Employment tutoring system based on artificial intelligence AI

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an employment tutoring system based on artificial intelligence AI, which comprises a database module, an analysis module, an information receiving module and a verification module, the database module can store enterprise sample data information of employment of different professional types and different education stages extracted in advance in a historical period, so that enterprise matching feature factors can be determined, individual difference features of different employment targets are found through analysis, the employment recommendation accuracy is improved, and the employment recommendation efficiency is improved. Through the verification module, employment tutoring labels can be divided, matching enterprise potential conditions of a user side are mined, online enterprise categories which are not browsed by the user side and have potential tendencies are found based on online enterprise pages accessed by the user side, and potential enterprise tendencies of the user side are matched. The enterprise pushing method can effectively aim at the enterprise pushing mode of the online enterprises based on the types of the accessed online enterprises, and the employment matching enterprise pushing efficiency is further improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an employment counseling system based on artificial intelligence (AI). Background Art

[0002] In today's digital age, employment counseling systems based on artificial intelligence (AI) are thriving thanks to a series of cutting-edge technologies. Machine learning technology is its core support. By studying massive amounts of employment data, the system can explore the potential connections between job seekers and positions, accurately screen resumes based on past success cases, and recommend matching positions. Natural language processing technology allows the system to understand and process recruitment information and resume texts, extract key skills, job requirements and other content, assist in intelligent matching, and drive intelligent chatbots to provide real-time consultation. Big data technology provides the system with a rich source of data, covering data from multiple channels such as recruitment websites and social media. After analysis, insights into employment market trends and changes in talent supply and demand are gained. Based on user characteristics and behavioral data, recommendation algorithms are used to recommend suitable positions, learning resources and career development suggestions to job seekers, and to recommend qualified candidates to companies.

[0003] Chinese patent publication number: CN117408564B, discloses an online academic tutoring system, including a biological data collection module, a learning plan formulation module, a facial analysis module, and a learning plan adjustment module. The biological data collection module is used to collect the user's biorhythm data and facial expression data; the learning plan formulation module includes a biorhythm analysis module and a learning plan generation module. The biorhythm analysis module applies a machine learning algorithm to analyze the collected biorhythm data and determines the user's current learning efficiency based on the biorhythm data; the learning plan generation module uses the user's current learning efficiency determined by the data analysis module; the facial analysis module includes a facial data processing module and a facial expression recognition module, and the facial data processing module pre-processes the collected facial expression data; the user's learning plan is adjusted by real-time analysis and processing of the above learning data to improve and optimize learning efficiency.

[0004] Chinese Patent Publication No.: CN117436830B discloses a graduate employment enterprise identification system, including: obtaining a low evaluation parameter according to the ratio of the number of likes to the number of comments in each group data of the enterprise, obtaining the weight of the low evaluation parameter of the group data according to the mean of the number of group comments and likes and the difference between the number of comments and likes in each group combined with the group sequence and the neighborhood group difference, weighting the low evaluation parameter with the weight of the low evaluation parameter to obtain the degree of negative evaluation, dividing the enterprise group data into two parts according to the time series and calculating the expected parameter, and comprehensively judging the enterprise recommendation degree by combining the expected parameter and the degree of negative evaluation. The present invention can more accurately judge whether an enterprise is of high quality, so as to facilitate job seekers to more efficiently and accurately select high-quality enterprises and reduce enterprise matching.

[0005] However, the following problems still exist in the prior art:

[0006] In the prior art, the differences in characteristics of different professional types and different educational stages of the user side are not considered, resulting in different enterprise preference categories on the user side. Due to the balanced push of employment guidance for different user sides by big data, the enterprise delivery frequency uploaded by the user side is not appropriate, resulting in low efficiency of enterprise employment guidance. Summary of the Invention

[0007] Therefore, the present invention provides an employment guidance system based on artificial intelligence AI to overcome the problems in the prior art that the differences in characteristics of different professional types and different educational stages of the user side are not considered, resulting in different enterprise preference categories on the user side, and due to the balanced push of employment guidance for different user sides by big data, the enterprise delivery frequency uploaded by the user side is not appropriate, resulting in low efficiency of enterprise employment guidance.

[0008] To achieve the above object, the present invention provides an employment guidance system based on artificial intelligence AI, including:

[0009] A database module, which is used to store the enterprise sample data information of different professional types and different educational stages extracted in advance during the historical period, and is used to determine the enterprise matching characteristic factors of each educational stage of the target body employment of different professional types and different educational stages;

[0010] An analysis module, which is connected to the database module and is used to calculate the enterprise matching characteristic parameters of different professional type target body employment at different educational stages according to the enterprise matching characteristic factors of each educational stage of the target body employment of different professional types;

[0011] An information receiving module, which is connected to the user side and is used to obtain the actual data of the professional type of the target body uploaded by the user side and the enterprise sample data information corresponding to the educational stage;

[0012] A verification module, which is respectively connected to the database module, the analysis module and the information receiving module, is used to obtain the enterprise matching characteristic parameters of each educational stage of the corresponding professional type of the target body uploaded by the user terminal according to the enterprise sample data information, and divide the employment guidance labels according to the enterprise matching characteristic parameters;

[0013] Based on the division result of the employment guidance label, it is used to push the enterprise verification for the actual data of the target body uploaded by the user terminal, including,

[0014] It is used to obtain the response of the user terminal click behavior after the placement verification push to determine whether to adjust the enterprise push method and push enterprises in the corresponding push method; or, collect the number of click behaviors on the user terminal page to determine to increase the push frequency.

[0015] Furthermore, the database module is used to determine the enterprise matching characteristic factors of each educational stage of the target body's employment in different professional types and different educational stages, including,

[0016] Compare the enterprise sample data information of each educational stage of a single professional type with the enterprise sample data information of the corresponding educational stage of the target body's employment in other professional types respectively;

[0017] Solve the average employment rate of the database and obtain the employment difference degree of each educational stage of the target body's employment in a single professional type.

[0018] Furthermore, the database module is used to obtain the employment difference degree of different educational stages of the target body's employment in a single professional type, including,

[0019] Calibrate the number of employment types and the total number of employment positions at the educational stage of the target body's employment in a single professional type;

[0020] Calculate the ratio of the number of employment types of the target body in a single professional type to the benchmark employment type threshold and determine it as the first difference impact factor;

[0021] Calculate the ratio of the total number of employment positions of the target body in a single professional type to the benchmark total number of employment positions threshold and determine it as the second difference impact factor;

[0022] Determine the sum of the first difference impact factor and the second difference impact factor as the employment difference degree.

[0023] Furthermore, the analysis module is used to calculate the enterprise matching characteristic parameters of different educational stages of the target body's employment in different professional types, including,

[0024] Extract the average employment rate of the database and the employment difference degree;

[0025] Determine the ratio of the average employment rate of the database to the employment rate threshold of the benchmark database as the first matching characteristic factor;

[0026] Determine the ratio of the employment difference degree to the benchmark employment difference degree threshold as the second matching characteristic factor;

[0027] Determine the sum of the first matching characteristic factor and the second matching characteristic factor as the enterprise matching characteristic parameter.

[0028] Furthermore, the verification module is used to divide employment guidance labels according to the enterprise matching characteristic parameter, including,

[0029] If the enterprise matching characteristic parameter is less than the enterprise matching characteristic threshold, it is determined as the first label category;

[0030] If the enterprise matching characteristic parameter is greater than or equal to the enterprise matching characteristic threshold, it is determined as the second label category.

[0031] Furthermore, the verification module is used to perform a placement enterprise verification push on the actual data of the target body uploaded by the user side based on the division result of the employment guidance label, including,

[0032] If it is the first label category, perform a placement verification push, obtain the response of each characteristic after the placement verification push, determine whether to adjust the enterprise push method, and push the enterprise in the corresponding push method and then re - verify;

[0033] If it is the second label category, collect the number of click behaviors on the user - side page to determine whether to increase the push frequency and then re - verify.

[0034] Furthermore, the process by which the verification module is used to obtain the response of the user - side click behavior after the placement verification push to determine whether to adjust the enterprise push method includes,

[0035] Extract the reduction amount of the number of user - side click behaviors within the time period;

[0036] If there is a reduction amount of the number of user - side click behaviors greater than or equal to the predetermined change threshold, it is determined to adjust the push method and push the enterprise in the corresponding push method.

[0037] Furthermore, the process by which the verification module is used to adjust the enterprise push method and push the enterprise in the corresponding push method includes,

[0038] Determine the keywords in the online enterprise page of the employment guidance system;

[0039] Determine the online enterprise categories to which each of the keywords belongs;

[0040] Among them, the attribution relationship between each keyword and the online enterprise category is preset;

[0041] Determine the remaining unvisited online enterprise categories based on the visited online enterprise categories;

[0042] Determine to re-verify after pushing online enterprises for each of the unvisited online enterprise categories.

[0043] Further, the verification module is used to collect the number of click behaviors on the user terminal page to determine an increase in the push frequency, including,

[0044] Extract the number of page clicks on the user terminal before the online enterprise behavior;

[0045] If the number of page clicks is greater than or equal to a predetermined page click threshold, it is determined that there is an enterprise matching behavior on the user terminal, and re-verification is performed after increasing the push frequency.

[0046] Further, the process by which the verification module increases the push frequency includes,

[0047] Collect the average decrease in the number of click behaviors on the user terminal within a time period;

[0048] Determine that the increase in the online enterprise push frequency is positively correlated with the average decrease.

[0049] Compared with the prior art, the present invention provides an employment counseling system based on artificial intelligence AI, including a database module, an analysis module, an information receiving module, and a verification module. Through the database module, the present invention can store the enterprise sample data information of different professional types and different educational levels in the historical period for employment, so as to determine the enterprise matching characteristic factors of different educational levels for the employment of the target body of different professional types and different educational levels. Through the analysis module, the enterprise matching characteristic parameters of different educational levels for the employment of the target body of different professional types can be analyzed according to the enterprise matching characteristic factors of different educational levels for the employment of the target body of different professional types, and the personalized difference characteristics of each professional type and each educational level can be found, improving the accuracy of the analysis. Through the verification module, the enterprise matching characteristic parameters of each educational level of the corresponding professional type can be obtained according to the enterprise sample data information, and different employment counseling label types can be divided according to the enterprise matching characteristic parameters, and the potential enterprise matching tendency of the user side can be mined. Based on the division result of the employment counseling label, the actual data of the target body uploaded by the user side is verified and pushed to the enterprise. By obtaining the response of the user side click behavior after the placement verification push, it can be determined whether to adjust the enterprise push method. Therefore, the present invention considers the online enterprise pages already visited by the user side, considers the online enterprise categories with potential tendencies that the user side has not browsed, matches the potential matching tendency of the user side, determines the online enterprise pages already visited by the user side, determines the online enterprise categories already visited based on the online enterprise pages, and can effectively target the enterprise push methods for the online enterprises based on each already visited online enterprise category, further improving the efficiency and accuracy of the enterprise push for employment matching in this system.

[0050] In particular, by obtaining the enterprise matching characteristic factors and enterprise matching characteristic parameters of the user side of different professional types and different educational levels before the employment application behavior, the present invention can divide the employment counseling label tendency, and based on the division result, it can perform the placement enterprise verification push, customize the online enterprise push method and push frequency for each user side, and can analyze the enterprise matching characteristics for each user side based on the change of the user side click behavior, improving the efficiency of the online enterprise matching intelligent recommendation in this system and reducing the occurrence of misjudgment of the online enterprise push by the user side. By determining the online enterprise pages already visited by the user side, determining the online enterprise categories already visited based on each of the online enterprise pages, and being able to effectively adjust the enterprise push methods and push frequencies for each online enterprise category based on each already visited online enterprise category, the efficiency of the enterprise push for employment counseling in this system is further improved.

[0051] In particular, for the second tag category of the employment counseling tags, by collecting the number of click behaviors on the user side page, analyzing whether the recommended enterprises match the user side based on the number of click behaviors, re-verifying after increasing the push frequency, the situation of abnormal enterprise matching on the user side is reduced, and the employment counseling enterprise push efficiency of the system is improved. Brief Description of the Drawings

[0052] Figure 1 It is a structural block diagram of an employment counseling system based on artificial intelligence AI according to an embodiment of the present invention;

[0053] Figure 2 It is a step flow chart for determining the enterprise matching characteristic factors of different academic stages of target body employment in different professional types according to an embodiment of the present invention;

[0054] Figure 3 It is a step flow chart for obtaining the employment difference degrees of different academic stages of target body employment in a single professional type according to an embodiment of the present invention;

[0055] Figure 4 It is a step flow chart for calculating the enterprise matching characteristic parameters of different academic stages of target body employment in different professional types according to an embodiment of the present invention. Detailed Embodiment

[0056] In order to make the purpose and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0057] The preferred embodiments of the present invention will be described below with reference to the drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0058] It should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the term "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific situation.

[0059] Please refer to Figure 1 as shown, which is a structural block diagram of an employment counseling system based on artificial intelligence AI according to an embodiment of the present invention. The present invention provides an employment counseling system based on artificial intelligence AI, including:

[0060] A database module for storing the enterprise sample data information of different professional types and different educational levels employed within a historical period, and for determining the enterprise matching characteristic factors of each educational level for the employment of the target entity of different professional types and different educational levels;

[0061] An analysis module, connected to the database module, for calculating the enterprise matching characteristic parameters of different educational levels for the employment of the target entity of different professional types based on the enterprise matching characteristic factors of each educational level for the employment of the target entity of different professional types;

[0062] An information receiving module, connected to the user terminal, for obtaining the actual data of the professional type of the target entity uploaded by the user terminal and the enterprise sample data information corresponding to the educational level;

[0063] A verification module, respectively connected to the database module, the analysis module and the information receiving module, for obtaining the enterprise matching characteristic parameters of each educational level of the corresponding professional type of the target entity uploaded by the user terminal based on the enterprise sample data information, and dividing employment guidance labels according to the enterprise matching characteristic parameters;

[0064] For performing enterprise verification push on the actual data of the target entity uploaded by the user terminal based on the division result of the employment guidance label, including,

[0065] For obtaining the response situation of the click behavior of the user terminal after the placement verification push to determine whether to adjust the enterprise push method and push enterprises in the corresponding push method; or, collecting the number of click behaviors on the user terminal page to determine to increase the push frequency.

[0066] In implementation, first, store the enterprise sample data information of different professional types and different educational levels employed within a historical period to determine the enterprise matching characteristic factors of each educational level for the employment of the target entity of different professional types and different educational levels; then, calculate the enterprise matching characteristic parameters of different educational levels for the employment of the target entity of different professional types based on the enterprise matching characteristic factors of each educational level for the employment of the target entity of different professional types; finally, obtain the actual data of the professional type of the target entity uploaded by the user terminal and the enterprise sample data information corresponding to the educational level; obtain the enterprise matching characteristic parameters of each educational level of the corresponding professional type of the target entity uploaded by the user terminal based on the enterprise sample data information, and divide employment guidance labels according to the enterprise matching characteristic parameters; perform enterprise verification push on the actual data of the target entity uploaded by the user terminal based on the division result of the employment guidance label. If it is the first label category, obtain the response situation of the click behavior of the user terminal after the placement verification push to determine whether to adjust the enterprise push method and push enterprises in the corresponding push method; if it is the second label category, collect the number of click behaviors on the user terminal page to determine to increase the push frequency.

[0067] Specifically, for the corresponding big data models of enterprises employed at each professional type and educational stage that are pre-stored and constructed from enterprise sample data information, it can also be in other forms, which will not be elaborated here.

[0068] Specifically, there is no limitation on the classification of professional categories. In implementation, the professional categories are mathematics, physics, chemistry, biology, Chinese, and English. It can also be in other forms, which will not be elaborated here.

[0069] Specifically, there is no limitation on the classification of educational stages. In implementation, the educational stages are the preschool education stage, the nine-year compulsory education stage, the high school education stage, the junior college education stage, the undergraduate education stage, and the postgraduate education stage. It can also be in other forms, which will not be elaborated here.

[0070] Specifically, there is no limitation on the specific structures of the database module, the analysis module, the information receiving module, and the verification module. Each of them or the units therein can be composed of logic components, and the logic components include field programmable components, computers, or microprocessors in a computer.

[0071] Specifically, there is no limitation on the historical period. In implementation, it is the enterprise sample data information model stored and analyzed within the first three months of the system for each professional type and educational stage.

[0072] Specifically, there is no limitation on the method of obtaining the click behavior characteristics of the user terminal. It can be obtained using relevant tracking software. For example, it can be one of ClickMagick or Trackier. Of course, it can also be in other forms as long as the number of click behaviors can be obtained.

[0073] Specifically, the present invention provides an employment counseling system based on artificial intelligence AI, including a database module, an analysis module, an information receiving module, and a verification module. Through the analysis module, the present invention can analyze the enterprise matching characteristic parameters of different professional type targets at different educational levels based on the enterprise matching characteristic factors of different professional type targets at different educational levels of employment, find the personalized difference characteristics of each professional type and each educational level, and improve the accuracy of the analysis. Through the verification module, the enterprise matching characteristic parameters of each educational level of the corresponding professional type can be obtained based on the enterprise sample data information, and different employment counseling label types can be divided based on the enterprise matching characteristic parameters, and the potential enterprise matching tendency of the user side can be mined. Based on the classification result of the employment counseling label, the actual data of the target uploaded by the user side is verified and pushed to the enterprise. By obtaining the response of the user side click behavior after the placement verification push, it can be determined whether to adjust the enterprise push method. Therefore, the present invention considers the online enterprise pages that the user side has visited, considers the online enterprise categories with potential tendencies that the user side has not browsed, matches the potential matching tendency of the user side, determines the online enterprise pages that the user side has visited, determines the online enterprise categories that have been visited based on the online enterprise pages, and can effectively target the enterprise push method of the online enterprise based on each visited online enterprise category, further improving the efficiency and accuracy of the enterprise push for employment matching of this system.

[0074] Please refer to Figure 2 as shown, which is a flowchart of the steps for determining the enterprise matching characteristic factors of different professional type targets at different educational levels of employment in the embodiment of the present invention. The database module is used to determine the enterprise matching characteristic factors of different professional type targets at different educational levels of employment, including

[0075] Comparing the enterprise sample data information of each educational level of a single professional type with the enterprise sample data information of the corresponding educational level of other professional type targets for employment respectively;

[0076] Solving the average employment rate of the database, and obtaining the employment difference degree of each educational level of a single professional type target for employment.

[0077] In implementation, the average employment rate of the database is determined as the ratio of the number of employed people registered on the platform in the enterprise sample data information stored in the first three months before the system operation in the historical period to the total number of job seekers on the platform, which will not be elaborated here.

[0078] Please refer to Figure 3 as shown, which is a flowchart of the steps for obtaining the employment difference degree of a single professional type target for employment at different educational levels in the embodiment of the present invention. The database module of the present invention is used to obtain the employment difference degree of a single professional type target for employment at different educational levels, including

[0079] Calibrate the number of employment types and the total number of employment positions at the educational level for a single professional type of target entity.

[0080] Calculate the ratio of the number of employment types of the target entity in a single professional type to the benchmark employment type threshold, and determine it as the first difference impact factor.

[0081] Calculate the ratio of the total number of employment positions of the target entity in a single professional type to the benchmark total number of employment positions threshold, and determine it as the second difference impact factor.

[0082] Determine the sum of the first difference impact factor and the second difference impact factor as the employment difference degree.

[0083] In implementation, the benchmark employment type threshold is pre-determined. Among them, the average value of the number of employment types of the target entity of this professional type in the calculation platform is obtained in advance, and the benchmark threshold is set as the product of the average value of the number of employment types and the precision coefficient. The precision system is selected within the interval [1.1, 1.2]. Preferably, the historical period is three months.

[0084] Similarly, the benchmark total number of employment positions threshold all comes from the product of the total number of employment positions corresponding to the historical period of big data and the precision coefficient, which will not be elaborated here.

[0085] The difference degree is the sum of the values of the first difference impact factor and the second difference impact factor, which will not be elaborated here.

[0086] Please refer to Figure 4 As shown, it is a step flowchart for the embodiment of the present invention to calculate the enterprise matching characteristic parameters for different educational levels of employment of target entities of different professional types. The analysis module for calculating the enterprise matching characteristic parameters for different educational levels of employment of target entities of different professional types includes,

[0087] Extract the average employment rate and employment difference degree in the database.

[0088] Determine the ratio of the average employment rate in the database to the benchmark database employment rate threshold as the first matching characteristic factor.

[0089] Determine the ratio of the employment difference degree to the benchmark employment difference degree threshold as the second matching characteristic factor.

[0090] Determine the sum of the first matching characteristic factor and the second matching characteristic factor as the enterprise matching characteristic parameter.

[0091] Specifically, the benchmark database employment rate threshold is 1.15 times the average value of the database employment rate in the system within the historical period; similarly, the benchmark employment difference degree threshold is 1.2 times the average value of the employment difference degree in the first three months before the system recommendation behavior within the historical period.

[0092] Specifically, the verification module is used to divide employment counseling labels according to the enterprise matching characteristic parameters, including,

[0093] If the enterprise matching characteristic parameter is less than the enterprise matching characteristic threshold, it is determined as the first label category;

[0094] If the enterprise matching characteristic parameter is greater than or equal to the enterprise matching characteristic threshold, it is determined as the second label category.

[0095] Specifically, the enterprise matching characteristic threshold is obtained in advance and is 1.12 times the average value of the enterprise matching characteristic parameters in the database in the first three months before the system runs in the historical cycle.

[0096] Specifically, the verification module is used to perform enterprise verification push on the actual data of the target uploaded by the user side based on the division result of the employment counseling label, including,

[0097] If it is the first label category, perform delivery verification push, obtain the response of each feature after the delivery verification push, determine whether to adjust the enterprise push method, and re-verify after pushing the enterprise in the corresponding push method;

[0098] If it is the second label category, collect the number of click behaviors on the user side page to determine whether to increase the push frequency and then re-verify.

[0099] In implementation, in response to the division result of the employment counseling label, determine the types of online enterprises recommended for the employment enterprises required by the user side, determine the online enterprise page corresponding to the corresponding professional type and educational stage characteristics of the user side, determine the online enterprise category to which each keyword belongs from the keywords of the online enterprise page, recommend enterprises in the corresponding online enterprise category, and then analyze whether to adjust the push method based on the change in the number of click behaviors of the user side after the online enterprise recommendation to determine whether to adjust the enterprise push method.

[0100] Specifically, the process by which the verification module is used to obtain the response of the click behavior of the user side after the delivery verification push to determine whether to adjust the enterprise push method includes,

[0101] Extract the reduction amount of the number of click behaviors of the user side within the time period;

[0102] If there is a reduction amount of the number of click behaviors of the user side that is greater than or equal to the predetermined change threshold, it is determined to adjust the push method and push the enterprise in the corresponding push method.

[0103] In implementation, the change threshold for the number of click behaviors is determined based on the corresponding threshold for the number of click behaviors and is set between 1.1 times and 1.2 times the threshold for the number of click behaviors.

[0104] Specifically, the verification module is used to adjust the enterprise push method and push enterprises according to the corresponding push method, including:

[0105] Determine the keywords in the online enterprise page of the employment guidance system;

[0106] Determine the online enterprise categories to which each of the keywords belongs;

[0107] Among them, the attribution relationship between each keyword and the online enterprise category is preset;

[0108] Based on the accessed online enterprise categories, determine the remaining unaccessed online enterprise categories;

[0109] Determine to re-verify after pushing online enterprises for each of the unaccessed online enterprise categories.

[0110] Specifically, the process by which the verification module is used to increase the push frequency includes:

[0111] Collect the average decrease in the number of click behaviors of the user terminal within the time period;

[0112] Determine that the increase in the online enterprise push frequency is positively correlated with the average decrease;

[0113] In implementation, solve the ratio of the average decrease to the Euclidean change threshold, and multiply the obtained ratio by the initial online enterprise push frequency to obtain the online enterprise push frequency that needs to be reduced.

[0114] Specifically, for the second label category of the employment guidance label, by collecting the number of click behaviors on the user terminal page and analyzing whether the enterprises recommended by the user terminal match based on the number of click behaviors, re-verifying after increasing the push frequency reduces the occurrence of abnormal enterprise matching on the user terminal and improves the push efficiency of the employment guidance enterprises in this system.

[0115] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An employment counseling system based on artificial intelligence AI, characterized in that, Including: A database module for storing the enterprise sample data information of different professional types and different educational levels employed during a historical period, and for determining the enterprise matching characteristic factors of different educational levels for the employment of the target body of different professional types and different educational levels; An analysis module connected to the database module for calculating the enterprise matching characteristic parameters of different educational levels for the employment of the target body of different professional types based on the enterprise matching characteristic factors of different educational levels for the employment of the target body of different professional types; An information receiving module connected to the user terminal for obtaining the actual data of the professional type of the target body uploaded by the user terminal and the enterprise sample data information of the corresponding educational level; A verification module connected to the database module, the analysis module, and the information receiving module respectively, for obtaining the enterprise matching characteristic parameters of different educational levels of the corresponding professional type of the target body uploaded by the user terminal based on the enterprise sample data information, and for dividing employment guidance labels based on the enterprise matching characteristic parameters; For performing enterprise verification push on the actual data of the target body uploaded by the user terminal based on the division result of the employment guidance label, including, For obtaining the response situation of the click behavior of the user terminal after the placement verification push to determine whether to adjust the enterprise push method and push enterprises in the corresponding push method; Or, collecting the number of click behaviors on the user terminal page to determine to increase the push frequency.

2. The employment counseling system based on artificial intelligence AI according to claim 1, characterized in that, The database module is used to determine the enterprise matching characteristic factors of different educational levels for the employment of the target body of different professional types and different educational levels, including, Comparing the enterprise sample data information of each educational level of a single professional type with the enterprise sample data information of the corresponding educational level of the employment of the target body of other professional types respectively; Solving the average employment rate of the database and obtaining the employment difference degree of each educational level of the employment of the target body of a single professional type.

3. The employment counseling system based on artificial intelligence AI according to claim 2, characterized in that, The database module is used to obtain the employment difference degree of different educational levels of the employment of the target body of a single professional type, Including, Calibrating the number of employment types and the total number of employment positions of the educational level of the employment of the target body of a single professional type; Calculating the ratio of the number of employment types of the target body in a single professional type to the benchmark employment type threshold and determining it as the first difference influencing factor; Calculating the ratio of the total number of employment positions of the target body in a single professional type to the benchmark total number of employment positions threshold and determining it as the second difference influencing factor; Determining the sum of the first difference influencing factor and the second difference influencing factor as the employment difference degree.

4. The employment counseling system based on artificial intelligence AI according to claim 3, wherein The analysis module is used to calculate the enterprise matching characteristic parameters of different educational levels for the employment of the target body of different professional types, Including, Extracting the average employment rate of the database and the employment difference degree; Determining the ratio of the average employment rate of the database to the benchmark database employment rate threshold as the first matching characteristic factor; Determining the ratio of the employment difference degree to the benchmark employment difference degree threshold as the second matching characteristic factor; Determining the sum of the first matching characteristic factor and the second matching characteristic factor as the enterprise matching characteristic parameter.

5. The employment counseling system based on artificial intelligence AI according to claim 4, characterized in that, The verification module is used to divide employment guidance labels based on the enterprise matching characteristic parameters, Including, If the enterprise matching characteristic parameter is less than the enterprise matching characteristic threshold, it is determined as the first label category; If the enterprise matching feature parameter is greater than or equal to the enterprise matching feature threshold, it is determined as the second label category.

6. The employment counseling system based on artificial intelligence AI according to claim 5, characterized in that, The verification module is used to perform enterprise verification push on the actual data of the target uploaded by the user side based on the classification result of the employment guidance label, including If it is the first label category, perform placement verification push, obtain the response of each feature after the placement verification push, determine whether to adjust the enterprise push method, and re - verify after pushing the enterprise in the corresponding push method; If it is the second label category, collect the number of click behaviors on the user - side page to determine whether to increase the push frequency and then re - verify.

7. The employment counseling system based on artificial intelligence AI according to claim 1, characterized in that, The process by which the verification module is used to obtain the response of the user - side click behavior after the placement verification push to determine whether to adjust the enterprise push method includes extracting the reduction amount of the number of user - side click behaviors within a time period; If there is a reduction amount of the number of user - side click behaviors greater than or equal to a predetermined change threshold, it is determined to adjust the push method and push the enterprise in the corresponding push method.

8. The employment counseling system based on artificial intelligence AI according to claim 1, characterized in that, The process by which the verification module is used to adjust the enterprise push method and push the enterprise in the corresponding push method includes determining the keywords in the online enterprise page of the employment guidance system; determining the online enterprise categories to which each of the keywords belongs; wherein, the attribution relationship between each keyword and the online enterprise category is preset; based on the accessed online enterprise categories, determining the remaining unaccessed online enterprise categories; determining to re - verify after pushing online enterprises for each of the unaccessed online enterprise categories.

9. The employment counseling system based on artificial intelligence AI according to claim 1, characterized in that, The process by which the verification module is used to collect the number of click behaviors on the user - side page to determine whether to increase the push frequency includes extracting the number of page clicks before the user's online enterprise behavior on the user side; If the number of page clicks is greater than or equal to a predetermined page click threshold, it is determined that the user side has an enterprise matching behavior, and re - verify after increasing the push frequency.

10. The employment counseling system based on artificial intelligence AI according to claim 1, characterized in that, The process by which the verification module is used to increase the push frequency includes collecting the average reduction amount of the number of user - side click behaviors within a time period; determining that the increase amount of the online enterprise push frequency is positively correlated with the average reduction amount.

Images