Artificial intelligence-based talent evaluation recommendation method and system

Abstract

The invention relates to the technical field of talent evaluation and distribution, and discloses a talent evaluation recommendation method and system based on artificial intelligence, and the method comprises the following steps: S101, collecting the personnel data of candidates and the post data of posts; s102, preprocessing the personnel data of the candidates and the post data of the posts to obtain third feature data and fourth feature data; s103, constructing graph structure data according to the third feature data and the fourth feature data; step S104, constructing a matching degree prediction model according to the graph structure data, and outputting scores of edges of the graph structure data; and S105, generating a distribution scheme according to the improved genetic algorithm in combination with the matching degree prediction model. According to the invention, objective evaluation of talents is realized, and talent distribution is more reasonable.

Description

Technical Field

[0001] The present invention belongs to the technical field of talent evaluation and allocation, and specifically relates to a talent evaluation and recommendation method and system based on artificial intelligence. Background Art

[0002] In contemporary enterprises, talent assessment and job matching constitute one of the core responsibilities of human resource management. With the intensification of global competition and the rapid development of technology, it is particularly important to discover and allocate suitable talents. The accuracy of talent quality and job matching is directly related to the innovation strength, operational efficiency and sustainable competitiveness of the enterprise. Therefore, how to conduct scientific and accurate talent assessment and arrange them to the most suitable positions has become the most concerned issue in the field of human resource management for various organizations.

[0003] Traditional assessment methods mainly rely on resume screening, interview assessment and skills testing. Resume screening can usually only provide basic information about candidates and cannot fully reflect their comprehensive abilities; interview assessment is easily affected by the interviewer's subjective judgment, making it difficult to ensure the objectivity of the assessment. In addition, the assessment dimensions often focus on hard skills, ignoring soft skills and potential abilities, resulting in incomplete assessment results. Especially in large-scale recruitment processes, manual assessments are inefficient and can easily miss out on outstanding talents.

[0004] In terms of job assignment, traditional methods mainly rely on the experience and intuition of human resource managers to classify candidates. Similar to traditional assessment methods, this approach is often too one-sided and lacks objectivity, resulting in inaccurate recommendation results.

[0005] Therefore, there is an urgent need for a talent assessment and recommendation method to solve the above problems. Summary of the invention

[0006] The present invention provides a talent assessment and recommendation method and system based on artificial intelligence, which solves the technical problems of strong subjectivity, single dimension, low efficiency and poor accuracy in related technologies.

[0007] The present invention provides a talent evaluation and recommendation method and system based on artificial intelligence, comprising the following steps:

[0008] Step S101, collecting personnel data of M candidates and position data of N positions, which are represented by first characteristic data and second characteristic data respectively;

[0009] Personnel data include: education, work experience, professional skills, and health status;

[0010] Position data includes: educational requirements, work experience requirements, and required professional skills;

[0011] Step S102, preprocessing the first characteristic data and the second characteristic data to obtain third characteristic data and fourth characteristic data;

[0012] Step S103, constructing graph structure data according to the third characteristic data and the fourth characteristic data;

[0013] Graph structure data includes: nodes, initial features of nodes, and edges;

[0014] The nodes include: a first node and a second node;

[0015] The first node establishes a mapping relationship with the candidate;

[0016] The second node establishes a mapping relationship with the position;

[0017] The initial feature of the first node is represented by the third feature data of the candidate that establishes a mapping relationship with the first node;

[0018] The initial feature of the second node is represented by the fourth feature data of the position that establishes a mapping relationship with the second node;

[0019] The edge represents the connection relationship between the first node and the second node;

[0020] Step S104, constructing a matching degree prediction model according to the graph structure data, and outputting the scores of the edges of the graph structure data;

[0021] Step S105, generating an allocation plan according to the improved genetic algorithm combined with the matching degree prediction model;

[0022] The allocation plan represents the allocation relationship between M candidates and N positions.

[0023] Furthermore, the educational background, work experience, health condition, educational background requirements and work experience requirements are represented by real number coding, and the professional skills and required professional skills are represented by one-hot coding.

[0024] Furthermore, the step of preprocessing the first feature data and the second feature data includes:

[0025] Step S201, filling missing values ​​in the first feature data and the second feature data by using the most frequently occurring value therein;

[0026] Step S202, replacing the abnormal values ​​in the first feature data and the second feature data by calculating the mean of all non-abnormal values;

[0027] Step S203: normalize the first feature data and the second feature data using a z-score normalization method.

[0028] Furthermore, the matching degree prediction model includes: a first hidden layer, a second hidden layer, a third hidden layer and a classifier;

[0029] The first hidden layer includes M first units, the mth first unit inputs the initial feature of the mth first node of the graph structure data, and outputs the first updated feature;

[0030] The second hidden layer includes N second units, the nth second unit inputs the initial feature of the nth second node of the graph structure data, and outputs the second updated feature;

[0031] The third hidden layer inputs the graph structure data, and outputs the third updated feature and the fourth updated feature after the first updated feature and the second updated feature are updated;

[0032] The third updated feature and the fourth updated feature are respectively put into the classifier, and the classification space of the classifier represents the score of the edge of the graph structure data.

[0033] Furthermore, the first hidden layer and the second hidden layer are constructed based on a multi-layer perceptron.

[0034] Furthermore, the calculation formula of the third hidden layer is:

[0035]

[0036] in represents the updated features of the node, H represents the initial features of the node, W represents the weight parameter, represents the weighted adjacency matrix, A represents the adjacency matrix of the third hidden layer input graph structure data, the elements of the adjacency matrix represent the connection relationship between the first node and the second node, and the element value is represented by 0 or 1, 0 means that there is no connection relationship between the nodes, otherwise there is a connection relationship, I represents the unit matrix, the element value on the diagonal of the unit matrix is ​​assigned to 1, and the remaining element values ​​are assigned to 0, represents the normalized degree matrix, the elements of the degree matrix represent the number of edge connections with the node, ReLU represents the ReLU activation function, the updated features of the above nodes include: the first updated features of the first node and the second updated features of the second node, and the initial features of the above nodes include: the initial features of the first node and the initial features of the second node.

[0037] Furthermore, the sample labels are used as training samples of the matching prediction model through manual annotation.

[0038] Furthermore, the generation of the allocation scheme according to the improved genetic algorithm combined with the matching degree prediction model includes the following steps:

[0039] Step S301, generating an initialization population with Q number of individuals meeting the constraint conditions, where Q is a custom parameter;

[0040] Step S302, constructing an objective function by combining a matching degree prediction model;

[0041] The objective function is calculated as follows:

[0042]

[0043] Where Fit represents the fitness value of the individual, represents the score of the edge between the mth first node and the nth second node obtained by the matching prediction model, Represents the element value of the mth row and nth column of the individual code;

[0044] Step S303, obtaining the fitness value of each individual in the initialized population through the objective function calculation;

[0045] Step S304, selecting two individuals with the largest fitness values ​​in the initialization population as parents;

[0046] Step S305, generating a random number in the range of 0 to 1, and when the random number is less than a first threshold, performing a crossover operation that satisfies the constraint condition;

[0047] Step S306, mutating the individuals in the population based on the Cauchy mutation strategy;

[0048] Step S307, if it is determined that the current number of iterations is greater than or equal to the maximum number of iterations, the individual with the largest fitness value in the initialized population is used as the allocation scheme, otherwise, the process returns to step S303, where the maximum number of iterations is a custom parameter.

[0049] Furthermore, the specific steps of step S306 include:

[0050] Step S3061, determining the location parameter and scale parameter of the Cauchy distribution;

[0051] Step S3062, determining the variation ratio;

[0052] Step S3063, generating mutant individuals, for the selected individuals, randomly extracting mutation values ​​from the Cauchy distribution and applying them to each dimension of the individual, the dimension of the individual is represented by each element value of the matrix.

[0053] The present invention also provides a talent evaluation and recommendation method based on artificial intelligence, comprising the following modules:

[0054] A data collection module, which is used to collect personnel data of candidates and position data of positions;

[0055] A preprocessing module, which is used to preprocess the personnel data of the candidate and the position data of the position to obtain the third characteristic data and the fourth characteristic data;

[0056] A graph structure building module, which is used to build graph structure data according to the third feature data and the fourth feature data;

[0057] A matching prediction module is used to construct a matching prediction model based on the graph structure data and output the scores of the edges of the graph structure data;

[0058] The allocation scheme generation module is used to generate an allocation scheme based on an improved genetic algorithm combined with a matching degree prediction model.

[0059] The beneficial effects of the present invention are as follows: the present invention comprehensively considers the multi-dimensional characteristics of candidates and positions by constructing a matching degree prediction model, ensures the objectivity of the evaluation, makes the matching results more reasonable, and uses a genetic algorithm based on Cauchy mutation to optimize the allocation plan, thereby improving the accuracy of the allocation plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a talent assessment and recommendation method based on artificial intelligence of the present invention;

[0061] Figure 2 is a flow chart of preprocessing the first characteristic data and the second characteristic data of the present invention;

[0062] Figure 3 It is a flow chart of the improved genetic algorithm of the present invention. DETAILED DESCRIPTION

[0063] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0064] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0065] like Figure 1-Figure 3 As shown, a talent assessment and recommendation method and system based on artificial intelligence includes the following steps:

[0066] Step S101, collecting personnel data of M candidates and position data of N positions, which are represented by first characteristic data and second characteristic data respectively;

[0067] Personnel data include: education, work experience, professional skills, and health status;

[0068] Position data includes: educational requirements, work experience requirements, and required professional skills;

[0069] Step S102, preprocessing the first characteristic data and the second characteristic data to obtain third characteristic data and fourth characteristic data;

[0070] Step S103, constructing graph structure data according to the third characteristic data and the fourth characteristic data;

[0071] Graph structure data includes: nodes, initial features of nodes, and edges;

[0072] The nodes include: a first node and a second node;

[0073] The first node establishes a mapping relationship with the candidate;

[0074] The second node establishes a mapping relationship with the position;

[0075] The initial feature of the first node is represented by the third feature data of the candidate that establishes a mapping relationship with the first node;

[0076] The initial feature of the second node is represented by the fourth feature data of the position that establishes a mapping relationship with the second node;

[0077] The edge represents the connection relationship between the first node and the second node;

[0078] Step S104, constructing a matching degree prediction model according to the graph structure data, and outputting the scores of the edges of the graph structure data;

[0079] Step S105, generating an allocation plan according to the improved genetic algorithm combined with the matching degree prediction model;

[0080] The allocation plan represents the allocation relationship between M candidates and N positions.

[0081] In one embodiment of the present invention, both M and N are custom parameters, and M>N.

[0082] In one embodiment of the present invention, academic qualifications, work experience, health status, academic qualification requirements and work experience requirements are represented by real number coding; for example, academic qualifications are divided into three levels: high school and below, undergraduate and graduate, and are assigned real number codes 1, 2 and 3 respectively, among which undergraduate degree corresponds to real number code 2; professional skills and required professional skills are represented by one-hot coding; for example, professional skills include: java, spring, springboot, mysql, mybatis and redis, among which when the candidate's professional skills include java and mysql, the corresponding one-hot coding is: [1, 0, 0, 1, 0, 0].

[0083] In one embodiment of the present invention, the step of preprocessing the first feature data and the second feature data includes:

[0084] Step S201, filling missing values ​​in the first feature data and the second feature data by using the most frequently occurring value therein;

[0085] Step S202, performing replacement processing on the abnormal values ​​in the first feature data and the second feature data by calculating the mean of all non-abnormal values;

[0086] Step S203: normalize the first feature data and the second feature data using a z-score normalization method.

[0087] In one embodiment of the present invention, the graph structure data is constructed based on a bipartite graph, a first node can only be connected to a second node, and an edge between the first node and the second node represents an allocation relationship between candidates and positions.

[0088] In one embodiment of the present invention, the matching degree prediction model includes: a first hidden layer, a second hidden layer, a third hidden layer and a classifier;

[0089] The first hidden layer includes M first units, the mth first unit inputs the initial feature of the mth first node of the graph structure data, and outputs the first updated feature;

[0090] The second hidden layer includes N second units, the nth second unit inputs the initial feature of the nth second node of the graph structure data, and outputs the second updated feature;

[0091] The third hidden layer inputs the graph structure data, and outputs the third updated feature and the fourth updated feature after the first updated feature and the second updated feature are updated;

[0092] The third updated feature and the fourth updated feature are respectively put into the classifier, and the classification space of the classifier represents the score of the edge of the graph structure data.

[0093] In one embodiment of the present invention, the first hidden layer and the second hidden layer are constructed based on a multi-layer perceptron.

[0094] In one embodiment of the present invention, the calculation formula of the first hidden layer is:

[0095] F can =sigmoid(ReLU(x can w1+b1)*w2+b2);

[0096] where F can represents the first updated feature of the first hidden layer output, x can represents the initial feature of the first node of the first hidden layer input, w1, w2, b1 and b2 are the first weight parameter, the second weight parameter, the first bias parameter and the second bias parameter of the first hidden layer, ReLU represents the ReLU activation function, and sigmoid represents the sigmoid activation function.

[0097] In one embodiment of the present invention, the calculation formula of the second hidden layer is:

[0098] F post =sigmoid(ReLU(x post w3+b3)*w4+b4);

[0099] where F post represents the second updated feature of the second hidden layer output, x post represents the initial feature of the second node of the second hidden layer input, w3, w4, b3 and b4 are the third weight parameter, the fourth weight parameter, the third bias parameter and the fourth bias parameter of the second hidden layer.

[0100] In one embodiment of the present invention, the calculation formula of the third hidden layer is:

[0101]

[0102] in represents the updated features of the node, H represents the initial features of the node, W represents the weight parameter, represents the weighted adjacency matrix, A represents the adjacency matrix of the third hidden layer input graph structure data, the elements of the adjacency matrix represent the connection relationship between the first node and the second node, and the element value is represented by 0 or 1, 0 means that there is no connection relationship between the nodes, otherwise there is a connection relationship, I represents the unit matrix, the element value on the diagonal of the unit matrix is ​​assigned to 1, and the remaining element values ​​are assigned to 0, represents the normalized degree matrix, the elements of the degree matrix represent the number of edge connections with the node, ReLU represents the ReLU activation function, the updated features of the above nodes include: the first updated features of the first node and the second updated features of the second node, and the initial features of the above nodes include: the initial features of the first node and the initial features of the second node.

[0103] In one embodiment of the present invention, manual annotation is used as sample labels of training samples of the matching prediction model.

[0104] In one embodiment of the present invention, a cross entropy loss function is used as the loss function of the matching prediction model.

[0105] In one embodiment of the present invention, the generation of the allocation scheme according to the improved genetic algorithm combined with the matching degree prediction model comprises the following steps:

[0106] Step S301, generating an initialization population with Q individuals meeting the constraint conditions, where Q is a custom parameter, preferably, Q is set to 20;

[0107] Constraints include: a candidate can only be assigned to one position; a position can only be assigned to a maximum of 3 candidates;

[0108] The individuals of the initialized population are represented by matrix coding, which is expressed as:

[0109]

[0110] in They represent the allocation of the 1st candidate to the Mth candidate to the 1st position, They represent the allocation of the first candidate to the first position to the Nth position, respectively. Indicates the allocation of the Mth candidate to the Nth position, and the element value of the matrix code is represented by 0 or 1;

[0111] For example The value assigned is 0, indicating that the first candidate is not assigned to the second position;

[0112] Step S302, constructing an objective function by combining a matching degree prediction model;

[0113] The objective function is calculated as follows:

[0114]

[0115] Where Fit represents the fitness value of the individual, represents the score of the edge between the mth first node and the nth second node obtained by the matching prediction model, Represents the element value of the mth row and nth column of the individual code;

[0116] Step S303, obtaining the fitness value of each individual in the initialized population through the objective function calculation;

[0117] Step S304, selecting two individuals with the largest fitness values ​​in the initialization population as parents;

[0118] Step S305, generating a random number in the range of 0 to 1, and when the random number is less than a first threshold, performing a crossover operation that satisfies the constraint condition;

[0119] The first threshold is a custom parameter. Preferably, the first threshold is set to 0.7;

[0120] The crossover operation means randomly selecting the element value of one position in the matrix encoding of two individuals in the parent generation to exchange;

[0121] For example, an individual in the parent generation corresponds to the matrix encoding The matrix encoding corresponding to another individual of the parent generation Make an exchange;

[0122] Step S306, mutating the individuals in the population based on the Cauchy mutation strategy;

[0123] The probability density function of the Cauchy distribution is: Where x0 represents the location parameter, γ represents the scale parameter, and x represents the custom variable;

[0124] Step S307, if it is determined that the current number of iterations is greater than or equal to the maximum number of iterations, the individual with the largest fitness value in the initialized population is used as the allocation scheme, otherwise return to step S303, where the maximum number of iterations is a custom parameter, preferably, the maximum number of iterations is set to 200.

[0125] In one embodiment of the present invention, the specific steps of step S306 include:

[0126] Step S3061, determine the location parameter and scale parameter of the Cauchy distribution. Preferably, the location parameter x0 is set to 0, and the scale parameter γ is adjusted according to the current number of iterations. k+1 =γ k *β, where γ k+1 represents the scale parameter when the number of population iterations is k+1, γ k represents the scale parameter when the number of population iterations is k, β represents a decreasing factor between 0 and 1, preferably, the decreasing factor is set to 0.99 and the scale parameter is set to 0.7;

[0127] Step S3062, determining the variation ratio, preferably, the variation ratio is set to 10%;

[0128] Step S3063, generate mutant individuals. For the selected individuals, randomly extract mutation values ​​from the Cauchy distribution and apply them to each dimension of the individual. The dimension of the individual is represented by each element value of the matrix. The specific application method is: when the mutation value is greater than the second threshold, the element value mapped by the mutation value is flipped, that is, 0 becomes 1, and 1 becomes 0. Preferably, the third threshold is set to 0.5.

[0129] In one embodiment of the present invention, a talent evaluation and recommendation system based on artificial intelligence is also provided, which specifically includes the following modules:

[0130] A data collection module, which is used to collect personnel data of candidates and position data of positions;

[0131] A preprocessing module, which is used to preprocess the personnel data of the candidate and the position data of the position to obtain the third characteristic data and the fourth characteristic data;

[0132] A graph structure building module, which is used to build graph structure data according to the third feature data and the fourth feature data;

[0133] A matching prediction module is used to construct a matching prediction model based on the graph structure data and output the scores of the edges of the graph structure data;

[0134] The allocation scheme generation module is used to generate an allocation scheme based on an improved genetic algorithm combined with a matching degree prediction model.

[0135] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A talent assessment and recommendation method based on artificial intelligence, characterized in that: The following steps are involved: Step S101, collecting personnel data of M candidates and position data of N positions, which are represented by first characteristic data and second characteristic data respectively; Personnel data include: education, work experience, professional skills, and health status; Position data includes: educational requirements, work experience requirements, and required professional skills; Step S102, preprocessing the first characteristic data and the second characteristic data to obtain third characteristic data and fourth characteristic data; Step S103, constructing graph structure data according to the third characteristic data and the fourth characteristic data; Graph structure data includes: nodes, initial features of nodes, and edges; The nodes include: a first node and a second node; The first node establishes a mapping relationship with the candidate; The second node establishes a mapping relationship with the position; The initial feature of the first node is represented by the third feature data of the candidate that establishes a mapping relationship with the first node; The initial feature of the second node is represented by the fourth feature data of the position that establishes a mapping relationship with the second node; The edge represents the connection relationship between the first node and the second node; Step S104, constructing a matching degree prediction model according to the graph structure data, and outputting the scores of the edges of the graph structure data; Step S105, generating an allocation plan according to the improved genetic algorithm combined with the matching degree prediction model; The allocation plan represents the allocation relationship between M candidates and N positions.

2. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The educational background, work experience, health condition, educational requirements and work experience requirements are represented by real number coding, and the professional skills and required professional skills are represented by one-hot coding.

3. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of preprocessing the first feature data and the second feature data comprises: Step S201, filling missing values ​​in the first feature data and the second feature data by using the most frequently occurring value therein; Step S202, performing replacement processing on the abnormal values ​​in the first feature data and the second feature data by calculating the mean of all non-abnormal values; Step S203: normalize the first feature data and the second feature data using a z-score normalization method.

4. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The matching degree prediction model includes: a first hidden layer, a second hidden layer, a third hidden layer and a classifier; The first hidden layer includes M first units, the mth first unit inputs the initial feature of the mth first node of the graph structure data, and outputs the first updated feature; The second hidden layer includes N second units, the nth second unit inputs the initial feature of the nth second node of the graph structure data, and outputs the second updated feature; The third hidden layer inputs the graph structure data, and outputs the third updated feature and the fourth updated feature after the first updated feature and the second updated feature are updated; The third updated feature and the fourth updated feature are respectively put into the classifier, and the classification space of the classifier represents the score of the edge of the graph structure data.

5. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The first hidden layer and the second hidden layer are constructed based on a multi-layer perceptron.

6. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The calculation formula for the third hidden layer is: in represents the updated features of the node, H represents the initial features of the node, W represents the weight parameter, represents the weighted adjacency matrix, A represents the adjacency matrix of the third hidden layer input graph structure data, the elements of the adjacency matrix represent the connection relationship between the first node and the second node, and the element value is represented by 0 or 1, 0 means that there is no connection relationship between the nodes, otherwise there is a connection relationship, I represents the unit matrix, the element value on the diagonal of the unit matrix is ​​assigned to 1, and the remaining element values ​​are assigned to 0, represents the normalized degree matrix, the elements of the degree matrix represent the number of edge connections with the node, ReLU represents the ReLU activation function, the updated features of the above nodes include: the first updated features of the first node and the second updated features of the second node, and the initial features of the above nodes include: the initial features of the first node and the initial features of the second node.

7. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The sample labels are manually annotated as training samples for the matching prediction model.

8. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The method of generating an allocation scheme based on an improved genetic algorithm combined with a matching degree prediction model comprises the following steps: Step S301, generating an initialization population with Q individuals meeting the constraint conditions, where Q is a custom parameter; Step S302, constructing an objective function by combining a matching degree prediction model; The calculation formula of the objective function is: Where Fit represents the fitness value of the individual, represents the score of the edge between the mth first node and the nth second node obtained by the matching prediction model, Represents the element value of the mth row and nth column of the individual code; Step S303, obtaining the fitness value of each individual in the initialized population through the objective function calculation; Step S304, selecting two individuals with the largest fitness values ​​in the initialization population as parents; Step S305, generating a random number in the range of 0 to 1, and when the random number is less than a first threshold, performing a crossover operation that satisfies the constraint condition; Step S306, mutating the individuals in the population based on the Cauchy mutation strategy; Step S307, if it is determined that the current number of iterations is greater than or equal to the maximum number of iterations, the individual with the largest fitness value in the initialized population is used as the allocation scheme, otherwise, the process returns to step S303, where the maximum number of iterations is a custom parameter.

9. The talent assessment and recommendation method based on artificial intelligence according to claim 1, characterized in that: The specific steps of step S306 include: Step S3061, determining the location parameter and scale parameter of the Cauchy distribution; Step S3062, determining the variation ratio; Step S3063, generating mutant individuals, for the selected individuals, randomly extracting mutation values ​​from the Cauchy distribution and applying them to each dimension of the individual, the dimension of the individual is represented by each element value of the matrix.

10. A talent assessment and recommendation system based on artificial intelligence, characterized in that: A talent assessment and recommendation method based on artificial intelligence as described in any one of claims 1 to 9 is adopted, comprising the following modules: A data collection module, which is used to collect personnel data of candidates and position data of positions; A preprocessing module, which is used to preprocess the personnel data of the candidate and the position data of the position to obtain the third characteristic data and the fourth characteristic data; A graph structure building module, which is used to build graph structure data according to the third feature data and the fourth feature data; A matching prediction module is used to construct a matching prediction model based on the graph structure data and output the scores of the edges of the graph structure data; The allocation scheme generation module is used to generate an allocation scheme based on an improved genetic algorithm combined with a matching degree prediction model.

Images