Concrete affirmation method and system based on duty performance behavior

Abstract

The invention discloses a concrete affirmation method and system based on job performance behaviors. The credibility of a behavior combination is defined based on job performance evaluation logic and a plurality of job performance behaviors; and dividing into a core combination, a common combination and an edge combination based on each behavior combination and the distribution hierarchy of the credibility. Defining the behavior level of the to-be-evaluated person based on the weight distribution table and the behavior evaluation result of the to-be-evaluated person within the preset time; matching a corresponding equivalent logic based on the behavior level, determining a corresponding behavior determination result according to the behavior set of the to-be-evaluated person and the equivalent logic, and defining an influence parameter based on the behavior determination result and a reference result output by a determination learning model, and according to the influence parameters and the behavior determination result, a final behavior determination result is defined, so that multiple optimization is performed on the behavior determination result, the accuracy of the final behavior determination result is ensured, and equivalent logic control is performed on the behavior set of the to-be-evaluated person.

Description

Technical Field

[0001] The present invention relates to the technical field of job performance behavior, and in particular to a method and system for concrete identification based on job performance behavior. Background Art

[0002] Human resource assessment and evaluation method is an important method to evaluate the performance of established objects in the process of human resource management. The evaluation results of human resource assessment and evaluation also occupy an important position in the results of human resource assessment.

[0003] With the development of science and technology, the identification of talents has gradually adopted the method of concrete performance evaluation. Different performance behaviors are placed in scenarios for corresponding assessment. In the existing technology, a separate performance identification is conducted for the performance behavior of the person to be evaluated, and the performance identification result is controlled in a single dimension. As a result, the existing technology does not fully consider the multiple optimization of the behavior identification results, nor does it have corresponding equivalent identification control for the performance behavior. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a concrete identification method and system based on job performance behavior, which collects a behavior set of a person to be evaluated, and constructs multiple behavior combinations based on the behavior set; in each behavior combination, the corresponding job performance dimensions are matched for the multiple job performance behaviors in the behavior combination; the corresponding job performance evaluation logic is defined according to the job performance dimension, and the credibility of the behavior combination is defined based on the job performance evaluation logic and the multiple job performance behaviors; the credibility of each behavior combination is collected, and is divided into core combinations, ordinary combinations and edge combinations based on the distribution level of each behavior combination and credibility, so as to facilitate the division of each behavior combination, and is divided into core combinations, ordinary combinations and edge combinations in combination with the distribution level of credibility, so as to further process the core combinations, ordinary combinations and edge combinations.

[0005] Furthermore, a corresponding weight distribution table is defined according to the core combination, the common combination and the edge combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; the corresponding equivalent logic is matched based on the behavior level, and the corresponding behavior identification result is determined according to the behavior set of the person to be evaluated and the equivalent logic, the influencing parameters are defined based on the behavior identification results and the reference results output by the identification learning model, and the final behavior identification result is defined according to the influencing parameters and the behavior identification results, so as to facilitate multiple optimizations of the behavior identification results and ensure the accuracy of the final behavior identification results. At the same time, the behavior set of the person to be evaluated is controlled by equivalent logic, so as to facilitate equivalent control of each performance behavior and ensure the accuracy of the behavior identification results.

[0006] In order to solve the above technical problems, the embodiment of the present invention provides a concrete identification method based on job performance behavior, which is applied to the identification scenario of concrete behavior;

[0007] The concrete identification method based on job performance behavior includes:

[0008] Collect the behavior set of the person to be evaluated, and construct multiple behavior combinations based on the behavior set;

[0009] In each behavior combination, the corresponding performance dimension is matched for the multiple performance behaviors in the behavior combination;

[0010] Define the corresponding job performance evaluation logic according to the job performance dimension, and define the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors;

[0011] Collect the credibility of each behavior combination, and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility;

[0012] A corresponding weight distribution table is defined according to the core combination, the common combination and the marginal combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time;

[0013] Based on the equivalent logic corresponding to the behavior level matching, and according to the behavior set of the person to be evaluated and the equivalent logic, the corresponding behavior identification result is determined, and the influence parameters are defined based on the behavior identification result and the reference result output by the identification learning model. The final behavior identification result is defined based on the influence parameters and the behavior identification result.

[0014] Optionally, the collecting of a behavior set of the person to be evaluated and constructing a plurality of behavior combinations according to the behavior set include:

[0015] Mark the person to be evaluated, and democratically evaluate and match multiple behaviors associated with the person to be evaluated based on the person's mark and job performance;

[0016] Construct a set of behaviors of the personnel to be evaluated based on multiple performance situations;

[0017] The combined factors corresponding to the performance status marks of each job performance in the behavior set of the person to be evaluated;

[0018] Multiple behavior combinations are constructed based on the labels of the combination factors and the behavior sets of the persons to be evaluated. In the same behavior combination, the combination factors of multiple job performance situations match each other.

[0019] Optionally, in each behavior combination, matching corresponding job performance dimensions for multiple job performance behaviors in the behavior combination includes:

[0020] Freeze each behavior combination;

[0021] Perform positioning detection for each behavior combination;

[0022] In each behavior combination, select the corresponding performance situation of the performance behavior;

[0023] Divide multiple behavior nodes based on the performance of the job performance behavior, and define multiple job performance behaviors according to the multiple behavior nodes to output multiple job performance behaviors in the behavior combination;

[0024] Matching corresponding job performance types according to multiple job performance behaviors in the behavior combination;

[0025] The corresponding job performance dimension is matched based on the job performance type and the location of the job performance behavior.

[0026] Optionally, defining a corresponding job performance evaluation logic according to the job performance dimension, and defining the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors, includes:

[0027] Determine the performance dimension of job performance;

[0028] Define the corresponding job performance evaluation logic based on job performance dimensions and the previous strategic habits of the person to be evaluated;

[0029] In the same behavior combination, an optimization coefficient is defined based on the dimensional differences between multiple job performance dimensions, and the optimization coefficient is associated with the job performance evaluation logic to output the optimized job performance evaluation logic;

[0030] Associate optimized job performance evaluation logic and multiple job performance behaviors;

[0031] The credibility of the behavior combination is defined based on the optimized job performance evaluation logic and multiple job performance behaviors.

[0032] Optionally, the collecting of the credibility of each behavior combination and the division of each behavior combination and the distribution level of the credibility into a core combination, a common combination and a marginal combination include:

[0033] Collect the credibility of multiple behavior combinations, and build a corresponding credibility set based on the credibility of the multiple behavior combinations;

[0034] Defining the distribution level of credibility based on credibility set and credibility distribution mechanism;

[0035] Associate each behavior combination with a distribution hierarchy of credibility;

[0036] According to the distribution level of each behavior combination and credibility, it is divided into core combination, common combination and marginal combination, and each behavior combination is classified. At the same time, interaction testing is carried out based on the core combination, common combination and marginal combination, and the division of core combination, common combination and marginal combination is clearly defined in the interaction test.

[0037] Optionally, the step of defining a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time, includes:

[0038] Associate core combinations, common combinations, and edge combinations;

[0039] Match the corresponding weights based on the core combination, common combination and edge combination.

[0040] Optionally, the method of defining a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time, further includes:

[0041] Collecting the behavioral weights of the persons to be evaluated within a preset time, and associating the behavioral weights of the persons to be evaluated within the preset time with a weight distribution table;

[0042] Define the behavior grading mechanism based on the behavior preference of the person to be evaluated within a preset time and the weight distribution table;

[0043] The mechanism for classifying related behaviors and the behavior evaluation results of the persons to be evaluated within a preset time;

[0044] The behavior level of the person to be evaluated is defined according to the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time.

[0045] Optionally, the equivalent logic corresponding to the behavior level matching is determined based on the behavior set of the person to be evaluated and the equivalent logic, the corresponding behavior identification result is determined based on the behavior identification result and the reference result output by the identification learning model, and the final behavior identification result is defined based on the influence parameter and the behavior identification result, including:

[0046] Determine the behavioral level of the person to be evaluated;

[0047] Match the corresponding equivalent logic according to the behavior level and the behavior equivalent logic table;

[0048] The association data is the set of behaviors of the person to be evaluated and the equivalent logic;

[0049] The corresponding behavior identification result is determined based on the behavior set of the person to be evaluated and the equivalent logic.

[0050] Optionally, the equivalent logic corresponding to the behavior level matching is determined based on the behavior set of the person to be evaluated and the equivalent logic, the corresponding behavior identification result is determined based on the behavior identification result and the reference result output by the identification learning model, and the final behavior identification result is defined based on the influence parameter and the behavior identification result, and further includes:

[0051] Perform anomaly detection on the behavior identification results and output multiple behavior anomaly factors in the behavior identification results;

[0052] Matching corresponding result optimization logic based on multiple abnormal behavior factors, and optimizing based on the result optimization logic and the behavior identification results to output optimized behavior identification results;

[0053] Associating the optimized behavior identification results with the reference results output by the identification learning model; defining influencing parameters based on the optimized behavior identification results and the reference results output by the identification learning model; and defining the final behavior identification results based on the influencing parameters and the behavior identification results.

[0054] In addition, the embodiment of the present invention also provides a method and system for concrete identification based on job performance behavior, and the precise two-way matching system for people and positions includes:

[0055] The collection module is used to collect the behavior set of the person to be evaluated and construct multiple behavior combinations based on the behavior set;

[0056] A matching module, for matching corresponding job performance dimensions in each behavior combination for multiple job performance behaviors in the behavior combination;

[0057] The credibility module is used to define the corresponding performance evaluation logic according to the performance dimension, and define the credibility of the behavior combination based on the performance evaluation logic and multiple performance behaviors;

[0058] The combination module is used to collect the credibility of each behavior combination and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility;

[0059] The behavior grade module is used to define a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and define the behavior grade of the person to be evaluated based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time;

[0060] The behavior identification module is used to match the corresponding equivalent logic based on the behavior level, and determine the corresponding behavior identification result based on the behavior set and the equivalent logic of the person to be evaluated, define the influencing parameters based on the behavior identification result and the reference result output by the identification learning model, and define the final behavior identification result based on the influencing parameters and the behavior identification result.

[0061] In an embodiment of the present invention, through the method in the embodiment of the present invention, a behavior set of the person to be evaluated is collected, and a plurality of behavior combinations are constructed based on the behavior set; in each behavior combination, corresponding job performance dimensions are matched for multiple job performance behaviors in the behavior combination; corresponding job performance evaluation logic is defined according to the job performance dimension, and the credibility of the behavior combination is defined based on the job performance evaluation logic and multiple job performance behaviors; the credibility of each behavior combination is collected, and is divided into core combinations, common combinations and edge combinations based on each behavior combination and the distribution level of credibility, so as to facilitate the division of each behavior combination, and is divided into core combinations, common combinations and edge combinations in combination with the distribution level of credibility, so as to further process the core combinations, common combinations and edge combinations.

[0062] Furthermore, a corresponding weight distribution table is defined according to the core combination, the common combination and the edge combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; the corresponding equivalent logic is matched based on the behavior level, and the corresponding behavior identification result is determined according to the behavior set of the person to be evaluated and the equivalent logic, the influencing parameters are defined based on the behavior identification results and the reference results output by the identification learning model, and the final behavior identification result is defined according to the influencing parameters and the behavior identification results, so as to facilitate multiple optimizations of the behavior identification results and ensure the accuracy of the final behavior identification results. At the same time, the behavior set of the person to be evaluated is controlled by equivalent logic, so as to facilitate equivalent control of each performance behavior and ensure the accuracy of the behavior identification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 It is a flowchart of a concrete identification method based on job performance behavior in an embodiment of the present invention.

[0065] Figure 2 It is a flowchart of S11 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0066] Figure 3 It is a flowchart of S12 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0067] Figure 4 It is a flowchart of S13 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0068] Figure 5 It is a flowchart of S14 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0069] Figure 6 It is a flowchart of S15 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0070] Figure 7 It is a flowchart of S16 in the concrete identification method based on job performance behavior in an embodiment of the present invention.

[0071] Figure 8 It is a schematic diagram of the structural composition of a concrete recognition system based on job performance behavior in an embodiment of the present invention.

[0072] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0074] See also Figures 1 to 9 , a concrete identification method based on job performance behavior, applied to the identification scenario of concrete behavior; the concrete identification method based on job performance behavior includes:

[0075] Step S11: collecting a behavior set of the person to be evaluated, and constructing multiple behavior combinations based on the behavior set;

[0076] Step S12: In each behavior combination, matching corresponding job performance dimensions for multiple job performance behaviors in the behavior combination;

[0077] Step S13: defining a corresponding job performance evaluation logic according to the job performance dimension, and defining the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors;

[0078] Step S14: Collect the credibility of each behavior combination, and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility;

[0079] Step S15: defining a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time;

[0080] Step S16: Match the corresponding equivalent logic based on the behavior level, and determine the corresponding behavior identification result according to the behavior set of the person to be evaluated and the equivalent logic, define the influencing parameters based on the behavior identification result and the reference result output by the identification learning model, and define the final behavior identification result according to the influencing parameters and the behavior identification result.

[0081] In an embodiment of the present invention, through the method in the embodiment of the present invention, a behavior set of the person to be evaluated is collected, and a plurality of behavior combinations are constructed based on the behavior set; in each behavior combination, corresponding job performance dimensions are matched for multiple job performance behaviors in the behavior combination; corresponding job performance evaluation logic is defined according to the job performance dimension, and the credibility of the behavior combination is defined based on the job performance evaluation logic and multiple job performance behaviors; the credibility of each behavior combination is collected, and is divided into core combinations, common combinations and edge combinations based on each behavior combination and the distribution level of credibility, so as to facilitate the division of each behavior combination, and is divided into core combinations, common combinations and edge combinations in combination with the distribution level of credibility, so as to further process the core combinations, common combinations and edge combinations.

[0082] Furthermore, a corresponding weight distribution table is defined according to the core combination, the common combination and the edge combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; the corresponding equivalent logic is matched based on the behavior level, and the corresponding behavior identification result is determined according to the behavior set of the person to be evaluated and the equivalent logic, the influencing parameters are defined based on the behavior identification results and the reference results output by the identification learning model, and the final behavior identification result is defined according to the influencing parameters and the behavior identification results, so as to facilitate multiple optimizations of the behavior identification results and ensure the accuracy of the final behavior identification results. At the same time, the behavior set of the person to be evaluated is controlled by equivalent logic, so as to facilitate equivalent control of each performance behavior and ensure the accuracy of the behavior identification results.

[0083] refer to Figure 2 , in step S11, a behavior set of the person to be evaluated is collected, and a plurality of behavior combinations are constructed according to the behavior set;

[0084] In the specific implementation process of the present invention, the specific steps may be:

[0085] S111: marking the person to be evaluated, and democratically evaluating and matching multiple behaviors associated with the person to be evaluated based on the person's mark and job performance;

[0086] S112: Constructing a behavior set of the person to be evaluated based on multiple job performance situations;

[0087] S113: the combined factors corresponding to the performance situation marks of each job performance behavior in the behavior set of the person to be evaluated;

[0088] S114: Construct multiple behavior combinations based on the labels of the combination factors and the behavior sets of the persons to be evaluated. In the same behavior combination, the combination factors of multiple job performance situations match each other.

[0089] In an embodiment of the present application, the person to be evaluated is marked, and multiple performance situations of the job behavior associated with the person to be evaluated are matched based on the mark of the person to be evaluated and the democratic evaluation of the job performance situation, so as to control the mark of the person to be evaluated and the democratic evaluation of the job performance situation, thereby matching the multiple performance situations of the job behavior associated with the person to be evaluated, and then performing multi-dimensional control based on the mark of the person to be evaluated and the democratic evaluation of the job performance situation, thereby ensuring the accuracy of the mark of the person to be evaluated and the democratic evaluation of the job performance situation.

[0090] At this time, a behavior set of the person to be evaluated is constructed based on multiple job performance situations, and data is collected based on multiple job performance situations in order to construct the behavior set of the person to be evaluated, thereby further controlling the behavior set of the person to be evaluated as a whole.

[0091] At the same time, the combination factors corresponding to the marks of each job performance situation in the behavior set of the person to be evaluated are used to mark the combination factors for each job performance situation, thereby classifying each job performance situation, so as to construct multiple behavior combinations based on the marks of the combination factors and the behavior set of the person to be evaluated, so as to control multiple behavior combinations. Therefore, in the same behavior combination, the combination factors of multiple job performance situations match each other.

[0092] refer to Figure 3 , in step S12, in each behavior combination, the corresponding performance dimension is matched for the multiple performance behaviors in the behavior combination;

[0093] In the specific implementation process of the present invention, the specific steps may be:

[0094] S121: freeze each behavior combination;

[0095] S122: Performing positioning detection on each behavior combination;

[0096] S123: In each behavior combination, select the corresponding performance situation of the performance behavior;

[0097] S124: dividing a plurality of behavior nodes based on the performance of the job performance behavior, and defining a plurality of job performance behaviors according to the plurality of behavior nodes, so as to output a plurality of job performance behaviors in the behavior combination;

[0098] S125: Matching corresponding job performance types according to multiple job performance behaviors in the behavior combination;

[0099] S126: Matching corresponding job performance dimensions based on the job performance type and the location of the job performance behavior.

[0100] In the embodiment of the present application, each behavior combination is frozen so as to facilitate positioning detection for each behavior combination, thereby conducting in-depth control of each behavior combination. At this time, in each behavior combination, the corresponding performance of the performance of the duty is screened so as to facilitate targeted processing for each performance of the performance of the duty.

[0101] Therefore, multiple behavior nodes are divided based on the performance of job performance situations to facilitate the control of the behavior in the performance of job performance situations, and nodes are divided for the behavior to facilitate the formation of multiple behavior nodes, thereby defining multiple job performance behaviors based on the multiple behavior nodes to output multiple job performance behaviors in the behavior combination, clarifying multiple job performance behaviors in the behavior combination, and realizing the control of multiple job performance behaviors.

[0102] Furthermore, corresponding job performance types are matched according to multiple job performance behaviors in the behavior combination to clarify the corresponding job performance types, thereby further controlling the job performance types, so as to match the corresponding job performance dimensions based on the job performance types and the positions of the job performance behaviors, thereby introducing overall control of the job performance types and the positions of the job performance behaviors, so as to match the corresponding job performance dimensions, and achieve precise control of the job performance dimensions. Optionally, the job performance dimensions include test performance dimensions, sitting performance dimensions, standing performance dimensions or work performance dimensions, which are not controlled here.

[0103] refer to Figure 4 In step S13, the corresponding job performance evaluation logic is defined according to the job performance dimension, and the credibility of the behavior combination is defined based on the job performance evaluation logic and multiple job performance behaviors;

[0104] In the specific implementation process of the present invention, the specific steps may be:

[0105] S131: Fixed-frame job performance dimension;

[0106] S132: Define the corresponding job performance evaluation logic based on the job performance dimension and the previous strategic habits of the person to be evaluated;

[0107] S133: In the same behavior combination, an optimization coefficient is defined based on the dimensional difference between multiple job performance dimensions, and the optimization coefficient is associated with the job performance evaluation logic, and the optimized job performance evaluation logic is output;

[0108] S134: Associate optimized job performance evaluation logic and multiple job performance behaviors;

[0109] S135: Define the credibility of the behavior combination based on the optimized job performance evaluation logic and multiple job performance behaviors.

[0110] In an embodiment of the present application, the job performance dimension is fixed to facilitate further control over the job performance dimension, thereby defining the corresponding job performance evaluation logic based on the job performance dimension and the previous strategic habits of the person to be evaluated, introducing the control of the job performance dimension and the previous strategic habits of the person to be evaluated, thereby further controlling the job performance evaluation logic, ensuring multi-dimensional control of the job performance evaluation logic, and fully considering the job performance dimension and the previous strategic habits of the person to be evaluated, thereby ensuring the accuracy of the job performance evaluation logic.

[0111] Therefore, in the same behavior combination, the optimization coefficient is defined based on the dimensional difference between multiple performance dimensions, and the dimensional difference between multiple performance dimensions is controlled to facilitate definition of the optimization coefficient in the same behavior combination, thereby associating the optimization coefficient with the performance evaluation logic, and outputting the optimized performance evaluation logic to facilitate further control over the optimized performance evaluation logic.

[0112] Furthermore, the optimized performance evaluation logic and multiple performance behaviors are associated; the credibility of the behavior combination is defined based on the optimized performance evaluation logic and multiple performance behaviors, thereby performing multi-dimensional control on the optimized performance evaluation logic and multiple performance behaviors to facilitate evaluation of the credibility of the behavior combination, thereby ensuring the accuracy of the credibility of the behavior combination.

[0113] refer to Figure 5 , S14: Collect the credibility of each behavior combination, and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility;

[0114] In the specific implementation process of the present invention, the specific steps may be:

[0115] S141: Collecting the credibility of multiple behavior combinations, and constructing a corresponding credibility set based on the credibility of the multiple behavior combinations;

[0116] S142: defining a credibility distribution level based on a credibility set and a credibility distribution mechanism;

[0117] S143: Correlate the distribution levels of each behavior combination and credibility;

[0118] S144: Divide each behavior combination into core combination, common combination and marginal combination according to the distribution level of each behavior combination and credibility, and classify each behavior combination. At the same time, perform interaction test based on the core combination, common combination and marginal combination, and clearly define the division of core combination, common combination and marginal combination in the interaction test.

[0119] In an embodiment of the present application, the credibility of multiple behavior combinations is collected, and a corresponding credibility set is constructed based on the credibility of the multiple behavior combinations. The credibility set contains the credibility of the multiple behavior combinations, and the credibility of the multiple behavior combinations is controlled in an integrated manner.

[0120] At this time, the distribution level of credibility is defined based on the credibility set and the credibility distribution mechanism, so as to facilitate the overall control of the credibility set and the credibility distribution mechanism, thereby ensuring the accuracy of the distribution level of credibility.

[0121] Therefore, each behavior combination and the distribution level of credibility are associated, and each behavior combination and the distribution level of credibility are managed and controlled, so that they can be divided into core combinations, ordinary combinations and edge combinations according to their distribution levels of credibility, and different levels of control can be performed on the core combinations, ordinary combinations and edge combinations, so as to perform multi-dimensional control based on each behavior combination and the distribution level of credibility.

[0122] Furthermore, each behavior combination is classified, and at the same time, interaction testing is carried out based on core combinations, common combinations and edge combinations. The division of core combinations, common combinations and edge combinations is clearly defined in the interaction test to facilitate further processing of the core combinations, common combinations and edge combinations, thereby ensuring the accuracy of the core combinations, common combinations and edge combinations.

[0123] refer to Figure 6 , S15: defining a corresponding weight distribution table according to the core combination, the common combination and the edge combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time;

[0124] In the specific implementation process of the present invention, the specific steps may be:

[0125] S151: Associate core combination, common combination and edge combination;

[0126] S152: Matching corresponding weights based on the core combination, the common combination, and the edge combination;

[0127] S153: Collecting the behavioral weights of the person to be evaluated within a preset time, and associating the behavioral weights of the person to be evaluated within the preset time with a weight distribution table;

[0128] S154: defining a behavior grading mechanism based on the behavior preference of the person to be evaluated within a preset time and a weight distribution table;

[0129] S155: The mechanism for classifying the associated behaviors and the behavior evaluation results of the person to be evaluated within a preset time;

[0130] S156: defining the behavior level of the person to be evaluated according to the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time.

[0131] In an embodiment of the present application, core combinations, common combinations and edge combinations are associated, and weight management is performed on the core combinations, common combinations and edge combinations, so as to clarify the weights corresponding to the core combinations, common combinations and edge combinations based on the matching of corresponding weights.

[0132] At this time, the behavioral emphasis of the person to be evaluated within the preset time is collected, and the behavioral emphasis of the person to be evaluated within the preset time and the weight distribution table are associated to facilitate the introduction of behavioral emphasis, and further control the behavioral emphasis and the weight distribution table, so as to define the behavioral grading mechanism based on the behavioral emphasis of the person to be evaluated within the preset time and the weight distribution table, freeze the behavioral grading mechanism, and control the behavioral grading mechanism in multiple dimensions to ensure the accuracy of the behavioral grading mechanism.

[0133] Therefore, the behavior grade division mechanism and the behavior evaluation results of the person to be evaluated within the preset time are associated; the behavior grade of the person to be evaluated is defined according to the weight distribution table and the behavior evaluation results of the person to be evaluated within the preset time, so as to facilitate multi-dimensional control of the weight distribution table and the behavior evaluation results of the person to be evaluated within the preset time, thereby ensuring the accuracy of the behavior grade of the person to be evaluated.

[0134] refer to Figure 7 , S16: Matching the corresponding equivalent logic based on the behavior level, and determining the corresponding behavior identification result according to the behavior set of the person to be evaluated and the equivalent logic, defining the influencing parameters based on the behavior identification result and the reference result output by the identification learning model, and defining the final behavior identification result according to the influencing parameters and the behavior identification result;

[0135] In the specific implementation process of the present invention, the specific steps may be:

[0136] S161: Determine the behavioral level of the person to be evaluated;

[0137] S162: Matching corresponding equivalent logic according to the behavior level and the behavior equivalent logic table;

[0138] S163: Associating the behavior set of the person to be evaluated and the equivalent logic;

[0139] S164: Determine the corresponding behavior identification result according to the behavior set of the person to be evaluated and the equivalent logic;

[0140] S165: performing anomaly detection on the behavior identification result, and outputting multiple behavior anomaly factors in the behavior identification result;

[0141] S166: Matching corresponding result optimization logic based on multiple abnormal behavior factors, and optimizing based on the result optimization logic and the behavior identification result to output an optimized behavior identification result;

[0142] S167: Associating the optimized behavior identification results and the reference results output by the identification learning model; defining influencing parameters based on the optimized behavior identification results and the reference results output by the identification learning model; defining the final behavior identification results based on the influencing parameters and the behavior identification results.

[0143] In the specific implementation process of the present invention, a corresponding weight distribution table is defined according to the core combination, the common combination and the edge combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; the corresponding equivalent logic is matched based on the behavior level, and the corresponding behavior identification result is determined according to the behavior set of the person to be evaluated and the equivalent logic, the influencing parameters are defined based on the behavior identification result and the reference result output by the identification learning model, and the final behavior identification result is defined according to the influencing parameters and the behavior identification result, so as to facilitate multiple optimizations of the behavior identification result and ensure the accuracy of the final behavior identification result. At the same time, the behavior set of the person to be evaluated is controlled by equivalent logic, so as to facilitate equivalent control of each job performance behavior and ensure the accuracy of the behavior identification result.

[0144] At this time, the behavior level of the person to be evaluated is fixed, and the corresponding equivalent logic is matched according to the behavior level and the behavior equivalent logic table, so as to facilitate the matching of the behavior level and the behavior equivalent logic table, thereby introducing the corresponding equivalent logic and ensuring further control of the equivalent logic.

[0145] In equivalent logic, the behavioral standard equivalence index is introduced, and the behavioral standard equivalence index is defined as E, E=w1R+w2S+w3C+w4A.

[0146] Among them, R, S, C, and A are the measurements of the source credibility, scientific evaluation, social cognition, and applicability of the behavior standard, respectively, and w1, w2, w3, and w4 are the corresponding weights. Generally speaking, the theoretical basis is the most important focus of the behavior standard, and the source credibility has the largest weight w1, followed by social cognition, scientific evaluation, and applicability of the application object, that is, w1>w3>w2>w4, and the value ranges are: w1∈[35%,45%], w2∈[25%,35%], w1∈[15%,25%], w1∈[5%,15%], which depends on the actual assessment situation of different industries and enterprises.

[0147] Therefore, the correlation is based on the behavior set and equivalent logic of the person to be evaluated; the corresponding behavior identification result is determined based on the behavior set and equivalent logic of the person to be evaluated. The behavior identification result is used as the initial result, and the behavior set and equivalent logic of the person to be evaluated are controlled in multiple dimensions, thereby ensuring the accuracy of the behavior identification result.

[0148] At this time, anomaly detection is performed on the behavior identification results, and multiple behavior anomaly factors in the behavior identification results are output; the corresponding result optimization logic is matched based on the multiple behavior anomaly factors, and optimization is performed based on the result optimization logic and the behavior identification results to output the optimized behavior identification results. Therefore, the optimized behavior identification results are controlled to optimize the result optimization logic and the behavior identification results, thereby ensuring the optimization effect of the behavior identification results.

[0149] Therefore, the optimized behavior identification results and the reference results output by the identification learning model are associated; the influencing parameters are defined based on the optimized behavior identification results and the reference results output by the identification learning model; and the final behavior identification results are defined based on the influencing parameters and the behavior identification results.

[0150] In an embodiment of the present invention, through the method in the embodiment of the present invention, a behavior set of the person to be evaluated is collected, and a plurality of behavior combinations are constructed based on the behavior set; in each behavior combination, corresponding job performance dimensions are matched for multiple job performance behaviors in the behavior combination; corresponding job performance evaluation logic is defined according to the job performance dimension, and the credibility of the behavior combination is defined based on the job performance evaluation logic and multiple job performance behaviors; the credibility of each behavior combination is collected, and is divided into core combinations, common combinations and edge combinations based on each behavior combination and the distribution level of credibility, so as to facilitate the division of each behavior combination, and is divided into core combinations, common combinations and edge combinations in combination with the distribution level of credibility, so as to further process the core combinations, common combinations and edge combinations.

[0151] Furthermore, a corresponding weight distribution table is defined according to the core combination, the common combination and the edge combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; the corresponding equivalent logic is matched based on the behavior level, and the corresponding behavior identification result is determined according to the behavior set of the person to be evaluated and the equivalent logic, the influencing parameters are defined based on the behavior identification results and the reference results output by the identification learning model, and the final behavior identification result is defined according to the influencing parameters and the behavior identification results, so as to facilitate multiple optimizations of the behavior identification results and ensure the accuracy of the final behavior identification results. At the same time, the behavior set of the person to be evaluated is controlled by equivalent logic, so as to facilitate equivalent control of each performance behavior and ensure the accuracy of the behavior identification results.

[0152] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of a concrete recognition system based on job performance behavior in an embodiment of the present invention.

[0153] like Figure 8 As shown, a concrete recognition system based on job performance behavior, the precise two-way matching system for people and positions includes:

[0154] The collection module 21 is used to collect the behavior set of the person to be evaluated and construct multiple behavior combinations according to the behavior set;

[0155] A matching module 22, for matching, in each behavior combination, a corresponding job performance dimension for a plurality of job performance behaviors in the behavior combination;

[0156] The credibility module 23 is used to define the corresponding job performance evaluation logic according to the job performance dimension, and define the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors;

[0157] A combination module 24 is used to collect the credibility of each behavior combination, and divide each behavior combination and the distribution level of the credibility into a core combination, a common combination and a marginal combination;

[0158] The behavior grade module 25 is used to define a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and define the behavior grade of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time;

[0159] The behavior identification module 26 is used to match the corresponding equivalent logic based on the behavior level, and determine the corresponding behavior identification result based on the behavior set of the person to be evaluated and the equivalent logic, define the influencing parameters based on the behavior identification result and the reference result output by the identification learning model, and define the final behavior identification result based on the influencing parameters and the behavior identification result.

[0160] See also Fig. 9 , refer to the following Fig. 9 The electronic device 40 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0161] like Fig. 9 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0162] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0163] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0164] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0165] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0166] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.

[0167] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0168] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0169] In addition, the above detailed introduction to the concrete recognition system based on job performance behavior and the system provided by the embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A concrete identification method based on job performance behavior, characterized in that: Applied to the identification scenario of concrete behavior; The concrete identification method based on job performance behavior includes: Collect the behavior set of the person to be evaluated, and construct multiple behavior combinations based on the behavior set; In each behavior combination, the corresponding performance dimension is matched for the multiple performance behaviors in the behavior combination; Define the corresponding job performance evaluation logic according to the job performance dimension, and define the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors; Collect the credibility of each behavior combination, and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility; A corresponding weight distribution table is defined according to the core combination, the common combination and the marginal combination, and the behavior level of the person to be evaluated is defined based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; Based on the equivalent logic corresponding to the behavior level matching, and according to the behavior set of the person to be evaluated and the equivalent logic, the corresponding behavior identification result is determined, and the influence parameters are defined based on the behavior identification result and the reference result output by the identification learning model. The final behavior identification result is defined based on the influence parameters and the behavior identification result.

2. The method for concrete identification based on job performance behavior according to claim 1 is characterized in that: The collecting of the behavior set of the person to be evaluated and constructing a plurality of behavior combinations according to the behavior set include: Mark the person to be evaluated, and democratically evaluate and match multiple behaviors associated with the person to be evaluated based on the person's mark and job performance; Construct a set of behaviors of the personnel to be evaluated based on multiple performance situations; The combined factors corresponding to the performance status marks of each job performance in the behavior set of the person to be evaluated; Multiple behavior combinations are constructed based on the labels of the combination factors and the behavior sets of the persons to be evaluated. In the same behavior combination, the combination factors of multiple job performance situations match each other.

3. The method for concrete identification based on job performance behavior according to claim 2 is characterized in that: In each behavior combination, the corresponding performance dimension is matched to the multiple performance behaviors in the behavior combination, including: Freeze each behavior combination; Perform positioning detection for each behavior combination; In each behavior combination, select the corresponding performance situation of the performance behavior; Divide multiple behavior nodes based on the performance of the job performance behavior, and define multiple job performance behaviors according to the multiple behavior nodes to output multiple job performance behaviors in the behavior combination; Matching corresponding job performance types according to multiple job performance behaviors in the behavior combination; The corresponding job performance dimension is matched based on the job performance type and the location of the job performance behavior.

4. The method for concrete identification based on job performance behavior according to claim 3 is characterized in that: Defining the corresponding job performance evaluation logic according to the job performance dimension, and defining the credibility of the behavior combination based on the job performance evaluation logic and multiple job performance behaviors, includes: Determine the performance dimension of job performance; Define the corresponding job performance evaluation logic based on job performance dimensions and the previous strategic habits of the person to be evaluated; In the same behavior combination, an optimization coefficient is defined based on the dimensional differences between multiple job performance dimensions, and the optimization coefficient is associated with the job performance evaluation logic to output the optimized job performance evaluation logic; Associate optimized job performance evaluation logic and multiple job performance behaviors; The credibility of the behavior combination is defined based on the optimized job performance evaluation logic and multiple job performance behaviors.

5. The method for concrete identification based on job performance behavior according to claim 4 is characterized in that: The credibility of each behavior combination is collected and divided into core combination, common combination and edge combination based on the distribution level of each behavior combination and credibility, including: Collect the credibility of multiple behavior combinations, and build a corresponding credibility set based on the credibility of the multiple behavior combinations; Defining the distribution level of credibility based on credibility set and credibility distribution mechanism; Associate each behavior combination with a distribution hierarchy of credibility; According to the distribution level of each behavior combination and credibility, it is divided into core combination, common combination and marginal combination, and each behavior combination is classified. At the same time, interaction testing is carried out based on the core combination, common combination and marginal combination, and the division of core combination, common combination and marginal combination is clearly defined in the interaction test.

6. The method for concrete identification based on job performance behavior according to claim 5 is characterized in that: Defining a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time, includes: Associate core combinations, common combinations, and edge combinations; Match the corresponding weights based on the core combination, common combination and edge combination.

7. The method for concrete identification based on job performance behavior according to claim 6 is characterized in that: The method further includes defining a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and defining the behavior level of the person to be evaluated based on the weight distribution table and the behavior evaluation result of the person to be evaluated within a preset time, and further includes: Collecting the behavioral weights of the persons to be evaluated within a preset time, and associating the behavioral weights of the persons to be evaluated within the preset time with a weight distribution table; Define the behavior grading mechanism based on the behavior preference of the person to be evaluated within a preset time and the weight distribution table; The mechanism for classifying related behaviors and the behavior evaluation results of the persons to be evaluated within a preset time; The behavior level of the person to be evaluated is defined according to the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time.

8. The method for concrete identification based on job performance behavior according to claim 7 is characterized in that: The equivalent logic corresponding to the behavior level matching is determined based on the behavior set of the person to be evaluated and the equivalent logic, the corresponding behavior identification result is determined based on the behavior identification result and the reference result output by the identification learning model, and the final behavior identification result is defined based on the influence parameter and the behavior identification result, including: Determine the behavioral level of the person to be evaluated; Match the corresponding equivalent logic according to the behavior level and the behavior equivalent logic table; The association data is the set of behaviors of the person to be evaluated and the equivalent logic; The corresponding behavior identification result is determined based on the behavior set of the person to be evaluated and the equivalent logic.

9. The method for concrete identification based on job performance behavior according to claim 8 is characterized in that: The method includes matching the corresponding equivalent logic based on the behavior level, determining the corresponding behavior identification result according to the behavior set of the person to be evaluated and the equivalent logic, defining the influence parameter based on the behavior identification result and the reference result output by the identification learning model, and defining the final behavior identification result according to the influence parameter and the behavior identification result, and further includes: Perform anomaly detection on the behavior identification results and output multiple behavior anomaly factors in the behavior identification results; Matching corresponding result optimization logic based on multiple abnormal behavior factors, and optimizing based on the result optimization logic and the behavior identification results to output optimized behavior identification results; Associating the optimized behavior identification results with the reference results output by the identification learning model; defining influencing parameters based on the optimized behavior identification results and the reference results output by the identification learning model; and defining the final behavior identification results based on the influencing parameters and the behavior identification results.

10. A concrete recognition system based on job performance behavior, characterized in that: The concrete recognition system based on job performance behavior is applied to the concrete recognition method based on job performance behavior as claimed in any one of claims 1 to 9, and the concrete recognition system based on job performance behavior includes: The collection module is used to collect the behavior set of the person to be evaluated and construct multiple behavior combinations based on the behavior set; A matching module, for matching corresponding job performance dimensions in each behavior combination for multiple job performance behaviors in the behavior combination; The credibility module is used to define the corresponding performance evaluation logic according to the performance dimension, and define the credibility of the behavior combination based on the performance evaluation logic and multiple performance behaviors; The combination module is used to collect the credibility of each behavior combination and divide it into core combination, common combination and marginal combination based on the distribution level of each behavior combination and credibility; The behavior grade module is used to define a corresponding weight distribution table according to the core combination, the common combination and the marginal combination, and define the behavior grade of the person to be evaluated based on the weight distribution table and the behavior evaluation results of the person to be evaluated within a preset time; The behavior identification module is used to match the corresponding equivalent logic based on the behavior level, and determine the corresponding behavior identification result based on the behavior set and the equivalent logic of the person to be evaluated, define the influencing parameters based on the behavior identification result and the reference result output by the identification learning model, and define the final behavior identification result based on the influencing parameters and the behavior identification result.

Images