated through a dynamic programming algorithm.

[0069] As a further improvement of the technical solution, in S3.1, construct the fused user feature value U * and occupational characteristic value J * The multi-level decision tree model is as follows:

[0070] The nodes of the multi-level decision tree model are defined as: matching degree calculation of feature dimensions;

[0071] The node matching function is as follows:

[0072]

[0073] Among them, f node (U * ,J * ) is the matching function of the node.

[0074] As a further improvement of the technical solution, in S3.2, based on the user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * ), the specific method is as follows:

[0075]

[0076]

[0077] Among them, S(U * ,J * ) is the matching similarity between user and occupation S(U * ,J * );D max is the maximum matching gap;

[0078] In S3.3, based on the matching similarity between the user and the occupation, a career planning path is dynamically generated through a dynamic programming algorithm. The specific method is as follows:

[0079]

[0080] Among them, Optimal Path is the career planning path; N is the total number of all occupations; n is the nth occupation; is the matching similarity between the user and the nth occupation; For the future development potential of the nth career.

[0081] As a further improvement of the technical solution, in S4, a feedback error value is defined based on the matching similarity between the user and the occupation and the user rating value, and the occupation feature weight is dynamically adjusted based on the feedback error value. The specific method is as follows:

[0082] S4.1. Define a feedback error value ΔS based on the matching similarity and user rating value:

[0083] ΔS=|S(U * ,J * )-FeedbackScore|;

[0084] Among them, Feedback Score is the rating value corresponding to the user rating;

[0085] S4.2. Dynamically adjust the job feature weights based on the feedback error value ΔS:

[0086]

[0087] in, is the adjusted weight of the k-th column position feature; α is the learning rate parameter; The feedback error value ΔS is the weight of the k-th column position feature The partial derivative of .

[0088] On the other hand, the present invention provides a career planning auxiliary analysis system based on AI artificial intelligence, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned career planning auxiliary analysis method based on AI artificial intelligence.

[0089] Compared with the prior art, the present invention has the following beneficial effects:

[0090] 1. In this AI-based career planning auxiliary analysis method and system, based on the fusion of analytical hierarchy process method and multi-level decision tree model, the multi-dimensional matching similarity between user characteristics and job characteristics is calculated, and the optimal career planning path is dynamically generated.

[0091] 2. In this AI-based career planning auxiliary analysis method and system, the feedback error value is defined based on the matching similarity between users and occupations and the user rating value, so as to dynamically adjust the occupational feature weights according to user feedback and dynamically optimize the subsequent career matching and planning paths. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 The figure is a flow chart of the overall method of the present invention. DETAILED DESCRIPTION

[0093] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0094] Embodiment 1:

[0095] See also Figure 1 As shown, this embodiment provides a career planning auxiliary analysis method based on AI artificial intelligence, including the following steps:

[0096] S1. Collect user characteristic data and position characteristic data and perform standardization processing;

[0097] In this embodiment S1, user characteristic data and position characteristic data are collected and standardized. The specific method steps are as follows:

[0098] S1.1. User characteristic data U includes: education, work experience, career interests, skills mastered, current career and salary expectations;

[0099] U=[u1,u2,u3,…,u6];

[0100] Among them, u1 represents education; u2 represents work experience; u3 represents career interest; u4 represents skill mastery; u5 represents current occupation; u6 represents salary expectation;

[0101] Job characteristic data J include:

[0102] J = [j1, j2, j3];

[0103] Among them, j1 represents the salary level of the position; j2 represents the industry type of the position; j3 represents the career development potential;

[0104] In this embodiment:

[0105] u1 represents educational background: 0 represents high school, 1 represents undergraduate, 2 represents master's degree, and 3 represents doctorate;

[0106] u2 represents work experience: 0 represents 0 years, 1 represents 1 year, and so on;

[0107] u3 represents career interest: it is expressed using a Likert scale, where specific positions are represented by numerical values, 0 represents no interest, 1 represents a technical position, 2 represents a management position, etc.;

[0108] u4 indicates skill mastery: expressed using a Likert scale;

[0109] u5 indicates current occupation: 0 indicates no job, 1 indicates a technical position, 2 indicates a management position, etc.;

[0110] u6 represents salary expectation: a numerical value is used to represent the annual salary;

[0111] j1 represents the salary level of the position: it is expressed as a numerical value, representing the level of annual salary;

[0112] j2 represents the type of job industry: it uses the same numerical value as the current occupation u5;

[0113] j3 represents career development potential: the value 1-10 represents the future growth potential of the career, 1 represents low potential, and 10 represents high potential;

[0114] S1.2. Standardize the user feature data U and the position feature data J:

[0115] For user feature u in user feature data U i To standardize:

[0116]

[0117] Where i is a subscript, i∈[1,6]; u i is the i-th user feature; is the mean of the i-th user feature; is the standard deviation of the i-th user feature;

[0118] For job feature j in job feature data J k To standardize:

[0119]

[0120] Where k is a subscript, k∈[1,3]; j k is the k-th position feature; is the mean of the k-th position characteristic; σ jk is the standard deviation of the k-th position characteristic;

[0121] S1.3, after standardization:

[0122] User feature matrix U′:

[0123] U′=[u′1,u′2,u′3,…,u′6];

[0124] Position feature matrix J′:

[0125] J′=[j′1,j′2,j′3];

[0126] Among them, u′1 represents the standardized academic qualifications; u′2 represents the standardized work experience; u′3 represents the standardized career interests; u′4 represents the standardized skills mastery; u′5 represents the standardized current occupation; u′6 represents the standardized salary expectation; j′1 represents the standardized position salary level; j′2 represents the standardized position industry type; j′3 represents the standardized career development potential.

[0127] S2. Use the analytical hierarchy process to construct a multi-level decision-making structure, use the pairwise comparison matrix to quantitatively analyze users and occupations, and calculate the characteristic weights and characteristic values ​​of users and occupations;

[0128] In this embodiment S2, the analytic hierarchy process is used to calculate the relative importance weights of user characteristics and job characteristics, and the weighted characteristic values ​​are used for personalized recommendation of job matching;

[0129] In this embodiment, the analytic hierarchy process is used to construct a multi-level decision structure, and a pairwise comparison matrix is ​​used to perform quantitative analysis on users and occupations, and the characteristic weights and characteristic values ​​of users and occupations are calculated. The specific method steps are as follows:

[0130] S2.1. Use the analytical hierarchy process to construct a multi-level decision-making structure:

[0131] Target level: Optimize the matching degree of career planning;

[0132] Criteria layer: user feature matrix U′ and position feature matrix J′;

[0133] S2.2. Use the analytic hierarchy process to construct a user feature pairwise comparison matrix A u , calculate the user feature weight w u And the user characteristic value U * ;

[0134] S2.3. Use the analytic hierarchy process to construct a pairwise comparison matrix of occupational characteristics A j , calculate the occupational feature weight w j and the position characteristic value J * .

[0135] In this embodiment, the Analytical Hierarchy Process is a mathematical method for multi-criteria decision making, which determines the weights of different criteria by comparing their importance in pairs; in this embodiment, the purpose of using AHP is to ensure more accurate personalized matching in the career planning process by quantifying the relative importance of user and position characteristics;

[0136] Construct a hierarchical decision-making structure to decompose the complex career planning problem into multiple easy-to-handle levels. In this structure, the target layer is the ultimate goal to be optimized: optimizing the career planning matching degree; the criterion layer includes the user feature matrix and the position feature matrix; through this structure, the analytical hierarchy process method can systematically handle user preferences and career characteristics;

[0137] Use the user feature pairwise comparison matrix to compare each user's features, evaluate their relative importance in career planning, and calculate the weight of each user feature based on the user's preference to quantify the impact of each user feature on the final career matching decision;

[0138] The occupational characteristic pairwise comparison matrix is ​​used to compare the job characteristics in pairs, and the weight of each job characteristic is calculated to quantify the impact of job characteristics on user decisions.

[0139] In this embodiment S2.2, the user feature pairwise comparison matrix A is constructed using the analytic hierarchy process method. u , calculate the user feature weight w u And the user characteristic value U * , the specific steps are as follows:

[0140] S2.2.1. Constructing a six-order user feature pairwise comparison matrix A u :

[0141]

[0142] Among them, A u is the user feature pairwise comparison matrix; a 12 Indicates the importance of the first user feature relative to the second user feature, and so on;

[0143] S2.2.2. Compare the user features into pairs using the matrix A u Perform column normalization:

[0144]

[0145] in, is the user feature pairwise comparison matrix after column normalization; i is the subscript, i∈[1,6];

[0146] S2.2.3 Calculation The mean of each row is used to obtain the user feature weight of the i-th column And add them together to get the user feature weight w u :

[0147]

[0148]

[0149] in, is the feature weight of the user in the i-th column; p is the subscript, p∈[1,6]; w u is the user feature weight;

[0150] S2.2.3. According to the user feature weight w u , weighted calculation to obtain the user characteristic value U * :

[0151]

[0152] Among them, U * is the user characteristic value; u′ i is the i-th standardized user feature.

[0153] In this embodiment S2.3, the analytic hierarchy process is used to construct the occupational characteristics pairwise comparison matrix A j , calculate the occupational feature weight w j and the position characteristic value J * , the specific steps are as follows:

[0154] S2.3.1. Constructing a third-order occupational characteristic pairwise comparison matrix A j :

[0155]

[0156] Among them, A j is the pairwise comparison matrix of occupational characteristics; b 12 It indicates the importance of the first occupational characteristic relative to the second occupational characteristic, and so on;

[0157] S2.3.2. Pairwise comparison matrix A of occupational characteristics j Perform column normalization:

[0158]

[0159] in, is the column-normalized occupational characteristic pairwise comparison matrix; k is the subscript, k∈[1,3];

[0160] S2.3.3 Calculation The mean of each row gives the occupational feature weight of the kth column And add them together to get the occupational characteristic weight w j :

[0161]

[0162]

[0163] in, is the occupational feature weight of the kth column q is a subscript, q∈[1,3]; w j is the occupational characteristic weight;

[0164] S2.3.4. According to the occupational characteristic weight w j , weighted calculation to obtain the position characteristic value J * :

[0165]

[0166] Among them, J * is the position characteristic value; j′ k is the kth standardized occupational characteristic.

[0167] S3, integrating the user feature value and the occupation feature value into the decision tree model, calculating the matching similarity between the user and the occupation, and dynamically generating the career planning path;

[0168] In this embodiment S3, the user feature value and the occupation feature value are integrated into the decision tree model, the matching similarity between the user and the occupation is calculated, and the career planning path is dynamically generated. The specific method is as follows:

[0169] S3.1. Constructing the fused user feature value U * and occupational characteristic value J * Multi-level decision tree model;

[0170] S3.2. Based on user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * );

[0171] S3.3. Based on the matching similarity between users and occupations, a career planning path is dynamically generated through a dynamic programming algorithm.

[0172] In this embodiment S3.1, the fused user feature value U is constructed * and occupational characteristic value J * The multi-level decision tree model is as follows:

[0173] The nodes of the multi-level decision tree model are defined as: matching degree calculation of feature dimensions;

[0174] The node matching function is as follows:

[0175]

[0176] Among them, f node (U * ,J * ) is the matching function of the node.

[0177] In this embodiment,

[0178] User features u′1,u′6 are mapped to job salary level j′1, indicating the match between education level, salary expectation and job salary;

[0179] User features u′3, u′5, mapped to job salary level j′2, indicating the match between career interests, current career and job type;

[0180] User features u′2, u′4 are mapped to job salary level j′3, indicating the matching of work experience, skill mastery and job development potential.

[0181] In this embodiment S3.2, based on the user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * ), the specific method is as follows:

[0182]

[0183]

[0184] Among them, S(U * ,J * ) is the matching similarity between user and occupation S(U * ,J * );D max is the maximum matching gap;

[0185] In this embodiment, the maximum matching gap D max It means that the node matching function f is the maximum difference between user characteristics and job characteristics. node (U * ,J * )’s maximum value;

[0186] In this embodiment S3.3, based on the matching similarity between users and occupations, a career planning path is dynamically generated through a dynamic programming algorithm. The specific method is as follows:

[0187]

[0188] Among them, Optimal Path is the career planning path; N is the total number of all occupations; n is the nth occupation; is the matching similarity between the user and the nth occupation; For the future development potential of the nth career.

[0189] In this embodiment, the future development potential of the nth occupation The calculation is as follows:

[0190]

[0191] Among them, Market Growth Rate is the market growth rate of the industry in which the position is located; Skill Demand Index is the changing trend of future skill requirements for the position; Job Stability is the long-term stability of the position and the potential for salary growth;

[0192] Through dynamic programming algorithms, different career development stages are simulated, and the career planning path finally generated is the optimal path selection based on comprehensive consideration of similarity and future potential;

[0193] Among all possible career paths, select those positions with the highest matching similarity and the greatest future development potential to generate the user's optimal career planning path;

[0194] In this embodiment, the optimal job recommendations for the user's current career stage are first given, and these jobs are generated based on the current matching similarity and current career goals; then multiple optional paths are provided to the user.

[0195] S4, defining a feedback error value based on the user and occupation matching similarity and the user rating value, and dynamically adjusting the occupation feature weight based on the feedback error value;

[0196] In this embodiment S4, a feedback error value is defined based on the matching similarity between the user and the occupation and the user rating value, and the occupation feature weight is dynamically adjusted based on the feedback error value. The specific method is as follows:

[0197] S4.1. Define a feedback error value ΔS based on the matching similarity and user rating value:

[0198] ΔS=|S(U * ,J * )-Feedback Score|;

[0199] Among them, Feedback Score is the rating value corresponding to the user rating;

[0200] S4.2. Dynamically adjust the job feature weights based on the feedback error value ΔS:

[0201]

[0202] in, is the adjusted weight of the k-th column position feature; α is the learning rate parameter; The feedback error value ΔS is the weight of the k-th column position feature The partial derivative of .

[0203] In this embodiment, the feedback error value ΔS is used to calculate the deviation when matching similarity. If the deviation is large, the corresponding occupational feature weight needs to be adjusted. By feedbacking the error value ΔS, the position feature weight can be dynamically adjusted;

[0204] User feature weights need to be modified subjectively by users based on their own circumstances.

[0205] Embodiment 2:

[0206] This embodiment provides a career planning auxiliary analysis system based on AI artificial intelligence, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the above-mentioned career planning auxiliary analysis method based on AI artificial intelligence.

[0207] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. The AI-based career planning auxiliary analysis method is characterized by: The following steps are involved: S1. Collect user characteristic data and position characteristic data and perform standardization processing; S2. Use the analytical hierarchy process to construct a multi-level decision-making structure, use the pairwise comparison matrix to quantitatively analyze users and occupations, and calculate the characteristic weights and characteristic values ​​of users and occupations; S3, integrating the user feature value and the occupation feature value into the decision tree model, calculating the matching similarity between the user and the occupation, and dynamically generating the career planning path; S4. Define a feedback error value based on the user and occupation matching similarity and the user rating value, and dynamically adjust the occupation feature weight based on the feedback error value.

2. The career planning auxiliary analysis method based on AI artificial intelligence according to claim 1 is characterized by: In S1, user characteristic data and position characteristic data are collected and standardized. The specific method steps are as follows: S1.

1. User characteristic data U includes: education, work experience, career interests, skills mastered, current career and salary expectations; U=[u1,u2,u3,…,u6]; Among them, u1 represents education; u2 represents work experience; u3 represents career interest; u4 represents skill mastery; u5 represents current occupation; u6 represents salary expectation; Job characteristic data J include: J = [j1, j2, j3]; Among them, j1 represents the salary level of the position; j2 represents the industry type of the position; j3 represents the career development potential; S1.

2. Standardize the user feature data U and the position feature data J: For user feature u in user feature data U i To standardize: Where i is a subscript, i∈[1,6]; u i is the i-th user feature; is the mean of the i-th user feature; is the standard deviation of the i-th user feature; For job feature j in job feature data J k To standardize: Where k is a subscript, k∈[1,3]; j k is the k-th position feature; is the mean of the k-th position characteristic; is the standard deviation of the k-th position characteristic; S1.3, after standardization: User feature matrix U′: U′=[u′1,u′2,u′3,…,u′6]; Position feature matrix J′: J′=[j′1,j′2,j′3]; Among them, u′1 represents the standardized academic qualifications; u′2 represents the standardized work experience; u′3 represents the standardized career interests; u'4 represents the standardized skills mastery; u'5 represents the standardized current occupation; u'6 represents the standardized salary expectation; j'1 represents the standardized position salary level; j'2 represents the standardized position industry type; j'3 represents the standardized career development potential.

3. The career planning auxiliary analysis method based on AI artificial intelligence according to claim 2 is characterized by: In S2, the analytic hierarchy process is used to calculate the relative importance weights of user characteristics and job characteristics, so that the weighted characteristic values ​​are used for personalized recommendation of job matching; The method uses the analytical hierarchy process to construct a multi-level decision structure, uses a pairwise comparison matrix to perform quantitative analysis on users and occupations, and calculates the characteristic weights and characteristic values ​​of users and occupations. The specific method steps are as follows: S2.

1. Use the analytical hierarchy process to construct a multi-level decision-making structure: Target level: Optimize the matching degree of career planning; Criteria layer: user feature matrix U′ and position feature matrix J′; S2.

2. Use the analytic hierarchy process to construct a user feature pairwise comparison matrix A u , calculate the user feature weight w u And the user characteristic value U * ; S2.

3. Use the analytic hierarchy process to construct a pairwise comparison matrix of occupational characteristics A j , calculate the occupational feature weight w j and the position characteristic value J * .

4. The career planning auxiliary analysis method based on AI artificial intelligence according to claim 3 is characterized by: In S2.2, the user feature pairwise comparison matrix A is constructed using the analytic hierarchy process method. u , calculate the user feature weight w u And the user characteristic value U * , the specific steps are as follows: S2.2.

1. Constructing a six-order user feature pairwise comparison matrix A u : Among them, A u is the user feature pairwise comparison matrix; a 12 Indicates the importance of the first user feature relative to the second user feature, and so on; S2.2.

2. Compare the user features into pairs using the matrix A u Perform column normalization: in, is the user feature pairwise comparison matrix after column normalization; i is the subscript, i∈[1,6]; S2.2.3 Calculation The mean of each row is used to obtain the user feature weight of the i-th column And add them together to get the user feature weight w u : in, is the feature weight of the user in the i-th column; p is the subscript, p∈[1,6]; w u is the user feature weight; S2.2.

3. According to the user feature weight w u , weighted calculation to obtain the user characteristic value U * : Among them, U * is the user characteristic value; u′ i is the i-th standardized user feature.

5. The AI-based career planning auxiliary analysis method according to claim 4 is characterized in that: In S2.3, the analytic hierarchy process is used to construct the occupational characteristics pairwise comparison matrix A j , calculate the occupational feature weight w j and the position characteristic value J * , the specific steps are as follows: S2.3.

1. Constructing a third-order occupational characteristic pairwise comparison matrix A j : Among them, A j is the pairwise comparison matrix of occupational characteristics; b 12 It indicates the importance of the first occupational characteristic relative to the second occupational characteristic, and so on; S2.3.

2. Pairwise comparison matrix A of occupational characteristics j Perform column normalization: in, is the column-normalized occupational characteristic pairwise comparison matrix; k is the subscript, k∈[1,3]; S2.3.3 Calculation The mean of each row gives the occupational feature weight of the kth column And add them together to get the occupational characteristic weight w j : Among them, w jk is the occupational feature weight w of the kth column jk ; q is a subscript, q∈[1,3]; w j is the occupational characteristic weight; S2.3.

4. According to the occupational characteristic weight w j , weighted calculation to obtain the position characteristic value J * : Among them, J * is the position characteristic value; j′ k is the kth standardized occupational characteristic.

6. The AI-based career planning auxiliary analysis method according to claim 5 is characterized by: In S3, the user feature value and the occupation feature value are integrated into the decision tree model, the matching similarity between the user and the occupation is calculated, and the career planning path is dynamically generated. The specific method is as follows: S3.

1. Constructing the fused user feature value U * and occupational characteristic value J * Multi-level decision tree model; S3.

2. Based on user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * ); S3.

3. Based on the matching similarity between users and occupations, a career planning path is dynamically generated through a dynamic programming algorithm.

7. The AI-based career planning auxiliary analysis method according to claim 6 is characterized by: In S3.1, the fused user feature value U is constructed * and occupational characteristic value J * The multi-level decision tree model is as follows: The nodes of the multi-level decision tree model are defined as: matching degree calculation of feature dimensions; The node matching function is as follows: Among them, f node (U * ,J * ) is the matching function of the node.

8. The AI-based career planning auxiliary analysis method according to claim 7 is characterized in that: In S3.2, based on the user characteristic value U * and occupational characteristic value J * , calculate the matching similarity S(U * ,J * ), the specific method is as follows: Among them, S(U * ,J * ) is the matching similarity between user and occupation S(U * ,J * );D max is the maximum matching gap; In S3.3, based on the matching similarity between the user and the occupation, a career planning path is dynamically generated through a dynamic programming algorithm. The specific method is as follows: Among them, Optimal Path is the career planning path; N is the total number of all occupations; n is the nth occupation; is the matching similarity between the user and the nth occupation; For the future development potential of the nth career.

9. The AI-based career planning auxiliary analysis method according to claim 8 is characterized by: In S4, a feedback error value is defined based on the matching similarity between the user and the occupation and the user rating value, and the occupation feature weight is dynamically adjusted based on the feedback error value. The specific method is as follows: S4.

1. Define a feedback error value ΔS based on the matching similarity and user rating value: ΔS=|S(U * ,J * )-Feedback Score|; Among them, Feedback Score is the rating value corresponding to the user rating; S4.

2. Dynamically adjust the job feature weights based on the feedback error value ΔS: in, is the adjusted weight of the k-th column position feature; α is the learning rate parameter; The feedback error value ΔS is the weight of the k-th column position feature The partial derivative of .

10. A career planning auxiliary analysis system based on AI artificial intelligence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes a computer program to implement the AI ​​artificial intelligence-based career planning auxiliary analysis method as described in any one of claims 1 to 9.

Images