Occupational interest evaluation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an occupational interest evaluation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring occupational interest associated data of a target user in each preset dimension of a first quantity; sending the occupational interest associated data to a preset feature representation model, and performing feature extraction from the occupational interest associated data through the feature representation model to obtain occupational interest feature vectors of each preset dimension; performing vector splicing operation on the occupational interest feature vectors of the preset dimensions to obtain occupational interest fusion feature vectors; and inputting the occupational interest fusion feature vector to a trained occupational interest prediction model, and receiving an occupational interest evaluation result corresponding to the target user output by the occupational interest prediction model. According to the method, the accuracy and reliability of occupational interest evaluation results are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a career interest assessment method, device, electronic device and storage medium. Background Art

[0002] Career interest assessment is an effective tool that can help individuals understand their inclinations and preferences in career choices. At the same time, career interest assessment can also help companies better match employees with positions and improve the overall efficiency and atmosphere of the team. Whether it is a new employee or a career changer, taking a career interest assessment is an important step in self-exploration and development. Most of the career interest assessments in the prior art are conducted through questionnaire questions and cumulative scoring. However, due to the fixed and simplified questions, this method cannot fully reflect the complex interests and career adaptability of individuals, and the results of the career interest test are also different from the actual results. Summary of the invention

[0003] The main technical problem solved by the implementation method of the present application is that the accuracy of the career interest assessment results obtained by the traditional career interest assessment technical solution is relatively low.

[0004] In order to solve the above technical problems, the first technical solution adopted by the implementation mode of the present application is: to provide a career interest assessment method, including: obtaining career interest related data of a target user in a first number of preset dimensions; sending the career interest related data to a preset feature representation model, extracting features from the career interest related data through the feature representation model, and obtaining career interest feature vectors of the preset dimensions; performing vector splicing operations on the career interest feature vectors of the preset dimensions, and obtaining career interest fusion feature vectors; inputting the career interest fusion feature vectors into a trained career interest prediction model, and receiving the career interest assessment results corresponding to the target user output by the career interest prediction model.

[0005] Optionally, the preset feature representation model is an autoencoder network model, and the step of extracting features from the career interest-related data through the feature representation model to obtain the career interest feature vectors of each preset dimension includes: performing data cleaning and data preprocessing operations on the career interest-related data to obtain a first career interest feature vector in a preset data format; sending the first career interest feature vector to the encoder module of the autoencoder network model, and performing feature dimensionality reduction processing on the first career interest feature vector through the encoder module to obtain a second career interest feature vector; sending the second career interest feature vector to the decoder module of the autoencoder network model, and performing feature dimensionality increase processing on the second career interest feature vector through the decoder module to obtain a third career interest feature vector; and setting the third career interest feature vector as the career interest feature vector.

[0006] Optionally, the step of performing feature dimensionality reduction processing on the first professional interest feature vector through the encoder module to obtain the second professional interest feature vector includes: extracting the spatial features of the first professional interest feature vector through the first convolutional layer of the encoder module to obtain the first professional interest spatial feature vector; using the first pooling layer of the encoder module to perform maximum pooling or average pooling processing on the first professional interest spatial feature vector to obtain the first professional interest pooling feature vector; mapping the first professional interest pooling feature vector to the latent space for representation through the first fully connected layer of the encoder module to obtain the second professional interest feature vector.

[0007] Optionally, the step of performing feature dimensionality upgrading processing on the second professional interest feature vector through the decoder module to obtain a third professional interest feature vector includes: performing linear combination and nonlinear transformation processing on the second professional interest feature vector through the second fully connected layer of the decoder module to obtain the original features of the second professional interest feature vector represented in the latent space to obtain a professional interest fully connected feature vector; using the depooling layer of the decoder to perform inverse pooling operation on the professional interest fully connected feature vector to obtain a second professional interest pooling feature vector; performing deconvolution operation on the second professional interest pooling feature vector through the deconvolution layer of the decoder to obtain the reconstructed third professional interest feature vector.

[0008] Optionally, after the step of inputting the career interest fusion feature vector into the trained career interest prediction model, it also includes: preprocessing the career interest fusion feature vector through the normalization layer of the career interest prediction model to obtain a preprocessed feature vector in a preset data format; using the convolution layer and the pooling layer of the career interest prediction model to perform step-by-step feature extraction processing and feature combination processing in sequence to obtain a career interest prediction feature vector; sending the career interest prediction feature vector to the fully connected layer of the career interest prediction model, and converting the career interest prediction feature vector into a career interest prediction probability distribution through the activation function of the fully connected layer; setting the career interest probability distribution to the career interest assessment result corresponding to the target user.

[0009] Optionally, the training steps of the career interest prediction model include: obtaining personal characteristic information data of a target user group and career interest tag data corresponding to the target users, and performing data cleaning, data preprocessing and feature engineering on the personal characteristic information data and the career interest tag data in turn to obtain the career interest data to be trained; dividing the career interest data to be trained into a training data set and a test data set according to a preset ratio; training the career interest prediction model with the training data set, and optimizing various parameters of the convolution layer, pooling layer, fully connected layer and activation function according to a preset loss function until the loss function converges; using the test data set to evaluate the performance of the trained career interest prediction model, and performing hyperparameter optimization and model structure adjustment according to the results of the performance evaluation.

[0010] Optionally, after the step of receiving the career interest assessment result corresponding to the target user output by the career interest prediction model, it also includes: sending the career interest assessment result to the target user; receiving feedback information data from the target user on the career interest assessment result; and optimizing the feature representation model and the career interest prediction model based on the feedback information data.

[0011] In order to solve the above technical problems, the second technical solution adopted by the implementation mode of the present application is: to provide a career interest assessment device, including: an associated data acquisition module, used to obtain the career interest associated data of the target user in each preset dimension of a first number; a feature vector extraction module, used to send the career interest associated data to a preset feature representation model, and extract features from the career interest associated data through the feature representation model to obtain the career interest feature vectors of each preset dimension; a feature vector fusion module, used to perform vector splicing operations on the career interest feature vectors of each preset dimension to obtain a career interest fusion feature vector; an assessment result output module, used to input the career interest fusion feature vector into a trained career interest prediction model, and receive the career interest assessment result corresponding to the target user output by the career interest prediction model.

[0012] To solve the above technical problems, the third technical solution adopted in the implementation mode of the present application is: to provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the career interest assessment method as described above.

[0013] In order to solve the above technical problems, the fourth technical solution adopted in the implementation mode of the present application is: providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by an electronic device, the electronic device executes the career interest assessment method as described above.

[0014] Different from the related technologies, this application can capture the individual's career interests more comprehensively and accurately, taking into account the changes of individuals in different situations, thereby providing more personalized evaluation results, extracting complex features and associations from a large amount of historical data, thereby improving the accuracy and reliability of the evaluation, and can continuously learn and optimize. As the data increases and is updated, the evaluation results will become more accurate and able to adapt to the ever-changing application needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] One or more embodiments are exemplarily described by corresponding drawings, which do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and the figures in the drawings do not constitute proportional limitations unless otherwise stated.

[0016] Figure 1 It is a schematic diagram of the operating environment of the career interest assessment method provided in the embodiment of the present application.

[0017] Figure 2 It is a schematic diagram of the execution flow of the career interest assessment method provided in the embodiment of the present application.

[0018] Figure 3 It is a schematic diagram of the execution flow of obtaining a career interest feature vector in the career interest assessment method provided in an embodiment of the present application.

[0019] Figure 4 It is a schematic diagram of the data processing flow of the career interest prediction model in the career interest assessment method provided in the embodiment of the present application.

[0020] Figure 5 It is a system structure diagram of the career interest assessment device provided in the embodiment of the present application.

[0021] Figure 6 It is a schematic diagram of the hardware structure of an electronic device for executing the career interest assessment method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0023] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device schematic diagram or the order in the flow chart.

[0024] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0025] To facilitate understanding of this embodiment, firstly, a method for evaluating career interests disclosed in the embodiment of this application is described in detail. Figure 1 , Figure 1 Schematic diagram of the operating environment of the career interest assessment method provided in the embodiment of the present application. Figure 1As shown, the executor of the career interest assessment method provided in the embodiment of the present application is generally an electronic device with certain computing capabilities, such as a computer device. In some possible implementations, the career interest assessment method can be implemented by a processor calling a computer-readable instruction stored in a memory. Figure 1 The computer device in the term can be a server. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. It can be understood that Figure 1 The number of computer devices in the figure is only for reference and can be expanded to any number according to actual needs.

[0026] Please continue reading Figure 2 , Figure 2 is a schematic diagram of the execution flow of the career interest assessment method provided in the embodiment of the present application, such as Figure 2 As shown, the following steps are included:

[0027] S1. Obtaining occupational interest association data of a target user in a first number of preset dimensions.

[0028] As an example, the features related to career interest assessment can correspond to the features of four dimensions, namely personal basic information, career orientation, career interest, and personality status. These four dimensions can comprehensively affect the results of personal career interest assessment. The following is an explanation of the four dimensional features. Basic information includes age, gender, education level, major, etc. These personal basic information is related to career interest assessment; career orientation is obtained by setting a variety of questions for users to answer, such as "How satisfied are you with your current job?", "What kind of job do you want to do?", etc., and career interest assessment is carried out through these career orientation related questions. Career interest is obtained by setting a variety of questions for users to answer, such as "Are you willing to be the focus of attention?", "Are you a person who likes to complete work step by step?", etc. Career interest assessment is carried out through these career interest related questions. Psychological personality state In addition to the above personal basic information, career orientation and career interest characteristics, the psychological personality state of an individual also affects career interest. Personality state is obtained by setting a variety of questions for users to answer, such as "How is your recent work status?", "How would you choose to resolve a conflict with a colleague?", etc. The user answer data of the aforementioned four dimensions can be used as the above-mentioned career interest related data. In addition, other career interest related data of the target user can be reasonably collected through third-party channels to further improve the richness, diversity and objectivity of the obtained career interest related data, so as to make the obtained career interest prediction results more accurate.

[0029] S2. Send the career interest related data to a preset feature representation model, extract features from the career interest related data through the feature representation model, and obtain the career interest feature vectors of each preset dimension.

[0030] Among them, the above-mentioned preset feature representation model can be an autoencoder network model. Autoencoder (AutoEncoder) is an unsupervised learning model for learning effective data representation. It consists of an encoder (Encoder) and a decoder (Decoder), and reconstructs the input data through training data. The encoder maps the input data to a representation in the latent space, usually implemented by a multi-layer neural network. The output of the encoder is usually a compressed encoding (encoded representation) that contains the key features of the input data. The decoder maps the encoded representation back to the original input space and attempts to reconstruct the original input data. The decoder is usually also a multi-layer neural network, and its output is the same size as the input data. The encoder part of the autoencoder learns to compress the data into a representation in the latent space. This representation captures the key features of the data. After the training is completed, the encoder part can be used to extract the latent feature representation of the data for feature extraction or dimensionality reduction.

[0031] As a preferred implementation, please continue to refer to Figure 3 , Figure 3 is a schematic diagram of the execution flow of obtaining a career interest feature vector in the career interest assessment method provided in the embodiment of the present application, such as Figure 3 As shown, the following steps S21 to S24 may be included.

[0032] S21. Perform data cleaning and data preprocessing operations on the occupational interest related data to obtain a first occupational interest feature vector in a preset data format.

[0033] S22. Send the first occupational interest feature vector to the encoder module of the autoencoder network model, and perform feature dimensionality reduction processing on the first occupational interest feature vector through the encoder module to obtain a second occupational interest feature vector.

[0034] Feature dimensionality reduction refers to the process of reducing the number of features in the data to retain the most important information and reduce redundant information. Feature dimensionality reduction helps to simplify the complexity of the model, reduce computational costs, reduce the risk of overfitting, and improve the generalization ability of the model. The main feature dimensionality reduction methods include but are not limited to: Principal Component Analysis (PCA), Independent Component Analysis (ICA), Factor Analysis, etc.

[0035] S23. Send the second occupational interest feature vector to the decoder module of the autoencoder network model, and perform feature dimension upgrading processing on the second occupational interest feature vector through the decoder module to obtain a third occupational interest feature vector.

[0036] Feature dimensionality increase refers to increasing the feature dimension of the original data to a higher dimensional space during the data processing process. Although dimensionality reduction is a more common operation in general, dimensionality increase also has some specific application scenarios and advantages. For example, feature dimensionality increase can improve the model's ability to express data, making it easier to capture complex relationships in the data. When dealing with nonlinear problems, feature dimensionality increase can help linear models better adapt to the data. In some cases, feature dimensionality increase can make data easier to be separated by linear classifiers to improve the accuracy of predictive classification of career interests.

[0037] S24. Set the third occupational interest feature vector as the occupational interest feature vector.

[0038] As another preferred implementation, the step of performing feature dimensionality reduction processing on the first professional interest feature vector by the encoder module in the above step S22 to obtain the second professional interest feature vector may include the following steps S221 to S223.

[0039] S221. Extract the spatial features of the first occupational interest feature vector through the first convolutional layer of the encoder module to obtain the first occupational interest spatial feature vector.

[0040] S222. Use the first pooling layer of the encoder module to perform maximum pooling or average pooling on the first occupational interest spatial feature vector to obtain the first occupational interest pooling feature vector.

[0041] Among them, pooling processing is generally used to reduce the spatial dimension of feature maps. By reducing the spatial dimension of feature maps, the number of model parameters can be reduced, the computational efficiency can be improved, and the risk of overfitting can be reduced. The pooling operation can improve the robustness of the model to the position of the target in the image, making the model insensitive to slight changes in the target position, thereby further improving the accuracy of the career interest prediction results.

[0042] S223. Map the first occupational interest pooling feature vector to the latent space for representation through the first fully connected layer of the encoder module to obtain a second occupational interest feature vector.

[0043] As another preferred implementation, the step of performing feature dimension upgrading processing on the second professional interest feature vector by a decoder module in the above step S23 to obtain a third professional interest feature vector may include the following steps S231 to S233.

[0044] S231. Perform linear combination and nonlinear transformation processing on the second occupational interest feature vector through the second fully connected layer of the decoder module to obtain the original features of the second occupational interest feature vector represented in the latent space, and obtain the occupational interest fully connected feature vector.

[0045] Among them, performing linear combination and nonlinear transformation refers to performing linear combination or nonlinear transformation on the original feature vectors during data processing to obtain more meaningful feature representations. Linear combination refers to weighted summation of the original feature vectors according to certain weights to generate new feature vectors. Through linear combination, the correlation between different features can be extracted, important patterns and structures in the data can be captured, and the dimension of the data can be reduced. Reduce the complexity of calculations, help compress data information, retain the main features and reduce redundant information. Nonlinear transformation refers to transforming the original feature vectors through nonlinear functions to generate new feature representations, which helps the model learn complex nonlinear relationships in the data, improve the model's expressiveness, and map the data to a higher-dimensional space, making the data easier to separate.

[0046] S232. Use the de-pooling layer of the decoder to perform a de-pooling operation on the occupational interest fully connected feature vector to obtain a second occupational interest pooled feature vector.

[0047] S233. Perform a deconvolution operation on the second occupational interest pooling feature vector through the deconvolution layer of the decoder to obtain a reconstructed third occupational interest feature vector.

[0048] S3. Perform vector concatenation operation on the occupational interest feature vectors of each preset dimension to obtain an occupational interest fusion feature vector.

[0049] Among them, vector concatenation refers to connecting two or more feature vectors in a certain order to form a longer feature vector, which can fuse information from different sources or different types together, provide a more comprehensive feature representation, improve the expressiveness of the model, as well as the performance, generalization ability and robustness of the model, so that the analysis of the target user's career interests is more comprehensive and the obtained career interest assessment results are more accurate.

[0050] S4. Input the career interest fusion feature vector into the trained career interest prediction model, and receive the career interest assessment result corresponding to the target user output by the career interest prediction model.

[0051] As an optional implementation, please continue to refer to Figure 4 , Figure 4 : is a schematic diagram of the data processing flow of the career interest prediction model in the career interest assessment method provided in the embodiment of the present application, such as Figure 4 As shown, after the step of inputting the career interest fusion feature vector into the trained career interest prediction model in the above step S4, the process of processing data using the career interest prediction model may include the following steps S51 to S54.

[0052] S51. Preprocess the occupation interest fusion feature vector through the normalization layer of the occupation interest prediction model to obtain a preprocessed feature vector in a preset data format.

[0053] S52. Use the convolution layer and pooling layer of the career interest prediction model to perform step-by-step feature extraction and feature combination processing in sequence to obtain a career interest prediction feature vector.

[0054] S53. Send the career interest prediction feature vector to the fully connected layer of the career interest prediction model, and convert the career interest prediction feature vector into a career interest prediction probability distribution through the activation function of the fully connected layer.

[0055] Among them, the activation function plays the role of introducing nonlinear transformation in the fully connected layer, thereby increasing the expressive power of the neural network, such as Sigmoid function, hyperbolic tangent function, ReLU function, etc. In addition, different activation functions can be flexibly set according to actual execution needs to obtain different career interest prediction effects. For example, the hyperbolic tangent function introduces nonlinear transformation, which helps the neural network learn more complex patterns, and the ReLU function alleviates the gradient vanishing problem of the model, making the training more stable.

[0056] S54. Setting the career interest probability distribution to the career interest assessment result corresponding to the target user.

[0057] As another optional implementation, the training process of the aforementioned career interest prediction model may include the following steps S61 to S64.

[0058] S61. Obtain personal characteristic information data of the target user group and the career interest tag data corresponding to the target users, and perform data cleaning, data preprocessing and feature engineering on the personal characteristic information data and the career interest tag data in turn to obtain the career interest data to be trained.

[0059] S62. Divide the occupational interest data to be trained into a training data set and a test data set according to a preset ratio.

[0060] S63. Train the career interest prediction model using the training data set, and optimize the parameters of the convolution layer, pooling layer, fully connected layer, and activation function according to the preset loss function until the loss function converges.

[0061] S64. Use the test data set to evaluate the performance of the trained career interest prediction model, and perform hyperparameter optimization and model structure adjustment based on the results of the performance evaluation.

[0062] As another optional implementation, after receiving the career interest assessment result corresponding to the target user output by the career interest prediction model in step S5, the career interest assessment result can also be sent to the target user. Then, feedback information data of the target user on the career interest assessment result is received, and the feature representation model and the career interest prediction model are optimized according to the feedback information data, thereby continuously improving the accuracy of the above-mentioned feature representation model in representing the career interest features, and the accuracy of the career interest prediction result output by the career interest prediction model.

[0063] The career interest assessment method provided in the embodiment of the present application obtains career interest related data of a target user in a first number of preset dimensions; sends the career interest related data to a preset feature representation model, extracts features from the career interest related data through the feature representation model, and obtains career interest feature vectors of the preset dimensions; performs vector splicing operations on the career interest feature vectors of the preset dimensions to obtain a career interest fusion feature vector; inputs the career interest fusion feature vector into a trained career interest prediction model, and receives the career interest assessment result corresponding to the target user output by the career interest prediction model. This method can capture the individual's career interests more comprehensively and accurately, take into account the changes of the individual in different situations, thereby providing more personalized evaluation results, extract complex features and associations from a large amount of historical data, and thus improve the accuracy and reliability of the evaluation.

[0064] Please continue reading Figure 5 , Figure 5 is a schematic diagram of the system structure of the career interest assessment device provided in the embodiment of the present application, such as Figure 5 As shown, the career interest assessment device 50 includes: a related data acquisition module 51, a feature vector extraction module 52, a feature vector fusion module 53 and an assessment result output module 54.

[0065] The associated data acquisition module 51 is used to acquire the target user's occupational interest associated data in each of the first number of preset dimensions.

[0066] The feature vector extraction module 52 is used to send the career interest related data to a preset feature representation model, and extract features from the career interest related data through the feature representation model to obtain the career interest feature vectors of each preset dimension.

[0067] The feature vector fusion module 53 is used to perform a vector splicing operation on the professional interest feature vectors of each preset dimension to obtain a professional interest fusion feature vector.

[0068] The evaluation result output module 54 is used to input the career interest fusion feature vector into the trained career interest prediction model, and receive the career interest evaluation result corresponding to the target user output by the career interest prediction model.

[0069] As an optional implementation, the feature vector extraction module 52 is specifically used to perform data cleaning and data preprocessing operations on the career interest related data to obtain a first career interest feature vector in a preset data format; send the first career interest feature vector to the encoder module of the autoencoder network model, and perform feature dimensionality reduction processing on the first career interest feature vector through the encoder module to obtain a second career interest feature vector; send the second career interest feature vector to the decoder module of the autoencoder network model, and perform feature dimensionality increase processing on the second career interest feature vector through the decoder module to obtain a third career interest feature vector; set the third career interest feature vector as the career interest feature vector.

[0070] As an optional implementation, the feature vector extraction module 52 is also specifically used to extract the spatial features of the first professional interest feature vector through the first convolutional layer of the encoder module to obtain the first professional interest spatial feature vector; use the first pooling layer of the encoder module to perform maximum pooling or average pooling processing on the first professional interest spatial feature vector to obtain the first professional interest pooling feature vector; map the first professional interest pooling feature vector to the latent space for representation through the first fully connected layer of the encoder module to obtain the second professional interest feature vector.

[0071] As an optional implementation, the feature vector extraction module 52 is also specifically used to perform linear combination and nonlinear transformation processing on the second professional interest feature vector through the second fully connected layer of the decoder module, obtain the original features of the second professional interest feature vector represented in the latent space, and obtain the professional interest fully connected feature vector; use the depooling layer of the decoder to perform inverse pooling operation on the professional interest fully connected feature vector to obtain the second professional interest pooled feature vector; perform deconvolution operation on the second professional interest pooled feature vector through the deconvolution layer of the decoder to obtain the reconstructed third professional interest feature vector.

[0072] As an optional implementation, the evaluation result output module 54 is also specifically used to preprocess the career interest fusion feature vector through the normalization layer of the career interest prediction model to obtain a preprocessed feature vector in a preset data format; use the convolution layer and pooling layer of the career interest prediction model to perform step-by-step feature extraction processing and feature combination processing in sequence to obtain a career interest prediction feature vector; send the career interest prediction feature vector to the fully connected layer of the career interest prediction model, and convert the career interest prediction feature vector into a career interest prediction probability distribution through the activation function of the fully connected layer; set the career interest probability distribution to the career interest evaluation result corresponding to the target user.

[0073] As an optional implementation, the career interest assessment device 50 also includes a career interest prediction model training module, which is specifically used to obtain personal characteristic information data of a target user group and career interest tag data corresponding to the target user, and perform data cleaning, data preprocessing and feature engineering processing on the personal characteristic information data and the career interest tag data in turn to obtain the career interest data to be trained; divide the career interest data to be trained into a training data set and a test data set according to a preset ratio; train the career interest prediction model with the training data set, and optimize the parameters of the convolution layer, pooling layer, fully connected layer and activation function according to a preset loss function until the loss function converges; use the test data set to evaluate the performance of the trained career interest prediction model, and perform hyperparameter optimization and model structure adjustment according to the results of the performance evaluation.

[0074] As an optional implementation, the career interest assessment device 50 also includes a user feedback processing module, which is specifically used to send the career interest assessment results to the target user; receive feedback information data from the target user on the career interest assessment results; and optimize the feature representation model and the career interest prediction model based on the feedback information data.

[0075] It should be noted that the above-mentioned career interest assessment device can execute the career interest assessment method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in the embodiment of the career interest assessment device, please refer to the career interest assessment method provided in the embodiment of the present application.

[0076] Figure 6 is a schematic diagram of the hardware structure of an electronic device 600 for executing a method for evaluating career interests provided in an embodiment of the present application, such as Figure 6 As shown, the electronic device 600 includes:

[0077] One or more processors 610 and memory 620, Figure 6 A processor 610 is taken as an example.

[0078] The processor 610 and the memory 620 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0079] The memory 620 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the career interest assessment method in the embodiment of the present application. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, the career interest assessment method in the above method embodiment is implemented.

[0080] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the career interest assessment device, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 620 may optionally include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the career interest assessment device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0081] The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, the career interest assessment method in any of the above method embodiments is executed, for example, the career interest assessment method described above is executed. Figure 2 Steps S1 to S4 of the method, Figure 3 Steps S21 to S24 of the method, Figure 4 Steps S51 to S54 of the method are implemented Figure 4 The functions of modules 51-54 in.

[0082] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.

[0083] The embodiment of the present application provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, such as Figure 6 A processor 610 in the embodiment may enable the one or more processors to execute the career interest assessment method in any of the above method embodiments, for example, to execute the above described Figure 2 Steps S1 to S4 of the method, Figure 3 Steps S21 to S24 of the method, Figure 4Steps S51 to S54 of the method are implemented Figure 4 The functions of modules 51-54 in.

[0084] The present application provides a computer program product, wherein the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by the electronic device, the electronic device is enabled to execute the career interest assessment method in any of the above method embodiments, for example, to execute the above described Figure 2 Steps S1 to S4 of the method, Figure 3 Steps S21 to S24 of the method, Figure 4 Steps S51 to S54 of the method are implemented Figure 4 The functions of modules 51-54 in.

[0085] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] Through the description of the above implementation methods, ordinary technicians in this field can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Ordinary technicians in this field can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present application as described above, which are not provided in detail for the sake of simplicity. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for evaluating career interests, characterized in that: include: Obtaining career interest association data of the target user in each of the first number of preset dimensions; Sending the career interest related data to a preset feature representation model, extracting features from the career interest related data through the feature representation model, and obtaining the career interest feature vectors of each preset dimension; Performing a vector concatenation operation on the occupational interest feature vectors of the preset dimensions to obtain an occupational interest fusion feature vector; The career interest fusion feature vector is input into the trained career interest prediction model, and the career interest assessment result corresponding to the target user output by the career interest prediction model is received.

2. The method for evaluating career interests according to claim 1, characterized in that: The preset feature representation model is an autoencoder network model, and the step of extracting features from the career interest related data through the feature representation model to obtain the career interest feature vectors of each preset dimension includes: Performing data cleaning and data preprocessing operations on the occupational interest related data to obtain a first occupational interest feature vector in a preset data format; Sending the first professional interest feature vector to the encoder module of the autoencoder network model, and performing feature dimension reduction processing on the first professional interest feature vector by the encoder module to obtain a second professional interest feature vector; Sending the second professional interest feature vector to the decoder module of the autoencoder network model, performing feature dimension upgrading processing on the second professional interest feature vector through the decoder module to obtain a third professional interest feature vector; The third occupational interest feature vector is set as the occupational interest feature vector.

3. The method for evaluating career interests according to claim 2, characterized in that: The step of performing feature dimensionality reduction processing on the first occupational interest feature vector by the encoder module to obtain a second occupational interest feature vector comprises: Extracting the spatial features of the first occupational interest feature vector through the first convolutional layer of the encoder module to obtain a first occupational interest spatial feature vector; Using the first pooling layer of the encoder module to perform maximum pooling or average pooling processing on the first occupational interest spatial feature vector to obtain a first occupational interest pooling feature vector; The first occupational interest pooling feature vector is mapped to a latent space for representation through the first fully connected layer of the encoder module to obtain the second occupational interest feature vector.

4. The method for evaluating career interests according to claim 2, characterized in that: The step of performing feature dimension upgrading processing on the second occupational interest feature vector by the decoder module to obtain a third occupational interest feature vector comprises: Performing linear combination and nonlinear transformation processing on the second occupational interest feature vector through the second fully connected layer of the decoder module to obtain the original features of the second occupational interest feature vector represented in the latent space, and obtaining the occupational interest fully connected feature vector; Using the de-pooling layer of the decoder to perform a de-pooling operation on the occupational interest fully connected feature vector to obtain a second occupational interest pooled feature vector; The second occupational interest pooling feature vector is deconvolved by the deconvolution layer of the decoder to obtain the reconstructed third occupational interest feature vector.

5. The method for evaluating career interests according to claim 1, characterized in that: After the step of inputting the career interest fusion feature vector into the trained career interest prediction model, the method further includes: Preprocessing the career interest fusion feature vector through the normalization layer of the career interest prediction model to obtain a preprocessed feature vector in a preset data format; Using the convolution layer and the pooling layer of the career interest prediction model to perform step-by-step feature extraction processing and feature combination processing in sequence, to obtain a career interest prediction feature vector; Sending the career interest prediction feature vector to the fully connected layer of the career interest prediction model, and converting the career interest prediction feature vector into a career interest prediction probability distribution through the activation function of the fully connected layer; The career interest probability distribution is set to the career interest assessment result corresponding to the target user.

6. The method for evaluating career interests according to claim 1, characterized in that: The training steps of the career interest prediction model include: Obtaining personal characteristic information data of a target user group and occupational interest tag data corresponding to the target users, and sequentially performing data cleaning, data preprocessing and feature engineering on the personal characteristic information data and the occupational interest tag data to obtain occupational interest data to be trained; Dividing the occupational interest data to be trained into a training data set and a test data set according to a preset ratio; Training the career interest prediction model through the training data set, and optimizing various parameters of the convolution layer, the pooling layer, the fully connected layer and the activation function according to a preset loss function until the loss function converges; The test data set is used to evaluate the performance of the trained career interest prediction model, and hyperparameter optimization and model structure adjustment are performed based on the results of the performance evaluation.

7. The method for evaluating career interests according to claim 1, characterized in that: After the step of receiving the career interest assessment result corresponding to the target user output by the career interest prediction model, the method further includes: Sending the career interest assessment result to the target user; Receiving feedback information data from the target user on the career interest assessment result; The feature representation model and the career interest prediction model are optimized according to the feedback information data.

8. A career interest assessment device, characterized in that: include: A related data acquisition module, used to acquire the target user's career interest related data in each of the first number of preset dimensions; A feature vector extraction module, used for sending the career interest related data to a preset feature representation model, extracting features from the career interest related data through the feature representation model, and obtaining the career interest feature vectors of each preset dimension; A feature vector fusion module is used to perform a vector splicing operation on the professional interest feature vectors of each preset dimension to obtain a professional interest fusion feature vector; The evaluation result output module is used to input the career interest fusion feature vector into the trained career interest prediction model, and receive the career interest evaluation result corresponding to the target user output by the career interest prediction model.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the career interest assessment method described in any one of claims 1-7.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by an electronic device, the electronic device executes the career interest assessment method described in any one of claims 1-7.

Images