A labor management system based on big data

Abstract

This invention relates to the field of data management, and more particularly to a big data-based employment management system, comprising: a user monitoring module, used to periodically respond to target evaluation conditions to determine whether to perform access behavior analysis on each target service user; an access analysis module, used to respond to evaluation analysis conditions to determine the behavior analysis strategy for each user to be evaluated; a user evaluation module, used to execute the behavior analysis strategy determined by the access analysis module to obtain abnormal behavior parameters for each user to be evaluated; a restriction analysis module, connected to the user evaluation module, used to respond to restriction determination conditions to determine whether to restrict information access for each user to be evaluated who has completed the determination of abnormal behavior parameters; and a restriction execution module, used to respond to restriction execution conditions to compress the displayed information of each candidate employment information of restricted users. This invention improves the security of employment information stored in the employment management system.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data management, and in particular to a labor management system based on big data. BACKGROUND

[0002] The labor management system can effectively provide reliable and effective labor information recommendation for the labor demand side through big data analysis, effectively improving the personnel recruitment efficiency of the labor demand side. For the labor data management side that provides labor management services, if the source and detailed information of a large number of workers it masters are completely open to the labor demand side, it cannot guarantee the personnel search efficiency of the labor demand side, nor can it guarantee the safety of its own data. Therefore, how to monitor the actual behavior of the labor demand side in personnel search in real time and timely adjust the access range of the labor demand side to ensure the safety of the labor data management side's worker data is a problem that needs to be solved by those skilled in the art.

[0003] Chinese Patent Publication No. CN118172029A discloses a labor information sharing platform based on a blockchain, including a plurality of nodes, and a plurality of nodes jointly build an identity-equal alliance chain network, and any node runs a labor information sharing system. The system includes a flexible task crowdsourcing subsystem, a flexible salary settlement subsystem, a user identity management subsystem, an IPFS distributed file system, and a MongoDB distributed database, which can complete the operation of flexible labor, salary settlement, batch payment, invoice provision, and legal tax whole process in one station. However, the above-mentioned scheme has the following defects: it fails to analyze the actual behavior information of the labor demand side when searching for personnel, and timely adjust the access range of the labor demand side, resulting in the safety of the labor data management side's worker data cannot be guaranteed. SUMMARY

[0004] Therefore, the present application provides a labor management system based on big data to overcome the problem that the prior art fails to analyze the actual behavior information of the labor demand side when searching for personnel, and timely adjust the access range of the labor demand side, resulting in low safety of the labor data management side's worker data.

[0005] To achieve the above-mentioned purpose, the present application provides a labor management system based on big data, comprising:

[0006] The user supervision module is used to periodically determine the demand change abnormality of each target service user based on the access tendency change coefficient and the access difference coefficient, and to determine whether to perform access behavior analysis on each target service user in response to the target evaluation condition;

[0007] an access analysis module connected with the user supervision module, configured to determine a behavior analysis strategy of each to-be-evaluated user according to a user access stability coefficient, and determine a behavior abnormality parameter of the to-be-evaluated user according to a setting mode of the user access stability coefficient, or determine the behavior abnormality parameter of the to-be-evaluated user according to an execution interval stability coefficient and an execution depth stability coefficient in response to an evaluation analysis condition;

[0008] a user evaluation module connected with the access analysis module, including a first user evaluation unit and a second user evaluation unit, configured to execute the behavior analysis strategy determined by the access analysis module to obtain a behavior abnormality parameter of each to-be-evaluated user;

[0009] a restriction analysis module connected with the user evaluation module, configured to determine whether to perform information access restriction on each to-be-evaluated user whose behavior abnormality parameter is determined in response to a restriction judgment condition;

[0010] a restriction execution module connected with the restriction analysis module, configured to perform display information compression on each item of candidate employment information of the restricted access user in response to a restriction execution condition.

[0011] Further, the target evaluation condition to which the user supervision module responds is that a demand change abnormality degree of a target service user is greater than a preset demand change abnormality degree, and the access analysis module is determined to perform access behavior analysis on the target service user;

[0012] The demand change abnormality degree is in a positive correlation relationship with an access tendency change coefficient and an access difference coefficient.

[0013] Further, the access analysis module responds to a behavior analysis condition, and determines a behavior analysis strategy of each to-be-evaluated user based on an access tendency richness of the to-be-evaluated user and a reference tendency change coefficient;

[0014] The behavior analysis condition is that a target service user needs to perform access behavior analysis, and the target service user needing to perform access behavior analysis is recorded as a to-be-evaluated user.

[0015] Further, the evaluation analysis condition to which the access analysis module responds is that an access tendency richness of a to-be-evaluated user is less than or equal to a preset access tendency richness and a reference tendency change coefficient is less than or equal to a preset reference tendency change coefficient, and the first user evaluation unit is determined to determine a setting mode of a behavior abnormality parameter of the to-be-evaluated user according to a user access stability coefficient;

[0016] The user access stability coefficient is determined according to an access depth difference index and an access time length difference index.

[0017] Furthermore, the abnormal setting condition for the response of the first user evaluation unit is that the user access stability coefficient of the user to be evaluated is greater than the preset user access stability coefficient, and then the abnormal behavior parameters of the user to be evaluated are determined according to the access preference change index and the access parameter change index.

[0018] If the abnormal setting condition of the first user evaluation unit response is that the user access stability coefficient of the user to be evaluated is less than or equal to the user access stability coefficient, then the abnormal behavior parameters of the user to be evaluated are determined according to the access overlap index and the overlap conflict index.

[0019] Furthermore, if the evaluation and analysis condition of the access analysis module is that the access tendency richness of the user to be evaluated is greater than the preset access tendency richness or the reference tendency change coefficient is greater than the preset reference tendency change coefficient, then the second user evaluation unit determines the abnormal behavior parameters of the user to be evaluated based on the execution interval stability coefficient and the execution depth stability coefficient.

[0020] The abnormal behavior parameters are positively correlated with the execution interval stability coefficient and the execution depth stability coefficient, respectively.

[0021] Furthermore, the restriction analysis module responds to the evaluation completion conditions and determines whether to restrict information access for each user to be evaluated who has completed the determination of the behavioral anomaly parameters, based on the behavioral anomaly parameters and trend anomaly parameters.

[0022] For a single user whose abnormal behavior parameters have been determined, if the restriction analysis module responds with a restriction judgment condition that the abnormal behavior parameter is greater than a preset abnormal behavior parameter or the abnormal trend parameter is greater than a preset abnormal trend parameter, then it is determined that information access restrictions will be imposed on the user to be evaluated.

[0023] The assessment is completed when abnormal behavioral parameters of the user to be assessed are determined.

[0024] Furthermore, the restriction execution module responds to the restriction execution conditions and compresses the display information for various candidate employment information of the restricted user, including:

[0025] Filter the related stage information of each candidate employee information, and test the suitability recommendation coefficient of each candidate employee information;

[0026] Users with restricted access are only allowed to view the associated stage information and the matching recommendation coefficient of their various candidate employment information;

[0027] The restriction is enforced when there are users to be evaluated who require information access restrictions. These users are referred to as restricted users.

[0028] Furthermore, the restriction execution module determines the association stage information of each candidate employment information based on the employment scenario association degree and the employment operation association degree;

[0029] The matching recommendation coefficients for each candidate worker information are determined based on the associated job parameters and the effective evaluation parameters. The matching recommendation coefficients are positively correlated with the associated job parameters and the effective evaluation parameters, respectively.

[0030] Furthermore, the restriction execution module determines the effective evaluation parameters for each associated stage based on the effective evaluation ratio and the evaluation conflict parameters;

[0031] The associated restriction condition for the execution restriction module's response is that if the effective evaluation parameter of the associated stage information is less than or equal to the preset effective evaluation parameter, then the associated stage information is determined not to be used in the process of determining the matching recommendation coefficient of the corresponding candidate worker information, and the relevant content of the associated stage information is not displayed.

[0032] Compared with the prior art, the beneficial effects of the present invention are that, when the demand change abnormality of the target service user is large, the present invention determines a targeted behavior analysis strategy based on the access tendency richness and the reference tendency change coefficient, ensuring that the behavior analysis process for the user to be evaluated is more consistent with its actual access status. While ensuring the reliability of the determination results of abnormal behavior parameters, the analysis efficiency of the behavior analysis process is improved. Furthermore, information access restrictions are imposed on the user to be evaluated with large abnormal behavior parameters or large trend abnormal parameters, thereby improving the security of employment information stored in the employment management system.

[0033] Furthermore, in this invention, the abnormality of demand change for each target service user is determined based on the access tendency change coefficient and the access difference coefficient, so as to preliminarily determine whether there is a sudden change in employment demand in the near future, and thereby determine whether there is a risk of abnormal access behavior. The abnormality of demand change determines whether further access behavior analysis should be carried out. While ensuring the security of employment information stored in the employment management system, unnecessary data analysis process is avoided.

[0034] Furthermore, in this invention, for users to be evaluated who require access behavior analysis, a targeted behavior analysis strategy is determined based on their access tendency richness and reference tendency change coefficient. The access tendency richness and reference tendency change coefficient characterize whether the user to be evaluated has obvious access tendencies, and the behavior analysis strategy is determined accordingly. This ensures the accuracy of judging abnormal access behavior of the user to be evaluated while ensuring the efficiency of the behavior analysis process.

[0035] Furthermore, in this invention, for users to be evaluated with both low access tendency richness and low reference tendency change coefficient, since such users often have relatively obvious access tendency characteristics for the information they access, the analysis of their access content is used to determine whether there is a possibility of malicious crawling behavior in the access process, and the access depth difference index and access duration difference index are used to determine whether there is obvious regularity in the access behavior of the users to be evaluated, so as to determine the setting method of targeted abnormal behavior parameters, thereby further ensuring the reliability of the evaluation results of abnormal behavior of the users to be evaluated.

[0036] Furthermore, in this invention, for users to be evaluated with a large degree of access tendency richness or a large reference tendency change coefficient, since such users do not have obvious access tendency characteristics, the risk of malicious crawling is determined by analyzing the execution interval stability coefficient and execution depth stability coefficient during their access process, so as to ensure the efficiency of the analysis of abnormal behavior of the users to be evaluated and the reliability of the evaluation results.

[0037] Furthermore, this invention determines whether to restrict information access for each user to be evaluated after the behavior anomaly parameters have been determined, based on behavior anomaly parameters and trend anomaly parameters. This not only restricts information access for users to be evaluated with large behavior anomaly parameters, but also restricts information access for users to be evaluated whose behavior anomaly parameters are continuously rising, thereby further improving the security of worker information in the employment management system.

[0038] Furthermore, when restricting information access for users to be evaluated, this invention processes the available alternative employment information, compresses the completeness of the information displayed, and only displays information content corresponding to the employment experience that matches their current access needs during the compression process. Adaptive recommendation parameters are output through corresponding evaluation content. This ensures the security of the employment information of the employment management system while guaranteeing the matching efficiency of the users to be evaluated when selecting employment personnel. Attached Figure Description

[0039] Fig. 1 This is a module connection diagram of the big data-based employment management system of the present invention;

[0040] Fig. 2 This is a module structure diagram of the user evaluation module of the present invention;

[0041] Fig. 3 This is a flowchart of the access analysis module of the present invention responding to evaluation analysis conditions to determine the behavior analysis strategy for each user to be evaluated;

[0042] Fig. 4This is a flowchart illustrating how the restriction analysis module of the present invention responds to restriction determination conditions to determine whether to impose information access restrictions on the user to be evaluated. Detailed Implementation

[0043] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0044] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0045] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0046] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0047] Please see Figs. 1 to 4 As shown, this invention provides a big data-based employment management system, comprising:

[0048] The user monitoring module is used to periodically determine the degree of abnormality in demand changes for each target service user based on the access tendency change coefficient and the access difference coefficient, and to determine whether to conduct access behavior analysis for each target service user in response to the target evaluation conditions.

[0049] The access analysis module, which is connected to the user monitoring module, is used to determine the behavior analysis strategy for each user to be evaluated in response to the evaluation analysis conditions. This strategy may be based on the user access stability coefficient to determine the abnormal behavior parameters of the user to be evaluated, or based on the execution interval stability coefficient and the execution depth stability coefficient to determine the abnormal behavior parameters of the user to be evaluated.

[0050] The user evaluation module, which is connected to the access analysis module, includes a first user evaluation unit and a second user evaluation unit, and is used to execute the behavior analysis strategy determined by the access analysis module to obtain abnormal behavior parameters of each user to be evaluated.

[0051] The restriction analysis module, which is connected to the user evaluation module, is used to determine whether to restrict information access for users whose abnormal behavior parameters are determined in response to restriction judgment conditions.

[0052] The restriction execution module, which is connected to the restriction analysis module, is used to respond to restriction execution conditions and compress the display information for various alternative employment information of restricted users.

[0053] In this invention, the security of worker information in the employment management system is ensured. The target service user is the user who provides employment recommendation services to the employment management system in this invention. The employment management system can grant access to the target service user to preliminarily matched worker information according to the target service user's actual employment needs, so as to save the target service user's screening efficiency. The preliminarily matched worker information is recorded as candidate worker information. Before the information is compressed, how to perform the preliminary matching of worker information according to the actual needs of the target service user is a topic that is already known to those skilled in the art and will not be elaborated here. The target service user can normally access complete worker information, including but not limited to: basic personal information, work experience, and work evaluation content corresponding to each work stage.

[0054] This invention utilizes several service monitoring records. Each service monitoring record records at least one instance of monitoring the access behavior of a target service user, including access dwell time, tendency change index, demand change anomaly degree, access tendency richness, reference tendency change coefficient, user access stability coefficient, anomaly parameter difference degree, behavior anomaly parameters, trend anomaly parameters, related operation parameters, and evaluation validity parameters. Each service monitoring record also has a corresponding qualification mark, which records whether the security of the worker information stored in the employment system meets the user's needs.

[0055] Specifically, the target evaluation condition for the user supervision module is that if the abnormality of the demand change of a target service user is greater than the preset abnormality of the demand change, then the access analysis module will determine to perform access behavior analysis on the target service user.

[0056] The abnormality of demand change is positively correlated with the access tendency change coefficient and the access difference coefficient.

[0057] In this invention, a cyclical user monitoring cycle is applied. The duration of the user monitoring cycle can be determined by the user. The higher the user's requirements for the security of the worker information stored in the employment system, the shorter the duration of the user monitoring cycle. A user monitoring cycle duration of 24 hours is provided. At the end of each user monitoring cycle, the abnormality of the demand change of the target service user is detected, and the access behavior analysis of each target service user is determined accordingly.

[0058] For a single target service user, the abnormality of demand change is the sum of the access tendency change coefficient and the access difference coefficient. The access tendency change coefficient is the number of times the target service user changes access information within the current user monitoring period / the number of times the target service user references access information within the current user monitoring period. The reference access information is migrant worker information whose access dwell time is greater than the preset access dwell time. The changed access information is reference access information whose tendency change index is greater than the preset tendency change index. For a single migrant worker information, the access dwell time is the sum of the dwell time on each page where the migrant worker information is located within the current user monitoring period.

[0059] For a single target service user, at the end of the current user monitoring period, the demand keywords contained in the migrant worker information accessed by the target service user during the current user monitoring period are extracted. For a single migrant worker information, the tendency to change is calculated as follows: the number of demand keywords contained in the migrant worker information / the number of change demand keywords contained in the migrant worker information. The access difference coefficient is calculated as the number of different demand keywords contained in each change access information / the number of overlapping demand keywords. For a single demand keyword, if the demand keyword does not exist in any reference access information during the access evaluation phase, the demand keyword is recorded as a change demand keyword. If the number of change access information containing the demand keyword is greater than the preset overlap index, the demand keyword is recorded as overlapping. The value of the preset overlap index for the demand keywords can be determined by the user based on the actual work scenario. For example, the user can set it based on service monitoring records. The higher the user's requirements for the security of the worker information stored in the employment system, the smaller the value of the preset overlap index. One preset overlap index value is 5. How to identify the demand keywords contained in the worker information is content that is already known to those skilled in the art and will not be elaborated here. The user can set the content of the demand keywords according to the actual work scenario. For example, if the target service user is a construction company, the demand keywords include but are not limited to: electric drill, cutting machine, electric welding, bricklaying, concrete pouring, scaffolding erection, construction-related certificates, electric welder certificate, safety officer certificate, and special operation certificate.

[0060] The values ​​of the preset access dwell time and the preset tendency change index can be determined by the user according to the actual work scenario. For example, the user can set them according to the service monitoring records. The higher the user's requirements for the security of the worker information stored in the employment system, the larger the value of the preset access dwell time and the larger the value of the preset tendency change index. A method for determining the preset access dwell time is provided, which is to record the minimum value of the access dwell time of each change reference access information in the service monitoring records that meets the user's security requirements for the worker information stored in the employment system as the preset access dwell time. A method for determining the preset tendency change index is provided, which is to record the average value of the tendency change index of each change access information in the service monitoring records that meets the user's security requirements for the worker information stored in the employment system as the preset tendency change index.

[0061] The value of the preset demand change anomaly level can be determined by the user based on the actual work scenario. For example, the user can set it based on service monitoring records. The higher the user's requirements for the security of the worker information stored in the employment system, the smaller the value of the preset demand change anomaly level and the larger the value of the preset access dwell time. A method for determining the value of the preset demand change anomaly level is provided, which records the average value of the demand change anomaly level of each user to be evaluated in the service monitoring records that meet the user's security requirements for the worker information stored in the employment system as the preset demand change anomaly level.

[0062] Specifically, the access analysis module responds to the behavior analysis conditions and determines the behavior analysis strategy for each user to be evaluated based on the richness of the user’s access tendency and the reference tendency change coefficient.

[0063] The behavioral analysis condition is that there are target service users who need to have their access behavior analyzed. These target service users who need to have their access behavior analyzed are recorded as users to be evaluated.

[0064] Specifically, for a single user to be evaluated, the access tendency richness is the number of different demand keywords contained in the worker information accessed by the user during the access evaluation phase. The reference tendency change coefficient is the average value of the access tendency change coefficients of the user to be evaluated determined in each user supervision cycle during the access evaluation phase. The end time of the access evaluation phase is the end time of the current user supervision cycle. The duration of the access evaluation phase can be set by the user according to the actual work scenario. The higher the user's requirements for the security of the worker information stored in the employment system, the longer the duration of the access evaluation phase. One possible duration of the access evaluation phase is 6 times the user supervision cycle.

[0065] Specifically, the evaluation and analysis conditions responded by the access analysis module are that if the access tendency richness of the user to be evaluated is less than or equal to the preset access tendency richness and the reference tendency change coefficient is less than or equal to the preset reference tendency change coefficient, then the first user evaluation unit determines the setting method of the abnormal behavior parameters of the user to be evaluated based on the user access stability coefficient.

[0066] The user access stability coefficient is determined based on the access depth difference index and the access duration difference index.

[0067] The values ​​of the preset access tendency richness and the preset reference tendency change coefficient can be determined by the user according to the actual work scenario. For example, the user can set them according to service monitoring records. A method for determining the value of the preset access tendency richness is provided, in which the service monitoring record that determines the setting method of the abnormal behavior parameters of the user to be evaluated according to the user access stability coefficient is recorded as the evaluation reference record, and the maximum value of the access tendency richness of the user to be evaluated in the evaluation reference record that meets the user's security requirements for the worker information stored in the employment system is recorded as the preset access tendency richness. A method for determining the value of the preset reference tendency change coefficient is provided, in which the maximum value of the reference tendency change coefficient of the user to be evaluated in the evaluation reference record that meets the user's security requirements for the worker information stored in the employment system is recorded as the preset reference tendency change coefficient.

[0068] For a single user to be evaluated, if the access tendency richness of the user to be evaluated is less than or equal to the preset access tendency richness and the reference tendency change coefficient is less than or equal to the preset reference tendency change coefficient, then the setting method of the abnormal behavior parameters of the user to be evaluated is determined according to the user access stability coefficient. The fact that both the access tendency richness and the reference tendency change coefficient are small indicates that the user to be evaluated has a relatively obvious tendency in the process of accessing migrant worker information. Therefore, by analyzing and evaluating the migrant worker information accessed by the user to be evaluated during the user supervision period, there is a risk of malicious crawling behavior.

[0069] For a single user to be evaluated, the user access stability coefficient = 1 / (access depth difference index + access duration difference index), where the access depth difference index... 'a' represents the number of worker information entries accessed by the user under evaluation during the evaluation phase; 'fj' represents the access depth parameter corresponding to the j-th access to worker information by the user under evaluation during the evaluation phase; 'f0' represents the average access depth parameter corresponding to each access to worker information by the user under evaluation during the evaluation phase. For a single worker information entry, the access depth parameter is the number of pages accessed during the access to that worker information entry. The access duration difference value... b is the number of pages visited by the user to be evaluated during the access evaluation phase, te is the dwell time of the user on the e-th page visited during the access evaluation phase, and t0 is the average dwell time of the user on all pages visited during the access evaluation phase.

[0070] Specifically, the abnormal setting condition for the response of the first user evaluation unit is that the user access stability coefficient of the user to be evaluated is greater than the preset user access stability coefficient. Then, the abnormal behavior parameters of the user to be evaluated are determined according to the access preference change index and the access parameter change index.

[0071] The abnormal setting condition for the response of the first user evaluation unit is that the user access stability coefficient of the user to be evaluated is less than or equal to the user access stability coefficient. Then, the abnormal behavior parameters of the user to be evaluated are determined according to the access overlap index and the overlap conflict index.

[0072] The value of the preset user access stability coefficient can be determined by the user based on the actual work scenario. For example, the user can set it based on service monitoring records. The method of setting the preset user access stability coefficient is provided. The service monitoring records that determine the abnormal behavior parameters of the user to be evaluated based on the access overlap index and the overlap conflict index are recorded as stable reference records. The minimum value of the user access stability coefficient of the user to be evaluated in the stable reference records that meet the user's security requirements for the information of workers stored in the employment system is recorded as the preset user access stability coefficient.

[0073] For a single user to be evaluated, if the user's access stability coefficient is greater than the preset user access stability coefficient, it indicates that the user's access behavior to migrant worker information has been relatively regular in the recent period. Therefore, by combining the abnormal access behavior and content, the risk of malicious web scraping by the user to be evaluated is determined. The abnormal behavior parameter is positively correlated with the access change index, which is the product of the access preference change index and the access parameter change index. The access preference change index = the number of overlapping demand keywords among the change demand keywords determined in the current user monitoring period / the number of change demand keywords determined in the current user monitoring period. The access parameter change index is the access depth change index. The sum of access depth and access duration change, wherein the access depth change = |average of access depth parameters corresponding to each access to worker information by the user under evaluation during the access evaluation phase - average of access depth parameters corresponding to each access to worker information by the user under evaluation during the current employment supervision period| / average of access depth parameters corresponding to each access to worker information by the user under evaluation during the access evaluation phase, wherein the access duration change = |average of dwell time on each page visited by the user under evaluation during the access evaluation phase - average of dwell time on each page visited by the user under evaluation during the current user supervision period| / average of dwell time on each page visited by the user under evaluation during the access evaluation phase;

[0074] For a single user to be evaluated, if the user access stability coefficient is less than or equal to the preset user access stability coefficient, it indicates that the user's access behavior to the migrant worker information in the recent period does not have an obvious pattern. Therefore, the risk of malicious crawling behavior of the user to be evaluated is determined only by analyzing the content of the accessed migrant worker information. The abnormal behavior parameter is negatively correlated with the access overlap quality coefficient. The overlap quality coefficient = access overlap index / overlap conflict index. The access overlap index = the number of overlapping keywords obtained in the current user supervision period / the number of different demand keywords in the migrant worker information accessed in the current user supervision period. The overlap conflict index = the number of conflicting overlapping keywords / the number of overlapping keywords obtained in the current user supervision period. For a single demand keyword, if the number of migrant worker information containing the demand keyword accessed by the user to be evaluated in the current user supervision period is greater than the preset overlap index, then the demand keyword is recorded as an overlapping keyword. For a single overlapping keyword, if it does not exist in any migrant worker information in the access evaluation stage, then the overlapping keyword is recorded as a conflicting overlapping keyword.

[0075] Specifically, if the evaluation and analysis condition of the access analysis module is that the access tendency richness of the user to be evaluated is greater than the preset access tendency richness or the reference tendency change coefficient is greater than the preset reference tendency change coefficient, then the second user evaluation unit determines the abnormal behavior parameters of the user to be evaluated based on the execution interval stability coefficient and the execution depth stability coefficient.

[0076] The abnormal behavior parameters are positively correlated with the execution interval stability coefficient and the execution depth stability coefficient, respectively.

[0077] Specifically, for a single user to be evaluated, if the access tendency richness of the user to be evaluated is greater than the preset access tendency richness or the reference tendency change coefficient is greater than the preset reference tendency change coefficient, then the abnormal behavior parameters of the user to be evaluated are determined according to the execution interval stability coefficient and the execution depth stability coefficient. A large access tendency richness or a large reference tendency change coefficient indicates that the user to be evaluated does not have a significant tendency in the process of accessing migrant worker information, that is, it is impossible to determine whether there is an access anomaly by looking at the information content accessed. Therefore, the execution interval stability coefficient and the execution depth stability coefficient are used to characterize whether there is a risk of malicious crawling in the access process of the user to be evaluated.

[0078] For users to be evaluated whose access tendency richness exceeds a preset access tendency richness or whose reference tendency change coefficient exceeds a preset reference tendency change coefficient, the behavioral anomaly parameter and the operation anomaly coefficient are positively correlated. The operation anomaly coefficient = execution interval stability coefficient + execution depth stability coefficient. The time when the user to be evaluated performs an access operation within the current user monitoring period is obtained and recorded as the access execution time. For any two access execution times, if there are no other access execution times between them, these two access execution times are recorded as a group of adjacent access times. The interval duration between each group of adjacent access times within the user monitoring period is detected and recorded as the execution interval duration corresponding to each group of adjacent access times. The execution interval stability coefficient... n represents the number of times the user to be evaluated performs access operations within the current user monitoring period, zi represents the execution interval duration of the i-th group of adjacent access times within the current user monitoring period, the average execution interval duration of each group of adjacent access times within the current user monitoring period, and the execution depth stability coefficient. m represents the number of worker information accessed by the user to be evaluated within the current user monitoring period, sk represents the access depth parameter corresponding to the kth access to worker information within the current user monitoring period, and s0 represents the average value of the access depth parameter corresponding to each access to worker information within the current user monitoring period. In this invention, the access operation is the user to be evaluated switching access pages.

[0079] Specifically, the restriction analysis module responds to the evaluation completion conditions and determines whether to restrict information access for each user to be evaluated who has completed the behavior anomaly parameters based on the behavior anomaly parameters and trend anomaly parameters.

[0080] For a single user whose abnormal behavior parameters have been determined, if the restriction analysis module responds with a restriction judgment condition that the abnormal behavior parameter is greater than a preset abnormal behavior parameter or the abnormal trend parameter is greater than a preset abnormal trend parameter, then it is determined that information access restrictions will be imposed on the user to be evaluated.

[0081] The assessment is completed when abnormal behavioral parameters of the user to be assessed are determined.

[0082] Specifically, for a single user to be evaluated, the trend anomaly parameter is determined based on the behavioral anomaly parameters determined for that user at each stage of the trend evaluation phase. The trend anomaly parameter is the product of the anomaly parameter change degree and the percentage of change persistence. The anomaly parameter change degree = the absolute value of the difference between the maximum and minimum values ​​of the behavioral anomaly parameters determined for that user during the trend evaluation phase / the minimum value of the behavioral anomaly parameters determined for that user during the trend evaluation phase. The percentage of change persistence = the number of change supervision cycles during the trend evaluation phase / the number of user supervision cycles during the trend evaluation phase. The anomaly parameter difference degree of each user supervision cycle during the trend evaluation phase is detected, and the user supervision cycle with an anomaly parameter difference degree greater than the preset anomaly parameter difference degree is recorded as a change supervision cycle. For a single user supervision cycle, the anomaly parameter difference degree = (the behavioral anomaly parameter determined at the end of the user supervision cycle - the behavioral anomaly parameter determined at the end of the previous user supervision cycle) / the behavioral anomaly parameter determined at the end of the previous user supervision cycle.

[0083] The value of the preset anomaly parameter difference can be determined by the user based on the actual work scenario. For example, the user can set it based on service monitoring records. The higher the user's security requirements for the worker information stored in the employment system, the smaller the value of the preset anomaly parameter difference. A method for determining the value of the preset anomaly parameter difference is provided, which is the average value of the anomaly parameter difference in each change supervision cycle in the service monitoring records that meet the user's security requirements for the worker information stored in the employment system as the preset anomaly parameter difference. The end time of the trend assessment phase is the end time of the current user supervision cycle. The duration of the trend assessment phase can be set by the user based on the actual work scenario. The higher the user's security requirements for the worker information stored in the employment system, the larger the duration of the trend assessment phase. A value for the duration of the trend assessment phase is provided, where the duration of the trend assessment phase is 8 times the user supervision cycle.

[0084] For a single user to be evaluated, if the abnormal behavior parameter is greater than the preset abnormal behavior parameter, it directly indicates that the user to be evaluated is likely to have malicious crawling behavior, and information access restrictions are imposed on the user to be evaluated. However, for users to be evaluated whose abnormal behavior parameter is less than or equal to the preset abnormal behavior parameter, it is necessary to further analyze whether the abnormal behavior parameter of the user to be evaluated has a significant or continuous increase, that is, to obtain the trend abnormal parameter of the user to be evaluated. If the trend abnormal parameter is greater than the preset trend abnormal parameter, information access restrictions are also imposed on the user to be evaluated. If the abnormal behavior parameter of the user to be evaluated is less than or equal to the preset abnormal behavior parameter and the trend abnormal parameter is less than or equal to the preset trend abnormal parameter, then information access restrictions are not imposed on the user to be evaluated.

[0085] The values ​​of the preset behavioral anomaly parameters and preset trend anomaly parameters can be determined by the user based on the actual work scenario. For example, the user can set them based on service monitoring records. The higher the user's security requirements for the worker information stored in the employment system, the smaller the values ​​of the preset behavioral anomaly parameters and preset trend anomaly parameters. A method for determining the value of the preset behavioral anomaly parameters is provided, in which service monitoring records that do not restrict information access for the user to be evaluated are recorded as restriction reference records, and the maximum value of the behavioral anomaly parameters of each person to be evaluated in the restriction reference records that meet the user's security requirements for the worker information stored in the employment system is recorded as the preset behavioral anomaly parameter. A method for determining the value of the preset trend anomaly parameters is provided, in which the maximum value of the trend anomaly parameters of each person to be evaluated in the restriction reference records that meet the user's security requirements for the worker information stored in the employment system is recorded as the preset trend anomaly parameter.

[0086] Specifically, the restriction execution module responds to the restriction execution conditions and compresses the displayed information for various candidate employment information of restricted users, including:

[0087] Filter the related stage information of each candidate employee information, and test the suitability recommendation coefficient of each candidate employee information;

[0088] Users with restricted access are only allowed to view the associated stage information and the matching recommendation coefficient of their various candidate employment information;

[0089] The restriction is enforced when there are users to be evaluated who require information access restrictions. These users are referred to as restricted users.

[0090] Specifically, the restriction execution module determines the association stage information of each candidate employment information based on the employment scenario association degree and the employment operation association degree;

[0091] The matching recommendation coefficients for each candidate worker information are determined based on the associated job parameters and the effective evaluation parameters. The matching recommendation coefficients are positively correlated with the associated job parameters and the effective evaluation parameters, respectively.

[0092] Specifically, for any candidate employment information of a single restricted user, the associated operation parameters of each employment stage within the candidate employment information are determined based on the employment scenario correlation and employment operation correlation. The employment evaluation content corresponding to the employment stage with associated operation parameters greater than the preset associated operation parameters is recorded as the associated stage information. The adaptation recommendation coefficient is the sum of the products of the associated operation parameters of each associated stage information of the candidate employment information and their corresponding evaluation weight index. For a single associated stage information, the evaluation weight index is positively correlated with its effective evaluation parameter.

[0093] For a single work phase, the associated operation parameter is the sum of the employment scenario correlation degree and the employment operation correlation degree for that work phase. If the work scenario corresponding to the work phase is in the same scenario category as the work scenario corresponding to the employment demand of the restricted user, the employment scenario correlation degree is recorded as 1. If the work scenario corresponding to the work phase is not in the same scenario category as the work scenario corresponding to the employment demand of the restricted user, the employment scenario correlation degree is recorded as 0. If the operation content corresponding to the work phase is in the same operation category as the operation content corresponding to the employment demand of the restricted user, the employment operation correlation degree is recorded as 1. If the operation content corresponding to the work phase is not in the same operation category as the operation content corresponding to the employment demand of the restricted user, the employment operation correlation degree is recorded as 0.

[0094] Determining whether a work scenario falls under the same scenario category and whether the work content falls under the same work category are topics easily understood by those skilled in the art and will not be elaborated upon here. Users can determine the classification results of scenario categories and work categories based on actual needs. This invention provides a method for classifying scenario categories and work categories. For example, outdoor construction scenarios include building site construction scenarios, road and bridge construction scenarios, and demolition construction scenarios; manufacturing scenarios include workshop operation scenarios and assembly line operation scenarios; and manufacturing work categories include machining, assembly, and quality inspection.

[0095] The value of the preset associated operation parameter can be determined by the user according to the actual work scenario. For example, the user can set it according to the service monitoring record. The higher the user's requirements for the security of the worker information stored in the employment system, the larger the value of the preset associated operation parameter. A method for determining the value of the preset associated operation parameter is provided, which records the average value of the associated operation parameters of each associated stage information in the service monitoring record that meets the user's security requirements for the worker information stored in the employment system as the preset associated operation parameter.

[0096] Specifically, the restriction execution module determines the effective evaluation parameters for each associated stage based on the effective evaluation ratio and the evaluation conflict parameters;

[0097] If the associated restriction condition of the execution restriction module response is that the effective evaluation parameter of the associated stage information is less than or equal to the preset effective evaluation parameter, then it is determined that the associated stage information is not used in the process of determining the matching recommendation coefficient of the corresponding candidate worker information, and the relevant content of the associated stage information is not displayed.

[0098] Specifically, for a single associated stage information, the effective evaluation parameter = ln(effective evaluation percentage / evaluation conflict parameter), the effective evaluation percentage = / the number of evaluation messages output by the target service user corresponding to the associated stage information / the number of evaluation messages output by the target service user corresponding to the associated stage information, and the evaluation conflict parameter = |the associated evaluation parameter of the associated stage information - the average value of the associated evaluation parameters of each employment stage information of the candidate employment information corresponding to the associated stage information| / the average value of the associated evaluation parameters of each employment stage information of the candidate employment information corresponding to the associated stage information;

[0099] For a single associated stage information, if the effective evaluation parameter is less than or equal to the preset effective evaluation parameter, it is determined that the associated stage information is not used in the process of determining the matching recommendation coefficient of the corresponding candidate worker information, and the relevant content of the associated stage information is not displayed. If the effective evaluation parameter is greater than the preset effective evaluation parameter, it is determined that the associated stage information is used in the process of determining the matching recommendation coefficient of the corresponding candidate worker information. The value of the preset effective evaluation parameter can be determined by the user according to the actual work scenario. For example, the user can set it according to the service monitoring record. The higher the user's requirements for the security of the worker information stored in the employment system, the larger the value of the preset effective evaluation parameter. A method for determining the value of the preset effective evaluation parameter is provided, which records the maximum value of the effective evaluation parameter of each undisplayed associated stage information in the service monitoring record that meets the user's security requirements for the worker information stored in the employment system as the preset effective evaluation parameter.

[0100] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles 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 all fall within the scope of protection of the present invention.

[0101] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A big data-based employment management system, characterized in that, include: The user monitoring module is used to periodically determine the degree of abnormality in demand changes for each target service user based on the access tendency change coefficient and the access difference coefficient, and to determine whether to conduct access behavior analysis for each target service user in response to the target evaluation conditions. The access analysis module, which is connected to the user monitoring module, is used to determine the behavior analysis strategy for each user to be evaluated in response to the evaluation analysis conditions. This strategy may be based on the user access stability coefficient to determine the abnormal behavior parameters of the user to be evaluated, or based on the execution interval stability coefficient and the execution depth stability coefficient to determine the abnormal behavior parameters of the user to be evaluated. The user evaluation module, which is connected to the access analysis module, includes a first user evaluation unit and a second user evaluation unit, and is used to execute the behavior analysis strategy determined by the access analysis module to obtain abnormal behavior parameters of each user to be evaluated. The restriction analysis module, which is connected to the user evaluation module, is used to determine whether to restrict information access for users whose abnormal behavior parameters are determined in response to restriction judgment conditions. The restriction execution module, which is connected to the restriction analysis module, is used to respond to restriction execution conditions and compress the display information for various alternative employment information of restricted users. The evaluation and analysis conditions responded by the access analysis module are that if the access tendency richness of the user to be evaluated is less than or equal to the preset access tendency richness and the reference tendency change coefficient is less than or equal to the preset reference tendency change coefficient, then the first user evaluation unit determines the setting method of the abnormal behavior parameters of the user to be evaluated based on the user access stability coefficient. The user access stability coefficient is determined based on the access depth difference index and the access duration difference index. The abnormal setting condition for the response of the first user evaluation unit is that the user access stability coefficient of the user to be evaluated is greater than the preset user access stability coefficient. Then, the abnormal behavior parameters of the user to be evaluated are determined according to the access preference change index and the access parameter change index. If the abnormal setting condition of the first user evaluation unit response is that the user access stability coefficient of the user to be evaluated is less than or equal to the user access stability coefficient, then the abnormal behavior parameters of the user to be evaluated are determined according to the access overlap index and the overlap conflict index.

2. The big data-based employment management system according to claim 1, characterized in that, The target evaluation condition for the user supervision module response is that if the abnormality of the demand change of a target service user is greater than the preset abnormality of the demand change, then the access analysis module will determine to perform access behavior analysis on the target service user. The abnormality of demand change is positively correlated with the access tendency change coefficient and the access difference coefficient.

3. The big data-based employment management system according to claim 2, characterized in that, The access analysis module responds to the behavior analysis conditions and determines the behavior analysis strategy for each user to be evaluated based on the richness of the user’s access tendency and the reference tendency change coefficient. The behavioral analysis condition is that there are target service users who need to have their access behavior analyzed. These target service users who need to have their access behavior analyzed are recorded as users to be evaluated.

4. The big data-based employment management system according to claim 3, characterized in that, The evaluation and analysis conditions responded by the access analysis module are that if the access tendency richness of the user to be evaluated is greater than the preset access tendency richness or the reference tendency change coefficient is greater than the preset reference tendency change coefficient, then the second user evaluation unit determines the abnormal behavior parameters of the user to be evaluated based on the execution interval stability coefficient and the execution depth stability coefficient. The abnormal behavior parameters are positively correlated with the execution interval stability coefficient and the execution depth stability coefficient, respectively.

5. The big data-based employment management system according to claim 4, characterized in that, The restriction analysis module responds to the evaluation completion conditions and determines whether to restrict information access for each user to be evaluated based on the behavioral anomaly parameters and trend anomaly parameters. For a single user whose abnormal behavior parameters have been determined, if the restriction analysis module responds with a restriction judgment condition that the abnormal behavior parameter is greater than a preset abnormal behavior parameter or the abnormal trend parameter is greater than a preset abnormal trend parameter, then it is determined that information access restrictions will be imposed on the user to be evaluated. The assessment is completed when abnormal behavioral parameters of the user to be assessed are determined.

6. The big data-based employment management system according to claim 5, characterized in that, The restriction execution module responds to the restriction execution conditions and displays compressed information on various candidate employment information for users with restricted access, including: Filter the related stage information of each candidate employee information, and test the suitability recommendation coefficient of each candidate employee information; Users with restricted access are only allowed to view the associated stage information and the matching recommendation coefficient of their various candidate employment information; The restriction is enforced when there are users to be evaluated who require information access restrictions. These users are referred to as restricted users.

7. The big data-based employment management system according to claim 6, characterized in that, The restriction execution module determines the association stage information of each candidate employment information based on the employment scenario association degree and the employment operation association degree; The matching recommendation coefficients for each candidate worker information are determined based on the associated job parameters and the effective evaluation parameters. The matching recommendation coefficients are positively correlated with the associated job parameters and the effective evaluation parameters, respectively.

8. The big data-based employment management system according to claim 7, characterized in that, The restriction execution module determines the effective evaluation parameters for each associated stage based on the effective evaluation ratio and evaluation conflict parameters. If the associated restriction condition of the execution restriction module response is that the effective evaluation parameter of the associated stage information is less than or equal to the preset effective evaluation parameter, then it is determined that the associated stage information is not used in the process of determining the matching recommendation coefficient of the corresponding candidate worker information, and the relevant content of the associated stage information is not displayed.

Images