Employee competency analysis and adjustment method and system based on behavior style

Abstract

The invention discloses a behavior style-based employee competency analysis and adjustment method and system, relates to the technical field of employee behavior style analysis, and is used for solving the problem that the accuracy of a competency evaluation result is affected due to the fact that dynamic changes of employee behavior styles are difficult to flexibly adapt to the employee behavior styles. Determining a behavior mode and a weight, calculating a behavior style adaptability score to set a capability adjustment type, and generating a recommendation strategy; and optimizing strategy matching through a contribution evaluation mechanism, readjusting the capability type, and filling and resetting. According to the method, the employee behavior style adaptability can be accurately analyzed, the behavior data optimization efficiency is improved, the flexibility and adaptability of employee capability adjustment are enhanced, and comprehensive and dynamic employee competency analysis and optimization support is provided for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of employee behavior style analysis. More specifically, the present invention relates to a method and system for analyzing and adjusting employee competency based on behavior style. Background Art

[0002] Employee behavior style analysis technology is a series of methods and techniques used to evaluate and optimize employee competency. These techniques collect and analyze employee behavior data, and combine specific evaluation models to reveal the correlation between behavior style and job performance, so as to provide a basis for organizational talent management. The application of employee behavior style analysis technology in the field of enterprise management can effectively improve organizational effectiveness and human resource allocation efficiency.

[0003] The existing technologies have the following deficiencies: Currently, in previous employee behavior style analysis, it mostly focuses on the ability evaluation in specific fields or task scenarios. For example, the innovative ability is quantitatively analyzed through a preset behavior index model. However, the coverage of these methods is limited and cannot comprehensively reflect the comprehensive competency of employees in diverse work scenarios. In addition, the existing technologies rely on preset models and are difficult to flexibly adapt to the dynamic changes of employee behavior styles, which affects the accuracy of evaluation results. Another type of technology focuses on the static evaluation of behavior frequency and importance, lacking in-depth exploration of the dynamic relationship between behavior style and actual job performance, and it is difficult to meet the needs of enterprises in terms of employee ability adjustment. Therefore, a method and system for analyzing and adjusting employee competency based on behavior style are proposed.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for analyzing and adjusting employee competency based on behavior style, and solve the problems raised in the above background art by using an algorithm based on behavior pattern recognition and dynamic ability mapping.

[0006] To achieve the above object, the present invention provides the following technical solution, a method and system for analyzing and adjusting employee competency based on behavior style, including step S1: obtaining employee behavior data, analyzing the time distribution characteristics of the behavior data, screening out high-fluctuation time periods in the behavior data according to the time distribution characteristics, popping up a behavior marking pop-up window to the user terminal, and determining the behavior pattern and behavior weight according to the behavior marking pop-up window; Step S2: Calculate the overlap coefficient by comparing the overlap between the behavior pattern and the high-fluctuation time period. Evaluate the adaptability of the behavior style comprehensively based on the overlap coefficient and the behavior weight. Set the type of ability adjustment as single-dimensional, two-dimensional, or multi-dimensional according to the evaluation score of the behavior style adaptability; Step S3: Select the corresponding level of ability adjustment strategy as the recommended strategy for the ability optimization module according to the type of ability adjustment, and send it to the authorized user terminal. When the type of ability adjustment is not single-dimensional, after the first ability optimization module fills in the strategy, determine whether the strategy matches. If the strategy does not match, enter the contribution evaluation mechanism; Step S4: In the contribution evaluation mechanism, count the number of times the user behavior marking pop-up window is processed, evaluate the contribution of the user based on the number of times the user behavior marking pop-up window is processed, detect the optimization frequency of the chain behavior data by the user, reset the type of ability adjustment and select the recommended strategy comprehensively based on the user contribution evaluation result and the optimization frequency of the chain behavior data, and fill in and reset according to the recommended strategy.

[0007] In a preferred embodiment, in step S1, the obtained employee behavior data is divided into multiple time periods according to a preset time division ratio, the behavior data is imported into the data analysis library for processing, the behavior quantity and behavior intensity value of each time period of the behavior data are obtained, and the behavior average value and behavior intensity variance of the corresponding time period of the behavior data are calculated according to the behavior quantity and behavior intensity value of each time period of the behavior data.

[0008] In a preferred embodiment, in step S1, the fluctuation segmentation threshold of the behavior data is set using the recursive partitioning method according to the behavior intensity variance of each time period of the behavior data. The specific steps are as follows: Sort the behavior intensity variances of each time period of the behavior data from small to large, set the basic segmentation coefficient and the upper limit segmentation coefficient, use the basic segmentation coefficient to divide the sequence into two parts, calculate the average value of the behavior intensity variances of the two parts, and select the part with the larger average value as the secondary sorting sequence; Reduce the denominator of the basic segmentation score by a preset reduction coefficient to increase the basic segmentation coefficient; divide the secondary sorting sequence according to the basic segmentation score, calculate the average value of the behavior intensity variances of the two parts, and select the part with the smaller average value as the tertiary sorting sequence. Repeat the operation until the basic segmentation coefficient reaches the upper limit segmentation coefficient or there is only one value left in the sequence; If there is only one value left in the sequence, use it as the fluctuation segmentation threshold. If the basic segmentation coefficient reaches the upper limit segmentation coefficient, select the median value of the sequence as the fluctuation segmentation threshold; Mark the part of the behavior data with a behavior intensity variance exceeding the fluctuation segmentation threshold as the high-fluctuation part; mark the part of the behavior data with a behavior intensity variance lower than the fluctuation segmentation threshold as the low-fluctuation part.

[0009] In a preferred embodiment, in step S1, after marking each time period of the behavior data, a behavior marking pop-up window is popped up to the user side.

[0010] In a preferred embodiment, in step S2, the behavior pattern is compared with the high-fluctuation time period to determine its overlap degree; If the behavior pattern is completely within the high-fluctuation time period, the overlap degree coefficient is set to 1; If the behavior pattern is completely outside the high-fluctuation time period, the overlap degree coefficient is set to 0; If the behavior pattern is partially within the high-fluctuation time period, the ratio of the proportion of the behavior within the high-fluctuation time period to the behavior weight is used as the overlap degree coefficient, and the overlap degree coefficient is between 0 and 1; After obtaining the overlap degree coefficient, access multiple historical behavior weights stored in the historical database, and calculate the average value of the historical behavior weights as the behavior weight threshold; If the behavior weight obtained by the user side exceeds the behavior weight threshold, the weight coefficient is set to 0; if the behavior weight obtained by the user side is lower than the behavior weight threshold, the weight coefficient is set to 1.

[0011] In a preferred embodiment, in step S2, the behavior style adaptability is scored by integrating the overlap degree coefficient and the weight coefficient, and the ability adjustment type is set according to the behavior style adaptability score. The specific steps are as follows: The product result obtained by multiplying the overlap degree coefficient and the weight coefficient is used as the behavior style adaptability score value; Rule 1: When the behavior style adaptability score value is 1, it is determined that the behavior style adaptability is high adaptability; Rule 2: When the behavior style adaptability score value is between 0 and 1, it is determined that the behavior style adaptability is medium adaptability; Rule 3: When the behavior style adaptability score value is 0, it is determined that the behavior style adaptability is low adaptability; When the behavior style adaptability is determined to be low adaptability, the ability adjustment type is set to the single-dimensional adjustment type; When the behavior style adaptability is determined to be medium adaptability, the ability adjustment type is set to the two-dimensional adjustment type; when the behavior style adaptability is determined to be high adaptability, the ability adjustment type is set to the multi-dimensional adjustment type.

[0012] In a preferred embodiment, in step S3, the recommendation strategy is obtained by randomly combining logical conditions and behavior parameters with a preset number of rules and stored in the policy management system in advance. Different levels of complexity of the strategy are obtained by setting different preset numbers of rules; Select the corresponding type of policy in the policy management system as the recommended policy for the ability optimization module according to the ability adjustment type; After the user inputs the policy into the ability optimization module, compare the user-input policy and the recommended policy sent to the user account item by item. When all logical conditions and behavior parameters are the same, it is determined that the policy matches, and the user can perform optimization operations on the behavior data; When there are differences in logical conditions or behavior parameters, it is determined that the policy does not match, fill in and reset, and recalculate the recommended policy and send it to the information receiving place preset by the user; when the ability adjustment type is two-dimensional or multi-dimensional, when the user needs to optimize behavior data, judge the user account. After judging that the user account is an authorized account, send the first recommended policy to the user account; After the user inputs the policy into the ability optimization module, if it is determined that the policy matches, send the second recommended policy to the user account; if it is determined that the policy does not match, enter the contribution evaluation mechanism.

[0013] In a preferred embodiment, in step S4, select a past period of time as the statistical time in the contribution evaluation mechanism, and count the number of times the current user behavior mark pop-up window is processed within the statistical time; Use the linear normalization method to calculate the contribution index based on the number of times the user behavior mark pop-up window is processed to evaluate the contribution of the user; Detect the optimization frequency of the user's chain behavior data within the statistical time, and use the user's contribution index and the optimization frequency of the chain behavior data as input parameters to calculate the policy matching coefficient using the support vector machine algorithm; Compare the policy matching coefficient with the preset first policy matching threshold and second policy matching threshold to set the ability adjustment type, and the first policy matching threshold is lower than the second policy matching threshold; When the policy matching coefficient is lower than the first policy matching threshold, the ability adjustment type is set to the multi-dimensional adjustment type; When the policy matching coefficient is between the first policy matching threshold and the second policy matching threshold, the ability adjustment type is set to the two-dimensional adjustment type; When the policy matching coefficient exceeds the second policy matching threshold, the ability adjustment type is set to the single-dimensional adjustment type.

[0014] The employee competency analysis and adjustment system based on behavioral style includes a behavior detection module, an adaptability scoring module, a contribution evaluation module, and a policy reset module; The behavior detection module is used to analyze the time distribution characteristics of the employee behavior data, screen out the high-fluctuation time periods of the behavior data, and determine the behavior pattern and behavior weight input by the user end; The adaptability scoring module is used to score the adaptability of employees' behavior styles, set the type of ability adjustment according to the adaptability score of the behavior style, and generate a recommended strategy. The contribution evaluation module is used to send the recommended strategy to the user account, proofread whether the strategy matches, and if the strategy does not match, enter the contribution evaluation mechanism to evaluate the user's contribution. The strategy reset module is used to reset the type of ability adjustment according to the user's contribution and generate a recommended strategy, and reset the strategy filling. The behavior detection module calculates the average behavior value and the variance of behavior intensity in each time period of the behavior data through the data analysis library; the adaptability scoring module calculates the behavior weight threshold and sets the weight coefficient through the historical database; the contribution evaluation module calculates the strategy matching coefficient through the support vector machine algorithm; the strategy reset module resets the type of ability adjustment according to the contribution evaluation result and generates a recommended strategy.

[0015] The technical effects and advantages of the present invention: 1. By analyzing the time distribution characteristics of employees' behavior data, the present invention screens out the high-fluctuation time periods of the behavior data, determines the analysis direction and provides a data basis for subsequent analysis of the adaptability of behavior styles, pops up a behavior marking pop-up window at the user end, determines the behavior pattern and behavior weight according to the behavior marking pop-up window, compares the behavior pattern with the high-fluctuation time period, calculates its overlap degree, comprehensively analyzes the adaptability of the behavior style based on the behavior weight and the overlap degree, sets the type of ability adjustment according to the adaptability of the behavior style, generates a recommended strategy according to the type of ability adjustment. By matching the type of ability adjustment with the adaptability of the behavior style, the optimization efficiency of the behavior data can be improved. When the type of ability adjustment is multi-dimensional, if the first input strategy does not match, it enters the contribution evaluation mechanism, counts the number of times the user processes the behavior marking pop-up window for contribution evaluation, detects the optimization frequency of the user's chained behavior data, comprehensively re-sets the type of ability adjustment according to the user's contribution evaluation result and the optimization frequency of the chained behavior data, selects a recommended strategy, and performs filling reset according to the recommended strategy. In addition to facilitating the timely optimization of employees' behavior data, it also improves the accuracy and adaptability of employees' ability adjustment. Brief Description of the Drawings

[0016] Figure 1 It is a flowchart for implementing the method for analyzing and adjusting employees' competency based on behavior style of the present invention.

[0017] Figure 2 It is a flowchart of the method for analyzing and adjusting employees' competency based on behavior style of the present invention.

[0018] Figure 3 It is a schematic diagram of the modules of the system for analyzing and adjusting employees' competency based on behavior style of the present invention. Detailed Embodiment

[0019] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0020] Embodiment 1: Please refer to Figures 1 to 3 , the overall structure of the employee competency analysis and adjustment system based on behavioral style includes: a behavior detection module, an adaptability scoring module, a contribution evaluation module, and a strategy reset module.

[0021] These modules form a close cooperation relationship through the data flow method.

[0022] The behavior detection module is responsible for extracting the time distribution characteristics from the employee's behavior data and screening high-fluctuation time periods, and at the same time popping up a behavior marking pop-up window to the user side to obtain the behavior pattern and behavior weight.

[0023] The adaptability scoring module receives the data from the behavior detection module, calculates the overlap coefficient and the weight coefficient, and generates a behavior style adaptability score value, and then sets the ability adjustment type.

[0024] The contribution evaluation module is used to handle the situation of failed strategy matching, count the number of times the user behavior marking pop-up window is processed and the frequency of chain behavior data optimization, and calculate the strategy matching coefficient through the support vector machine algorithm.

[0025] The strategy reset module readjusts the ability adjustment type according to the result of the contribution evaluation module and generates a new recommended strategy.

[0026] In the specific operation process, first, the behavior detection module executes step S1, that is, obtains the employee's behavior data.

[0027] The behavior data comes from the enterprise internal information system or external monitoring devices, such as the employee's work log, project progress record, and communication tool usage, etc.

[0028] The behavior detection module divides the behavior data into multiple time periods according to the preset time division ratio, and the behavior data of each time period is imported into the data analysis library for processing to calculate the behavior quantity and behavior intensity value of each time period.

[0029] The behavior quantity refers to the total number of specific behavior events completed by the employee within that time period, and the behavior intensity value reflects the importance or complexity of the behavior event.

[0030] The behavior detection module further calculates the behavior average value and behavior intensity variance of each time period, laying a foundation for subsequent determination of high-fluctuation time periods.

[0031] To accurately identify high - volatility time periods, the behavior detection module uses a recursive segmentation method to set the volatility segmentation threshold.

[0032] Specifically, the behavior detection module sorts the variances of behavior intensities for all time periods from smallest to largest, and sets a basic segmentation coefficient and an upper - limit segmentation coefficient.

[0033] The basic segmentation coefficient is used to divide the sorted sequence into two parts. After calculating the average values of the variances of behavior intensities for the two parts, the part with the larger average value is selected as the secondary sorted sequence.

[0034] Subsequently, the basic segmentation coefficient is gradually increased by reducing the denominator, and the above - mentioned segmentation process is repeated until the basic segmentation coefficient reaches the upper - limit segmentation coefficient or there is only one value left in the sequence.

[0035] If there is only one value left in the sequence, it is used as the volatility segmentation threshold; otherwise, the median of the sequence is selected as the volatility segmentation threshold.

[0036] Finally, the part where the variance of behavior intensity exceeds the volatility segmentation threshold is marked as a high - volatility time period, and the part below the volatility segmentation threshold is marked as a low - volatility time period.

[0037] After completing the screening of high - volatility time periods, the behavior detection module pops up a behavior - marking pop - up window to the user side, asking the user to input the behavior pattern and behavior weight.

[0038] The behavior pattern is a description of the characteristics of employees' behavior by the user based on their own experience or observation results, such as "innovative behavior" or "team - collaboration behavior".

[0039] The behavior weight represents the importance of this behavior pattern in the overall work performance of employees, usually presented in the form of a percentage.

[0040] After the user input is completed, the behavior detection module transmits the behavior pattern and behavior weight to the adaptability scoring module.

[0041] The adaptability scoring module executes step S2, that is, it compares the behavior pattern with the high - volatility time periods and calculates the overlap coefficient.

[0042] Specifically, if the behavior pattern is completely within the high - volatility time period, the overlap coefficient is set to 1; if the behavior pattern is completely outside the high - volatility time period, the overlap coefficient is set to 0; if the behavior pattern is partially within the high - volatility time period, the ratio of the proportion of the behavior within the high - volatility time period to the behavior weight is used as the overlap coefficient, and its value is between 0 and 1.

[0043] In addition, the adaptability scoring module accesses the historical database and calculates the average value of the historical behavior weights as the behavior weight threshold.

[0044] If the behavior weight obtained by the client exceeds the behavior weight threshold, the weight coefficient is set to 0; if the behavior weight obtained by the client is lower than the behavior weight threshold, the weight coefficient is set to 1.

[0045] The adaptability scoring module multiplies the overlap coefficient by the weight coefficient to obtain the behavior style adaptability score value.

[0046] According to the behavior style adaptability score value, the adaptability scoring module sets the ability adjustment type.

[0047] When the score value is 1, it is judged that the behavior style adaptability is high adaptability, and the ability adjustment type is set to the multi-dimensional adjustment type; When the score value is between 0 and 1, it is judged that the behavior style adaptability is medium adaptability, and the ability adjustment type is set to the two-dimensional adjustment type; When the score value is 0, it is judged that the behavior style adaptability is low adaptability, and the ability adjustment type is set to the one-dimensional adjustment type.

[0048] The adaptability scoring module generates a recommendation strategy according to the ability adjustment type and sends it to the client.

[0049] The generation process of the recommendation strategy depends on the strategy management system, which pre-stores strategies randomly combined by various logical conditions and behavior parameters.

[0050] The complexity of each strategy is determined by the number of preset rules. The more rules there are, the more complex the strategy is.

[0051] The adaptability scoring module selects the corresponding type of strategy from the strategy management system according to the ability adjustment type as the recommendation strategy.

[0052] After receiving the recommendation strategy, the user inputs it into the ability optimization module for matching and verification.

[0053] If the strategy input by the user is exactly the same as the recommendation strategy, it is judged that the strategy matches, and the user can perform optimization operations on the behavior data; if there is an inconsistency, it is judged that the strategy does not match, and the contribution evaluation mechanism is entered.

[0054] The contribution evaluation module executes step S4, counts the number of times the user behavior mark pop-up window is processed in the past period of time, and calculates the contribution index using the linear normalization method.

[0055] The contribution index reflects the user's participation in the process of optimizing behavior data.

[0056] Meanwhile, the contribution evaluation module detects the optimization frequency of the user's chain behavior data, takes the contribution index and the optimization frequency as input parameters, and calculates the strategy matching coefficient through the support vector machine algorithm.

[0057] The calculation formula of the strategy matching coefficient is N equals e to the power of w, where e is the natural base, and w is the support vector machine parameter and equals the sum of the contribution index and the optimization frequency.

[0058] The contribution evaluation module compares the strategy matching coefficient with the preset first strategy matching threshold and the second strategy matching threshold, and sets a new ability adjustment type.

[0059] If the strategy matching coefficient is lower than the first strategy matching threshold, the ability adjustment type is set to the multi-dimensional adjustment type; if the strategy matching coefficient is between the first strategy matching threshold and the second strategy matching threshold, the ability adjustment type is set to the two-dimensional adjustment type; If the strategy matching coefficient is higher than the second strategy matching threshold, the ability adjustment type is set to the single-dimensional adjustment type.

[0060] Finally, the strategy reset module regenerates the recommended strategy according to the result of the contribution evaluation module and resets the strategy filling.

[0061] If the ability adjustment type is two-dimensional or multi-dimensional, the strategy reset module sequentially sends multiple recommended strategies to the user account until all strategies are successfully matched.

[0062] Throughout the process, the behavior detection module, the adaptability scoring module, the contribution evaluation module, and the strategy reset module maintain efficient cooperation through the data flow method to ensure the timely optimization of the employee behavior data and the accuracy and adaptability of the ability adjustment.

[0063] The above embodiments, in conjunction with the attached Figure 1 to the attached Figure 3 describe in detail the specific operation principles and processes of the employee competency analysis and adjustment method and system based on behavior style, fully reflecting how the technical solution of the present invention is implemented in actual scenarios.

[0064] In order to better enable relevant personnel in the technical field to fully understand and implement the present invention, the following supplements the specific implementation principles of the present invention with a specific application scenario.

[0065] In the human resource management scenario of an enterprise, the analysis of employees' behavior styles and the adjustment of competency become important means to optimize team efficiency.

[0066] The enterprise hopes to dynamically adjust the ability configuration of employees by collecting and analyzing employees' behavior data to improve their comprehensive performance in diverse work scenarios.

[0067] The following is a supplementary description of the specific implementation steps and operating principles based on the technical solution of the present invention.

[0068] First, during the operation of the behavior detection module, the system obtains the behavior data of employees from the enterprise internal information system, such as the project task completion records, email communication frequencies, and meeting participation situations of employees.

[0069] These behavior data are divided into multiple time periods according to a preset time division ratio, and the behavior quantity and behavior intensity value of each time period are calculated through the data analysis library.

[0070] The behavior quantity reflects the activity of employees within a specific time period, while the behavior intensity value further reveals the importance or complexity of the behavior event.

[0071] To identify high-fluctuation time periods, the system uses the recursive partitioning method to sort and partition the variance of behavior intensity, gradually narrowing the range until the fluctuation partitioning threshold is determined.

[0072] This process ensures the high accuracy of screening high-fluctuation time periods, thus providing a reliable data basis for subsequent analysis.

[0073] Next, the adaptability scoring module calculates the overlap coefficient according to the results of the behavior detection module.

[0074] Suppose the behavior pattern of an employee is "innovative behavior", and this behavior pattern is mainly concentrated in high-fluctuation time periods, then the overlap coefficient is set to 1; If part of the behavior pattern is in high-fluctuation time periods, the system combines the proportion of behaviors in high-fluctuation time periods with the behavior weight input by the user to calculate an overlap coefficient between 0 and 1.

[0075] Meanwhile, the system accesses the historical database, calculates the average value of historical behavior weights as the behavior weight threshold, and sets the weight coefficient according to the behavior weight input by the user.

[0076] Finally, the adaptability scoring module multiplies the overlap coefficient by the weight coefficient to obtain the behavior style adaptability scoring value.

[0077] This scoring value directly determines the setting of the ability adjustment type. For example, when the score is 1, the system determines that the behavior style adaptability is high adaptability, and sets the ability adjustment type to the multi-dimensional adjustment type.

[0078] During the generation of the recommendation strategy, the strategy management system selects an appropriate strategy according to the ability adjustment type.

[0079] For example, for the multi-dimensional adjustment type, the system will preferentially select complex strategies with a larger number of rules to meet the needs of employees in diverse work scenarios.

[0080] After receiving the recommended strategy, the user inputs it into the ability optimization module for matching and verification. If the strategy input by the user is exactly the same as the recommended strategy, the system determines that the strategy matching is successful and allows the user to perform optimization operations on the behavior data; if there is a difference, it enters the contribution evaluation mechanism.

[0081] The contribution evaluation module plays an important role at this stage. The system counts the number of times the user processes the behavior marking pop-up window in the past period of time and calculates the user's contribution index using the linear normalization method.

[0082] At the same time, the system detects the frequency of the user's optimization of the chain behavior data, takes the contribution index and the optimization frequency as input parameters, and calculates the strategy matching coefficient through the support vector machine algorithm.

[0083] The calculation formula for the strategy matching coefficient is N equals e to the power of w, where e is the natural base and w is the support vector machine parameter and is equal to the sum of the contribution index and the optimization frequency.

[0084] The system compares the strategy matching coefficient with the preset first strategy matching threshold and the second strategy matching threshold, and re-sets the ability adjustment type.

[0085] For example, when the strategy matching coefficient is lower than the first strategy matching threshold, the system sets the ability adjustment type to the multi-dimensional adjustment type; when the coefficient is between the two thresholds, it is set to the two-dimensional adjustment type.

[0086] Finally, the strategy reset module regenerates the recommended strategy according to the results of the contribution evaluation module and resets the strategy filling.

[0087] If the ability adjustment type is two-dimensional or multi-dimensional, the system sequentially sends multiple recommended strategies to the user account until all strategies are successfully matched.

[0088] Throughout the process, the behavior detection module, the adaptability scoring module, the contribution evaluation module, and the strategy reset module maintain efficient cooperation through the data flow method to ensure the timely optimization of the employee behavior data and the accuracy and adaptability of the ability adjustment.

[0089] Through the implementation of the above specific application scenarios, the technical solution of the present invention is fully demonstrated.

[0090] The system analyzes the time distribution characteristics of the employee behavior data, screens out the high-fluctuation time periods, and performs adaptability scoring in combination with the behavior pattern and the behavior weight, so as to dynamically adjust the ability configuration of the employees.

[0091] This process not only improves the efficiency of behavior data optimization, but also significantly enhances the comprehensive competence of employees in diverse work scenarios, providing a scientific basis and technical support for the enterprise's talent management.

[0092] Furthermore, the employee competence analysis and adjustment method based on behavior style includes the following steps: Step S1: Obtain the behavior data of employees, analyze the time distribution characteristics of the behavior data, screen out the high-fluctuation time periods in the behavior data according to the time distribution characteristics, pop up a behavior marking window on the user side, and determine the behavior pattern and behavior weight according to the behavior marking window; Step S2: Calculate the overlap coefficient by comparing the overlap degree between the behavior pattern and the high-fluctuation time period, score the behavior style adaptability by integrating the overlap coefficient and the behavior weight, and set the ability adjustment type as single-dimensional, two-dimensional or multi-dimensional according to the behavior style adaptability score; Step S3: Select the corresponding level of ability adjustment strategy as the recommended strategy for the ability optimization module according to the ability adjustment type and send it to the authorized user side. When the ability adjustment type is not single-dimensional, judge whether the strategy matches after the first ability optimization module fills in the strategy. If the strategy does not match, enter the contribution evaluation mechanism; Step S4: In the contribution evaluation mechanism, count the number of times the user behavior marking window is processed, evaluate the contribution of the user according to the number of times the user behavior marking window is processed, detect the optimization frequency of the user's chained behavior data, reset the ability adjustment type and select the recommended strategy again by integrating the user contribution evaluation result and the chained behavior data optimization frequency, and fill in and reset according to the recommended strategy.

[0093] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by technical personnel in this field according to the actual situation.

[0094] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0095] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0096] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0097] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0098] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals may use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0099] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0100] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0101] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, the functional units in each embodiment of this application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0103] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0104] As described above, the above are only specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for analyzing and adjusting employees' competency based on behavioral styles, characterized in that: Including: Step S1: Obtain the behavior data of employees, analyze the time distribution characteristics of the behavior data, filter out the high-fluctuation time periods in the behavior data according to the time distribution characteristics, pop up a behavior marking window on the user side, and determine the behavior pattern and behavior weight according to the behavior marking window; Step S2: Compare the overlap degree between the behavior pattern and the high-fluctuation time period to calculate the overlap degree coefficient, comprehensively score the adaptability of the behavior style based on the overlap degree coefficient and the behavior weight, and set the ability adjustment type to single-dimensional, two-dimensional or multi-dimensional according to the behavior style adaptability score; Step S3: Select the corresponding level of ability adjustment strategy as the recommended strategy of the ability optimization module according to the ability adjustment type and send it to the authorized user side. When the ability adjustment type is not single-dimensional, judge whether the strategy matches after the first ability optimization module fills in the strategy. If the strategy does not match, enter the contribution evaluation mechanism; Step S4: In the contribution evaluation mechanism, count the number of times the user behavior marking window is processed, conduct a contribution evaluation on the user according to the number of times the user behavior marking window is processed, detect the optimization frequency of the user's chain behavior data, and re-set the ability adjustment type and select the recommended strategy based on the comprehensive user contribution evaluation result and the chain behavior data optimization frequency, and fill in and reset according to the recommended strategy.

2. The method for analyzing and adjusting the employee's competence based on behavioral style according to claim 1, wherein: In step S1, divide the obtained employee behavior data into multiple time periods according to a preset time division ratio, import the behavior data into a data analysis library for processing, obtain the behavior quantity and behavior intensity value of each time period of the behavior data, and calculate the behavior average value and behavior intensity variance of the corresponding time period of the behavior data according to the behavior quantity and behavior intensity value of each time period of the behavior data.

3. The method for analyzing and adjusting employee competency based on behavior style according to claim 2, wherein: In step S1, set the fluctuation segmentation threshold of the behavior data using the recursive segmentation method according to the behavior intensity variance of each time period of the behavior data. The specific steps are as follows: Sort the behavior intensity variances of each time period of the behavior data from small to large, set a basic segmentation coefficient and an upper segmentation coefficient, use the basic segmentation coefficient to divide the sequence into two parts, calculate the average value of the behavior intensity variances of the two parts, and select the part with the larger average value as the secondary sorting sequence; Reduce the denominator of the basic segmentation fraction through a preset reduction coefficient to increase the basic segmentation coefficient; divide the secondary sorting sequence according to the basic segmentation fraction, calculate the average value of the behavior intensity variances of the two parts, and select the part with the smaller average value as the tertiary sorting sequence, and repeat the operation until the basic segmentation coefficient reaches the upper segmentation coefficient or there is only one value left in the sequence; If there is only one value left in the sequence, use it as the fluctuation segmentation threshold. If the basic segmentation coefficient reaches the upper segmentation coefficient, select the median value of the sequence as the fluctuation segmentation threshold; Mark the part of the behavior data with a behavior intensity variance exceeding the fluctuation segmentation threshold as the high-fluctuation part; Mark the part of the behavior data with a behavior intensity variance lower than the fluctuation segmentation threshold as the low-fluctuation part.

4. The method for analyzing and adjusting the competence of employees based on behavior style according to claim 1, wherein: In step S1, after marking each time period of the behavior data, pop up a behavior marking window on the user side.

5. The method for analyzing and adjusting employee competency based on behavioral style according to claim 1, wherein: In step S2, compare the behavior pattern with the high-fluctuation time period to determine its overlap degree; If the behavior pattern is completely within the high - volatility time period, set the overlap coefficient to 1; If the behavior pattern is completely outside the high - volatility time period, set the overlap coefficient to 0; If the behavior pattern is partially within the high - volatility time period, take the ratio of the proportion of the behavior within the high - volatility time period to the behavior weight as the overlap coefficient, and the overlap coefficient is between 0 and 1; After obtaining the overlap coefficient, access the multiple historical behavior weights stored in the historical database, and calculate the average value of the historical behavior weights as the behavior weight threshold; If the behavior weight obtained by the client exceeds the behavior weight threshold, set the weight coefficient to 0; If the behavior weight obtained by the client is lower than the behavior weight threshold, set the weight coefficient to 1.

6. The method for analyzing and adjusting the competence of employees based on behavioral styles according to claim 5, characterized in that: In step S2, comprehensively score the behavior style adaptability based on the overlap coefficient and the weight coefficient, and set the ability adjustment type according to the behavior style adaptability score. The specific steps are as follows: Take the product result obtained by multiplying the overlap coefficient and the weight coefficient as the behavior style adaptability score value; Rule 1: When the behavior style adaptability score value is 1, it is judged that the behavior style adaptability is high adaptability; Rule 2: When the behavior style adaptability score value is between 0 and 1, it is judged that the behavior style adaptability is medium adaptability; Rule 3: When the behavior style adaptability score value is 0, it is judged that the behavior style adaptability is low adaptability; When the behavior style adaptability is judged to be low adaptability, set the ability adjustment type to the single - dimension adjustment type; When the behavior style adaptability is judged to be medium adaptability, set the ability adjustment type to the two - dimension adjustment type; when the behavior style adaptability is judged to be high adaptability, set the ability adjustment type to the multi - dimension adjustment type.

7. The method for analyzing and adjusting the competence of employees based on behavioral styles according to claim 6, characterized in that: In step S3, the recommendation strategy is obtained by randomly combining the logical conditions and behavior parameters of the preset number of rules and stored in the strategy management system in advance. Different levels of complexity of the strategy can be obtained by setting different preset numbers of rules; Select the corresponding type of strategy in the strategy management system according to the ability adjustment type as the recommendation strategy of the ability optimization module; After the user inputs the strategy into the ability optimization module, compare the user - input strategy item by item with the recommendation strategy sent to the user account. When all the logical conditions and behavior parameters are the same, it is judged that the strategy matches, and the user can perform optimization operations on the behavior data; When there are differences in the logical conditions or behavior parameters, it is judged that the strategy does not match, perform filling and resetting, and recalculate the recommendation strategy and send it to the information receiving place preset by the user; when the ability adjustment type is two - dimension or multi - dimension, when the user needs to optimize the behavior data, judge the user account. When it is judged that the user account is an authorized account, send the first recommendation strategy to the user account; After the user inputs the strategy into the ability optimization module, if it is judged that the strategy matches, send the second recommendation strategy to the user account; if it is judged that the strategy does not match, enter the contribution evaluation mechanism.

8. The method for analyzing and adjusting employee competency based on behavioral style according to claim 7, wherein: In step S4, select a past period of time as the statistical time in the contribution evaluation mechanism, and count the number of times the current user's behavior - marked pop - up window is processed within the statistical time; Use the linear normalization method to calculate the contribution index based on the number of pop-up window processing times marked by user behavior, and evaluate the contribution of users; Detect the optimization frequency of the user's chain behavior data within the statistical time, and use the contribution index of the user and the optimization frequency of the chain behavior data as input parameters to calculate the strategy matching coefficient using the support vector machine algorithm; Compare the strategy matching coefficient with the preset first strategy matching threshold and second strategy matching threshold to set the ability adjustment type, and the first strategy matching threshold is lower than the second strategy matching threshold; When the strategy matching coefficient is lower than the first strategy matching threshold, the ability adjustment type is set to the multi-dimensional adjustment type; When the strategy matching coefficient is between the first strategy matching threshold and the second strategy matching threshold, the ability adjustment type is set to the two-dimensional adjustment type; When the strategy matching coefficient exceeds the second strategy matching threshold, the ability adjustment type is set to the one-dimensional adjustment type.

9. An employee competency analysis and adjustment system based on behavioral style, which is used to implement the employee competency analysis and adjustment method based on behavioral style according to any one of claims 1-8, and is characterized in that: It includes a behavior detection module, an adaptability scoring module, a contribution evaluation module, and a strategy reset module; The behavior detection module is used to analyze the time distribution characteristics of the employee behavior data, screen out the high-fluctuation time periods of the behavior data, and determine the behavior pattern and behavior weight input by the user terminal; The adaptability scoring module is used to score the adaptability of the employee behavior style, set the ability adjustment type according to the behavior style adaptability score, and generate a recommended strategy; The contribution evaluation module is used to send the recommended strategy to the user account, check whether the strategy matches, and if the strategy does not match, enter the contribution evaluation mechanism to evaluate the contribution of the user; The strategy reset module is used to reset the ability adjustment type according to the user contribution and generate a recommended strategy, and reset the strategy filling; The behavior detection module calculates the behavior average value and behavior intensity variance of each time period of the behavior data through the data analysis library; the adaptability scoring module calculates the behavior weight threshold and sets the weight coefficient through the historical database; the contribution evaluation module calculates the strategy matching coefficient through the support vector machine algorithm; The strategy reset module resets the ability adjustment type according to the contribution evaluation result and generates a recommended strategy.

Images