Innovation and entrepreneurship talent incubation evaluation method based on artificial intelligence
Through artificial intelligence technology and smart talent neural network model, combined with text and image information, the subjective problem of evaluation of innovative and entrepreneurial talents has been solved, objective evaluation and resource matching of innovative and entrepreneurial talents has been achieved, the success rate and efficiency of incubation have been improved, and the success rate and efficiency of incubation have been promoted. The development of the innovation and entrepreneurship ecosystem.
Patent Information
- Application Number
- CN202411087221.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-29
AI Technical Summary
The existing methods for evaluating innovative and entrepreneurial talents are subjective, unfair and inaccurate, and it is difficult to comprehensively evaluate the matching of talent potential and demand, resulting in low incubation efficiency and success rate, and it is impossible to effectively promote the development of the innovation and entrepreneurship ecosystem.
Adopt the incubation and evaluation method of innovative and entrepreneurial talents based on artificial intelligence, analyze the data of innovative and entrepreneurial talents through the smart talent neural network model, combine text and image information to build talent characteristics and demand matching degree to achieve objective and accurate evaluation of talents and resource optimization .
It improves the matching degree between talents and projects, improves the success rate and efficiency of incubation, provides data-driven optimization and improvement, and promotes the development of the innovation and entrepreneurship ecosystem.
Smart Images

Figure CN119047908A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data analysis, and in particular to an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence. Background Art
[0002] In modern society, innovation and entrepreneurship have always been considered an important force to promote economic growth and social progress. At the same time, in the current innovation and entrepreneurship environment, talent incubation and evaluation is an important link. The evaluation method for incubation of innovative and entrepreneurial talents is to evaluate and measure the potential, ability and achievements of innovative and entrepreneurial talents in the incubation process, which is an important means to promote economic development and social progress.
[0003] However, the evaluation and selection of innovative and entrepreneurial talents has always been a challenging task. Existing evaluation methods usually rely on subjective judgment and experience, and there are problems of subjectivity, unfairness and inaccuracy; they may be limited by subjective opinions and limited data analysis capabilities, making it difficult to comprehensively evaluate the potential of talents and the degree of matching between needs. Specifically, the key characteristics of innovative and entrepreneurial talents cannot be obtained, and thus talents cannot be effectively incubated, which reduces the efficiency and success rate of incubation; incubation cannot be carried out according to the actual needs and characteristics of innovative and entrepreneurial enterprises or projects and talents, which is not conducive to promoting the development of the innovative and entrepreneurial ecosystem.
[0004] Therefore, there is a need for an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence. Summary of the invention
[0005] The invention provides an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence, which aims to objectively and accurately evaluate innovative and entrepreneurial talents, improve the matching degree between talents and projects, and increase the probability of successful incubation; artificial intelligence technology can realize the rapid processing and analysis of large amounts of data, thereby speeding up the speed and efficiency of the evaluation process and reducing the waste of time and resources; it also provides data-driven optimization and improvement for the incubation of innovative and entrepreneurial talents, thereby improving the incubation effect and quality.
[0006] The technical solution of the present invention is specifically as follows:
[0007] An innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence comprises the following steps:
[0008] S1. Collect data information on innovative and entrepreneurial talents and data information on innovative and entrepreneurial projects or enterprises, and perform pre-processing operations;
[0009] S2. Divide the acquired data and information on innovative and entrepreneurial talents into basic personal data and capability upgrade data of innovative and entrepreneurial talents, establish a neural network model for intelligent talents, and divide the acquired data and information on innovative and entrepreneurial talents into a test set and a training set;
[0010] S3. Using the smart items obtained by the smart talent neural network model and the acquired data information of innovative entrepreneurial projects or enterprises, a set of innovative entrepreneurial smart talents and a set of innovative entrepreneurial talent needs are constructed to obtain a matching degree set of innovative entrepreneurial smart talents and innovative entrepreneurial talent needs;
[0011] S4. Comprehensively evaluate the incubation of innovative and entrepreneurial talents based on the obtained set of matching degrees of innovative and entrepreneurial talents.
[0012] Further, step S2 specifically includes:
[0013] The smart talent neural network model includes an input layer, a text feature extraction layer, a convolution operation layer, a fusion processing layer, a bidirectional RNN layer, and an output layer.
[0014] Further, step S2 specifically includes:
[0015] The input of the smart talent neural network model is the data information of innovative and entrepreneurial talents, including text information x and image information g, and the output is the characteristic information of innovative and entrepreneurial talents, namely, the smart item.
[0016] Furthermore, in the fusion processing layer, text features and image features are combined to represent the characteristic information of innovative and entrepreneurial talents. The specific process is as follows:
[0017]
[0018] Among them, R x,g represents the fusion result; ω x,g The weight representing the interaction between the text features and image features of innovative and entrepreneurial talents; Represents the jth feature data in the text information, there are J in total; Indicates the kth feature data in the image information, there are K in total; b r Represents the bias in the fusion processing layer.
[0019] Furthermore, the matching degree between innovative and entrepreneurial talents and the demand for innovative and entrepreneurial talents TD αγ , the calculation process is as follows:
[0020]
[0021] Among them, P(Sm|Tal) represents the proportion of smart talents Sm in the set of innovative and entrepreneurial smart talents Tal; Ua q represents the weight of the qth smart item; P(Sma q |(Sm,Tal)) means that among the innovative and entrepreneurial smart talent set Tal and the smart talent Sm, there are smart items Sma qThe probability of talent; α = 1, 2, ..., C; γ = 1, 2, ..., I; d1 = 1, 2, ..., I; d2 = 1, 2, ..., C; C represents the total number of innovative entrepreneurial projects or enterprises; I represents the total number of talent types; TD αγ represents the matching degree between the αth innovation and entrepreneurship project or enterprise and the γth talent; tal pq represents the qth wisdom item possessed by the pth talent; p = 1, 2, ..., A; q = 1, 2, ..., B; A represents the total number of talents; B represents the total number of wisdom items.
[0022] Further, step S3 specifically includes:
[0023] According to the innovation and entrepreneurship talent matching set TD, Calculate the evaluation parameter HEN.
[0024] Further, step S3 specifically includes:
[0025]
[0026] Where, μ represents the error coefficient; Sm q Indicates the situation of the qth wisdom item of the intelligent talent; Dm s Indicates the situation of the Sth type of talent required by the project or enterprise.
[0027] Beneficial effects:
[0028] 1. The present invention can provide a comprehensive understanding and analysis of innovative and entrepreneurial talents through the intelligent talent neural network model, and provide strategic guidance on talent resources for decision makers; by analyzing the data information of the ability upgrade of innovative and entrepreneurial talents, the intelligent talent neural network model can provide targeted guidance and suggestions to help talents develop and improve key capabilities, and help talents achieve better results and performance in the field of innovation and entrepreneurship. The intelligent talent neural network model can combine text information and image information to achieve a comprehensive analysis of innovative and entrepreneurial talents; through the fusion of multimodal data, the model can capture more comprehensive and multi-dimensional talent characteristics and provide more accurate evaluation and analysis results; based on the model's in-depth understanding and analysis of talents, it can provide customized support for talent career planning, training needs, etc., provide decision makers with accurate and efficient talent evaluation and decision support, and also provide personalized development guidance for innovative and entrepreneurial talents.
[0029] 2. The smart items of the smart talent neural network model of the present invention reflect the individual characteristics and skills of innovative and entrepreneurial talents, while the innovative and entrepreneurial talent demand set reflects the specific requirements of innovative and entrepreneurial projects or enterprises. The matching evaluation can help find the most suitable talents, improve matching and work efficiency, and improve the incubation effect. Through the matching degree between smart talents and innovative and entrepreneurial talent needs, the resource allocation for the incubation of innovative and entrepreneurial talents can be optimized. Incubation institutions can provide targeted and appropriate training, guidance and support based on the matching evaluation results, maximize the use of incubation resources, and improve incubation efficiency and success rate; at the same time, innovative entrepreneurs can cooperate more targetedly with projects or enterprises that have needs for them, realize resource sharing, mutual benefit and win-win results, build a closer innovation and entrepreneurship network, and promote the development of cooperation and innovation.
[0030] 3. The present invention can understand the overall effect of incubation of innovative and entrepreneurial talents through comprehensive evaluation of the matching degree set of innovative and entrepreneurial talents. The comprehensive evaluation can examine the overall level of matching degree and the innovative and entrepreneurial achievements after incubation, etc.; by analyzing the results of the matching degree set, the incubation institution can find potential improvement points and shortcomings, and take targeted improvement measures to continuously improve the ability and level of the incubation institution and improve the effect and quality of incubation of innovative and entrepreneurial talents; by understanding the overall performance and effect of incubation of innovative and entrepreneurial talents, it can provide decision-makers with a basis for decision-making, which is helpful to promote the development of the innovative and entrepreneurial ecosystem and promote the sustainable prosperity of innovative and entrepreneurial enterprises. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 A flowchart of an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence of the present invention;
[0032] Figure 2 A module diagram of an innovative and entrepreneurial talent incubation and evaluation system based on artificial intelligence according to the present invention;
[0033] Figure 3 Schematic diagram of the intelligent talent neural network model of the present invention. DETAILED DESCRIPTION
[0034] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0035] See attached Figure 1 This embodiment provides an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence, comprising the following steps:
[0036] S1. Collect relevant data information of innovative and entrepreneurial talents and relevant data information of innovative and entrepreneurial projects or enterprises, and perform pre-processing.
[0037] Through the system platform, we collect resume information and related data information of innovative and entrepreneurial talents, and clean the collected information, including removing duplicate data, processing missing values, correcting erroneous data, etc., to ensure the accuracy and completeness of the data. If there is a class imbalance problem in the data set, we adopt sampling methods such as undersampling, oversampling, etc., or class weight adjustment methods to balance the data set to avoid excessive bias of the model for minority categories. Then, we normalize or standardize the numerical features so that they have similar numerical ranges, which is conducive to the training and convergence of the model.
[0038] S2. Divide the acquired data information of innovative and entrepreneurial talents into basic personal data information and capability upgrade data information of innovative and entrepreneurial talents. Basic personal data information includes but is not limited to the name, age, education background, work experience, language level, personal introduction, awards and honors of innovative and entrepreneurial talents, and capability upgrade data information includes but is not limited to project participation experience, innovative project results, funding support, training and exchange experience, etc. Among them, based on the basic personal data information and capability upgrade data information of innovative and entrepreneurial talents, it is necessary to extract the wisdom item N, where N represents the number of categories of wisdom items, N≥1, and the wisdom item represents the characteristic performance of innovative and entrepreneurial talents, which can be used as an indicator to measure the innovative and entrepreneurial ability of talents.
[0039] In this embodiment, when there is text information in the personal basic data information and capability upgrade data information of innovative and entrepreneurial talents, the features of the text information are extracted by setting keywords to obtain smart items; when there is video or image information, the video is frozen into an image, the image information is converted into sequence data, and its features are extracted to obtain smart items.
[0040] According to the obtained personal basic data information and capability upgrade data information of innovative and entrepreneurial talents, a neural network model of smart talents is established, and the obtained data information related to innovative and entrepreneurial talents is divided into a test set and a training set, and the training set is used to train the neural network model of smart talents. Specifically, the neural network model of smart talents includes an input layer, a text feature extraction layer, a convolution operation layer, a fusion processing layer, a bidirectional RNN layer, and an output layer; (the bidirectional RNN layer is different from the traditional RNN. The bidirectional RNN considers not only the past historical information but also the future information at each time step); the input of the neural network model of smart talents is the information of innovative and entrepreneurial talents, including text information and image information, and the output is the feature information of innovative and entrepreneurial talents, namely the smart items.
[0041] Now define the text sequence of innovative and entrepreneurial talents as x, and the image information as g. Input x and g into the input layer of the intelligent talent neural network model. There are m neurons in the input layer. The preprocessed initial data is passed to the text feature extraction layer. In the text feature extraction layer, the input text information is processed and the features are extracted. The importance of words is taken into account by using TF-IDF. x=[w1,w2,...,w a ],w a represents the TF-IDF value of the a-th word;
[0042] In the convolution operation layer, the feature information of the text and image of innovative and entrepreneurial talents is further determined. A one-dimensional convolution operation is used for the text feature. The length of the input sequence is defined as M, a convolution kernel is h(b), the convolution kernel length is Z, and b represents the position index of the output sequence. The specific process is as follows:
[0043]
[0044] Among them, y(b) represents a one-dimensional convolution operation, that is, the b-th element in the output sequence; z represents the position index when the convolution kernel slides on the input sequence; for image features, a two-dimensional convolution operation is used, and g is defined i,j Represents the pixel point in the i-th row and j-th column in the image. The specific process is as follows:
[0045]
[0046] Among them, i,j represents the output of the convolution operation of the i-th row and j-th column; ω uv represents the weight of the u-th row and v-th column in the convolution kernel; g i+u,j+v Represents the pixel g at the i-th row and j-th column i,j Perform convolution operation with the convolution kernel; b o Represents the bias, which is used to control the activation of neurons. Then the dimension of the feature is reduced through the pooling layer
[0047] In the fusion processing layer, text features and image features are combined to better represent the characteristic information of innovative and entrepreneurial talents. The specific process is as follows:
[0048]
[0049] Among them, R x,g represents the fusion result; ω x,g The weight representing the interaction between the text features and image features of innovative and entrepreneurial talents; Represents the jth feature data in the text information, there are J in total; Indicates the kth feature data in the image information, there are K in total; b rRepresents the bias in the fusion processing layer.
[0050] In the bidirectional RNN layer, it is used to process the feature representation after feature fusion in both the forward and reverse directions to better understand the feature information of innovative and entrepreneurial talents. The specific process is as follows:
[0051]
[0052]
[0053] Where t represents the time step; Indicates positive implicit state; represents the reverse hidden state; σ represents the activation function; Respectively represent the weight matrices input to the forward and reverse hidden state units; Respectively represent the connection weights between the forward state hidden unit and the reverse state hidden unit; Represent the bias in the forward hidden unit and the reverse hidden unit respectively;
[0054] Furthermore, the hidden states of the forward RNN and the backward RNN are concatenated to obtain the output of the bidirectional RNN layer, namely:
[0055] In the output layer, the smart items of the smart talent neural network model are output. The specific process is as follows:
[0056] YU=softmax(ω YU *out t +b Y )
[0057] Among them, YU represents the output result of the output layer; ω YU represents the weight matrix of the output layer; b Y Represents the bias of the output layer.
[0058] In the embodiment of the present invention, N smart item categories are defined, and the dimension of YU is P; the probability distribution of each smart item category is obtained according to the output result, and the final smart item is selected through the preset threshold ε as the standard for distinguishing talents.
[0059] The present invention can provide a comprehensive understanding and analysis of innovative and entrepreneurial talents through the intelligent talent neural network model, and provide strategic guidance on talent resources for decision makers; by analyzing the data information of the ability upgrade of innovative and entrepreneurial talents, the intelligent talent neural network model can provide targeted guidance and suggestions to help talents develop and improve key capabilities, and help talents achieve better results and performance in the field of innovation and entrepreneurship. The intelligent talent neural network model can combine text information and image information to achieve a comprehensive analysis of innovative and entrepreneurial talents; through the fusion of multimodal data, the model can capture more comprehensive and multi-dimensional talent characteristics and provide more accurate evaluation and analysis results; based on the model's in-depth understanding and analysis of talents, it can provide customized support for talent career planning, training needs, etc., provide decision makers with accurate and efficient talent evaluation and decision support, and also provide personalized development guidance for innovative and entrepreneurial talents.
[0060] S3. Based on the smart items obtained from the smart talent neural network model and the acquired innovation and entrepreneurship projects or enterprise data information, a set of innovative and entrepreneurial smart talents and a set of innovative and entrepreneurial talent needs are constructed to obtain the matching degree between innovative and entrepreneurial smart talents and innovative and entrepreneurial talent needs.
[0061] According to the smart items obtained from the smart talent neural network model, we build a set of innovative and entrepreneurial smart talents Tal, and define smart talents as Sm. Among them, tal pq represents the qth wisdom item possessed by the pth talent; p=1,2,...,A; q=1,2,...,B; A represents the total number of talents; B represents the total number of wisdom items;
[0062] At the same time, we construct a set of innovative and entrepreneurial talent demand Dem, and define project or enterprise demand as Dm. Among them, vs represents the sth type of talent needed by the vth innovation and entrepreneurship project or enterprise; v=1,2,...,C; q=1,2,...,I; C represents the total number of innovation and entrepreneurship projects or enterprises; I represents the total number of talent types;
[0063] Then, according to the innovative entrepreneurial wisdom talent set Tal and the innovative entrepreneurial talent demand set Dem, fuzzy matching is performed to obtain the matching degree TD between the innovative entrepreneurial wisdom talent and the innovative entrepreneurial talent demand αγ , the calculation process is as follows:
[0064]
[0065] Among them, P(Sm|Tal) represents the proportion of smart talents Sm in the set of innovative and entrepreneurial smart talents Tal; Ua qrepresents the weight of the qth smart item; P(Sma q |(Sm,Tal)) means that among the innovative and entrepreneurial smart talent set Tal and the smart talent Sm, there are smart items Sma q The probability of talent; α=1,2,...,C; γ=1,2,...,I; d1=1,2,...,I; d2=1,2,...,C; TD αγ Represents the matching degree between the αth innovation and entrepreneurship project or enterprise and the γth talent. The obtained matching degree set of innovation and entrepreneurship talents TD.
[0066] The smart items of the smart talent neural network model of the present invention reflect the personalized characteristics and skills of innovative and entrepreneurial talents, while the innovative and entrepreneurial talent demand set reflects the specific requirements of innovative and entrepreneurial projects or enterprises. The matching evaluation can help find the most suitable talents, improve matching and work efficiency, and improve the incubation effect. Through the matching degree between smart talents and innovative and entrepreneurial talent needs, the resource allocation of innovative and entrepreneurial talent incubation can be optimized. Incubation institutions can provide appropriate training, guidance and support in a targeted manner based on the matching evaluation results, maximize the use of incubation resources, and improve incubation efficiency and success rate; at the same time, innovative entrepreneurs can cooperate more targetedly with projects or enterprises that have needs for them, realize resource sharing, mutual benefit and win-win results, build a closer innovation and entrepreneurship network, and promote the development of cooperation and innovation.
[0067] S4. Based on the obtained innovative and entrepreneurial talent matching degree set TD, conduct a comprehensive evaluation of the innovative and entrepreneurial talent incubation and calculate the evaluation parameter HEN.
[0068] Thus, we can get the matching degree set TD of innovative and entrepreneurial talents. By defining the evaluation parameter HEN, a comprehensive evaluation of the incubation of innovative and entrepreneurial talents is conducted. The specific process is as follows:
[0069]
[0070] Where, μ represents the error coefficient; Sm q Indicates the situation of the qth wisdom item of the intelligent talent; Dm s Indicates the situation of the sth type of talent required by the project or enterprise; Ua q Represents the weight of the qth wisdom item.
[0071] The present invention can understand the overall effect of incubation of innovative and entrepreneurial talents through comprehensive evaluation of the matching degree set of innovative and entrepreneurial talents. The comprehensive evaluation can examine the overall level of matching degree and the innovative and entrepreneurial achievements after incubation, etc.; by analyzing the results of the matching degree set, the incubation institution can find potential improvement points and shortcomings, and take targeted improvement measures to continuously improve the ability and level of the incubation institution and improve the effect and quality of incubation of innovative and entrepreneurial talents; by understanding the overall performance and effect of incubation of innovative and entrepreneurial talents, it can provide decision-makers with a basis for decision-making, which is helpful to promote the development of the innovative and entrepreneurial ecosystem and promote the sustainable prosperity of innovative and entrepreneurial enterprises.
[0072] See attached Figure 2 , this embodiment provides an innovative and entrepreneurial talent incubation evaluation system based on artificial intelligence, including the following contents:
[0073] Data acquisition module, data processing module, smart talent module, talent and demand matching module, talent incubation and evaluation module;
[0074] The data acquisition module is responsible for acquiring relevant data information of innovative and entrepreneurial talents and innovative and entrepreneurial projects or enterprises from different data sources; data sources may include talent databases, innovative and entrepreneurial project databases, enterprise information databases, etc. Through the data acquisition module, the system can obtain basic information of various talents and needs, etc.;
[0075] Data processing module: the acquired data needs to be processed and cleaned for subsequent analysis and matching; the data processing module can clean, organize, classify, and remove duplicates to ensure the accuracy and consistency of the data;
[0076] The smart talent module is used to analyze innovative and entrepreneurial talents. The smart talent module can build a smart talent neural network model based on the collected talent information and output the characteristic information of innovative and entrepreneurial talents, namely, smart items;
[0077] The talent and demand matching module matches innovative and entrepreneurial talents with the needs of innovative and entrepreneurial projects or enterprises based on the evaluation results of the smart talent module, and calculates the matching degree between talents and needs, which helps to find the most suitable talents to meet the needs of innovative and entrepreneurial projects or enterprises, and provides a basis for talent incubation;
[0078] The talent incubation evaluation module is used to evaluate the effectiveness and quality of innovative and entrepreneurial talent incubation. Based on the matching results, it evaluates the training, guidance and support during the incubation process. By analyzing the matching sets and the results of incubation projects, it provides scientific guidance and support for the innovative and entrepreneurial talent incubation process.
[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0082] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0083] The above contents are only for explaining the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.
Claims
1. An evaluation method for incubating innovative and entrepreneurial talents based on artificial intelligence, It is characterized in that The following steps are involved: S1. Collect data information on innovative and entrepreneurial talents and data information on innovative and entrepreneurial projects or enterprises, and perform pre-processing operations; S2. Divide the acquired data and information on innovative and entrepreneurial talents into basic personal data and capability upgrade data of innovative and entrepreneurial talents, establish a neural network model for intelligent talents, and divide the acquired data and information on innovative and entrepreneurial talents into a test set and a training set; S3. Using the smart items obtained by the smart talent neural network model and the acquired data information of innovative entrepreneurial projects or enterprises, a set of innovative entrepreneurial smart talents and a set of innovative entrepreneurial talent needs are constructed to obtain a matching degree set of innovative entrepreneurial smart talents and innovative entrepreneurial talent needs; S4. Comprehensively evaluate the incubation of innovative and entrepreneurial talents based on the obtained set of matching degrees of innovative and entrepreneurial talents.
2. According to the artificial intelligence-based innovative entrepreneurial talent incubation evaluation method of claim 1, It is characterized in that The step S2 specifically includes: The smart talent neural network model includes an input layer, a text feature extraction layer, a convolution operation layer, a fusion processing layer, a bidirectional RNN layer, and an output layer.
3. According to the artificial intelligence-based innovative entrepreneurial talent incubation evaluation method of claim 1, It is characterized in that The step S2 specifically includes: The input of the smart talent neural network model is the data information of innovative and entrepreneurial talents, including text information x and image information g, and the output is the characteristic information of innovative and entrepreneurial talents, namely, the smart item.
4. According to the artificial intelligence-based innovative entrepreneurial talent incubation evaluation method according to any one of claims 2 or 3, It is characterized in that In the fusion processing layer, text features and image features are combined to represent the characteristic information of innovative and entrepreneurial talents. The specific process is as follows: Among them, R x,g represents the fusion result; ω x,g The weight representing the interaction between the text features and image features of innovative and entrepreneurial talents; Represents the jth feature data in the text information, there are J in total; Indicates the kth feature data in the image information, there are K in total; b r Represents the bias in the fusion processing layer.
5. According to the artificial intelligence-based innovative entrepreneurial talent incubation evaluation method of claim 1, It is characterized in that The matching degree between the innovative and entrepreneurial talents and the innovative and entrepreneurial talents demand TD αγ , the calculation process is as follows: Among them, P(Sm|Tal) represents the proportion of smart talents Sm in the set of innovative and entrepreneurial smart talents Tal; Ua q represents the weight of the qth smart item; P(Sma q |(Sm,Tal)) means that among the innovative and entrepreneurial smart talent set Tal and the smart talent Sm, there are smart items Sma q The probability of talent; α=1,2,...,C; γ=1,2,...,I; d 1 =1,2,...,I;d 2 =1,2,...,C; C represents the total number of innovative entrepreneurial projects or enterprises; I represents the total number of talent types; TD αγ represents the matching degree between the αth innovation and entrepreneurship project or enterprise and the γth talent; tal pq represents the qth wisdom item possessed by the pth talent; p = 1, 2, ..., A; q = 1, 2, ..., B; A represents the total number of talents; B represents the total number of wisdom items.
6. According to any one of claims 1 to 5, an innovative and entrepreneurial talent incubation evaluation method based on artificial intelligence, It is characterized in that The step S3 specifically includes: According to the innovation and entrepreneurship talent matching set TD, Calculate the evaluation parameter HEN.
7. According to the artificial intelligence-based innovative entrepreneurial talent incubation evaluation method of claim 6, It is characterized in that The step S3 specifically includes: Where, μ represents the error coefficient; Sm q Indicates the situation of the qth wisdom item of the intelligent talent; Dm s Indicates the situation of the Sth type of talent required by the project or enterprise.
Citation Information
Cited By
Enterprise science and technology quality state diagnosis and innovation ability evaluation method and platform
CN120046999A
