AI technology-based student occupation direction intelligent planning system and method

Abstract

The invention relates to the technical field of occupational planning, in particular to an AI technology-based intelligent student occupational direction planning system and method, and the system comprises a dynamic ability analysis module, an occupational ecology adaptation module, an occupational path optimization module, a behavior growth analysis module and a skill achievement evaluation module. According to the system, pertinence and timeliness of occupational suggestions are enhanced through continuous assessment of student capabilities and immediate matching of market demands, the system not only can identify potential capabilities and growth areas of students, but also can adjust occupational path suggestions according to immediate data of a labor market, and the system can be used for providing proposal for students through quantification of data in occupational ecology. The system optimizes occupational path recommendation, ensures that the proposed suggestions have higher practicability and scientificity, and improves the accuracy and flexibility of occupational planning, so that students can more accurately understand the market dynamics, and make decisions more suitable for the occupational development of themselves.

Description

Technical Field

[0001] The present invention relates to the technical field of career planning, and particularly to an intelligent career direction planning system and method for students based on AI technology. Background Art

[0002] Career planning mainly involves using various tools and methods to help individuals determine and achieve their career goals. In the modern workplace environment, this field is constantly integrating new technologies such as artificial intelligence (AI), big data analysis, and machine learning to provide more personalized and data-driven career development advice. These technologies can analyze a large amount of career data, educational backgrounds, and labor market trends, thereby helping users formulate career paths that better suit their personal interests and market demands.

[0003] Among them, an intelligent career direction planning system for students based on AI technology refers to a system that uses artificial intelligence technology to assist students in career planning. This system analyzes students' interests, abilities, academic achievements, and other relevant data, combines them with labor market information, and intelligently recommends matching career paths. Its main purpose is to help students understand their career potential, provide targeted career development advice, and assist students in making more informed career decisions by simulating the possible outcomes of different career choices. It aims to guide students' career selection process and improve their employment satisfaction and career development efficiency.

[0004] The prior art provides career path suggestions based on static data, lacking continuous tracking and immediate updating of the evolution of personal abilities, which limits the adaptability and timeliness of the suggestions and often results in career suggestions being unable to keep up with personal growth needs and market changes. For example, a student may be initially suitable for a certain career path, but as time goes by and their abilities develop, a more suitable path has changed. In addition, the lack of in-depth analysis of learning behaviors and attitudes makes career planning unable to be fully targeted, reducing its effectiveness in guiding students' career choices and affecting students' career satisfaction and development efficiency. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an intelligent career direction planning system and method for students based on AI technology.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent career direction planning system for students based on AI technology, the system includes:

[0007] The ability dynamic analysis module obtains students' learning achievements, classroom participation records, and subject ability scores, analyzes the completion of homework and test scores, and identifies areas for ability improvement based on students' responses to learning tasks, obtaining ability weight indicators;

[0008] The professional ecological adaptation module calls the ability weight indicators, analyzes the industry development rate, the vocational skill update cycle, and the job demand volume, judges the market growth rate of each vocational category, and generates an industry adaptation index;

[0009] Based on the industry adaptation index, the career path optimization module calculates the matching difference between the ability weight and the skill requirements, evaluates the relevance between the job demand change rate and the industry growth trend, optimizes the sorting logic of the recommended path, and obtains the career path optimization information;

[0010] The behavior growth analysis module calls the career path optimization information, analyzes the participation rate of each type of task, analyzes the correlation between the behavior pattern and the ability change, and identifies the adaptability of the student to the career goal, and obtains the growth trend analysis result;

[0011] The skill achievement evaluation module calls the growth trend analysis result, analyzes the skill achievement degree of the student, evaluates the difference between the skill and the career demand, and adjusts the vocational skill scoring standard to obtain the skill evaluation index.

[0012] The improvements of the present invention are that the ability weight indicators include cognitive processing speed, comprehension ability, and problem-solving ability, the industry adaptation index includes skill adaptation rate, market demand comparison result, and career growth potential, the career path optimization information includes skill compatibility, career demand sensitivity, and development prospect evaluation result, the growth trend analysis result includes learning efficiency, behavior improvement points, and target adaptation evaluation, and the skill evaluation index includes skill mastery degree, adaptability evaluation, and vocational skill gap.

[0013] The improvements of the present invention are that the ability dynamic analysis module includes:

[0014] The learning outcome evaluation sub-module obtains the learning outcomes, classroom participation records, and subject ability scores of students, extracts the data of homework completion rate, correct rate, and test scores, analyzes the stability of homework completion and the degree of knowledge mastery, identifies the homework fluctuation of different students in the same subject, and uses the formula:

[0015]

[0016] Calculate the learning stability index S t where P i represents the score of the i-th homework, W i represents the weight of the i-th homework, n represents the total number of homeworks, and λ is the influence coefficient of homework score fluctuation, which is used to adjust the influence of fluctuation on the learning stability index;

[0017] The classroom participation analysis submodule collects the number of questions, answers and discussions in class based on the learning stability index, calculates the students' classroom participation activity in differentiated courses, analyzes their adaptability to differentiated teaching methods, determines the impact of classroom communication on subject mastery, and obtains the classroom interaction activity index;

[0018] The subject ability assessment submodule is based on the classroom interaction activity index and combines students' recent subject assessment results to evaluate students' logical reasoning ability, language expression ability and mathematical analysis ability, judge students' performance on the same subject tasks, identify key ability development areas, and obtain ability weight indicators.

[0019] The present invention is improved in that the occupational ecology adaptation module comprises:

[0020] The market demand assessment submodule calls the capability weight index, analyzes the industry development rate, professional skill update cycle and job demand, calculates the market demand level of each industry, and establishes a market demand index;

[0021] The occupation matching analysis submodule determines the market growth rate of each occupation category based on the market demand index, and compares the key demand variables and student ability weights of each occupation category item by item, using the formula:

[0022]

[0023] Calculate the degree of adaptation of occupational categories to students' abilities and generate the industry adaptation index, where MH i Represents the suitability of occupation i, CH ij represents the student's score on ability j, WH j represents the critical weight of ability j in occupation i, DH i represents the demand index of occupation i in the market, SH i represents the industry standard fitness of occupation i, and m is the total number of capabilities.

[0024] The present invention is improved in that the career path optimization module comprises:

[0025] The matching difference calculation submodule calculates the matching difference between the occupational skill requirements and the student's ability weight based on the industry adaptation index, collects the key skill variables of each occupational category, normalizes each skill item, and calculates the student's matching score in the occupational category to obtain the occupational matching difference;

[0026] The industry trend assessment submodule calls the occupation matching difference, analyzes the correlation with the industry growth trend, collects time series data of the job demand change rate, calculates the job demand growth rate, evaluates the stability of the difference occupation categories, and obtains the industry trend index;

[0027] Based on the industry trend index, the path sorting optimization sub-module optimizes the sorting logic of the recommended path, using the formula:

[0028]

[0029] Calculate the optimal sorting score for the occupation category to obtain the preferred occupation path information, where BP i represents the preference value of occupation i, Um i represents the matching difference of occupation i, UT i represents the industry trend index of occupation i, Ud i represents the change rate of the job demand for occupation i, Us i represents the industry growth trend benchmark value of occupation i.

[0030] The improvement of the present invention is that the behavior growth analysis module includes:

[0031] The learning behavior monitoring sub-module calls the preferred occupation path information, monitors the online learning time of students, analyzes the time investment in the learning stage, identifies the change trend of the task submission time, and counts the number of completed projects and the average completion time to obtain the learning behavior characteristic value;

[0032] Based on the learning behavior characteristic value, the task participation evaluation sub-module analyzes the correlation between the task type, difficulty and the student behavior characteristics, evaluates the influence degree of different tasks on the student learning behavior, using the formula:

[0033]

[0034] Calculate the standardized participation ratio of the task category to obtain the task participation index, where PR o represents the participation ratio of task o, TP o represents the total number of participants in task o, TF o represents the completion frequency of task o, represents the total completion volume of all task categories, o represents the current task category, and c represents the index of all task categories;

[0035] The growth trend identification sub-module calls the task participation index, analyzes the student behavior pattern, analyzes the ability growth curve, matches the ability deviation of the student in different learning stages, and evaluates the adaptability of the student to the career goal to obtain the growth trend analysis result.

[0036] The improvement of the present invention is that the skill achievement evaluation module includes:

[0037] The skill performance analysis sub-module calls the growth trend analysis result, calculates the completion rate of students in multiple types of virtual tasks, statistically analyzes the distribution of assessment scores, then analyzes the score fluctuations of students in different skill dimensions, and performs normalization processing to obtain skill performance eigenvalues;

[0038] The skill matching degree calculation sub-module analyzes the matching degree between the student's skills and the requirements of the career path based on the skill performance eigenvalues, compares with the student's skill performance data, and uses the formula:

[0039]

[0040] Calculate the skill point matching degree, where SN k represents the matching degree of skill k, NP k represents the expected value of skill k in the career path requirements, NR k represents the performance value of the student on skill k;

[0041] The skill score adjustment sub-module adjusts the professional skill scoring standard based on the skill point matching degree, according to the skill achievement deviation, reallocates the weight of each skill point, and calculates the score value after weight adjustment to obtain the skill evaluation index.

[0042] A method for intelligent planning of students' career directions based on AI technology, the method for intelligent planning of students' career directions based on AI technology is executed based on the above-mentioned system for intelligent planning of students' career directions based on AI technology, and includes the following steps:

[0043] S1: Obtain the learning achievements, classroom participation records and subject ability scores of students, evaluate the logical reasoning ability, language expression ability and mathematical analysis ability of students, judge the adaptability and performance of students in different learning environments, identify the areas for ability improvement, and obtain the ability weight index;

[0044] S2: Based on the ability weight index, analyze the industry development rate, the vocational skill update cycle and the job demand volume, judge the market growth rate of each vocational category, determine the matching degree between each vocational category and the student's ability, and generate an industry adaptation index;

[0045] S3: Based on the industry adaptation index, calculate the matching difference between the ability weight and the skill requirements, evaluate the correlation between the job demand change rate and the industry growth trend, optimize the sorting logic of the recommended path, and obtain the preferred career path information;

[0046] S4: Based on the preferred career path information, analyze the participation rate of each type of task, analyze the correlation between the behavior pattern and the ability change, identify the adaptability of the student to the career goal, and obtain the growth trend analysis result;

[0047] S5: Based on the growth trend analysis results, collect the virtual task performance, skill assessment scores, and internship position evaluations of students, analyze the skill attainment of students, evaluate the differences between skills and career requirements, adjust the vocational skill scoring criteria, and obtain skill assessment indicators.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0049] In the present invention, through continuous assessment of students' abilities and immediate matching with market demands, the pertinence and timeliness of career advice are strengthened. The system can not only identify students' potential abilities and growth areas, but also adjust career path suggestions according to the immediate data in the labor market. By quantifying the data in the vocational ecosystem, such as industry growth rates and changes in job demands, the system optimizes career path recommendations, ensuring that the suggestions are more practical and scientific, improving the accuracy and flexibility of career planning, enabling students to understand market dynamics more accurately, and thus making more suitable decisions for their own career development. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a module diagram of an intelligent career direction planning system for students based on AI technology proposed by the present invention;

[0051] Figure 2 It is a flowchart of the ability dynamic analysis module in the present invention;

[0052] Figure 3 It is a flowchart of the vocational ecosystem adaptation module in the present invention;

[0053] Figure 4 It is a flowchart of the career path optimization module in the present invention;

[0054] Figure 5 It is a flowchart of the behavior growth analysis module in the present invention;

[0055] Figure 6 It is a flowchart of the skill attainment assessment module in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0058] Example

[0059] See also Figure 1 The present invention provides a technical solution: an AI-based student career direction intelligent planning system comprising:

[0060] The ability dynamic analysis module obtains students' learning outcomes, class participation records and subject ability scores. By analyzing the completion of homework and assessment results, it evaluates students' logical reasoning ability, language expression ability and mathematical analysis ability. Based on students' responses to recent learning tasks, it judges students' adaptability in a differentiated learning environment, identifies key ability improvement areas, and obtains ability weight indicators.

[0061] The occupational ecology adaptation module calls the ability weight index, analyzes the industry development rate, occupational skill update cycle and job demand, calculates the market demand index, determines the market growth rate of each occupation category, and determines the matching degree between each occupation category and student ability by comparing it with the student ability data item by item, and generates the industry adaptation index;

[0062] The career path optimization module collects occupational skill requirements, job demand change rate and career development path based on the industry adaptation index, calculates the matching difference between student ability weight and occupational skill requirements, evaluates the correlation between job demand change rate and industry growth trend, optimizes the sorting logic of recommended paths, and obtains career path optimization information;

[0063] The behavior growth analysis module calls on the career path optimization information, monitors students' online learning time, task submission frequency and practical project completion, analyzes the participation rate of each type of task, analyzes the relationship between students' behavior patterns and ability changes, and identifies students' adaptability to career goals to obtain growth trend analysis results;

[0064] The skill achievement assessment module calls on the growth trend analysis results, collects students' virtual task performance, skill assessment scores and internship position evaluations, analyzes students' skill achievement, evaluates the difference between students' skills and career path requirements, and adjusts the career skill scoring standards based on the assessment results to obtain skill assessment indicators.

[0065] The ability weight indicators include cognitive processing speed, comprehension ability, and problem-solving ability. The industry adaptation index includes skill adaptation rate, market demand comparison result, and career growth potential. The preferred career path information includes skill compatibility, career demand sensitivity, and development prospect evaluation result. The growth trend analysis result includes learning efficiency, behavior improvement points, and goal adaptation evaluation. The skill evaluation indicators include skill mastery level, adaptability evaluation, and career skill gap.

[0066] Please refer to Figure 2 , the ability dynamic analysis module includes:

[0067] The learning outcome evaluation sub-module obtains the learning outcomes, classroom participation records, and subject ability scores of students, extracts data on homework completion rate, correct rate, and assessment scores, analyzes the stability of homework completion and knowledge mastery level, identifies the homework fluctuation situations of different students in the same subject, and uses the formula:

[0068]

[0069] Calculate the learning stability index S t , where P i represents the score of the i-th homework, W i represents the weight of the i-th homework, n represents the total number of homeworks, and λ is the influence coefficient of homework score fluctuation, which is used to adjust the influence of fluctuation on the learning stability index;

[0070] Collect data on the homework completion situation of students, record the submission time, correct rate, and score of each homework. The homework completion rate is calculated as the ratio of the number of submitted homeworks to the number of homeworks that should be submitted. If a student needs to submit 20 homeworks in a certain stage and actually submits 18, the homework completion rate is calculated as That is, the homework completion rate is 90%. The correct rate is calculated as the ratio of the number of correct questions to the total number of questions. Suppose there are 10 questions in a homework for this student and 8 questions are answered correctly, then the correct rate is calculated as After obtaining the score data of all homeworks, in order to evaluate the stability of students' learning outcomes, calculate the learning stability index S t , first calculate the weighted average score of all homework scores. This student has 5 homeworks, and the scores are 80, 85, 90, 75, and 88 respectively. The weights of each homework are 0.1, 0.2, 0.3, 0.15, and 0.25 respectively. Then the weighted average score is calculated as:

[0071]

[0072] Secondly, calculate the fluctuation of the homework scores, that is, the average of the sum of the change ranges of the scores of two adjacent homework assignments. If the score fluctuations of a student's 5 homework assignments are: |85 - 80| = 5, |90 - 85| = 5, |75 - 90| = 15, |88 - 75| = 13, then the calculation of the average value of the score fluctuations of his homework is as follows:

[0073]

[0074] If the average fluctuation of the students in a certain class is about 10 points, then λ = 0.8 can be set and substituted into the calculation to get:

[0075] S t = 85.25 - λ × 9.5;

[0076] S t = 85.25 - (0.8 × 9.5) = 77.65;

[0077] This value is used to measure the stability of the students' homework performance and can be compared with different students to obtain the learning stability index of the students.

[0078] The classroom participation analysis sub-module, based on the learning stability index, collects the number of questions asked, the number of answers given, and the number of discussion speeches in the classroom, calculates the classroom participation activity of the students in different courses, analyzes their adaptability to different teaching methods, determines the impact of classroom communication on subject mastery, and obtains the classroom interaction activity index;

[0079] Statistically record the questions asked, answers given, and discussions of the students in different classrooms. For example, if a certain student asks a total of 15 questions, answers 30 times, and participates in 20 group discussions in 10 classes, then the classroom participation behavior data are 15, 30, and 20 respectively. Based on this, calculate the classroom participation activity index, and the formula is:

[0080]

[0081] Substitute the values:

[0082]

[0083] Secondly, analyze the classroom participation of different students. If the average value of the classroom participation activity index of the whole class is 5.0, then the classroom participation of this student is relatively high. If it is less than 3.0, then this student has less classroom interaction. Combining with the students' mastery of subject knowledge, calculate their classroom adaptability index, evaluate their adaptability to different teaching methods, and obtain the classroom interaction activity index.

[0084] The sub-module of subject ability assessment evaluates students' logical reasoning ability, language expression ability and mathematical analysis ability based on the classroom interaction activity index, combines with the students' recent subject assessment scores, judges the students' performance on the same subject tasks, identifies the key ability development areas, and obtains the ability weight indicators.

[0085] Combined with the students' recent subject assessment scores, extract the students' subject assessment scores. If the scores of a student in the last three assessments are 75, 80 and 85 respectively, then calculate the average subject ability of this student:

[0086]

[0087] Next, calculate the subject ability scoring weight based on the classroom interaction activity index Az = 6.5. When the classroom activity is in the range of 3.0 - 8.0, it has a greater impact on the subject ability scoring. Set the impact coefficient α = 0.5, then calculate the subject ability score of this student:

[0088] Cr = Mz + αAz = 80 + (0.5×6.5) = 83.25;

[0089] According to the subject ability score, analyze the students' logical reasoning ability, language expression ability and mathematical analysis ability, compare the performance of different students, calculate their adaptability in subject tasks, and combine with the ability development curve to identify their key ability development areas and obtain the ability weight indicators.

[0090] Please refer to Figure 3 , the career ecological adaptation module includes:

[0091] The market demand assessment sub-module calls the ability weight indicators, analyzes the industry development rate, the vocational skill update cycle and the job demand volume, calculates the market demand level of each industry, and establishes a market demand index.

[0092] Collect the industry development rate, obtain the growth rate of each industry within a certain period of time in the past. The calculation method is to compare the market size data of the industry at different time points. For example, if the market size of an industry in 2020 is 500 billion yuan and grows to 750 billion yuan in 2025, then the industry development rate is calculated as That is, a growth rate of 50%. Secondly, analyze the vocational skill update cycle, collect the change data of the main job skill requirements in a certain industry in the past several years, and calculate the average skill replacement frequency. For example, if the main skill requirements of an industry change from A to B, C, D within 5 years and the number of updates is 3 times, then the skill update cycle is calculated as That is, the industry updates its major skills every 1.67 years on average. Next, calculate the job demand and count the changes in the number of recruitment demands for major jobs in the industry in the past few years. For example, if the recruitment demand for a certain job is 20,000 in 2020 and rises to 30,000 in 2025, the job demand growth rate is calculated as That is, a job demand growth rate of 50%. After normalizing the above three key variables, a market demand index is constructed.

[0093] The occupation matching analysis submodule determines the market growth rate of each occupation category based on the market demand index, and compares the key demand variables and student ability weights of each occupation category item by item, using the formula:

[0094]

[0095] Calculate the degree of adaptation of occupational categories to students' abilities and generate the industry adaptation index, where MH i Represents the suitability of occupation i, CH ij represents the student's score on ability j, such as logical reasoning ability, language expression ability, mathematical analysis ability, etc. j represents the critical weight of ability j in occupation i. For example, if a certain occupation requires programming ability much more than other abilities, then the programming ability weight of this occupation is relatively large. i represents the demand index of occupation i in the market, SH i represents the industry standard fitness of occupation i, and m is the total number of capabilities;

[0096] First, calculate the expansion of each occupation in the market. For example, if the number of employees in a certain occupation in 2020 is 1 million and increases to 1.2 million in 2025, the market growth rate is calculated as That is, a growth rate of 20%. Secondly, the key demand variables of different occupational categories are compared with the ability weights of students to extract the core demand variables of the occupation. For example, the demand for programming ability in an IT industry accounts for 40%, logical analysis ability 30%, communication ability 20%, and data processing ability 10%. Its key demand variables are {40, 30, 20, 10}, and the student scores on ability are {85, 75, 60, 70} respectively. The weight item W j According to the calculation settings based on occupational needs, if a student's ability score is as follows:

[0097] Logical reasoning ability (85 points), language expression ability (75 points), mathematical analysis ability (60 points), data processing ability (70 points);

[0098] The weights of abilities for a particular profession are as follows:

[0099] Logical reasoning ability (0.4), language expression ability (0.3), mathematical analysis ability (0.2), data processing ability (0.1);

[0100] The market demand index is DH i = 0.75, and the industry standard adaptation degree is SH i = 0.8.

[0101] Calculate the weighted score:

[0102]

[0103] Calculate the normalized adaptation degree:

[0104]

[0105] Calculate the market demand difference term:

[0106]

[0107] Calculate the adaptation degree:

[0108] MH i = 75.5×(1 - 0.0625) = 75.5×0.9375 = 70.8;

[0109] The result shows that the adaptation degree of the student in this occupation is 70.8, which means that this occupation is relatively suitable for the student, but there is still a certain gap in ability. After adjusting the ability weight matching degree and market demand fluctuations, the adaptation degree of this occupation is relatively close to the industry average level.

[0110] Please refer to Figure 4 , the career path optimization module includes:

[0111] The matching difference calculation sub-module calculates the matching difference between the occupational skill requirements and the student's ability weight based on the industry adaptation index, collects the key skill variables of each occupational category, normalizes each skill item, and calculates the student's matching score in the occupational category to obtain the occupational matching difference;

[0112] Obtain occupational skill requirement data, including the core skill items of each occupational category, and digitize the ability requirements of skill items, set the importance weights of different skills in the occupation, obtain student ability weight data, and compare the deviation between students' ability scores and occupational skill requirements. For example, the key skills of a certain occupation include programming ability (weight 0.4), data analysis ability (weight 0.3), communication ability (weight 0.2) and project management ability (weight 0.1). Students' scores on the skills are 85, 75, 60 and 70 respectively. Calculate the matching error of each skill item. For example, the error of programming ability is calculated as: |85-100|×0.4=6, and the error of data analysis ability is calculated as: |75-95|×0.3=6. Accumulate the weighted errors of each skill item, obtain the overall matching deviation value of the student in the occupational category, perform normalization so that the matching difference is between 0 and 1, and obtain the occupational matching difference.

[0113] The industry trend assessment submodule calls the occupation matching difference, analyzes the correlation with the industry growth trend, collects the time series data of the job demand change rate, calculates the job demand growth rate, evaluates the stability of the difference occupation categories, and obtains the industry trend index;

[0114] Collect time series data on the rate of change of job demand for each occupational category and analyze the fluctuation of job demand. For example, if the job demand for a certain occupation from 2020 to 2025 is 5000, 5500, 6000, 6200, 6400 and 6800 respectively, the annual growth rates are calculated as follows: Further calculate the average growth rate of the occupation and set a growth trend benchmark value to evaluate the stability of the occupational category in the market. Occupations with greater volatility can be regarded as unstable market demand, and the corresponding industry trend index will be adjusted to obtain the industry trend index.

[0115] The path sorting optimization submodule optimizes the sorting logic of the recommended paths based on the industry trend index, using the formula:

[0116]

[0117] Calculate the optimal ranking scores of occupational categories and obtain the optimal career path information, where BP i represents the preferred value of occupation i, Um i Represents the matching difference of occupation i, UT i Represents the industry trend index of occupation i, Ud i represents the rate of change in job demand for occupation i, Us i represents the industry growth trend benchmark value of occupation i;

[0118] BP iThe preferred value of occupation i, which is used to measure the ranking score of this occupation in the recommended path, Um i The matching difference of occupation i, which represents the matching degree of this occupation to the student's ability. The higher the value, the better the matching degree, UT i The industry trend index of occupation i, which represents the development trend of this occupation in the market. The higher the value, the better the industry development prospect, Ud i The change rate of job demand for occupation i, which represents the growth or decline rate of the job demand for this occupation, Us i The industry growth trend benchmark value of occupation i, which represents the stable growth level of this occupation in the industry. The parameter values of a certain occupation are as follows:

[0119] The matching difference Um i is 0.85, the industry trend index UT i is 1.2, the change rate of job demand Ud i is 0.08, the industry growth trend benchmark value Us i is 0.1;

[0120] Calculate the market volatility adjustment term:

[0121]

[0122] Calculate the final preferred value:

[0123]

[0124] This result indicates that the final preferred value of this occupation is 1.01, occupying a relatively high ranking in the occupation recommendation path ranking, reflecting the comprehensive performance of this occupation in terms of matching degree, market trend, and job demand, etc.

[0125] Please refer to Figure 5 , the behavior growth analysis module includes:

[0126] The learning behavior monitoring sub-module calls the occupation path optimization information, monitors the student's online learning time, analyzes the time investment in the learning stage, identifies the change trend of the task submission time, and counts the number of completed projects and the average completion time to obtain the learning behavior characteristic value;

[0127] Collect the learning duration of each student within different time periods, calculate the daily, weekly, and monthly learning durations according to the time distribution, and divide the high-intensity, moderate-intensity, and low-intensity learning time periods. For example, if the learning durations of student A in a week are 2h, 3h, 1h, 5h, 4h, 3h, and 6h respectively, then the average learning duration can be calculated as (2 + 3 + 1 + 5 + 4 + 3 + 6) / 7 = 3.43h. Further calculate the standard deviation of the learning duration to evaluate the stability of the learning rhythm. Call the task submission time, obtain the timestamps of the students submitting various tasks, and calculate the task submission intervals. For example, if a student submits tasks on the 1st, 3rd, and 6th days within 7 days, then the average task submission interval is (3 - 1) + (6 - 3) = 5 / 2 = 2.5 days. Judge the regularity of task submission and further analyze its change trend. Extract the completion status of practical projects, count the number of projects completed by students and the average completion time. Suppose a student has completed 5 projects, and their completion times are 7, 9, 12, 8, and 10 days respectively, then calculate the average completion time as (7 + 9 + 12 + 8 + 10) / 5 = 9.2 days. Normalize the learning behavior data to enhance the comparability of learning data in different dimensions, and finally obtain the learning behavior characteristic values.

[0128] Based on the learning behavior characteristic values, the task participation evaluation sub-module analyzes the correlation between task types, difficulty levels, and student behavior characteristics, evaluates the impact of different tasks on students' learning behaviors, and uses the formula:

[0129]

[0130] Calculate the standardized participation ratio of task categories to obtain the task participation index. Among them, PR o represents the participation ratio of task o, TP o represents the total number of participants in task o, TF o represents the completion frequency of task o, represents the total completion volume of all task categories, o represents the current task category, that is, the participation ratio of a single task being calculated, and c represents the index of all task categories;

[0131] Analyze the participation rates of different task categories, calculate the proportion of the number of participants in each task type. If there are 3 types of tasks in the system, namely A, B, and C, 50 people participate in task A, 30 people participate in task B, and 20 people participate in task C, then calculate the participation proportion of task A as 50 / (50 + 30 + 20) = 0.5, the participation proportion of task B as 0.3, and the participation proportion of task C as 0.2. Evaluate the difficulty of the task and the participation of students, calculate the task completion frequency. Tasks A, B, and C have the following parameters:

[0132] Task A: TP A = 50, TFA = 3;

[0133] Task B: TP B = 30, TF B = 4;

[0134] Task C: TP C = 20, TF C = 2;

[0135] Calculate the total weighted completion volume of all tasks:

[0136]

[0137] Calculate the standardized participation ratio of each task:

[0138]

[0139] The results show that the standardized participation ratio of Task A is the highest, accounting for 48.4%, and that of Task C is the lowest, accounting for 12.9%. Thus, it can be further determined which task types are more popular, and this result can be used to further optimize the distribution strategy of students' learning tasks.

[0140] The growth trend recognition sub-module calls the task participation index, analyzes students' behavior patterns, analyzes the ability growth curve, matches the ability deviation of students in different learning stages, and evaluates the adaptability of students to career goals to obtain the growth trend analysis result;

[0141] Call the task participation index, analyze students' behavior patterns, calculate the rate of change of students' abilities. If a student's ability values are 60, 65, 70, 72, 78, and 80 within 6 months, then calculate the growth rate of ability as Judge the stability of the ability growth rate, match the ability deviation of students in different learning stages, calculate their ability change trend, and further evaluate the adaptability of this student in the career direction to obtain the growth trend analysis result.

[0142] Please refer to Figure 6 , the skill achievement evaluation module includes:

[0143] The skill performance analysis sub-module calls the growth trend analysis result, collects the virtual task performance, skill assessment scores, and internship position evaluations of students, calculates the completion rate of students in multiple types of virtual tasks, statistics the distribution of assessment scores, then analyzes the score fluctuations of students in different skill dimensions, and performs normalization processing to obtain the skill performance characteristic value;

[0144] Collect the virtual task performance, skill assessment scores, and internship position evaluations of students, extract data related to various skills, obtain the completion status of students in various virtual tasks, calculate the task completion rate. Suppose a student participates in 10 virtual tasks in a certain period, and 7 of them are successfully completed. Then the task completion rate is calculated as 7 / 10 = 0.7. Statistically analyze the distribution of skill assessment scores, collect the score data of each assessment subject, and analyze the mean and standard deviation of each skill assessment. Suppose a student obtains 85, 78, 92, 80, and 88 points in 5 assessments respectively. Then the average assessment score is calculated as (85 + 78 + 92 + 80 + 88) / 5 = 84.6. Calculate the standard deviation to evaluate the score fluctuation range. Extract the internship position evaluation, analyze the scoring weights of the position evaluation, combine the virtual task performance and assessment scores, and calculate the comprehensive performance of each skill dimension. Suppose the scores in the three dimensions of technical ability, communication ability, and problem-solving ability are 4.2, 3.8, and 4.5 respectively. Then the mean is calculated as (4.2 + 3.8 + 4.5) / 3 = 4.17. Normalize each skill evaluation data and map it to the 0-1 interval to obtain the skill performance characteristic value.

[0145] Based on the skill performance characteristic value, the skill matching degree calculation sub-module analyzes the matching degree between the student's skills and the requirements of the career path, compares it with the student's skill performance data, and uses the formula:

[0146]

[0147] Calculate the skill point matching degree, where SN k represents the matching degree of skill k, NP k represents the expected value of skill k in the career path requirements, and NR k represents the student's performance value on skill k;

[0148] The scoring of programming skills, project management skills, and communication ability required for a certain position are 4.5, 4.0, and 4.2 respectively. Obtain the actual performance values of the student in the corresponding skills, such as 4.0, 3.5, and 3.8. Calculate the matching degree of each skill point and substitute the data for calculation:

[0149] Programming skill matching degree:

[0150] Project management skill matching degree:

[0151] Communication ability matching degree:

[0152] The result shows that the student's skill level basically meets the requirements of the target occupation. Among them, the communication ability performance is relatively prominent, while there is still room for improvement in programming skills and project management skills.

[0153] The skill score adjustment sub-module adjusts the professional skill scoring standard based on the skill point matching degree and according to the skill achievement deviation, reallocates the weight of each skill point, calculates the scoring value after weight adjustment, and obtains the skill evaluation index.

[0154] According to the skill achievement deviation, adjust the professional skill scoring standard, call the matching degree of each skill point, screen out the skill points with lower matching degree, recalculate the weight distribution. Assume that the skill points with a matching degree lower than 0.85 need to adjust the weight. Combine the skill matching degree index and adjust the scoring rule. For example, reduce the weight of the skill with a matching degree of 0.80 by 10%, and increase the weight of the skill with a matching degree higher than 0.90 by 5%. Calculate the adjusted professional skill scoring value, obtain a new professional skill evaluation system, and get the skill evaluation index.

[0155] An intelligent planning method for students' career directions based on AI technology includes the following steps:

[0156] S1: Obtain the learning achievements, classroom participation records and subject ability scores of students, evaluate the logical reasoning ability, language expression ability and mathematical analysis ability of students, judge the adaptability and performance of students in different learning environments, identify the areas for ability improvement, and obtain the ability weight index.

[0157] S2: Based on the ability weight index, analyze the industry development rate, the professional skill update cycle and the job demand volume, judge the market growth rate of each professional category, determine the matching degree between each professional category and the students' abilities, and generate the industry adaptation index.

[0158] S3: Based on the industry adaptation index, calculate the matching difference between the ability weight and the skill requirements, evaluate the correlation between the job demand change rate and the industry growth trend, optimize the sorting logic of the recommended path, and obtain the preferred career path information.

[0159] S4: Based on the preferred career path information, analyze the participation rate of each type of task, analyze the correlation between the behavior pattern and the ability change, identify the adaptability of students to the career goals, and obtain the growth trend analysis result.

[0160] S5: Based on the growth trend analysis result, collect the virtual task performance, skill assessment scores and internship position evaluations of students, analyze the skill achievement degree of students, evaluate the difference between skills and career needs, adjust the professional skill scoring standard, and obtain the skill evaluation index.

[0161] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An AI-based intelligent career planning system for students, characterized in that: The system comprises: The ability dynamic analysis module obtains students' learning outcomes, class participation records and subject ability scores, analyzes homework completion and assessment scores, identifies ability improvement areas based on students' responses to learning tasks, and obtains ability weight indicators; The occupational ecological adaptation module calls the capability weight index, analyzes the industry development rate, occupational skill update cycle and job demand, determines the market growth rate of each occupation category, and generates an industry adaptation index; The career path optimization module calculates the matching difference between the ability weight and the skill requirement based on the industry adaptation index, evaluates the correlation between the job demand change rate and the industry growth trend, optimizes the sorting logic of the recommended path, and obtains the career path optimization information; The behavior growth analysis module calls the career path optimization information, analyzes the participation rate of each type of task, parses the relationship between behavior patterns and ability changes, identifies students' adaptability to career goals, and obtains growth trend analysis results; The skill achievement assessment module calls the growth trend analysis results, analyzes the students' skill achievement, assesses the difference between skills and career requirements, adjusts the career skill scoring standards, and obtains skill assessment indicators.

2. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The ability weight indicators include cognitive processing speed, comprehension, and problem-solving ability. The industry adaptation index includes skill adaptation rate, market demand comparison results, and career growth potential. The career path optimization information includes skill compatibility, career demand sensitivity, and development prospects assessment results. The growth trend analysis results include learning efficiency, behavior improvement points, and goal adaptation evaluation. The skill evaluation indicators include skill mastery, adaptability evaluation, and career skill gap.

3. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The capability dynamic analysis module includes: The learning outcome assessment submodule obtains students' learning outcomes, class participation records and subject ability scores, extracts homework completion rate, accuracy rate and assessment score data, analyzes the stability of homework completion and knowledge mastery, and identifies the fluctuation of homework in the same subject among different students. The formula is: Calculate the learning stability index S t , where P i represents the score of the i-th assignment, W i represents the weight of the i-th homework, n represents the total number of homeworks, and λ is the homework score fluctuation influence coefficient, which is used to adjust the impact of fluctuations on the learning stability index; The classroom participation analysis submodule collects the number of questions, answers and discussions in class based on the learning stability index, calculates the students' classroom participation activity in differentiated courses, analyzes their adaptability to differentiated teaching methods, determines the impact of classroom communication on subject mastery, and obtains the classroom interaction activity index; The subject ability assessment submodule is based on the classroom interaction activity index and combines students' recent subject assessment results to evaluate students' logical reasoning ability, language expression ability and mathematical analysis ability, judge students' performance on the same subject tasks, identify key ability development areas, and obtain ability weight indicators.

4. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The occupational ecology adaptation module includes: The market demand assessment submodule calls the capability weight index, analyzes the industry development rate, professional skill update cycle and job demand, calculates the market demand level of each industry, and establishes a market demand index; The occupation matching analysis submodule determines the market growth rate of each occupation category based on the market demand index, and compares the key demand variables and student ability weights of each occupation category item by item, using the formula: Calculate the degree of adaptation of occupational categories to students' abilities and generate the industry adaptation index, where MH i Represents the suitability of occupation i, CH ij represents the student's score on ability j, WH j represents the critical weight of ability j in occupation i, DH i represents the demand index of occupation i in the market, SH i represents the industry standard fitness of occupation i, and m is the total number of capabilities.

5. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The career path optimization module includes: The matching difference calculation submodule calculates the matching difference between the occupational skill requirements and the student's ability weight based on the industry adaptation index, collects the key skill variables of each occupational category, normalizes each skill item, and calculates the student's matching score in the occupational category to obtain the occupational matching difference; The industry trend assessment submodule calls the occupation matching difference, analyzes the correlation with the industry growth trend, collects time series data of the job demand change rate, calculates the job demand growth rate, evaluates the stability of the difference occupation categories, and obtains the industry trend index; The path sorting optimization submodule optimizes the sorting logic of the recommended paths based on the industry trend index, using the formula: Calculate the optimal ranking scores of occupational categories and obtain the optimal career path information, where BP i represents the preferred value of occupation i, Um i Represents the matching difference of occupation i, UT i Represents the industry trend index of occupation i, Ud i represents the rate of change in job demand for occupation i, Us i Represents the industry growth trend benchmark value of occupation i.

6. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The behavior growth analysis module includes: The learning behavior monitoring submodule calls the career path optimization information, monitors the students' online learning time, analyzes the time investment in the learning stage, identifies the changing trend of task submission time, and counts the number of completed projects and the average completion time to obtain the learning behavior characteristic value; The task participation evaluation submodule analyzes the correlation between task type, difficulty and student behavior characteristics based on the learning behavior characteristic value, and evaluates the impact of different tasks on student learning behavior using the formula: Calculate the standardized participation ratio of the task category and obtain the task participation index, where PR o represents the participation rate of task o, TP o Represents the total number of participants in task o, TF o represents the completion frequency of task o, Represents the total completion amount of all task categories, o represents the current task category, and c represents the index of all task categories; The growth trend identification submodule calls the task participation index, analyzes the student behavior pattern, analyzes the ability growth curve, matches the ability deviation of the students in the differential learning stage, and evaluates the students' adaptation to the career goals to obtain the growth trend analysis results.

7. The AI-based student career direction intelligent planning system according to claim 1 is characterized in that: The skill attainment assessment module includes: The skill performance analysis submodule calls the growth trend analysis results, calculates the completion rate of students in multiple types of virtual tasks, collects statistics on the distribution of assessment scores, analyzes the fluctuation of students' scores in different skill dimensions, and performs normalization processing to obtain skill performance characteristic values; The skill matching calculation submodule analyzes the matching degree between the student's skills and the career path requirements based on the skill performance characteristic value, and compares it with the student's skill performance data using the formula: Calculate the skill point matching degree, where SN k Represents the matching degree of skill k, NP k represents the expected value of skill k in the career path requirement, NR k represents the student's performance value on skill k; The skill score adjustment submodule adjusts the professional skill score standard based on the skill point matching degree and the skill achievement deviation, reallocates the weight of each skill point, and calculates the score value after the weight adjustment to obtain the skill evaluation index.

8. An AI-based intelligent planning method for students' career direction, characterized in that: The student career direction intelligent planning system based on AI technology according to any one of claims 1 to 7 is implemented, comprising the following steps: S1: Obtain students’ learning outcomes, class participation records and subject ability scores, evaluate students’ logical reasoning ability, language expression ability and mathematical analysis ability, judge students’ adaptability and performance in a differentiated learning environment, identify areas for ability improvement, and obtain ability weight indicators; S2: Based on the ability weight index, analyze the industry development rate, professional skills update cycle and job demand, judge the market growth rate of each occupation category, determine the matching degree between each occupation category and student ability, and generate an industry adaptation index; S3: Based on the industry adaptation index, calculate the matching difference between the ability weight and the skill requirement, evaluate the correlation between the job demand change rate and the industry growth trend, optimize the sorting logic of the recommended path, and obtain the career path optimization information; S4: Based on the career path optimization information, analyze the participation rate of each type of task, analyze the relationship between behavior patterns and ability changes, identify students' adaptability to career goals, and obtain growth trend analysis results; S5: Based on the growth trend analysis results, collect students' virtual task performance, skill assessment scores and internship position evaluations, analyze students' skill achievement, evaluate the difference between skills and career requirements, adjust career skill scoring standards, and obtain skill evaluation indicators.

Images