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

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an occupational interest evaluation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining personal basic information, existing occupational experience and future occupational tendency of a user; a question recommendation model is adopted, and according to the personal basic information, the existing occupational experience and the future occupational tendency, occupational interest evaluation questions for the user are obtained; rewriting the occupational interest evaluation question according to the question rewriting cue word by adopting a language model to generate a rewritten evaluation question; obtaining reply content of the user for the rewritten evaluation question; and predicting the occupational interest tag of the user according to the reply content by adopting a tag classification model. In addition, the invention also relates to a block chain technology, and data such as personal basic information, existing occupational experiences and future occupational tendencies can be stored in a block chain. According to the invention, the participation degree of the user and the accuracy of the evaluation result can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment and storage medium for evaluating career interests. Background Art

[0002] As an assessment tool, career interest assessment is designed to help individuals gain a deeper understanding of their career inclinations and interests through questionnaires, and to provide a scientific basis for career planning. Career interest assessment can carefully analyze personal characteristics, provide users with targeted career advice, and reveal potential career development directions, thereby enhancing individuals' satisfaction and sense of accomplishment at work. At the same time, career interest assessment also provides strong support for companies to match employees with positions during the recruitment process, helping to improve the overall efficiency and cohesion of the team.

[0003] However, the current career assessment methods have significant shortcomings: on the one hand, the number of assessment questions is usually large, such as the Holland Career Interest Test Standard Edition contains 90 questions, which makes it difficult for the assessment users to answer them completely due to lack of patience; on the other hand, the traditional questionnaire format easily makes the assessment users feel tired or bored, which in turn affects the authenticity and effectiveness of the answers. Therefore, it is necessary to improve the existing career interest assessment methods to increase user participation and the accuracy of the assessment results. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a career interest assessment method, apparatus, computer equipment and storage medium that can improve user participation and the accuracy of assessment results.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for evaluating career interests, which adopts the following technical solutions:

[0006] Obtain the user's basic personal information, current career experience and future career orientation;

[0007] Using the trained question recommendation model, according to the basic personal information, current career experience and future career orientation, obtain career interest assessment questions for the user;

[0008] Obtaining predefined question rewriting prompt words, and rewriting the career interest assessment question according to the question rewriting prompt words using a language model to generate a rewritten assessment question;

[0009] Obtaining the user's reply to the rewritten evaluation question;

[0010] The trained label classification model is used to predict the user's occupational interest label according to the reply content.

[0011] In order to solve the above technical problems, the embodiment of the present application further provides a career interest assessment device, which adopts the following technical solution:

[0012] The information acquisition module is used to obtain the user's basic personal information, current career experience and future career orientation;

[0013] A question acquisition module, used to use the trained question recommendation model to acquire career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation;

[0014] A question rewriting module, used to obtain predefined question rewriting prompt words, and use a language model to rewrite the career interest assessment question according to the question rewriting prompt words to generate a rewritten assessment question;

[0015] A reply acquisition module, used to acquire the user's reply content to the rewritten evaluation question;

[0016] The tag prediction module is used to use the trained tag classification model to predict the user's career interest tag according to the reply content.

[0017] In order to solve the above-mentioned technical problems, an embodiment of the present application also provides a computer device, which adopts the technical solution described below: the computer device includes a memory and a processor, the memory stores computer-readable instructions, and the processor implements the steps of the career interest assessment method described in any one of the above items when executing the computer-readable instructions.

[0018] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, which adopts the following technical solution: the computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the career interest assessment method as described in any one of the above items are implemented.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0020] The embodiment of the present application adopts a trained question recommendation model to screen and recommend career interest assessment questions related to the user according to the user's personal basic information, existing career experience and future career inclinations, thereby significantly reducing the number of assessment questions and reducing the assessment burden on the user; by introducing a question rewriting mechanism, the language model is used to rewrite the career interest assessment questions according to the question rewriting prompt words to generate more vivid, interesting and easy-to-understand rewritten assessment questions, which not only increases the fun of the assessment, but also improves the enthusiasm and authenticity of the user's answering questions; by adopting a trained label classification model, the user's reply content to the rewritten assessment question is deeply analyzed, and the user's career interest label is accurately predicted. Based on the prediction method of natural language processing and deep learning, the useful information in the user's answer can be fully mined, thereby improving the accuracy and reliability of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0023] Figure 2 It is a flowchart of an embodiment of the career interest assessment method of the present application;

[0024] Figure 3 It is a structural schematic diagram of an embodiment of the career interest assessment device of the present application;

[0025] Figure 4 It is a structural diagram of an embodiment of a computer device of the present application. DETAILED DESCRIPTION

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0029] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0030] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0031] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0032] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0033] It should be noted that the career interest assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the career interest assessment device is generally set in the server / terminal device.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0035] Continue to refer Figure 2 , showing a flow chart of an embodiment of the question-answering method according to the present application. The career interest assessment method comprises the following steps:

[0036] Step S201, obtaining the user's basic personal information, current career experience and future career orientation;

[0037] In this embodiment, the career interest assessment method is executed on an electronic device (eg Figure 1 The server / terminal device shown in the figure) can obtain the user's basic personal information, current career experience and future career orientation through a wired connection or a wireless connection. It should be noted that the above wireless connection methods may include but are not limited to 2G / 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0038] Specifically, in the form of free question and answer, the user is asked questions according to pre-set questions, and the questions involve questions about the user's personal basic information, current career experience, and future career planning. Among them, free question and answer means that there is no fixed answer to the questions raised, and the participants of the questions are free to answer according to their own understanding and opinions. The way of asking can be to display the question to the user through a display device, or to make a voice inquiry to the user through a voice broadcasting device. Receive the answer to the user based on the question, wherein the way to receive the user's answer can be to obtain the reply content entered by the user in the text box, or to record the voice content of the user's reply in voice form through a recording device. Based on the question and answer, extract the user's personal basic information, current career experience and / or future career inclination.

[0039] Specifically, basic personal information may include the user's age, gender, education level, and other information. For example, questions about basic personal information can be set as "What is your date of birth", "What is your gender", "What is your education level", etc. Current career experience refers to the user's past and current work experience, including work content, responsibilities, industry, working hours, and other information. For example, questions about current career experience can be set as "What is your current job", "What are your past work experiences", etc. Future career orientation refers to the user's expectations and goals for future career development, including information such as the expected position, industry, and work environment. For example, questions about future career orientation can be set as "What are your expectations or goals for your future career", "What types of work do you hope to do", etc.

[0040] In some optional implementations, the above-mentioned obtaining of the user's basic personal information, current career experience, and future career orientation may include the following steps:

[0041] Obtaining preset inquiry questions, wherein the inquiry questions include questions about basic personal information, current career experience, and future career orientation;

[0042] Specifically, the pre-set inquiry questions are obtained, which cover three aspects: basic personal information, current career experience and future career orientation, including basic personal information questions, current career experience questions and future career orientation questions. Among them, basic personal information questions may include age, gender, education level, marital status, etc.; current career experience questions may involve current work, past work experience, industry, etc.; future career orientation questions may involve the user's expected career development, positions or industries of interest, etc.

[0043] The inquiry question is presented to the user interaction platform in the form of a free question and answer, and the user's reply content to the inquiry question is obtained;

[0044] Specifically, the inquiry question is displayed in the form of a free question and answer on the user interaction platform, which can be a web page, mobile application, smart speaker, etc. The inquiry question can be displayed to the user through a web page or mobile application, or it can be broadcast to the user through a smart speaker. The user's reply to the inquiry question is obtained. For example, when the user interaction platform is a web page or mobile application, the reply content entered by the user in the text box on the web page or mobile application is obtained; when the user interaction platform is a smart speaker, the voice content of the user's reply in voice form is recorded by the smart speaker.

[0045] The user's basic personal information, current career experience and future career orientation are extracted based on the reply content.

[0046] Specifically, a pre-built keyword library is obtained, which contains keywords related to basic personal information, current professional experience, and future professional orientation. The obtained reply content is matched with the keyword library to extract the user's basic personal information, current professional experience, and future professional orientation.

[0047] The embodiments of the present application can cover multiple aspects of the user's career development and ensure the comprehensiveness of information acquisition by presetting questions that include basic personal information, current career experience and future career inclinations; by adopting a free question-and-answer format, users can answer according to their own understanding and opinions, reducing the information bias that may be caused by fixed options and improving the accuracy of information acquisition; at the same time, the free question-and-answer format gives users greater freedom to answer, avoiding the limitations of fixed options in traditional questionnaires, and improving the user's answer experience and interactive fun; by extracting the user's basic personal information, current career experience and future career inclinations through means such as keyword matching and logical verification, the accuracy of the extracted information can be further ensured.

[0048] Step S202, using the trained question recommendation model to obtain career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation;

[0049] In this embodiment, a database of assessment questions related to career interests is pre-constructed. The career interest assessment questions in the database cover multiple dimensions such as interest points, skill preferences, work environment tendencies, etc. in different career fields to comprehensively evaluate the user's career interests.

[0050] Specifically, the user's personal basic information, current career experience and future career inclinations are input into the trained question recommendation model, and the trained question recommendation model is used to extract features of the personal basic information, current career experience and future career inclinations to obtain user characteristics. The user characteristics are matched with a pre-built assessment question library to obtain matching career interest assessment questions as the career interest assessment questions for the user.

[0051] In some optional implementations, the above-mentioned use of the trained question recommendation model to obtain career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation may include the following steps:

[0052] Inputting the personal basic information, current career experience and future career orientation into the trained question recommendation model for feature extraction to obtain user features;

[0053] Specifically, the user's personal basic information, current career experience and future career inclinations are input into the trained question recommendation model, and the trained question recommendation model is used to extract features of the personal basic information, current career experience and future career inclinations to obtain user features.

[0054] Obtain a pre-constructed assessment question set, and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics;

[0055] Specifically, a pre-built evaluation question library is obtained, which contains several career interest evaluation questions. The career interest evaluation questions in the evaluation question library cover multiple dimensions such as interest points, skill preferences, and work environment tendencies in different career fields to comprehensively evaluate the user's career interests. For each career interest evaluation question in the pre-built evaluation question library, the recommendation probability of each career interest evaluation question is calculated based on the extracted user features. The recommendation probability reflects the degree of match between the career interest evaluation question and the user's career interest.

[0056] Arrange each of the career interest assessment questions from large to small according to the recommendation probability, and obtain a preset number of career interest assessment questions that are ranked first as the career interest assessment questions for the user.

[0057] Specifically, a preset number N is obtained, which represents the number of questions allowed to be recommended to the user. According to the calculated recommendation probability, each career interest assessment question in the assessment question set is arranged from large to small according to its recommendation probability, and an arranged question list is obtained. Among them, the higher the recommendation probability of the question, the more it can reflect the user's career interest. From the arranged question list, the top N (N is the preset number) career interest assessment questions are selected as the career interest assessment questions for the user.

[0058] The embodiment of the present application performs feature extraction by inputting the user's personal basic information, current career experience, and future career inclinations into a trained question recommendation model, and selects career interest assessment questions from a pre-constructed assessment question set based on this. By combining the pre-constructed assessment question set with the question recommendation model, it is possible to quickly screen out questions that are most relevant to the user's characteristics, avoiding the lengthy and potentially irrelevant question lists in traditional assessments, and improving the personalization and efficiency of the assessment.

[0059] In some optional implementations, the trained question recommendation model may further include the following steps before obtaining the career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation:

[0060] Acquire a pre-collected first training data set, wherein the first training data set includes personal basic information, current career experience and future career orientation of a historical user, and actual career interest assessment questions marked by the historical user;

[0061] Inputting the first training data set into a pre-trained question recommendation model, extracting features based on the historical user's personal basic information, current career experience, and future career orientation, to obtain user features for training;

[0062] Obtain a pre-constructed assessment question set, and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics used for training;

[0063] Determining career interest assessment questions for the historical user according to the recommendation probability;

[0064] Using a preset loss function, calculate the loss function value between the career interest assessment question of the historical user and the actual career interest assessment question;

[0065] The model parameters of the pre-trained question recommendation model are updated according to the loss function value, and when the model meets the convergence condition, the trained question recommendation model is obtained.

[0066] In this embodiment, before using the trained question recommendation model to obtain career interest assessment questions for the user based on the user's personal basic information, current career experience and future career inclination, a series of training preparation and model optimization processes are also included. The question recommendation model can be constructed using the BERT network structure.

[0067] Specifically, firstly, a first training data set collected in advance is obtained, and the first training data set includes personal basic information, current career experience and future career tendency of the historical user, and the actual career interest assessment questions marked by the historical user. Then, the first training data set is input into the pre-trained question recommendation model, and the pre-trained question recommendation model is used to extract features according to the personal basic information, current career experience and future career tendency of the historical user to obtain the user features for training. Next, a pre-constructed evaluation question set is obtained, and the evaluation question set includes several career interest assessment questions, and the recommendation probability of each career interest assessment question is calculated according to the user features for training. After that, according to the calculated recommendation probability, each career interest assessment question in the evaluation question set is arranged from large to small according to its recommendation probability, and the top N (N is a preset number) career interest assessment questions are selected from the arranged question list to determine as the career interest assessment questions for the historical user. In order to evaluate the accuracy of the model, a preset loss function is used to calculate the loss function value between the career interest assessment questions of the historical user and the actual career interest assessment questions of the historical user. According to the calculated loss function value, the model parameters of the pre-trained question recommendation model are updated, and the model training process is continuously iterated until the model meets the convergence condition, then the model training process is stopped to obtain the trained question recommendation model.

[0068] Step S203, obtaining predefined question rewriting prompt words, and rewriting the career interest assessment question according to the question rewriting prompt words using a language model to generate a rewritten assessment question;

[0069] In this embodiment, the question rewriting prompt words are a series of predefined words, phrases or instructions for guiding the language model to perform specific semantic transformation on the original text. The question rewriting prompt words may include synonym replacement, antonym conversion, sentence transformation (such as transforming a question sentence into a declarative sentence or an inverted sentence), question focus adjustment instructions (such as switching from asking about specific skills to asking about abilities or attitudes), etc. Using question rewriting prompt words can stimulate the language model to generate new text that is similar to the original text but different.

[0070] Specifically, predefined question rewriting prompt words are obtained, and the question rewriting prompt words and the obtained career interest assessment questions are input into a language model. The language model is used to rewrite the career interest assessment questions according to the question rewriting prompt words, such as performing synonym replacement, antonym conversion or sentence transformation on the career interest assessment questions, to generate one or more rewritten assessment questions.

[0071] In some optional implementations, the above-mentioned rewriting of the career interest assessment question according to the question rewriting prompt word using the language model to generate the rewritten assessment question may include the following steps:

[0072] Inputting the career interest assessment question into the language model for semantic analysis to extract the question semantic vector;

[0073] Specifically, the obtained career interest assessment questions are input into the language model in text form, and the language model is used to perform semantic analysis on the input assessment questions, and the question text is converted into a vector representation, namely, the question semantic vector. The question semantic vector contains the meaning and key information of the question.

[0074] Clustering the question semantic vectors to obtain a number of question clusters, and selecting representative evaluation questions from each of the question clusters;

[0075] Specifically, clustering algorithms (such as K-means, hierarchical clustering, etc.) are used to cluster the extracted question semantic vectors to classify semantically similar questions into one category to form several question clusters. From each question cluster, one or several questions that can represent the semantic features of the cluster are selected as representative evaluation questions.

[0076] A predefined question rewriting template and question rewriting prompt words are obtained, and the representative evaluation question is rewritten according to the question rewriting template and the question rewriting prompt words to generate a rewritten evaluation question.

[0077] Specifically, one or more sets of question rewriting templates are predefined, and the question rewriting templates can be applicable to different types of question rewriting needs. For example, a question rewriting template can be "If you _____, will you feel _____" or "Are you more inclined to _____ or _____". The selected representative evaluation questions are matched with the predefined question rewriting templates, and the appropriate question rewriting template is determined, and the representative evaluation questions are filled into the question rewriting templates; the predefined question rewriting prompt words are obtained, and according to the question rewriting prompt words, appropriate words are selected to replace or add the content of the filled question rewriting template to generate the rewritten evaluation questions. For example, the original representative evaluation question "Do you like to work in a team or complete tasks alone" can be rewritten as "Do you prefer to collaborate in a team or complete projects independently?"

[0078] The embodiment of the present application utilizes the semantic analysis capability of the language model to convert the original evaluation questions into vector representations, and extracts representative evaluation questions through a clustering algorithm. Then, the representative evaluation questions are rewritten in combination with predefined question rewriting templates and question rewriting prompts to generate diversified evaluation questions, which can not only improve the interest and effectiveness of the evaluation, but also adapt to the expression habits and preferences of different users.

[0079] Step S204, obtaining the user's reply content to the rewritten evaluation question;

[0080] In this embodiment, the rewritten evaluation question is sent to the user through the selected communication channel, so that after receiving the rewritten evaluation question, the user makes a reply to the rewritten evaluation question and returns the corresponding reply content. The reply content made by the user to the rewritten evaluation question is obtained.

[0081] Step S205: using the trained label classification model, predicting the user's occupational interest label according to the reply content.

[0082] In this embodiment, the obtained reply content is input into the trained label classification model, and the trained label classification model is used to extract features according to the input reply content to obtain the occupational interest features. The occupational interest features refer to features related to occupational interests, such as specific skills, industry terms, work preferences, etc. The occupational interest tag of the user is predicted from all occupational interest tags based on the occupational interest features.

[0083] In some optional implementations, the above-mentioned using the trained label classification model to predict the user's occupational interest label according to the reply content may include the following steps:

[0084] Inputting the reply content into the trained label classification model for feature extraction to obtain occupational interest features;

[0085] Specifically, the obtained reply content is input into the trained label classification model, and the trained label classification model is used to extract features according to the input reply content to obtain the professional interest features. Professional interest features refer to features related to professional interests, such as specific skills, industry terms, work preferences, etc.

[0086] The professional interest tag of the user is matched according to the professional interest feature.

[0087] Specifically, the probability or score of each career interest tag is calculated based on the career interest feature; according to the set threshold or strategy (such as selecting N career interest tags with the highest probability), one or more career interest tags are matched from all career interest tags as the user's career interest tags.

[0088] The embodiment of the present application uses the obtained reply content as the input of the trained label classification model, and predicts the user's career interest label through feature extraction and matching steps, combining contextual information and text analysis technology, which can more accurately reflect the user's career interests and preferences.

[0089] In some optional implementations, before using the trained label classification model to predict the user's occupational interest label according to the reply content, the following steps may also be included:

[0090] Acquire a pre-collected second training data set, where the second training data set includes historical reply contents of historical users and actual career interest tags marked by the historical reply contents;

[0091] Inputting the second training data set into a pre-trained label classification model, performing feature extraction according to the historical reply content, and obtaining professional interest features for training, wherein the pre-trained label classification model is constructed using a BERT network structure;

[0092] According to the training occupational interest characteristics, matching the training occupational interest tags from the pre-constructed occupational interest tag set;

[0093] Calculating a loss function value between the training occupational interest tag and the actual occupational interest tag;

[0094] The model parameters of the pre-trained label classification model are updated according to the loss function value, and when the model meets the convergence condition, the trained label classification model is obtained.

[0095] Specifically, first, a second training data set collected in advance is obtained, and the second training data set includes the historical reply content of the historical user and the actual career interest tags marked by the historical reply content. Then, the second training data set is input into the pre-trained tag classification model, wherein the pre-trained tag classification model is constructed using the BERT network structure. The pre-trained tag classification model is used to extract features according to the historical reply content to obtain the professional interest features for training. Next, a pre-constructed career interest tag set is obtained, and the training career interest tags are matched from the pre-constructed career interest tag set according to the training career interest features. Afterwards, in order to evaluate the accuracy of the model, a preset loss function is used to calculate the loss function value between the training career interest tags and the actual career interest tags of the historical user. According to the calculated loss function value, the model parameters of the pre-trained tag classification model are updated, and the model training process is continuously iterated until the model meets the convergence conditions, and the model training process is stopped to obtain the trained tag classification model.

[0096] The embodiment of the present application adopts the above scheme, specifically by adopting a trained question recommendation model, to screen and recommend career interest assessment questions related to the user according to the user's personal basic information, existing career experience and future career inclinations, thereby significantly reducing the number of assessment questions and reducing the assessment burden on the user; by introducing a question rewriting mechanism, the language model is used to rewrite the career interest assessment questions according to the question rewriting prompt words, and more vivid, interesting and easy-to-understand rewritten assessment questions are generated, which not only increases the fun of the assessment, but also improves the enthusiasm and authenticity of the user's answering questions; by adopting a trained label classification model, the user's reply content to the rewritten assessment question is deeply analyzed, and the user's career interest label is accurately predicted, which can fully mine the useful information in the user's answer based on the prediction method of natural language processing and deep learning, thereby improving the accuracy and reliability of the evaluation results.

[0097] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned basic personal information, current career experience, future career inclinations and other relevant data, the above-mentioned basic personal information, current career experience, future career inclinations and other relevant data can also be stored in a blockchain node.

[0098] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0099] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions 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 aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0100] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0101] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a career interest assessment device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0102] like Figure 3 As shown, the career interest assessment device 400 described in this embodiment includes: an information acquisition module 401, a question acquisition module 402, a question rewriting module 403, a reply acquisition module 404 and a label prediction module 405. Among them:

[0103] Information acquisition module 401, used to acquire the user's basic personal information, current career experience and future career orientation;

[0104] The question acquisition module 402 is used to use the trained question recommendation model to acquire career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation;

[0105] The question rewriting module 403 is used to obtain predefined question rewriting prompt words, and use a language model to rewrite the career interest assessment question according to the question rewriting prompt words to generate a rewritten assessment question;

[0106] A reply acquisition module 404 is used to acquire the user's reply content to the rewritten evaluation question;

[0107] The tag prediction module 405 is used to use the trained tag classification model to predict the user's career interest tag according to the reply content.

[0108] In this embodiment, the information acquisition module 401 is used to ask questions to the user in the form of free questions and answers according to pre-set questions. The questions involve questions about the user's personal basic information, current career experience, and future career planning. Among them, free questions and answers refer to questions that do not have fixed answers, and the participants of the questions are free to answer according to their own understanding and opinions. The way of asking can be to display the question to the user through a display device, or to make a voice inquiry to the user through a voice broadcasting device. Receive the answer to the user based on the question, wherein the way to receive the user's answer can be to obtain the reply content entered by the user in the text box, or to record the voice content of the user's reply in voice form through a recording device. According to the question and answer, extract the user's personal basic information, current career experience and / or future career orientation.

[0109] Specifically, basic personal information may include the user's age, gender, education level, and other information. For example, questions about basic personal information can be set as "What is your date of birth", "What is your gender", "What is your education level", etc. Current career experience refers to the user's past and current work experience, including work content, responsibilities, industry, working hours, and other information. For example, questions about current career experience can be set as "What is your current job", "What are your past work experiences", etc. Future career orientation refers to the user's expectations and goals for future career development, including information such as the expected position, industry, and work environment. For example, questions about future career orientation can be set as "What are your expectations or goals for your future career", "What types of work do you hope to do", etc.

[0110] Specifically, the question acquisition module 402 is used to pre-build an assessment question library related to career interests. The career interest assessment questions in the assessment question library cover multiple dimensions such as interest points, skill preferences, and work environment tendencies in different career fields to comprehensively evaluate the user's career interests. The user's personal basic information, current career experience, and future career tendencies are input into the trained question recommendation model. The trained question recommendation model is used to extract features of the personal basic information, current career experience, and future career tendencies to obtain user features. The user features are matched with the pre-built assessment question library to obtain matching career interest assessment questions as career interest assessment questions for the user.

[0111] Specifically, the question rewriting prompts are a series of predefined words, phrases or instructions used to guide the language model to perform specific semantic transformations on the original text. The question rewriting prompts may include synonym replacement, antonym conversion, sentence transformation (such as transforming a question sentence into a declarative sentence or an inverted sentence), question focus adjustment instructions (such as switching from asking about specific skills to asking about abilities or attitudes), etc. Using question rewriting prompts can stimulate the language model to generate new text that is similar to the original text but different.

[0112] Specifically, the question rewriting module 403 is used to obtain predefined question rewriting prompt words, input the question rewriting prompt words and the obtained career interest assessment questions into the language model, and use the language model to rewrite the career interest assessment questions according to the question rewriting prompt words, such as performing synonym replacement, antonym conversion or sentence transformation on the career interest assessment questions, to generate one or more rewritten assessment questions.

[0113] Specifically, the reply acquisition module 404 is used to send the rewritten evaluation question to the user through the selected communication channel, so that the user can reply to the rewritten evaluation question and return the corresponding reply content after receiving the rewritten evaluation question. The reply content made by the user to the rewritten evaluation question is obtained.

[0114] Specifically, the tag prediction module 405 is used to input the acquired reply content into the trained tag classification model, and use the trained tag classification model to extract features based on the input reply content to obtain the professional interest features. Professional interest features refer to features related to professional interests, such as specific skills, industry terms, work preferences, etc. Based on the professional interest features, the user's professional interest tag is predicted from all professional interest tags.

[0115] The career interest assessment device 400 of the embodiment of the present application, by adopting a trained question recommendation model, screens and recommends career interest assessment questions related to the user according to the user's personal basic information, existing career experience and future career inclinations, thereby significantly reducing the number of assessment questions and reducing the assessment burden on the user; by introducing a question rewriting mechanism, the career interest assessment questions are rewritten according to question rewriting prompts using a language model to generate more vivid, interesting and easy-to-understand rewritten assessment questions, which not only increases the fun of the assessment, but also improves the enthusiasm and authenticity of the user in answering the questions; by adopting a trained label classification model, the user's reply content to the rewritten assessment question is deeply analyzed, and the user's career interest label is accurately predicted, which can fully mine the useful information in the user's answer based on the prediction method of natural language processing and deep learning, thereby improving the accuracy and reliability of the assessment results.

[0116] In some optional implementations of this embodiment, the information acquisition module 401 may include a question acquisition submodule, a question interaction submodule, and an information extraction submodule.

[0117] The question acquisition submodule is used to acquire preset inquiry questions, which include questions about basic personal information, current career experience, and future career orientation;

[0118] A question interaction submodule is used to present the inquiry question in a free question-and-answer format to a user interaction platform, and obtain the user's reply content to the inquiry question;

[0119] The information extraction submodule is used to extract the user's basic personal information, current career experience and future career orientation according to the reply content.

[0120] Specifically, the question acquisition submodule is used to obtain pre-set inquiry questions, which cover three aspects: basic personal information, current career experience and future career orientation, including basic personal information questions, current career experience questions and future career orientation questions. Among them, basic personal information questions may include age, gender, education level, marital status, etc.; current career experience questions may involve current work, past work experience, industry, etc.; future career orientation questions may involve the user's expected career development, positions or industries of interest, etc.

[0121] Specifically, the question interaction submodule is used to display the inquiry questions in the form of free questions and answers to the user interaction platform, which can be a web page, mobile application, smart speaker, etc. The inquiry questions can be displayed to the user through a web page or mobile application, or the inquiry questions can be broadcast to the user through a smart speaker. The user's reply content to the inquiry question is obtained. For example, when the user interaction platform is a web page or mobile application, the reply content entered by the user in the text box on the web page or mobile application is obtained; when the user interaction platform is a smart speaker, the voice content of the user's reply in voice form is recorded by the smart speaker.

[0122] Specifically, the information extraction submodule is used to obtain a pre-built keyword library, which contains keywords related to basic personal information, current professional experience, and future professional orientation. The obtained reply content is matched with the keyword library to extract the user's basic personal information, current professional experience, and future professional orientation.

[0123] The information acquisition module 401 of the embodiment of the present application can cover multiple aspects of the user's career development and ensure the comprehensiveness of information acquisition by presetting questions including personal basic information, current career experience and future career inclinations; by adopting a free question-and-answer format, users can answer according to their own understanding and opinions, reducing the information bias that may be caused by fixed options and improving the accuracy of information acquisition; at the same time, the free question-and-answer format gives users greater freedom to answer, avoiding the limitations of fixed options in traditional questionnaires, and improving the user's answer experience and interactive fun; by extracting the user's personal basic information, current career experience and future career inclinations through means such as keyword matching and logical verification, the accuracy of the extracted information can be further ensured.

[0124] In some optional implementations of this embodiment, the question acquisition module 402 may include a first input submodule, a probability calculation submodule, and a question arrangement submodule.

[0125] The first input submodule is used to input the personal basic information, current career experience and future career orientation into the trained question recommendation model for feature extraction to obtain user features;

[0126] A probability calculation submodule is used to obtain a pre-built assessment question set and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics;

[0127] The question arrangement submodule is used to arrange each of the career interest assessment questions from large to small according to the recommendation probability, and obtain a preset number of career interest assessment questions that are arranged at the top as the career interest assessment questions for the user.

[0128] Specifically, the first input submodule is used to input the user's personal basic information, current career experience and future career inclinations into the trained question recommendation model, and use the trained question recommendation model to extract features of the personal basic information, current career experience and future career inclinations to obtain user features.

[0129] Specifically, the probability calculation submodule is used to obtain a pre-built evaluation question library, which contains several career interest evaluation questions. The career interest evaluation questions in the evaluation question library cover multiple dimensions such as interest points, skill preferences, and work environment tendencies in different career fields to comprehensively evaluate the user's career interests. For each career interest evaluation question in the pre-built evaluation question library, the recommendation probability of each career interest evaluation question is calculated based on the extracted user features. The recommendation probability reflects the degree of match between the career interest evaluation question and the user's career interest.

[0130] Specifically, the question arrangement submodule is used to obtain a preset number N, which indicates the number of questions allowed to be recommended to the user. According to the calculated recommendation probability, each career interest assessment question in the assessment question set is arranged from large to small according to its recommendation probability to obtain an arranged question list. Among them, the higher the recommendation probability of the question, the more it can reflect the user's career interest. From the arranged question list, select the top N (N is the preset number) career interest assessment questions as the career interest assessment questions for the user.

[0131] The question acquisition module 402 of the embodiment of the present application performs feature extraction by inputting the user's personal basic information, current career experience and future career inclination into the trained question recommendation model, and selects career interest assessment questions from a pre-constructed assessment question set based on this. By combining the pre-constructed assessment question set with the question recommendation model, it is able to quickly screen out the questions most relevant to the user's characteristics, avoiding the lengthy and potentially irrelevant question lists in traditional assessments, and improving the personalization and efficiency of the assessment.

[0132] In some optional implementations of this embodiment, the career interest assessment device 400 may further include a first training module, wherein the first training module is used to obtain a pre-collected first training data set, wherein the first training data set includes personal basic information, current career experience and future career orientation of a historical user, and actual career interest assessment questions marked by the historical user;

[0133] Inputting the first training data set into a pre-trained question recommendation model, extracting features based on the historical user's personal basic information, current career experience, and future career orientation, to obtain user features for training;

[0134] Obtain a pre-constructed assessment question set, and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics used for training;

[0135] Determining career interest assessment questions for the historical user according to the recommendation probability;

[0136] Using a preset loss function, calculate the loss function value between the career interest assessment question of the historical user and the actual career interest assessment question;

[0137] The model parameters of the pre-trained question recommendation model are updated according to the loss function value, and when the model meets the convergence condition, the trained question recommendation model is obtained.

[0138] Specifically, before using the trained question recommendation model to obtain career interest assessment questions for the user based on the user's personal basic information, current career experience and future career inclination, a series of training preparation and model optimization processes are also included. The question recommendation model can be constructed using the BERT network structure.

[0139] Specifically, the first training module is used to first obtain a pre-collected first training data set, which includes the personal basic information, current career experience and future career tendency of the historical user, and the actual career interest assessment questions marked by the historical user. Then, the first training data set is input into the pre-trained question recommendation model, and the pre-trained question recommendation model is used to extract features according to the personal basic information, current career experience and future career tendency of the historical user to obtain the user features for training. Next, a pre-constructed assessment question set is obtained, which includes several career interest assessment questions, and the recommendation probability of each career interest assessment question is calculated according to the user features for training. After that, according to the calculated recommendation probability, each career interest assessment question in the assessment question set is arranged from large to small according to its recommendation probability, and the top N (N is a preset number) career interest assessment questions are selected from the arranged question list to determine as the career interest assessment questions for the historical user. In order to evaluate the accuracy of the model, a preset loss function is used to calculate the loss function value between the career interest assessment questions of the historical user and the actual career interest assessment questions of the historical user. According to the calculated loss function value, the model parameters of the pre-trained question recommendation model are updated, and the model training process is continuously iterated until the model meets the convergence condition. The model training process is stopped to obtain the trained question recommendation model.

[0140] In some optional implementations of this embodiment, the question rewriting module 403 may include a second input submodule, a question clustering submodule and a question rewriting submodule.

[0141] The second input submodule is used to input the career interest assessment question into the language model for semantic analysis and extract the question semantic vector;

[0142] A question clustering submodule is used to cluster the question semantic vectors to obtain a number of question clusters, and select representative evaluation questions from each of the question clusters;

[0143] The question rewriting submodule is used to obtain a predefined question rewriting template and question rewriting prompt words, rewrite the representative evaluation question according to the question rewriting template and question rewriting prompt words, and generate a rewritten evaluation question.

[0144] Specifically, the second input submodule is used to input the obtained career interest assessment questions in text form into the language model, use the language model to perform semantic analysis on the input assessment questions, and convert the question text into a vector representation, namely, a question semantic vector. The question semantic vector contains the meaning and key information of the question.

[0145] Specifically, the question clustering submodule is used to cluster the extracted question semantic vectors using a clustering algorithm (such as K-means, hierarchical clustering, etc.) to classify semantically similar questions into one category to form several question clusters. From each question cluster, one or several questions that can represent the semantic features of the cluster are selected as representative evaluation questions.

[0146] Specifically, the question rewriting submodule is used to predefine one or more sets of question rewriting templates, which can be applicable to different types of question rewriting needs. For example, a question rewriting template can be "If you _____, will you feel _____" or "Are you more inclined to _____ or _____". The selected representative evaluation questions are matched with the predefined question rewriting templates, and the appropriate question rewriting templates are determined, and the representative evaluation questions are filled into the question rewriting templates; the predefined question rewriting prompt words are obtained, and according to the question rewriting prompt words, appropriate vocabulary is selected to replace or add the content of the filled question rewriting template to generate the rewritten evaluation questions. For example, the original representative evaluation question "Do you like to work in a team or complete tasks alone" can be rewritten as "Do you prefer to collaborate in a team or complete projects independently?"

[0147] The question rewriting module 403 of the embodiment of the present application converts the original evaluation questions into vector representations by utilizing the semantic analysis capability of the language model, and extracts representative evaluation questions through a clustering algorithm. Then, the representative evaluation questions are rewritten in combination with predefined question rewriting templates and question rewriting prompts to generate diversified evaluation questions, which can not only improve the interest and effectiveness of the evaluation, but also adapt to the expression habits and preferences of different users.

[0148] In some optional implementations of this embodiment, the tag prediction module 405 may include a third input submodule and a tag matching submodule.

[0149] The third input submodule is used to input the reply content into the trained label classification model for feature extraction to obtain the occupational interest features;

[0150] The tag matching submodule is used to match the user's career interest tag according to the career interest characteristics.

[0151] Specifically, the third input submodule is used to input the obtained reply content into the trained label classification model, and use the trained label classification model to extract features according to the input reply content to obtain professional interest features. Professional interest features refer to features related to professional interests, such as specific skills, industry terms, work preferences, etc.

[0152] Specifically, the tag matching submodule is used to calculate the probability or score of each career interest tag based on the career interest characteristics; according to the set threshold or strategy (such as selecting the N career interest tags with the highest probability), one or more career interest tags are matched from all career interest tags as the user's career interest tags.

[0153] The tag prediction module 405 of the embodiment of the present application can more accurately reflect the user's career interests and preferences by combining the contextual information and text analysis technology by inputting the obtained reply content as the trained tag classification model and predicting the user's career interest tags through feature extraction and matching steps.

[0154] In some optional implementations of this embodiment, the career interest assessment device 400 may further include a second training module. The second training module is used to obtain a pre-collected second training data set, wherein the second training data set includes historical reply contents of historical users and actual career interest tags marked by the historical reply contents;

[0155] Inputting the second training data set into a pre-trained label classification model, performing feature extraction according to the historical reply content, and obtaining professional interest features for training, wherein the pre-trained label classification model is constructed using a BERT network structure;

[0156] According to the training occupational interest characteristics, matching the training occupational interest tags from the pre-constructed occupational interest tag set;

[0157] Calculating a loss function value between the training occupational interest tag and the actual occupational interest tag;

[0158] The model parameters of the pre-trained label classification model are updated according to the loss function value, and when the model meets the convergence condition, the trained label classification model is obtained.

[0159] Specifically, the second training module is used to first obtain a pre-collected second training data set, which includes the historical reply content of the historical user and the actual career interest tags marked by the historical reply content. Then, the second training data set is input into the pre-trained tag classification model, wherein the pre-trained tag classification model is constructed using the BERT network structure. The pre-trained tag classification model is used to extract features based on the historical reply content to obtain the training career interest features. Next, a pre-constructed career interest tag set is obtained, and the training career interest tags are matched from the pre-constructed career interest tag set according to the training career interest features. Afterwards, in order to evaluate the accuracy of the model, a preset loss function is used to calculate the loss function value between the training career interest tags and the actual career interest tags of the historical user. According to the calculated loss function value, the model parameters of the pre-trained tag classification model are updated, and the model training process is continuously iterated until the model meets the convergence conditions, the model training process is stopped, and the trained tag classification model is obtained.

[0160] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0161] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 6 with a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0162] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0163] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the career interest assessment method, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0164] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the computer-readable instructions stored in the memory 61 or process data, such as running the computer-readable instructions of the career interest assessment method.

[0165] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0166] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the career interest assessment method as described above.

[0167] The computer device, computer-readable storage medium and computer-readable instructions thereof provided in the embodiments of the present application use a trained question recommendation model to be executed by a processor, and screen and recommend career interest assessment questions related to the user according to the user's personal basic information, existing career experience and future career inclinations, thereby significantly reducing the number of assessment questions and reducing the assessment burden on the user; by introducing a question rewriting mechanism, the career interest assessment questions are rewritten according to question rewriting prompts using a language model to generate more vivid, interesting and easy-to-understand rewritten assessment questions, which not only increases the fun of the assessment, but also improves the enthusiasm and authenticity of the user in answering the questions; by using a trained label classification model, the user's reply content to the rewritten assessment question is deeply analyzed, and the user's career interest label is accurately predicted, which can fully mine the useful information in the user's answer based on the prediction method of natural language processing and deep learning, thereby improving the accuracy and reliability of the assessment results.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0169] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

[0170] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

Claims

1. A method for evaluating career interests, characterized in that: The steps include: Obtain the user's basic personal information, current career experience and future career orientation; Using the trained question recommendation model, according to the basic personal information, current career experience and future career orientation, obtain career interest assessment questions for the user; Obtaining predefined question rewriting prompt words, and rewriting the career interest assessment question according to the question rewriting prompt words using a language model to generate a rewritten assessment question; Obtaining the user's reply to the rewritten evaluation question; The trained label classification model is used to predict the user's occupational interest label according to the reply content.

2. The method for evaluating career interests according to claim 1, characterized in that: The steps of obtaining the user's basic personal information, current career experience and future career orientation include: Obtaining preset inquiry questions, wherein the inquiry questions include questions about basic personal information, current career experience, and future career orientation; The inquiry question is presented to the user interaction platform in the form of a free question and answer, and the user's reply content to the inquiry question is obtained; The user's basic personal information, current career experience and future career orientation are extracted based on the reply content.

3. The method for evaluating career interests according to claim 1, characterized in that: The step of using the trained question recommendation model to obtain career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation includes: Inputting the personal basic information, current career experience and future career orientation into the trained question recommendation model for feature extraction to obtain user features; Obtain a pre-constructed assessment question set, and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics; Arrange each of the career interest assessment questions from large to small according to the recommendation probability, and obtain a preset number of career interest assessment questions that are ranked first as the career interest assessment questions for the user.

4. The method for evaluating career interests according to any one of claims 1 to 3, characterized in that: Before the step of using the trained question recommendation model to obtain career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation, the step further includes: Acquire a pre-collected first training data set, wherein the first training data set includes personal basic information, current career experience and future career orientation of a historical user, and actual career interest assessment questions marked by the historical user; Inputting the first training data set into a pre-trained question recommendation model, extracting features based on the historical user's personal basic information, current career experience, and future career orientation, to obtain user features for training; Obtain a pre-constructed assessment question set, and calculate the recommendation probability of each career interest assessment question in the assessment question set according to the user characteristics used for training; Determining career interest assessment questions for the historical user according to the recommendation probability; Using a preset loss function, calculate the loss function value between the career interest assessment question of the historical user and the actual career interest assessment question; The model parameters of the pre-trained question recommendation model are updated according to the loss function value, and when the model meets the convergence condition, the trained question recommendation model is obtained.

5. The method for evaluating career interests according to claim 1, characterized in that: The step of rewriting the career interest assessment question using a language model according to the question rewriting prompt words to generate the rewritten assessment question includes: Inputting the career interest assessment question into the language model for semantic analysis to extract the question semantic vector; Clustering the question semantic vectors to obtain a number of question clusters, and selecting representative evaluation questions from each of the question clusters; A predefined question rewriting template and question rewriting prompt words are obtained, and the representative evaluation question is rewritten according to the question rewriting template and the question rewriting prompt words to generate a rewritten evaluation question.

6. The method for evaluating career interests according to claim 1, characterized in that: The step of using the trained tag classification model to predict the user's career interest tag according to the reply content includes: Inputting the reply content into the trained label classification model for feature extraction to obtain occupational interest features; The professional interest tag of the user is matched according to the professional interest feature.

7. The method for evaluating career interests according to claim 6, characterized in that: Before the step of using the trained tag classification model to predict the user's occupational interest tag according to the reply content, the step further includes: Acquire a pre-collected second training data set, where the second training data set includes historical reply contents of historical users and actual career interest tags marked by the historical reply contents; Inputting the second training data set into a pre-trained label classification model, performing feature extraction according to the historical reply content, and obtaining professional interest features for training, wherein the pre-trained label classification model is constructed using a BERT network structure; According to the training occupational interest characteristics, matching the training occupational interest tags from the pre-constructed occupational interest tag set; Calculating a loss function value between the training occupational interest tag and the actual occupational interest tag; The model parameters of the pre-trained label classification model are updated according to the loss function value, and when the model meets the convergence condition, the trained label classification model is obtained.

8. A career interest assessment device, characterized in that: The device comprises: The information acquisition module is used to obtain the user's basic personal information, current career experience and future career orientation; A question acquisition module, used to use the trained question recommendation model to acquire career interest assessment questions for the user according to the personal basic information, current career experience and future career orientation; A question rewriting module, used to obtain predefined question rewriting prompt words, and use a language model to rewrite the career interest assessment question according to the question rewriting prompt words to generate a rewritten assessment question; A reply acquisition module, used to acquire the user's reply content to the rewritten evaluation question; The tag prediction module is used to use the trained tag classification model to predict the user's career interest tag according to the reply content.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the career interest assessment method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the career interest assessment method as described in any one of claims 1 to 7 are implemented.

Images