Practice and training base employment tracking survey information processing method and system

Abstract

The invention is suitable for the technical field of data processing, and particularly relates to a practical training base employment tracking survey information processing method and system, and the method comprises the steps: obtaining the to-be-processed information of a student; extracting personal characteristics of the student from the personal information of the student, and extracting occupational characteristics of each occupational part of the student from occupational information of each occupational part in the practice employment information of the student; determining occupational interest characteristics of the student according to the occupational characteristics of each occupational part of the student and the practice employment information of the student; according to the personal characteristics of the student and the occupational characteristics of each occupational part of the student, determining the occupational change characteristics of the student; and on the basis of the occupational interest features of the students and the occupational change features of the students, performing prediction processing on the next occupations of the students to obtain prediction results of the students. According to the method, more personalized occupational prediction can be provided for students and practice training bases.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a method and system for processing employment tracking and investigation information of an internship and training base. Background Art

[0002] The main purpose of the employment tracking survey of internship and training bases is to understand the situation of students entering the job market after the internship or training, and to evaluate the effectiveness of the internship base in cultivating students' professional skills and employability. The employment tracking survey of internship and training bases can not only provide schools with first-hand data on students' career development, help schools optimize educational links such as curriculum settings and internship arrangements, but also provide references for subsequent employment guidance for students and promote close ties between schools, enterprises and students.

[0003] In the prior art, when tracking and investigating students' employment, internship training bases usually collect students' internship employment information. However, traditional career recommendations or career path predictions are often based only on students' internship employment information or simple career relevance, and fail to fully consider students' individual characteristics, which means that internship training bases cannot provide students with personalized career recommendations, limiting the satisfaction of students' personalized career development needs.

[0004] To sum up, in the process of processing employment tracking survey information from internship and training bases, there is a problem of lack of ability to predict students' personalized career development. Summary of the invention

[0005] The embodiments of the present application provide a method and system for processing employment tracking and investigation information of internship and training bases, which can solve the problem of lack of predictive ability for students' personalized career development when processing employment tracking and investigation information of internship and training bases in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a method for processing employment tracking survey information of an internship training base, comprising: Obtaining the student's pending information; wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information; Extracting personal characteristics of the student and occupational characteristics of each occupation of the student from the information to be processed of the student; Determining the career interest characteristics of the student based on the career characteristics of each of the student's careers and the student's internship employment information; Determining the occupational change characteristics of the student based on the personal characteristics of the student and the occupational characteristics of each of the student's occupations; Based on the student's career interest characteristics and the student's career change characteristics, the student's next career is predicted to obtain the student's prediction result.

[0007] The above technical solutions in the embodiments of the present application have at least the following technical effects: The present application provides an internship training base employment tracking survey information processing method, which first obtains the student's pending information to be processed, which is conducive to knowing the student's personal information and the student's internship employment information, then extracts the student's personal characteristics from the student's personal information, and extracts the occupational characteristics of each occupation of the student from the occupational information of each occupation in the student's internship employment information, and then determines the student's occupational interest characteristics according to the occupational characteristics of each occupation of the student and the student's internship employment information, and determines the student's occupational change characteristics according to the student's personal characteristics and the occupational characteristics of each occupation of the student, and finally predicts the student's next occupation based on the student's occupational interest characteristics and the student's occupational change characteristics, and obtains the student's prediction result. This method can effectively identify the student's occupational interest tendency and change possibility by analyzing the student's occupational interest and occupational change characteristics, so that the predicted next occupation is more in line with the student's personality and development needs, and improves the matching degree between the student and the future occupation. This method provides strong data support for internship training bases and educational institutions. Educational institutions and training bases can provide more personalized and targeted employment guidance and career planning suggestions based on the student's occupational interest characteristics and occupational change characteristics, helping students find a suitable career path faster.

[0008] In a possible implementation of the first aspect, determining the career interest characteristics of the student according to the career characteristics of each of the student's careers and the student's internship and employment information includes: According to the time information of each occupation in the internship employment information of the student, each occupation is arranged in ascending order of time to obtain an occupation time sequence; wherein the occupation time sequence includes the time information of each occupation; the time information of each occupation includes the start time and the end time of each occupation; Determine the first feature of each occupation according to the occupation time series and the occupational features of each occupation of the students; wherein the first feature is used to characterize the fusion feature between the position feature of each occupation in the occupation time series and the occupational features of each occupation; Based on the first characteristic of each occupation, the occupational interest characteristics of the students are determined.

[0009] In a possible implementation of the first aspect, determining the first feature of each occupation according to the occupation time series and the occupation feature of each occupation of the student includes: Determine the position feature of each occupation according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series; The position feature of each occupation and the occupation feature of each occupation of the students are fused to obtain the first feature of each occupation.

[0010] In a possible implementation of the first aspect, determining the position feature of each occupation according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series includes: Determine the position index of each occupation according to the position of each occupation in the occupation time series; wherein the position index is used to represent the absolute position of the occupation in the occupation time series; Calculate the duration of each occupation according to the time information of each occupation in the occupation time series; According to the time information of each occupation in the occupation time series, the occupation interval of each occupation is calculated; wherein the occupation interval is used to represent the time interval between two occupations; According to the time information of each occupation in the occupation time series, the relative position of each occupation in the occupation time series is calculated to obtain the relative time proportion of each occupation; The position index of each occupation, the duration of each occupation, the occupational interval of each occupation and the relative time proportion of each occupation are integrated to obtain the position characteristics of each occupation.

[0011] In a possible implementation of the first aspect, determining the occupational interest characteristic of the student according to the first characteristic of each occupation includes: Extracting correlation information from the internship employment information of the students, and calculating the correlation between each occupation in the occupation time series and the previous occupation based on the correlation information, to obtain the correlation feature of each occupation in the occupation time series; wherein the correlation information is used to characterize the correlation between each occupation and each occupation; Fusing the associated features of each occupation in the occupation time series with the first features of each occupation to obtain the second features of each occupation; The second feature of the last occupation in the occupation time series, the associated feature of each occupation and the first feature of each occupation are fused to obtain the third feature of each occupation; The second feature of the last occupation in the occupation time series and the third feature of the last occupation in the occupation time series are fused to obtain the occupational interest feature of the student.

[0012] In a possible implementation of the first aspect, determining the occupation change characteristics of the student according to the personal characteristics of the student and the occupation characteristics of each of the student's occupations includes: Constructing a career directed graph based on the personal characteristics of the student, the career characteristics of each of the student's careers and the association information; According to the occupation directed graph, the attention feature of each occupation is calculated using a graph neural network; The attention features of each occupation are integrated to obtain the occupation change features of the student.

[0013] In a possible implementation of the first aspect, constructing a career directed graph based on the personal characteristics of the student, the career characteristics of each of the student's careers, and the association information includes: Determine each occupation of the student as a node of the occupation directed graph, and determine the personal characteristics of the student and the occupational characteristics of each occupation of the student as initial characteristics of the node corresponding to each occupation; Determine the edges of the occupation directed graph according to the association information; Determining edge weights of the occupation directed graph according to the association information; The occupation directed graph is constructed based on the nodes of the occupation directed graph, the edges of the occupation directed graph and the edge weights of the occupation directed graph.

[0014] In a possible implementation of the first aspect, calculating the attention feature of each occupation using a graph neural network according to the occupation directed graph includes: According to the initial features of each node of the occupation directed graph, the attention weight between each node and each node's adjacent nodes is calculated using the attention mechanism of the graph neural network to obtain the attention weight of each node's adjacent nodes; Normalize the attention weights of the neighboring nodes of each node to obtain the normalized attention weights of the neighboring nodes of each node; According to the normalized attention weights of the neighboring nodes of each node, the initial features of the neighboring nodes of each node are weighted summed to obtain the attention features of each node; The attention feature of each node is determined as the attention feature of the profession corresponding to each node.

[0015] In a possible implementation of the first aspect, the predicting the student's next career based on the student's career interest characteristics and the student's career change characteristics to obtain the prediction result of the student includes: Extracting occupational characteristics of the last occupation in the occupational time series; The occupational characteristics of the last occupation in the occupational time series, the personal characteristics of the student, the occupational interest characteristics of the student and the occupational change characteristics of the student are integrated to obtain the overall characteristics of the student; Based on the overall characteristics of the student, a prediction model is used to predict the student's next career to obtain a prediction result for the student; wherein the prediction model is a deep learning model.

[0016] In a second aspect, the embodiment of the present application provides an internship and training base employment tracking survey information processing system, including: An acquisition unit is used to acquire the student's pending information; wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information; An extraction unit, used to extract the personal characteristics of the student from the personal information of the student, and to extract the occupational characteristics of each occupation of the student from the occupational information of each occupation in the internship employment information of the student; A career interest characteristic obtaining unit, used for determining the career interest characteristics of the student according to the career characteristics of each of the student's careers and the student's internship employment information; A career change characteristic obtaining unit, used for determining the career change characteristics of the student according to the personal characteristics of the student and the career characteristics of each of the student's careers; The prediction unit is used to predict the student's next career based on the student's career interest characteristics and the student's career change characteristics to obtain the student's prediction result.

[0017] In the third aspect, an embodiment of the present application provides an internship and training base employment tracking and investigation information processing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the embodiments of the first aspect when executing the computer program.

[0018] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only 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.

[0020] Figure 1 It is a flowchart of an employment tracking survey information processing method for an internship and training base provided in an embodiment of the present application; Figure 2 It is a schematic diagram of the implementation flow of step S310 and step S320 in the method for processing employment tracking survey information of an internship and training base provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the implementation flow of step S330 in the method for processing employment tracking survey information of an internship and training base provided in an embodiment of the present application; Figure 4 It is a flowchart of implementing step S400 in the method for processing employment tracking and investigation information of an internship and training base provided in an embodiment of the present application; Figure 5 It is a structural diagram of an employment tracking survey information processing system for an internship and training base provided in an embodiment of the present application; Figure 6 It is a structural diagram of an employment tracking and investigation information processing device for an internship and training base provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0022] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0025] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0026] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0027] In the related art, when tracking and investigating students' employment status, internship training bases usually collect students' internship employment information. However, traditional career recommendations or career path predictions are often based only on students' internship employment information or simple career relevance, and fail to fully consider students' individual characteristics, which means that internship training bases cannot provide students with personalized career recommendations, limiting the satisfaction of students' personalized career development needs.

[0028] To solve the above problems, the embodiment of the present application provides an internship training base employment tracking survey information processing method and system. In this method, first by obtaining the student's pending information, it is beneficial to know the student's personal information and the student's internship employment information, then extract the student's personal characteristics from the student's personal information, and extract the occupational characteristics of each occupation of the student from the occupational information of each occupation in the student's internship employment information, and then determine the student's occupational interest characteristics according to the occupational characteristics of each occupation of the student and the student's internship employment information, and determine the student's occupational change characteristics according to the student's personal characteristics and the occupational characteristics of each occupation of the student, and finally predict the student's next occupation based on the student's occupational interest characteristics and the student's occupational change characteristics, and obtain the student's prediction result. By analyzing the student's occupational interest and occupational change characteristics, this method can effectively identify the student's occupational interest tendency and change possibility, so that the predicted next occupation is more in line with the student's personality and development needs, and improves the matching degree between the student and the future occupation. This method provides strong data support for internship training bases and educational institutions. Educational institutions and training bases can provide more personalized and targeted employment guidance and career planning suggestions based on the student's occupational interest characteristics and occupational change characteristics, helping students find a suitable career path faster.

[0029] The employment tracking and investigation information processing method for internship and training bases provided in the embodiment of the present application can be applied to an employment tracking and investigation information processing device for internship and training bases. In this case, the employment tracking and investigation information processing device for internship and training bases is the executor of the employment tracking and investigation information processing method for internship and training bases provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the employment tracking and investigation information processing device for internship and training bases.

[0030] For example, the information processing device can be a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a computer, a laptop computer, a handheld computing device, a customer premises equipment (CPE) and / or other devices for communicating on wireless systems and next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved public land mobile networks (PLMN), etc.

[0031] In order to better understand the employment tracking and investigation information processing method of the internship and training base provided in the embodiment of the present application, the specific implementation process of the employment tracking and investigation information processing method of the internship and training base provided in the embodiment of the present application is exemplarily introduced below.

[0032] Figure 1 A schematic flow chart of an internship and training base employment tracking survey information processing method provided in an embodiment of the present application is shown. The internship and training base employment tracking survey information processing method includes: S100, obtaining the student's pending information, wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information.

[0033] It is understood that the student's personal information may include name, age, gender, educational background (such as major, academic qualifications, etc.), personal skills and certificates, etc. The student's internship and employment information may include detailed information about each internship or job, such as company name, job title, job content, internship or employment start and end time, work location, industry type, salary, and performance evaluation information during the internship or job.

[0034] For example, the student's pending information can be obtained from the database of the internship training base. The database of the internship training base can be constructed by collecting each student's personal information, internship employment information, and tracking data: each student's personal information can be collected from the student's academic information system or archives; each student's internship employment information can be collected from the internship base, employer feedback, and student self-report; each student's tracking data can be collected from the student feedback report, and the tracking data includes the student's satisfaction, performance evaluation, and subsequent career changes (such as resignation, promotion) in different internships or jobs. Data cleaning and preprocessing of all collected information is conducive to data without duplication, missing or outliers, and each student's personal information and internship employment information are associated to form a complete pending information entry, and the processed pending information is stored in the database of the internship training base for subsequent query and analysis.

[0035] S200, extracting the personal characteristics of the students from the personal information of the students, and extracting the professional characteristics of each occupation of the students from the professional information of each occupation in the internship and employment information of the students.

[0036] For example, personal information and internship employment information can be standardized to facilitate the unification of data formats.

[0037] The age field can be read directly from personal information or calculated by date of birth; the gender field can be read directly from personal information; the educational background information in personal information can be extracted and encoded as features, such as high school, undergraduate, master's degree, etc.; the professional information in personal information can be analyzed to extract professional features, such as computer science, electronic engineering, finance, etc.; the personal skills in personal information can be analyzed based on keyword matching (such as Python, Java, C++) or using natural language processing (NLP) technology, and specific skills can be used as features; if there is an interest field, keyword extraction or sentiment analysis can be used to identify interest areas, such as programming, design, etc. The above extracted features are converted into numerical vectors, and different feature vectors are combined into personal feature vectors. For example, the features such as educational characteristics, professional characteristics, and skill characteristics are encoded into numerical values ​​or labels for further analysis.

[0038] The job types (such as software development, project management, data analysis, etc.) in the internship employment information can be extracted through keyword matching or NLP; the job description in the internship employment information can be segmented and analyzed for word frequency to extract the core responsibilities and skill requirements of the job; TF-IDF or word vector models can be used to extract the key skills and tasks in the job content (such as programming, data analysis, management); topic models such as LDA can be used to analyze the job content and identify the main responsibilities of the occupation; classification models or predefined rule sets can be used to classify companies into Internet companies, financial companies, manufacturing, etc. by company name or type fields; occupations can be classified into specific industries (such as IT, finance, manufacturing, medical, etc.) according to industry fields or job content; key skills can be extracted from job content or job descriptions and used as one of the occupational features (such as SQL, data modeling, project management, etc.). The above features can be converted into feature vectors (for example, using One-hot encoding or word embedding), and different features can be combined into vectors to obtain the occupational features of each occupation.

[0039] The personal characteristics of students and the occupational characteristics of each occupation can be stored in a database or data table to facilitate subsequent query and analysis.

[0040] S300, determining the student's career interest characteristics based on the career characteristics of each of the student's careers and the student's internship and employment information.

[0041] For example, based on students' internship and employment information, the frequency of students' appearance in different types of occupations can be calculated. For example, if students repeatedly choose data analysis or software development positions, it can be preliminarily concluded that the students are more interested in data analysis or software development positions. The number of internships or working hours of students in specific industries (such as IT, finance, and manufacturing) can be counted to determine students' interest preferences in the industry. The frequency of skill requirements appearing in students' work content can be calculated to find out the skills that students frequently come into contact with (such as Python, data analysis, etc.), and infer students' interests at the skill level.

[0042] If the student's internship employment information contains a satisfaction score or work experience feedback, the satisfaction score or work experience feedback can be used to judge the student's interest in different positions or industries. Career types with high satisfaction can reflect the student's interest tendencies. The interest tendencies can be judged by the student's performance in different jobs. Students will perform better in positions that interest them, and this can be verified through performance scores.

[0043] The occupational interest features obtained above may be uniformly encoded or normalized to obtain an occupational interest feature vector.

[0044] The occupational feature vectors of all occupations of students can be clustered to find out the occupational type groups that students tend to be interested in. For example, if a student's internship experience is concentrated in technology research and development and data analysis positions, it can be considered that the student has a strong interest in technology research and development and data analysis positions.

[0045] Machine learning models (such as KNN, SVM, and decision trees) can be used to predict students' career interest characteristics. The career characteristics of each student's career are used as the input of the model, and the student's satisfaction and performance scores in the internship employment information are used as labels. The model is trained to predict students' interest preferences, and the model outputs the students' career interest characteristics.

[0046] Through this step, career interest characteristics can be extracted from the career characteristics of each student's career and internship employment information, which can help internship training bases or career guidance departments better understand students' career tendencies and provide students with personalized career planning suggestions.

[0047] In a possible implementation, S300 determines the student's career interest characteristics based on the career characteristics of each of the student's careers and the student's internship and employment information, including: S310, according to the time information of each occupation in the student's internship employment information, each occupation is arranged in ascending order of time to obtain an occupation time sequence, wherein the occupation time sequence includes the time information of each occupation, and the time information of each occupation includes the start time and the end time of each occupation.

[0048] For example, the start time and end time of each job can be extracted from the student's internship employment information, and all jobs are sorted in ascending order according to the start time to generate a time series containing jobs, each entry including job name, start time, end time, duration, etc. For example, the job time series can be a structure of [(job 1, start time, end time), (job 2, start time, end time), ...].

[0049] S320, determining a first feature of each occupation according to the occupation time series and the occupational features of each occupation of the students, wherein the first feature is used to characterize the fusion feature between the position feature of each occupation in the occupation time series and the occupational features of each occupation.

[0050] Exemplarily, the relative position of each occupation in the time series can be calculated. For example, for a time series containing 5 occupations, the relative position of the first occupation is 1 / 5, the relative position of the second occupation is 2 / 5, and so on. The time weight of each occupation in the entire occupation time series can be determined according to the duration of each occupation (i.e., the end time minus the start time), which represents the proportion of each occupation in the entire occupational experience. For example, if a certain occupation lasts for 6 months and the entire occupational experience is 24 months, the time weight is 6 / 24=0.25. The relative position of each occupation in the time series and the time weight of each occupation are used as the positional features of each occupation in the occupational time series.

[0051] The positional features and occupational features of each occupation can be quantized and concatenated to form a fused feature vector, for example, [relative position, time weight, job type code, industry type code, key skill code, ...]. The first feature of each occupation forms a multidimensional vector, which includes the time position and occupation information.

[0052] Optionally, see Figure 2 , S320, determining the first characteristic of each occupation according to the occupation time series and the occupation characteristics of each occupation of the students, including: S321, determining the position characteristics of each occupation according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series.

[0053] Exemplarily, the time evolution trend characteristics and distance-based characteristics of each occupation can be determined based on the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series, and the time evolution trend characteristics and distance-based characteristics of each occupation can be used as the position characteristics of each occupation.

[0054] The time evolution trend characteristics of each occupation can include the difference characteristics before and after and the time proportion of adjacent occupations. The time difference between the current occupation and the previous occupation can be calculated, that is, the start time of the current occupation minus the end time of the previous occupation (for the first occupation, it can be set to zero) to obtain the difference characteristics before and after. The difference between the proportion of the current occupation and the previous occupation in the entire time series can be calculated to obtain the time proportion of adjacent occupations. The time proportion of adjacent occupations can represent the evolution trend of occupations in the time dimension. The calculation formula for the time proportion of adjacent occupations can be ,in, Indicates the time proportion of adjacent occupations, Indicates the duration of the current occupation, indicates the duration of the previous occupation, Represents total professional experience time.

[0055] The distance-based features of each occupation may include a starting time distance feature and an average time interval. The starting time distance of each occupation relative to the first occupation can be calculated, that is, the starting time of the current occupation minus the starting time of the first occupation is subtracted to obtain the starting time distance feature. The starting time distance feature can represent the time span of the current occupation from the initial occupation. The average time interval of all occupations before the current occupation can be calculated to obtain the average time interval. The average time interval calculation formula can be ,in, represents the average time interval, Indicates that the current occupation is A career, Indicates The start time of the career, Indicates The end time of a career.

[0056] Exemplarily, S321, according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series, determines the position feature of each occupation, including: S3211, determining a position index of each occupation according to the position of each occupation in the occupation time series, wherein the position index is used to represent the absolute position of the occupation in the occupation time series.

[0057] For example, since the occupation time series is arranged in ascending order, The position index of an occupation can be , indicating the The absolute position of an occupation in the occupation time series. For example, if the occupation time series is [occupation 1, occupation 2, occupation 3], then the position index is [1, 2, 3].

[0058] S3212, calculating the duration of each occupation based on the time information of each occupation in the occupation time series.

[0059] For example, the start time and end time of each occupation can be used to calculate the duration of each occupation, and the duration can be in days, months or years, depending on the time granularity of the data. For example, if the start time of occupation 1 is January 2020 and the end time is December 2020, then the duration is 12 months.

[0060] S3213, calculating the career interval of each occupation according to the time information of each occupation in the occupation time series, wherein the career interval is used to represent the time interval between two occupations.

[0061] Exemplarily, the career interval is used to characterize the time difference between the end time of the previous career and the start time of the current career. The time interval of the current career can be obtained by subtracting the end time of the previous career from the start time of the current career. For the first career, the career interval can be defined as zero because there is no previous career. For example, if the end time of career 1 is December 2020 and the start time of career 2 is March 2021, the career interval is 3 months.

[0062] S3214, based on the time information of each occupation in the occupation time series, calculate the relative position of each occupation in the occupation time series to obtain the relative time proportion of each occupation.

[0063] For example, the relative time proportion of each occupation is used to characterize the relative proportion of the duration of each occupation in the entire occupational experience. The total duration of all occupations can be calculated based on the duration of each occupation, and the relative time proportion of each occupation can be calculated based on the duration of each occupation and the total duration. The calculation formula can be: ,in, Relative time ratio, Indicates duration of the job, = represents the total duration of all occupations. For example, if the duration of occupation 1 is 12 months, the duration of occupation 2 is 6 months, and the total duration is 18 months, then the relative time proportion of occupation 1 is 12 / 18=0.67, and the relative time proportion of occupation 2 is 6 / 18=0.33.

[0064] S3215, the position index of each occupation, the duration of each occupation, the occupational interval of each occupation and the relative time ratio of each occupation are integrated to obtain the position characteristics of each occupation.

[0065] For example, the position index, duration, occupation interval and relative time ratio of each occupation can be integrated to form the position feature of each occupation. The position feature of each occupation can be represented as a vector, for example, position feature = [position index, duration, occupation interval, relative time ratio]. The position feature of each occupation includes the absolute position of each occupation in the time series, the duration, the interval with the previous occupation and the relative position in the entire occupation time series.

[0066] S322, merging the position feature of each occupation with the occupation feature of each occupation of the students to obtain the first feature of each occupation.

[0067] For example, all position features and occupation features may be normalized or standardized, which is beneficial for integrating features of different scales and preventing certain features from dominating in terms of values.

[0068] The position feature and occupation feature of each occupation can be crossed. For example, the time proportion difference feature is crossed with the position type feature to obtain a new feature time proportion-position type, which is used to represent the change of time proportion under the current position type. By crossing features, the expressive power of features is increased, and more detailed correlations between position features and occupation features are captured.

[0069] The location characteristics and occupational characteristics (including cross-characteristics) of each occupation can be concatenated into a vector (first eigenvector). The first eigenvector of each occupation ultimately contains multi-dimensional information of the location characteristics and occupational characteristics in the time series.

[0070] Through the above steps, we can capture the changing patterns of occupations in the time series, which helps to more accurately analyze students' career interests and career development trends.

[0071] S330, determining the career interest characteristics of the students according to the first characteristics of each career.

[0072] For example, the first feature of each occupation may be time-weighted averaged to highlight features that last longer in the student's career. For example, the time weight of each occupation is multiplied and accumulated with the job type, industry type, and skill code to generate a student's career interest feature vector.

[0073] The first feature vector of each student's occupation can be clustered to find similar feature groups. By analyzing the center of the group, the student's occupational interest characteristics can be obtained. For example, if a group contains multiple occupations related to data analysis, it can be considered that the student has a strong interest in data analysis.

[0074] By analyzing the career time series, the first characteristic of each career can be determined. Based on the first characteristic, the career interest characteristics of students can be comprehensively analyzed to provide data support for further career recommendations and career development planning.

[0075] Optionally, see Figure 3 , S330, according to the first characteristic of each occupation, determining the occupational interest characteristics of the students, including: S331, extracting correlation information from the student's internship and employment information, and calculating the correlation between each occupation in the occupation time series and the previous occupation based on the correlation information, to obtain the correlation feature of each occupation in the occupation time series. The correlation information is used to characterize the correlation between each occupation and each occupation.

[0076] It can be understood that the associated information may include: similarity of job types, the similarity between each job and other job types, such as whether both job types are technical, management or sales jobs; similarity of industry types, the similarity between each job and other job types, such as whether both job types are in IT, finance, manufacturing and other industries; similarity of professional skills, the degree of overlap between the skills required for each job and other job types, the more overlap in skills, the stronger the association between the two; similarity of geographical locations, the same or similar geographical locations may reflect a certain connection between job types, for example, working in the same region may mean lower migration costs.

[0077] For example, the similarity of job type, industry type, occupational skill and geographic location in the association information can be used to calculate the job type similarity, industry type similarity, skill overlap and geographic location similarity of each job in the occupation time series (starting from the second job, because the first job has no previous job) and the previous job, and the job type similarity, industry type similarity, skill overlap and geographic location similarity of each job can be integrated to obtain the association characteristics of each job. The job type similarity and industry type similarity can be represented by binary values ​​(1 for the same and 0 for different), or by using embedded cosine similarity; skill overlap can be represented by the Jaccard similarity coefficient to calculate the ratio of the intersection and union of the skill sets; geographic location similarity can be represented by binary values ​​(1 for the same city and 0 for different cities), or similarity can be calculated based on geographic distance.

[0078] Assume that the students' occupation information is as shown in the following table: Calculate the correlation characteristics of occupation 1 and occupation 2: If occupation 1 and occupation 2 have the same job type, then the job type similarity is assigned a value of 1; if occupation 1 and occupation 2 have the same industry type, then the industry type similarity is assigned a value of 1; based on the professional skills of occupation 1 and occupation 2, the Jaccard similarity (skill overlap) can be calculated, that is, ; Occupation 1 and Occupation 2 have different locations, and the geographical location similarity is assigned to 0. Then the associated features of Occupation 2 = [1, 1, 0.33, 0].

[0079] Calculate the correlation characteristics of occupation 2 and occupation 3: Occupation 2 and occupation 3 have different job types, so the job type similarity is assigned to 0; Occupation 2 and occupation 3 have different industry types, so the industry type similarity is assigned to 0; based on the professional skills of occupation 2 and occupation 3, the Jaccard similarity (skill overlap) can be calculated, that is, ; Occupation 2 and Occupation 3 have different locations, and the geographical location similarity is assigned to 0. Then the associated features of occupation 3 = [0, 0, 0.25, 0].

[0080] S332, feature fusion is performed on the associated features of each occupation in the occupation time series and the first features of each occupation to obtain the second features of each occupation.

[0081] Exemplarily, the first feature and the associated feature are fused, and the two feature vectors can be directly concatenated to obtain the second feature of each occupation, that is, the second feature = [first feature, associated feature]. For example, the first feature of a certain occupation is [1, 12, 0, 0.33], and the associated feature is [1, 1, 0.33, 0]. The first feature and the associated feature of the occupation are concatenated to obtain the second feature of the occupation = [1, 12, 0, 0.33, 1, 1, 0.33, 0].

[0082] S333, the second feature of the last occupation in the occupation time series, the associated feature of each occupation and the first feature of each occupation are fused to obtain the third feature of each occupation.

[0083] For example, the last occupation (i.e., the latest occupation) can be found from the time series, and the second feature of the last occupation can be extracted. The second feature of the last occupation, the associated features of each occupation, and the first feature of each occupation are spliced ​​and fused to obtain the third feature of each occupation, that is, the third feature = [second feature of the last occupation, first feature, associated feature]. For example, the second feature of the last occupation is [1, 12, 0, 0.33, 0.8, 1, 0.5, 1, 0.2], the first feature of a certain occupation is [2, 10, 3, 0.28], and the associated feature of the occupation is [0, 0, 0.25, 0], then the third feature of the occupation = [1, 12, 0, 0.33, 0.8, 1, 0.5, 1, 0.2, 2, 10, 3, 0.28, 0, 0, 0.25, 0].

[0084] S334, performing feature fusion on the second feature of the last occupation in the occupation time series and the third feature of the last occupation in the occupation time series to obtain the student's occupational interest feature.

[0085] Exemplarily, the second eigenvector of the last occupation in the occupation time series and the third eigenvector of the last occupation in the occupation time series are concatenated to generate a eigenvector representing the student's career interest, that is, career interest feature = [second feature of the last occupation, third feature of the last occupation].

[0086] The career interest characteristics obtained through the above steps can be used for further analysis and prediction, such as recommending suitable career paths and analyzing students' career tendencies.

[0087] S400, determining the student's occupation change characteristics based on the student's personal characteristics and the occupation characteristics of each of the student's occupations.

[0088] For example, the factors of career change can be identified by analyzing the personal characteristics of students. The matching degree between the skills characteristics of students and the skill requirements of each occupation can be analyzed. If students frequently switch from positions with low skill matching to positions with high skill matching, then skill matching may be a key factor in career change; the age and work experience of students may affect the frequency and direction of career change. Young students or students with less experience may explore different occupations more frequently.

[0089] The factors of career change can be identified by analyzing the career characteristics of each student's career. The frequency of students' career changes can be calculated, and the average change time interval can be analyzed to identify whether students tend to work steadily or change careers frequently. The direction of career change can be identified through the students' career change path, for example, whether students gradually move from technical positions to management positions, or make lateral movements in a specific field. The common characteristics before each career change (such as low salary) can be found through data analysis to infer possible triggering factors for change.

[0090] The above-identified career change factors can be determined as the career change characteristics of students, and the career change factors can be converted into vector representations to obtain career change feature vectors for model training. The student's personal characteristics, career characteristics of each career, and career change characteristics can be input into a machine learning model (such as logistic regression, random forest, etc.), and the model can predict the student's next possible career change.

[0091] Through this step, a comprehensive analysis of students' personal and career characteristics can determine students' career change characteristics, help predict students' future career development trends, and provide personalized career advice to improve career matching and satisfaction.

[0092] In one possible implementation, see Figure 4 , S400, determine the characteristics of the student's career change based on the student's personal characteristics and the career characteristics of each of the student's careers, including: S410, constructing a career directed graph based on the personal characteristics of the students, the career characteristics of each of the students' careers and the associated information.

[0093] Exemplarily, a career directed graph is a graph structure used to represent a student's career path and associated relationships. Each node of the career directed graph can represent a student's career, and the career characteristics and personal characteristics of each career can be combined to form a feature vector for each node. Based on the associated information, directed edges can be established between each node (each career), and at the same time, edge features can be added to represent the associated information between careers, such as job type similarity, industry type similarity, skill overlap, geographical location similarity, etc.

[0094] Optionally, S410, constructing a career directed graph based on the student's personal characteristics, the career characteristics of each of the student's careers, and associated information, including: S411, determine each occupation of the student as a node of the occupation directed graph, and determine the personal characteristics of the student and the occupational characteristics of each occupation of the student as the initial characteristics of the node corresponding to each occupation.

[0095] For example, a student's career can be used as a node. For example, if a student has n career experiences, then the career directed graph has n nodes. The personal characteristics can be integrated with the career characteristics of each career to obtain the initial feature vector of each node.

[0096] S412, determining the edges of the occupation directed graph according to the association information.

[0097] Exemplarily, the edges of the occupational directed graph can represent the correlation between each occupation and each occupation. According to the association information, the nodes are connected to obtain the edges of the occupational directed graph.

[0098] S413, determining edge weights of the occupation directed graph according to the association information.

[0099] Exemplarily, edge weights can measure the strength of association between each occupation and each occupation. Based on the association information, the similarity of job types between two nodes (occupations) connected by the edge of the occupation directed graph can be calculated. A binary representation (1 for the same and 0 for different) or cosine similarity of job type embedding can be used. Based on the association information, the similarity of industry types between two nodes (occupations) connected by the edge of the occupation directed graph can be calculated. A binary or embedded similarity representation can be used. Based on the association information, the skill overlap between two nodes (occupations) connected by the edge of the occupation directed graph can be calculated using Jaccard similarity or cosine similarity. If the geographical locations of the two nodes (occupations) connected by the edge of the occupation directed graph are the same, a higher association score can be assigned, or the similarity can be calculated based on the geographical distance between the two.

[0100] The weighted sum method can be used to assign weights to each similarity calculated above and calculate the sum to obtain the edge weight of each edge. For example, in a career directed graph, the job type similarity of two nodes connected by an edge is 0.8, the industry type similarity is 1, the skill overlap is 0.5, and the geographical location similarity is 0. The weight parameter of each similarity is 1, then the edge weight of this edge = 1×0.8+1×1+1×0.5+1×0=2.3.

[0101] S414, constructing a career directed graph based on the nodes of the career directed graph, the edges of the career directed graph, and the edge weights of the career directed graph.

[0102] For example, a career directed graph can be constructed using nodes, edges, and edge weights, and the career directed graph can be used to represent the career path of students and the correlation between careers. The career directed graph can be represented by an adjacency matrix or an adjacency list. In the adjacency matrix, each element represents the strength of association (edge ​​weight) between two careers; in the adjacency list, each node contains other nodes connected to it and the corresponding edge weights.

[0103] S420, according to the occupation directed graph, using the graph neural network to calculate the attention features of each occupation.

[0104] For example, a graph neural network (such as a graph attention network GAT) can be used to pass messages on a directed graph of occupations to calculate the attention features of each occupation. For each node, GAT calculates the attention weight based on the features of the neighboring nodes. The attention weight indicates the degree of association between each node and each node's neighboring nodes. The higher the weight, the greater the influence of the node by the neighboring nodes.

[0105] Optionally, S420, calculating the attention feature of each occupation using a graph neural network according to the occupation directed graph, including: S421, according to the initial features of each node in the occupation directed graph, the attention weight between each node and each node's adjacent nodes is calculated using the attention mechanism of the graph neural network to obtain the attention weight of each node's adjacent nodes.

[0106] For example, it can be assumed that each node The initial characteristics are , for each node The initial characteristics Apply a linear transformation to obtain the transformed features ,in Represents a learnable weight matrix. Extract each node Each adjacent node of The transformed features , according to each node The transformed features , each node Each adjacent node of The transformed features And each node With each node Each adjacent node of The edge weight between , calculate each node Each adjacent node of The attention weight , the calculation formula is ,in, is a learnable weight vector used to calculate attention, Represents a feature concatenation operation.

[0107] S422, normalize the attention weights of the neighboring nodes of each node to obtain the normalized attention weights of the neighboring nodes of each node.

[0108] For example, each node obtained by calculation can be Each adjacent node of The attention weight Normalize and get each node Each adjacent node of The normalized attention weights The calculation formula is ,in, Representation Node The set of all adjacent nodes of . After normalization, the sum of the attention weights of all adjacent nodes of each node is 1.

[0109] S423, according to the normalized attention weights of the neighboring nodes of each node, weighted sum is performed on the initial features of the neighboring nodes of each node to obtain the attention features of each node.

[0110] For example, each node can be used Each adjacent node of The normalized attention weights For each node Each adjacent node of The transformed features Perform weighted summation to obtain the attention feature of each node. The calculation formula is: ,in, represents the attention feature of each node, is an activation function (e.g. ReLU) used to add non-linearity.

[0111] S424, determining the attention feature of each node as the attention feature of the occupation corresponding to each node.

[0112] For example, the attention feature of each node is That is, the attention characteristics of the profession corresponding to each node.

[0113] S430, integrating the attention features of each occupation to obtain the occupation change features of the students.

[0114] Exemplarily, the average pooling method can be used to average the attention features of all occupations to generate the student's career change features. Average pooling will equally consider the features of all nodes and is suitable for situations where all career changes are equally important to the student's career change features.

[0115] The maximum pooling method can be used to take the element-level maximum value of the attention features of all occupations to generate occupation change features. Maximum pooling can retain the key changes in the features and emphasize the important features in the occupation directed graph.

[0116] The weighted pooling method can be used to assign different weights to each occupation according to its position or importance in the time series, and the attention features of each occupation are weighted summed according to the weight of each occupation.

[0117] Through the above steps, the correlation between different occupations can be adaptively learned, thereby effectively capturing students' career development trends. The final career change characteristics can serve as the basis for further analysis and prediction, and can be used to generate personalized career development suggestions or path recommendations.

[0118] S500, based on the student's career interest characteristics and the student's career change characteristics, predict the student's next career to obtain the student's prediction result.

[0119] For example, based on the student's career interest characteristics (such as job type, industry preference, skill requirements, etc.), the career category that best matches the career interest characteristics can be found. For example, if the student has a strong interest in data analysis, data analysis positions can be recommended first. Weights can be set for career interest characteristics (such as 30% for industry preference, 40% for job type, and 30% for skill matching), and scores can be calculated based on the matching degree of different characteristics.

[0120] Based on the student's career change characteristics, such as change frequency, salary sensitivity, position or industry preference, etc., the possible direction of the next career change can be determined. For example, if the student's career change history shows that he is very sensitive to salary, then priority will be given to career categories with higher salaries; if the student shows a clear trend in the direction of change (such as gradually switching from a technical position to a management position), then priority can also be given to management positions when recommending positions. Weights can be set for career change characteristics, and scores can be calculated based on the matching degree of different characteristics.

[0121] The interest matching score and the change tendency score can be weighted and superimposed, and the occupation category with the highest score is the prediction result. Threshold conditions can be set to avoid recommending positions that are too far away from students' interests.

[0122] In a possible implementation, S500 predicts the student's next career based on the student's career interest characteristics and the student's career change characteristics, and obtains the student's prediction result, including: S510, extracting occupational characteristics of the last occupation in the occupational time series.

[0123] For example, the occupational characteristics of the last occupation can be extracted from the occupational time series.

[0124] S520, the occupational characteristics of the last occupation in the occupational time series, the personal characteristics of the students, the occupational interest characteristics of the students and the occupational change characteristics of the students are integrated to obtain the overall characteristics of the students.

[0125] Exemplarily, feature fusion can be performed by vector splicing, where the occupational feature vector of the last occupation, the student's personal feature vector, the student's occupational interest feature vector, and the student's occupational change feature vector are spliced ​​to form a complete feature vector. If the dimensions of the features are unbalanced, standardization or dimensionality reduction of the features can be considered to ensure the consistency of the prediction model input.

[0126] S530, based on the overall characteristics of the student, using the prediction model to predict the student's next career, and obtain the student's prediction result. The prediction model is a deep learning model.

[0127] Exemplarily, a suitable deep learning model can be selected, which may include: a multi-layer perceptron (MLP), in which the MLP input layer receives the overall features, undergoes nonlinear transformations in several hidden layers, and finally outputs the prediction results. The model has a simple structure and is suitable for scenarios where features have been extracted and fused; a Transformer model, in which the student's overall feature vector can be input into the Transformer model, which is processed and output with the self-attention mechanism of the Transformer model. The Transformer model can flexibly process long sequences and capture global dependencies.

[0128] Training process of prediction model: The data set can be composed of the information to be processed of multiple students from the database of the internship training base, and the actual next career of each student can be marked. The marked data set can be divided into training set, validation set and test set, with the ratio of 70% training set, 15% validation set and 15% test set.

[0129] After selecting a suitable deep learning model, you can choose the training configuration of the model: you can use the cross-entropy loss function (Cross-Entropy Loss). You can use the Adam or SGD optimizer. Adam is a more commonly used optimizer because of its fast convergence speed and automatic learning rate adjustment. You can set the model's hyperparameters. You can set the model's learning rate, starting from 0.001, and adjust it according to the validation set effect; you can set the model's batch size, such as 32, 64, or 128, and the specific size can be determined through experiments; you can set the number of model iterations (Epochs), ranging from 10 to 100, and decide whether to stop early based on the performance on the validation set.

[0130] Input the training set into the model, obtain the output probability after multiple layers of calculation, compare the model prediction results with the true label, calculate the loss value, calculate the gradient based on the loss value, and use the optimizer to update the model parameters to gradually reduce the loss. After each epoch, evaluate the performance of the model on the validation set, monitor the loss and accuracy of the validation set, and if the loss on the validation set no longer decreases, consider using the Early Stopping technique to terminate the training to prevent overfitting. After completing the training, evaluate the model on the test set, calculate indicators such as accuracy, precision, recall, and F1 score, and understand the generalization performance of the model.

[0131] After model training and optimization, the trained prediction model can be used to predict new data, that is, the overall characteristics of the student are taken as input, and after being processed by the prediction model, the prediction result of the next career is output. The prediction model outputs the probability distribution of career categories, indicating the possible categories of the student's next career, and the category with the highest probability is selected as the prediction result.

[0132] Through the above steps, students' career interests, career change patterns and personal backgrounds can be comprehensively considered to provide more accurate career predictions.

[0133] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0134] Corresponding to the internship and training base employment tracking and investigation information processing method described in the above embodiment, the embodiment of the present application also provides an internship and training base employment tracking and investigation information processing system, and each unit of the system can implement each step of the internship and training base employment tracking and investigation information processing method. Figure 5 A structural block diagram of an employment tracking and investigation information processing system for an internship and training base provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0135] Reference Figure 5 The system comprises: The acquisition unit is used to acquire the student's pending information, wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information.

[0136] The extraction unit is used to extract the personal characteristics of the students from the personal information of the students, and to extract the occupational characteristics of each occupation of the students from the occupational information of each occupation in the internship employment information of the students.

[0137] The occupational interest characteristic obtaining unit is used to determine the occupational interest characteristics of students according to the occupational characteristics of each occupation of the students and the internship employment information of the students.

[0138] The occupation change characteristic obtaining unit is used to determine the occupation change characteristics of students according to the personal characteristics of the students and the occupation characteristics of each of the students' occupations.

[0139] The prediction unit is used to predict the student's next career based on the student's career interest characteristics and the student's career change characteristics, and obtain the student's prediction result.

[0140] It should be noted that the information interaction, execution process and other contents between the above-mentioned units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0141] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0142] The present application embodiment also provides an internship and training base employment tracking survey information processing device, Figure 6 This is a schematic diagram of the structure of an internship training base employment tracking survey information processing device provided in an embodiment of the present application. Figure 6 As shown, the internship training base employment tracking survey information processing device 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one is shown), at least one memory 61 ( Figure 6Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the internship and training base employment tracking survey information processing device 6 implements the steps in any of the above-mentioned internship and training base employment tracking survey information processing method embodiments, or implements the functions of each unit in the above-mentioned device embodiments.

[0143] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the internship training base employment tracking survey information processing device 6.

[0144] The internship training base employment tracking survey information processing device 6 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The internship training base employment tracking survey information processing device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 6 It is only an example of the internship and training base employment tracking survey information processing device 6 and does not constitute a limitation on the internship and training base employment tracking survey information processing device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, buses, etc.

[0145] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0146] In some embodiments, the memory 61 may be an internal storage unit of the internship and training base employment tracking survey information processing device 6, such as a hard disk or memory of the internship and training base employment tracking survey information processing device 6. In other embodiments, the memory 61 may also be an external storage device of the internship and training base employment tracking survey information processing device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the internship and training base employment tracking survey information processing device 6. Further, the memory 61 may also include both the internal storage unit of the internship and training base employment tracking survey information processing device 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0147] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0148] An embodiment of the present application provides a computer program product. When the computer program product runs on an internship and training base employment tracking and investigation information processing device, the internship and training base employment tracking and investigation information processing device implements the steps in any of the above-mentioned method embodiments.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the information processing equipment of the internship training base employment tracking survey, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0150] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0151] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0152] In the embodiments provided in the present application, it should be understood that the disclosed internship and training base employment tracking survey information processing system, device and method can be implemented in other ways. For example, the internship and training base employment tracking survey information processing system and device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0153] 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for processing employment tracking survey information of an internship training base, characterized in that: include: Obtaining the student's pending information; wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information; Extracting the personal characteristics of the student from the personal information of the student, and extracting the occupational characteristics of each occupation of the student from the occupational information of each occupation in the internship employment information of the student; Determining the career interest characteristics of the student based on the career characteristics of each of the student's careers and the student's internship employment information; Determining the occupational change characteristics of the student based on the personal characteristics of the student and the occupational characteristics of each of the student's occupations; Based on the student's career interest characteristics and the student's career change characteristics, the student's next career is predicted to obtain the student's prediction result.

2. The method for processing employment tracking survey information of an internship and training base as claimed in claim 1, characterized in that: Determining the student's career interest characteristics based on the career characteristics of each of the student's careers and the student's internship employment information includes: According to the time information of each occupation in the internship employment information of the student, each occupation is arranged in ascending order of time to obtain an occupation time sequence; wherein the occupation time sequence includes the time information of each occupation; the time information of each occupation includes the start time and the end time of each occupation; Determine the first feature of each occupation according to the occupation time series and the occupational features of each occupation of the students; wherein the first feature is used to characterize the fusion feature between the position feature of each occupation in the occupation time series and the occupational features of each occupation; Based on the first characteristic of each occupation, the occupational interest characteristics of the students are determined.

3. The method for processing employment tracking survey information of an internship and training base as claimed in claim 2, characterized in that: The step of determining the first characteristic of each occupation according to the occupation time series and the occupation characteristics of each occupation of the students comprises: Determine the position feature of each occupation according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series; The position feature of each occupation and the occupation feature of each occupation of the students are fused to obtain the first feature of each occupation.

4. The method for processing employment tracking survey information of an internship and training base as claimed in claim 3, characterized in that: Determining the position feature of each occupation according to the position of each occupation in the occupation time series and the time information of each occupation in the occupation time series includes: Determine the position index of each occupation according to the position of each occupation in the occupation time series; wherein the position index is used to represent the absolute position of the occupation in the occupation time series; Calculate the duration of each occupation according to the time information of each occupation in the occupation time series; According to the time information of each occupation in the occupation time series, the occupation interval of each occupation is calculated; wherein the occupation interval is used to represent the time interval between two occupations; According to the time information of each occupation in the occupation time series, the relative position of each occupation in the occupation time series is calculated to obtain the relative time proportion of each occupation; The position index of each occupation, the duration of each occupation, the occupational interval of each occupation and the relative time proportion of each occupation are integrated to obtain the position characteristics of each occupation.

5. The method for processing employment tracking survey information of an internship and training base as claimed in claim 2, characterized in that: Determining the student's occupational interest characteristics according to the first characteristic of each occupation includes: Extracting correlation information from the internship employment information of the students, and calculating the correlation between each occupation in the occupation time series and the previous occupation based on the correlation information, to obtain the correlation feature of each occupation in the occupation time series; wherein the correlation information is used to characterize the correlation between each occupation and each occupation; Fusing the associated features of each occupation in the occupation time series with the first features of each occupation to obtain the second features of each occupation; The second feature of the last occupation in the occupation time series, the associated feature of each occupation and the first feature of each occupation are fused to obtain the third feature of each occupation; The second feature of the last occupation in the occupation time series and the third feature of the last occupation in the occupation time series are fused to obtain the occupational interest feature of the student.

6. The method for processing employment tracking survey information of an internship and training base as claimed in claim 5, characterized in that: Determining the occupation change characteristics of the student based on the personal characteristics of the student and the occupation characteristics of each of the student's occupations includes: Constructing a career directed graph based on the personal characteristics of the student, the career characteristics of each of the student's careers and the association information; According to the occupation directed graph, the attention feature of each occupation is calculated using a graph neural network; The attention features of each occupation are integrated to obtain the occupation change features of the student.

7. The method for processing employment tracking survey information of an internship and training base as claimed in claim 6, characterized in that: The step of constructing a career directed graph based on the personal characteristics of the student, the career characteristics of each of the student's careers and the association information includes: Determine each occupation of the student as a node of the occupation directed graph, and determine the personal characteristics of the student and the occupational characteristics of each occupation of the student as initial characteristics of the node corresponding to each occupation; Determine the edges of the occupation directed graph according to the association information; Determining edge weights of the occupation directed graph according to the association information; The occupation directed graph is constructed based on the nodes of the occupation directed graph, the edges of the occupation directed graph and the edge weights of the occupation directed graph.

8. The method for processing employment tracking survey information of an internship and training base as claimed in claim 7, characterized in that: The method of calculating the attention features of each occupation using a graph neural network according to the occupation directed graph includes: According to the initial features of each node of the occupation directed graph, the attention weight between each node and each node's adjacent nodes is calculated using the attention mechanism of the graph neural network to obtain the attention weight of each node's adjacent nodes; Normalize the attention weights of the neighboring nodes of each node to obtain the normalized attention weights of the neighboring nodes of each node; According to the normalized attention weights of the neighboring nodes of each node, the initial features of the neighboring nodes of each node are weighted summed to obtain the attention features of each node; The attention feature of each node is determined as the attention feature of the profession corresponding to each node.

9. The method for processing employment tracking survey information of an internship and training base as claimed in claim 2, characterized in that: The predicting process of the student's next career based on the student's career interest characteristics and the student's career change characteristics to obtain the student's prediction result includes: Extracting occupational characteristics of the last occupation in the occupational time series; The occupational characteristics of the last occupation in the occupational time series, the personal characteristics of the student, the occupational interest characteristics of the student and the occupational change characteristics of the student are integrated to obtain the overall characteristics of the student; Based on the overall characteristics of the student, a prediction model is used to predict the student's next career to obtain a prediction result for the student; wherein the prediction model is a deep learning model.

10. An employment tracking survey information processing system for an internship and training base, characterized in that: include: An acquisition unit is used to acquire the student's pending information; wherein the student's pending information is used to represent the information obtained by the internship training base from the follow-up investigation of the student's employment situation, and the student's pending information includes the student's personal information and the student's internship employment information; An extraction unit, used to extract the personal characteristics of the student from the personal information of the student, and to extract the occupational characteristics of each occupation of the student from the occupational information of each occupation in the internship employment information of the student; A career interest characteristic obtaining unit, used for determining the career interest characteristics of the student according to the career characteristics of each of the student's careers and the student's internship employment information; A career change characteristic obtaining unit, used for determining the career change characteristics of the student according to the personal characteristics of the student and the career characteristics of each of the student's careers; The prediction unit is used to predict the student's next career based on the student's career interest characteristics and the student's career change characteristics to obtain the student's prediction result.

Images