Dynamic Behavior Style Testing and Job Fit Screening and Evaluation Platform and Evaluation Method

Abstract

The present invention discloses a dynamic behavior style test and job suitability screening and evaluation platform and evaluation method, which relate to the technical field of job screening and evaluation, and are used to solve the problems of unclear candidate priority sorting and low job allocation resource utilization. The platform collects candidate dynamic behavior data and sets a default display ratio according to the number of enterprise positions in a shared interface, completes candidate marking and behavior change detection, classifies candidates based on behavior change and calculates job margins, generates behavior feature coefficients and adaptation levels, calculates behavior monitoring weight adjustment ratios through a convolutional neural network model, updates target monitoring weights and classification areas, combines with an interactive module, compares and interactively adjusts the behavior characteristics of active or stable area targets with job requirements, detects behavior intensity and frequency increments, determines whether monitoring transfer is needed, and improves the accuracy of job suitability.

Description

Technical Field

[0001] The present invention relates to the technical field of job screening and evaluation, and more specifically, to a dynamic behavior style test and job suitability screening and evaluation platform and evaluation method. Background Art

[0002] With the continuous advancement of intelligent human resource management, companies are gradually shifting from traditional static resume assessments to dynamic behavioral modeling and intelligent algorithm-assisted decision-making in talent screening, job matching, and behavior prediction. This is especially true in large enterprises or platform-based hiring environments, where the sheer number of positions and the complex, phased, contextual, and interactive nature of candidate behavior necessitate the use of real-time data collection, machine learning modeling, and dynamic assessment mechanisms to improve the accuracy and efficiency of job recommendations.

[0003] The existing technology has the following deficiencies:

[0004] Currently, most behavioral analysis systems focus solely on candidates' historical resume information, static scoring, or periodic assessments, lacking the ability to respond to changing behavioral trends in real time. This is particularly true given the dynamic changes in job resources and the dynamic adjustments in candidate behavioral styles. These systems often fail to promptly reflect the evolving match between individuals and positions. Furthermore, the behavioral differences between active and stable candidates are not effectively identified and quantified, leading to unclear candidate prioritization and low utilization of job allocation resources. Therefore, this paper proposes a dynamic behavioral style testing and job fit screening and assessment platform and method.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a dynamic behavioral style testing and job suitability screening and evaluation platform and evaluation method, which solves the problems raised in the above-mentioned background technology by using a multi-stage intelligent evaluation algorithm system that combines dynamic collection of behavioral data, area division and recognition, support vector machine modeling, convolutional neural network weighting and interactive feedback mechanism.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a dynamic behavioral style testing and job suitability screening and evaluation platform and evaluation method, comprising the following steps:

[0008] S1: Collect the candidate's dynamic behavior data, divide the shared interface into active areas and stable areas based on the collection results, and detect the change in the candidate's behavior in the active area;

[0009] S2: Candidates are classified as active or stable targets based on their behavioral changes within the active area. Targets are ranked by behavioral changes. The remaining positions and the number of candidates are combined to calculate the position surplus. The behavioral characteristic coefficient of each candidate is calculated based on the behavioral changes. The target adaptation level is determined based on the position surplus and the behavioral characteristic coefficient.

[0010] S3: Based on the amount of behavior change and the target adaptation level, a convolutional neural network model is constructed to calculate the behavior monitoring weight adjustment ratio. Based on the behavior monitoring weight adjustment ratio, the behavior monitoring weight of each target in the active area is adjusted and the classification area is updated. The number of target monitoring targets in the active area is determined for monitoring transfer.

[0011] S4: Use the interactive module to add interactive functions to active areas or stable areas, compare the behavioral characteristics of the marked target with the preset job requirements for interactive adjustment, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred.

[0012] In a preferred embodiment, the candidate's dynamic behavior data is the candidate's jump position on the sharing interface. When the candidate clicks an interactive key at a certain position on the sharing interface to jump, the position is recorded to generate the jump position on the sharing interface.

[0013] The shared interface is pre-divided into multiple areas according to the work content of the position. The area to which the candidate's jump position on the shared interface belongs is located. The total number of all jump positions in each area is counted, and the average value of the total number of jump positions in each area is calculated as the area classification threshold.

[0014] In a preferred embodiment, when the total number of all jump positions in a region exceeds the region classification threshold, the region is classified as an active region; when the total number of all jump positions in a region is lower than the region classification threshold, the region is classified as a stable region;

[0015] A period of time in the past is selected as the comparison period. The number of interaction key clicks by the candidate in the active area during the detection period is counted twice, and the difference between the secondary statistical results of the number of interaction key clicks is used as the change in the candidate's behavior in the active area.

[0016] In a preferred embodiment, the percentile method is used to set a percentage threshold to classify the candidates, the behavior change values of each candidate are compared, and the behavior change value that reaches the percentile ratio is selected as the percentage threshold;

[0017] When the candidate's behavior change value exceeds the percentage threshold, it is classified as an active target; when the candidate's behavior change value is lower than the percentage threshold, it is classified as a stable target;

[0018] The number of candidates classified as active targets is subtracted from the number of remaining positions to obtain the position surplus, and the logarithm of the behavioral change of each candidate is taken as the behavioral characteristic coefficient of the corresponding candidate.

[0019] In a preferred embodiment, the job margin and the behavioral characteristic coefficient are defined as inputs, and they are divided into different fuzzy sets respectively;

[0020] The target adaptation level is defined as the output variable and divided into fuzzy sets;

[0021] Formulate fuzzy rules to describe the impact of job margin and behavioral characteristic coefficient on target adaptation level;

[0022] Perform fuzzy reasoning based on fuzzy rules to determine the target setting level adaptation value.

[0023] In a preferred embodiment, the obtained behavior change amount and target adaptation level are substituted into the convolutional neural network model to obtain the monitoring weight adjustment ratio;

[0024] The behavior change is set as the candidate behavior feature vector; the target output of the convolutional neural network is the behavior monitoring weight adjustment ratio, and the steps are as follows:

[0025] Convert the input behavioral feature vector into a two-dimensional format;

[0026] Use one-dimensional convolution kernel to extract local behavior patterns;

[0027] Use maximum pooling to reduce feature dimensions and retain the main behavioral feature responses;

[0028] Flatten the pooled feature vector and input it into the fully connected network for feature fusion;

[0029] The final output behavior monitoring weight adjustment ratio;

[0030] According to the output adjustment ratio, the behavior monitoring weight is updated in combination with the original behavior monitoring weight.

[0031] In a preferred embodiment, based on updating the behavior monitoring weight, a weight threshold is introduced;

[0032] If the updated behavior monitoring weight is greater than or equal to the weight threshold, the active area corresponding to the current candidate will continue to be maintained; if the updated behavior monitoring weight is less than the weight threshold, the active area corresponding to the current candidate will be updated to a stable area;

[0033] The number of candidates in the current active area after the updated classification is counted and compared with the preset maximum active target monitoring number; if the number of candidates in the current active area is greater than the preset maximum active target monitoring number, the monitoring transfer is executed.

[0034] In a preferred embodiment, during the comparison and interactive adjustment of interactive functions, for active regional candidates, candidate behavior feature vectors and job requirement vectors are constructed;

[0035] Substitute the candidate's behavioral feature vector and the job requirement vector into the inverse Euclidean distance formula to obtain the matching degree between the candidate and the job's behavioral feature;

[0036] The matching degree between the behavioral characteristics of each candidate and the position is compared with the preset matching critical threshold. If the matching degree between the behavioral characteristics of the candidate and the position is less than the matching critical threshold, it is considered that the match is insufficient and interactive adjustment is required.

[0037] In a preferred embodiment, statistics are collected for the candidate's behavioral events within the time window, and the behavioral dimensions corresponding to each behavioral event are traversed and statistically analyzed to obtain the behavioral intensity of the marked target;

[0038] Count the candidate's behavior triggering frequency in the current time window and the previous time window, calculate the difference between the behavior triggering frequency in the current time window and the behavior triggering frequency in the previous time window, and then calculate the ratio with the behavior triggering frequency in the previous time window to obtain the behavior frequency increment of the marked target;

[0039] The behavioral intensity and behavioral frequency increment of the marked target are standardized and substituted into the polynomial regression calculation to obtain the behavioral fluctuation response coefficient;

[0040] The behavioral fluctuation response coefficient is compared with the preset fluctuation threshold. If the behavioral fluctuation response coefficient is greater than or equal to the fluctuation threshold, it is considered that the current candidate's behavioral characteristics have an obvious trend of change, and the candidate will be transferred for monitoring. If the behavioral fluctuation response coefficient is less than the fluctuation threshold, it is considered that the candidate's behavioral state is stable and the trend is normal, and there is no need to trigger monitoring transfer.

[0041] The dynamic behavior style test and job suitability screening and assessment platform includes a data acquisition module, a behavior analysis module, a model training module, and an interaction module, with signal connections between each module;

[0042] The data collection module is used to collect dynamic behavioral data of candidates, divide the shared interface into active areas and stable areas based on the collection results, and detect the changes in the candidate's behavior in the active area;

[0043] The behavior analysis module is used to calculate the change in candidate behavior within the active area, classify candidates as active targets or stable targets, sort the target behavior intensity, calculate the position surplus based on the number of remaining positions, calculate the behavior characteristic coefficient, and set the target adaptation level;

[0044] The model training module is used to build a convolutional neural network model based on the amount of behavior change and the adaptation level, output the behavior monitoring weight adjustment ratio, adjust the candidate monitoring weight according to the ratio, update the classification area, and determine the monitoring transfer;

[0045] The interactive module is used to compare the behavioral characteristics of the marked target with the preset job requirements for interactive adjustment, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred.

[0046] The technical effects and advantages of the present invention are as follows:

[0047] 1. The present invention collects dynamic behavioral data of candidates, divides the shared interface, marks all candidates, detects the behavioral changes of marked candidates in the active area and classifies the marked candidates, sorts the targets, calculates the position surplus based on the remaining number of positions and the number of candidates, calculates the behavioral characteristic coefficient of each candidate according to the behavioral change, sets the target adaptation level, constructs a convolutional neural network model according to the behavioral change and the target adaptation level to calculate the behavior monitoring weight adjustment ratio, adjusts the behavior monitoring weight of each target in the active area according to the behavior monitoring weight adjustment ratio and updates the classification area, uses an interactive module to add interactive functions to the active area or stable area, compares the behavioral characteristics of the marked target with the preset position requirements for interactive adjustment, detects the behavioral intensity and behavior frequency increment of the marked target, and determines whether the target needs to be monitored and transferred, thereby improving the accuracy of position adaptation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a diagram of the steps for implementing the dynamic behavior style testing and job suitability screening and evaluation method of the present invention.

[0049] Figure 2 This is a module diagram of the dynamic behavior style testing and job suitability screening and evaluation platform of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] Example 1: Please refer to Figure 1 , dynamic behavioral style test and job suitability screening and evaluation method, the specific operation process is as follows:

[0052] Step S1: Collect the candidate's dynamic behavior data, divide the shared interface into active areas and stable areas based on the collected data, and detect the change in the candidate's behavior in the active area;

[0053] Step S2: Classify candidates as active or stable targets based on their behavioral changes within the active area. Rank targets based on their behavioral changes. Calculate the position surplus based on the number of remaining positions and the number of candidates. Calculate the behavioral characteristic coefficient for each candidate based on their behavioral changes. Combine the position surplus and the behavioral characteristic coefficient to determine the target adaptation level.

[0054] Step S3: Construct a convolutional neural network model based on the behavior change amount and the target adaptation level to calculate the behavior monitoring weight adjustment ratio. Adjust the behavior monitoring weight of each target in the active area based on the behavior monitoring weight adjustment ratio and update the classification area. Determine the number of target monitoring in the active area for monitoring transfer.

[0055] Step S4: Use the interactive module to add interactive functions to the active area or stable area, compare the behavioral characteristics of the marked target with the preset job requirements, make interactive adjustments, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred;

[0056] The specific implementation is as follows:

[0057] In step S1: the candidate's dynamic behavior data is the candidate's jump position on the sharing interface. The jump position is recorded when the candidate clicks the interactive button at a certain position on the sharing interface to jump.

[0058] The shared interface is pre-divided into multiple regions based on the job content of the position. The region to which the candidate's jump position on the shared interface belongs is located. The total number of all jump positions in each region is counted, and the average of the total number of jump positions in each region is calculated as the region classification threshold.

[0059] When the total number of all jump positions in a region exceeds the region classification threshold, the region is classified as an active region; when the total number of all jump positions in a region is lower than the region classification threshold, the region is classified as a stable region.

[0060] Select a past period as a comparison period, detect the candidate's behavior data in the active area during the comparison period, the candidate's behavior data in the active area being the number of interaction key clicks by the candidate in the active area, count the number of interaction key clicks by the current candidate in the active area and obtain the statistical results;

[0061] A period of time with the same time interval as the comparison time is selected as the change time. The number of interaction key clicks of the candidate in the active area during the change time is detected and counted twice. The difference between the secondary statistical results of the number of interaction key clicks is used as the change amount of the candidate's behavior in the active area.

[0062] It should be noted that a shared interface refers to an interactive interface shared among multiple users or devices, allowing users to jointly access, operate and view information.

[0063] In step S2, the percentile method is used to set a percentage threshold to classify the candidates, N% is set as the percentile ratio, the behavior change values of each candidate are compared, and the behavior change value that reaches the percentile ratio is selected as the percentage threshold.

[0064] For example, if the percentile ratio is set to 60%, the behavior change values with a value greater than 60% of the behavior change values are selected as the percentage threshold.

[0065] When the candidate's behavior change value exceeds the percentage threshold, it is classified as an active target; when the candidate's behavior change data is lower than the percentage threshold, it is classified as a stable target.

[0066] The number of candidates classified as active targets is subtracted from the number of remaining positions to obtain the remaining positions. The logarithm of the change in each candidate's behavior is used as the corresponding candidate's behavioral characteristic coefficient.

[0067] The target adaptation level is set by using fuzzy reasoning based on the comprehensive job margin and behavioral characteristic coefficient. The specific steps are as follows:

[0068] The job margin and behavioral characteristic coefficients are defined as inputs and divided into different fuzzy sets respectively.

[0069] For example, the job surplus is divided into two fuzzy sets of "more" and "less", and the behavior characteristic coefficient is divided into two fuzzy sets of "large" and "small".

[0070] The target configuration level is defined as the output and divided into different fuzzy sets.

[0071] For example, the target configuration level is divided into multiple fuzzy sets such as "1", "2", and "3".

[0072] Formulate a set of fuzzy rules to describe the impact of different input variables on the output variable.

[0073] For example, when the number of job openings is "many" and the candidate's behavioral characteristic coefficient is "large", the target allocation level is "1";

[0074] When the job vacancies are "many" or the candidate's behavioral characteristic coefficient is "large", the target allocation level is "2";

[0075] When the number of job openings is "small" and the candidate's behavioral characteristic coefficient is "small", the target allocation level is "3".

[0076] Fuzzy reasoning is performed according to fuzzy rules to determine the target setting level adaptation value.

[0077] It should be noted that the set classification of job surplus and behavioral characteristic coefficients in the fuzzy set can be judged by setting thresholds according to actual conditions. For example, when the job surplus exceeds 10, it is classified as "many", and when the behavioral characteristic coefficient exceeds 0.5, it is classified as "large", etc., which will not be elaborated here.

[0078] In step S3, the obtained behavior change amount and target adaptation level are substituted into the convolutional neural network model to obtain the monitoring weight adjustment ratio;

[0079] The amount of behavioral change is set as the candidate's behavioral feature vector;

[0080] Among them, the target output of the convolutional neural network is the behavior monitoring weight adjustment ratio, which is expressed as:

[0081] in, Represents the adjustment coefficient of the candidate's current monitoring weight, which is used for subsequent weight updates;

[0082] Input layer: The input behavior feature vector is converted into a two-dimensional format through reshape to facilitate one-dimensional convolution processing;

[0083] Convolutional layer: uses a one-dimensional convolution kernel, sets the window size to k, and sets the sliding step size to s to extract local behavior patterns: ;

[0084] Where, is the activation function (such as ReLU), is the bias term, is the i-th value in the convolution output feature map;

[0085] It should be noted that the convolution kernel size, sliding step size, and number of convolution kernels used in the convolution layer are not limited to the specific values in the above embodiment. In actual applications, they can be flexibly configured according to the length, dimensionality complexity, and model fitting performance of the candidate's behavioral features.

[0086] For example, the convolution kernel size can be set to odd lengths such as 3, 5, or 7, and the sliding step size can be set to 1 or 2 to balance the locality of feature extraction and computational efficiency, which will not be described here.

[0087] Pooling layer: Use maximum pooling or average pooling to reduce feature dimensions and retain the main behavioral feature responses; ;

[0088] Where m is the pooling window size;

[0089] It should be noted that in the pooling layer, the dimensionality reduction processing method for behavioral features can adopt maximum pooling or average pooling, or a combination of the two pooling operations can be used based on the target task to enhance the feature expression ability. Different pooling methods have different retention strategies for feature responses. This experimenter can select the most appropriate strategy based on the discrete characteristics of the candidate's behavioral change amplitude, which will not be elaborated here.

[0090] Fully connected layer: flattens the pooled feature vector and inputs it into the fully connected network for feature fusion; ;

[0091] Where, is the concatenated vector output by the pooling layer, is the fully connected weight matrix, is the bias term, is the activation function (such as Sigmoid);

[0092] Output layer: final output behavior monitoring weight adjustment ratio;

[0093] ;

[0094] Where, is the output layer weight, is the output layer bias, is the Sigmoid function;

[0095] It should be noted that the activation functions used in the convolutional layer and the fully connected layer are not limited to ReLU or Sigmoid functions. In actual implementation, common neural network activation functions such as Leaky ReLU, Tanh or Swish can also be used to further optimize the network's nonlinear expression ability and convergence stability. We will not go into details here.

[0096] Furthermore, the model training steps are:

[0097] Data preparation: Building training data.

[0098] Loss function definition: Mean square error (MSE) is used as the loss function: ;

[0099] Where, Adjust the proportion of the targets marked according to the actual effect of behavioral evolution;

[0100] Backpropagation and optimization: use Adam or SGD optimizer for parameter update;

[0101] Model evaluation and iteration: Optimize network structure and hyperparameters based on validation set metrics (such as RMSE and MAE), which will not be described in detail here;

[0102] According to the output adjustment ratio, combined with the original behavior monitoring weight, the behavior monitoring weight is updated. The specific calculation is as follows: ;

[0103] Where, To adjust the ratio, is the original behavior monitoring weight, is the updated behavior monitoring weight, is an adjustable weight amplification factor;

[0104] Based on the update behavior monitoring weight, a weight threshold is introduced to determine whether each target in the active area updates its classification area;

[0105] The weight threshold was obtained by our experimenters based on the distribution characteristics of historical behavior monitoring data and the results of job response sensitivity assessment, and will not be elaborated here.

[0106] If the updated behavior monitoring weight is greater than or equal to the weight threshold, the active area corresponding to the current candidate continues to be maintained;

[0107] If the updated behavior monitoring weight is less than the weight threshold, the active area corresponding to the current candidate is updated to a stable area;

[0108] Count the number of candidates in the current active area after the updated classification, and monitor the number compared with the preset maximum active target;

[0109] If the number of candidates in the current active area is greater than the preset maximum number of active target monitoring, the monitoring transfer is performed;

[0110] It should be noted that the preset maximum number of active target monitoring is obtained by the experimenters based on the system processing capacity and historical task resource configuration, and will not be elaborated here;

[0111] Among them, monitoring transfer means that when the number of candidates in the current active area exceeds the preset maximum number of active target monitoring, the system determines the candidate targets with relatively low priority based on the candidate's updated behavior monitoring weight, target adaptation level or historical behavior response frequency, and transfers them from the current active area to free up monitoring resources and ensure the real-time monitoring performance of high-priority targets. It will not be elaborated here;

[0112] Optionally, monitoring transfer includes but is not limited to the following methods: reclassifying some candidates into the stable area, suspending their high-frequency behavior monitoring, reducing their monitoring frequency or adjusting their behavior feature sampling period, and temporarily removing them from the behavior weight dynamic adjustment mechanism and entering a static observation state;

[0113] In step S4, after the candidate is classified into the active area or the stable area, the interaction module is used to provide an interactive feedback mechanism, behavior adjustment suggestions, guidance prompts and task incentive strategies based on the match between the candidate's current behavior characteristics and the target position requirements, so as to achieve adaptive optimization of the candidate's behavior style;

[0114] Furthermore, the interaction module may include a behavior comparison and analysis unit, a prompt generation unit, a feedback receiving unit, and a task push unit, supporting targeted intervention and interactive optimization based on behavior characteristics, which will not be described in detail here;

[0115] Among them, the interactive functions include behavioral suggestion prompts, task training push, behavioral feedback recording, behavioral performance tracking and dynamic correction of matching degree, etc., which will not be detailed here;

[0116] Among them, in the comparison and interactive adjustment of interactive functions, for candidates in active areas, candidate behavior feature vectors and job demand vectors are constructed;

[0117] It should be noted that the above active area candidates refer to candidates corresponding to the update behavior monitoring weight greater than or equal to the weight threshold, which will not be elaborated here;

[0118] Substitute the candidate's behavioral feature vector and the job requirement vector into the inverse Euclidean distance formula to obtain the matching degree between the candidate and the job's behavioral feature;

[0119] Specifically, the inverse formula of Euclidean distance is expressed as follows: ;

[0120] Where, is the behavioral matching score between candidate i and position k, is the number of behavioral feature dimensions, is the characteristic value of candidate i on the jth behavioral dimension, is the ideal demand value of position k for the jth behavioral dimension, is the weight of the jth behavioral dimension, and the larger the value, the more important the dimension;

[0121] Compare the matching degree between each candidate and the position's behavioral characteristics with the preset matching threshold. If the matching degree between the candidate and the position's behavioral characteristics is less than the matching threshold, it is considered insufficient and interactive adjustment is required.

[0122] Specifically, interactive adjustments can be based on interactive prompts and guidance mechanisms. Optionally, when the degree of match between a candidate and the position's behavioral characteristics is less than a critical matching threshold, suggestions can be made to the corresponding candidate on the interactive interface to guide the candidate to strengthen or improve certain key behavioral characteristics. An example is as follows:

[0123] If the position expects high behavioral consistency, but the candidate's performance is relatively low, the interactive prompt will read: "It is recommended to improve stability and consistency in task execution."

[0124] Furthermore, the interactive module can provide dynamic behavioral feedback training tasks to help improve the score of this feature;

[0125] Preferably, the behavior adjustment is recorded after each interaction and the behavior feature vector is updated for the next round of evaluation in a multi-round evaluation application scenario;

[0126] It should be noted that the critical matching threshold was obtained by our experimenters based on the statistical analysis results of a large sample matching experiment and the actual job adaptation feedback performance, and will not be elaborated here;

[0127] The behavioral intensity of the marked target is the behavioral intensity of the corresponding candidate in the subsequent time window, which needs to be judged and interactively adjusted. It is used to measure the amplitude of the candidate's behavioral activities or the comprehensive weight of behavioral events in a unit of time. Its acquisition logic is to count the behavioral events of the candidate in the time window, traverse the behavioral dimensions corresponding to each behavioral event, and perform statistics to obtain the behavioral intensity of the marked target;

[0128] The time window refers to the fixed observation period used to calculate the behavior intensity and behavior frequency increments. It is set according to the system task rhythm and behavior evaluation frequency, and will not be detailed here.

[0129] The behavior frequency increment of the marked target requires interactive adjustment of the corresponding candidate's behavior frequency in the subsequent time window. Its acquisition logic is to count the candidate's behavior triggering frequency in the current time window and the previous time window, calculate the difference between the behavior triggering frequency in the current time window and the behavior triggering frequency in the previous time window, and then calculate the ratio with the behavior triggering frequency in the previous time window to obtain the behavior frequency increment of the marked target;

[0130] Among them, the time length corresponding to the previous time window is consistent with the time length corresponding to the current time window set by the experimenter, which will not be repeated here;

[0131] The behavioral intensity and behavioral frequency increment of the marked target are standardized and substituted into the polynomial regression calculation to obtain the behavioral fluctuation response coefficient;

[0132] It should be noted that the standardization methods include but are not limited to standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function. The application methods of standardization are not described in detail here.

[0133] The polynomial regression calculation formula is as follows: ;

[0134] Where, is the behavioral fluctuation response coefficient, To mark the target's behavioral intensity, To mark the target behavior frequency increment, is a constant term, and are the weights of the target's behavioral intensity and the target's behavioral frequency increment, respectively. The specific weight values are set by our experimenters based on the principle of minimizing the fitting error of large-scale behavioral trajectory samples and the regression residual constraint conditions of the job adaptation feedback model, and will not be elaborated here;

[0135] Compare the behavioral fluctuation response coefficient with the preset fluctuation threshold. If the behavioral fluctuation response coefficient is greater than or equal to the fluctuation threshold, it is considered that the current candidate's behavioral characteristics have a significant trend of change, and the candidate will be transferred to monitoring. If the behavioral fluctuation response coefficient is less than the fluctuation threshold, the candidate's behavioral status is considered stable and the trend is normal, and there is no need to trigger monitoring transfer;

[0136] It should be noted that the fluctuation threshold was obtained by our experimenters based on the distribution statistical characteristics of historical behavior fluctuation samples and the critical tolerance interval of the job adaptation tolerance model, which will not be elaborated here;

[0137] Specifically, monitoring transfer has been described in the above content and will not be repeated here;

[0138] Example 2: Please refer to Figure 2 ,Dynamic behavior style testing and job suitability screening and evaluation platform, including data acquisition module, behavior analysis module, model training module and interaction module, and signal connection between each module;

[0139] The data collection module is used to collect dynamic behavioral data of candidates, divide the shared interface into active areas and stable areas based on the collection results, and detect the changes in the candidate's behavior in the active area;

[0140] The behavior analysis module is used to calculate the change in candidate behavior within the active area, classify candidates as active targets or stable targets, sort the target behavior intensity, calculate the position surplus based on the number of remaining positions, calculate the behavior characteristic coefficient, and set the target adaptation level;

[0141] The model training module is used to build a convolutional neural network model based on the amount of behavior change and the adaptation level, output the behavior monitoring weight adjustment ratio, adjust the candidate monitoring weight according to the ratio, update the classification area, and determine the monitoring transfer;

[0142] The interactive module is used to compare the behavioral characteristics of the marked target with the preset job requirements for interactive adjustment, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred.

[0143] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0144] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. 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 program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. 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 data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0145] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0146] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0147] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0149] Those skilled in the art will 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 aforementioned method embodiments and will not be repeated here.

[0150] In the 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 schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0152] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] If the 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 the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0154] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. Dynamic behavioral style testing and job suitability screening and assessment method, characterized by: The steps include: S1: Collect the candidate's dynamic behavior data, divide the shared interface into active areas and stable areas based on the collection results, and detect the change in the candidate's behavior in the active area; S2: Candidates are classified as active or stable targets based on their behavioral changes within the active area. Targets are ranked by behavioral changes. The remaining positions and the number of candidates are combined to calculate the position surplus. The behavioral characteristic coefficient of each candidate is calculated based on the behavioral changes. The target adaptation level is determined based on the position surplus and the behavioral characteristic coefficient. S3: Based on the amount of behavior change and the target adaptation level, a convolutional neural network model is constructed to calculate the behavior monitoring weight adjustment ratio. Based on the behavior monitoring weight adjustment ratio, the behavior monitoring weight of each target in the active area is adjusted and the classification area is updated. The number of target monitoring targets in the active area is determined for monitoring transfer. S4: Use the interactive module to add interactive functions to active areas or stable areas, compare the behavioral characteristics of the marked target with the preset job requirements, make interactive adjustments, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred; Dynamic behavior data is the candidate's jump location on the sharing interface; The behavior change is obtained by subtracting the secondary statistical results of the number of interactive key clicks, and the logarithm of each candidate's behavior change is used as the behavior characteristic coefficient of the corresponding candidate; Count the candidate's behavioral events within the time window, traverse the behavioral dimensions corresponding to each behavioral event, and perform statistics to obtain the behavioral intensity of the marked target; Count the candidate's behavior triggering frequency in the current time window and the previous time window, calculate the difference between the behavior triggering frequency in the current time window and the behavior triggering frequency in the previous time window, and then calculate the ratio with the behavior triggering frequency in the previous time window to obtain the behavior frequency increment of the marked target; A time window is a preset fixed observation period used to calculate behavior intensity and behavior frequency increments.

2. The dynamic behavioral style test and job suitability screening and assessment method according to claim 1, characterized in that: The dynamic behavior data of the candidate is the jump position of the candidate on the sharing interface. When the candidate clicks the interactive button at a certain position on the sharing interface to jump, the position is recorded to generate the jump position of the sharing interface; The shared interface is pre-divided into multiple areas according to the work content of the position. The area to which the candidate's jump position on the shared interface belongs is located. The total number of all jump positions in each area is counted, and the average value of the total number of jump positions in each area is calculated as the area classification threshold.

3. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 2 is characterized by: When the total number of all jump positions in a region exceeds the region classification threshold, the region is classified as an active region; when the total number of all jump positions in a region is lower than the region classification threshold, the region is classified as a stable region; A period of time in the past is selected as the comparison period. The number of interaction key clicks by the candidate in the active area during the detection period is counted twice, and the difference between the secondary statistical results of the number of interaction key clicks is used as the change in the candidate's behavior in the active area.

4. The dynamic behavioral style test and job suitability screening and assessment method according to claim 3, characterized in that: Use the percentile method to set a percentage threshold to classify candidates, compare the behavioral change values of each candidate, and select the behavioral change value that reaches the percentile ratio as the percentage threshold; When the candidate's behavior change value exceeds the percentage threshold, it is classified as an active target; when the candidate's behavior change value is lower than the percentage threshold, it is classified as a stable target; The number of candidates classified as active targets is subtracted from the number of remaining positions to obtain the position surplus, and the logarithm of the behavioral change of each candidate is taken as the behavioral characteristic coefficient of the corresponding candidate.

5. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 4 is characterized by: Define job margin and behavior characteristic coefficient as input and divide them into different fuzzy sets respectively; The target adaptation level is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of job margin and behavioral characteristic coefficient on target adaptation level; Perform fuzzy reasoning based on fuzzy rules to determine the target setting level adaptation value.

6. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 5, characterized in that: Substitute the obtained behavior change and target adaptation level into the convolutional neural network model to obtain the monitoring weight adjustment ratio; The behavior change is set as the candidate behavior feature vector; the target output of the convolutional neural network is the behavior monitoring weight adjustment ratio, and the steps are as follows: Convert the input behavioral feature vector into a two-dimensional format; Use one-dimensional convolution kernel to extract local behavior patterns; Use maximum pooling to reduce feature dimensions and retain the main behavioral feature responses; Flatten the pooled feature vector and input it into the fully connected network for feature fusion; The final output behavior monitoring weight adjustment ratio; According to the output adjustment ratio, the behavior monitoring weight is updated in combination with the original behavior monitoring weight.

7. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 6, characterized in that: Based on the updated behavior monitoring weight, a weight threshold is introduced; If the updated behavior monitoring weight is greater than or equal to the weight threshold, the active area corresponding to the current candidate will continue to be maintained; if the updated behavior monitoring weight is less than the weight threshold, the active area corresponding to the current candidate will be updated to a stable area; Count the number of candidates in the current active area after the updated classification, and monitor the number compared with the preset maximum active target; If the number of candidates in the current active area is greater than the preset maximum number of active target monitoring, monitoring transfer is performed.

8. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 1 is characterized by: In the comparison and adjustment of interactive functions, for candidates in active areas, we construct candidate behavior feature vectors and job requirement vectors; Substitute the candidate's behavioral feature vector and the job requirement vector into the inverse Euclidean distance formula to obtain the matching degree between the candidate and the job's behavioral feature; The matching degree between the behavioral characteristics of each candidate and the position is compared with the preset matching critical threshold. If the matching degree between the behavioral characteristics of the candidate and the position is less than the matching critical threshold, it is considered that the match is insufficient and interactive adjustment is required.

9. The dynamic behavioral style test and job suitability screening and evaluation method according to claim 8, characterized in that: The behavioral intensity and behavioral frequency increment of the marked target are standardized and substituted into the polynomial regression calculation to obtain the behavioral fluctuation response coefficient; The behavioral fluctuation response coefficient is compared with the preset fluctuation threshold. If the behavioral fluctuation response coefficient is greater than or equal to the fluctuation threshold, it is considered that the current candidate's behavioral characteristics have an obvious trend of change, and the candidate will be transferred for monitoring. If the behavioral fluctuation response coefficient is less than the fluctuation threshold, it is considered that the candidate's behavioral state is stable and the trend is normal, and there is no need to trigger monitoring transfer.

10. A dynamic behavioral style test and job suitability screening and evaluation platform, for implementing the dynamic behavioral style test and job suitability screening and evaluation method according to any one of claims 1 to 9, characterized in that: It includes data acquisition module, behavior analysis module, model training module and interaction module, and the signal connections between each module; The data collection module is used to collect dynamic behavioral data of candidates, divide the shared interface into active areas and stable areas based on the collection results, and detect the changes in the candidate's behavior in the active area; The behavior analysis module is used to calculate the change in candidate behavior within the active area, classify candidates as active targets or stable targets, sort the target behavior intensity, calculate the position surplus based on the number of remaining positions, calculate the behavior characteristic coefficient, and set the target adaptation level; The model training module is used to build a convolutional neural network model based on the amount of behavior change and the adaptation level, output the behavior monitoring weight adjustment ratio, adjust the candidate monitoring weight according to the ratio, update the classification area, and determine the monitoring transfer; The interactive module is used to compare the behavioral characteristics of the marked target with the preset job requirements for interactive adjustment, detect the behavioral intensity and behavioral frequency increment of the marked target, and determine whether the target needs to be monitored and transferred.

Images