Human resource post digital evaluation model based on big data

Abstract

The invention discloses a human resource post digital evaluation model based on big data, and relates to the technical field of intelligent evaluation. According to the human resource post digital evaluation model based on the big data, a factor analysis method and a Cronbach coefficient method are used for carrying out reliability and validity test on a customized scale, the reliability and validity of the scale are tested, a digital detection system is established, post evaluation operation is simple and visual, evaluation of all posts is met, and the human resource post digital evaluation model based on the big data is suitable for popularization and application. And factors which are detected to be qualified are determined through the data detection model, and factors marked as suspicious data are screened, so that the accuracy and effectiveness of post evaluation are ensured, and the method has wide market prospects and social value.

Description

Technical Field

[0001] The present invention relates to the field of intelligent evaluation technology, and in particular to a digital evaluation model for human resources positions based on big data. Background Art

[0002] Human resource job evaluation includes narrow and broad concepts. In the narrow sense, human resource evaluation refers to the evaluation of the ideological and moral qualities, work attitudes, work abilities and work performance of enterprise employees in the process of performing their job duties. In the broad sense, human resource evaluation includes not only job evaluation of employees, but also evaluation of employee qualities, namely the evaluation of psychological quality, ideological quality, intellectual quality and other aspects. Job evaluation content plays an important role in human resources. The difficulty in quantification is the biggest difficulty, which makes job evaluation impossible for general enterprises. However, this system can easily achieve it, breaking the situation where European and American Hayes job evaluation dominates the world.

[0003] Currently, there is a lack of a corresponding system architecture for the evaluation of human resources positions. Traditional job evaluation methods are complex to operate and difficult to quantify data. They can only meet the needs of large enterprises and cannot be applied by small enterprises. They have great limitations, and the operation methods and calculations are relatively complex. The application efficiency needs to be further improved. Summary of the Invention

[0004] The purpose of the present invention is to provide a digital evaluation model for human resource positions based on big data to address the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a digital evaluation model for human resources positions based on big data, comprising the following generation steps:

[0006] A1. Based on the characteristics and evaluation requirements of human resources positions, a digital evaluation index system for human resources positions is established by combining the index system method with the improved DPSIR model;

[0007] A2: Develop a digital evaluation scale for human resources positions and conduct reliability and validity tests on the customized scale using factor analysis and Cronbach coefficient method to verify the reliability and effectiveness of the scale;

[0008] A3, using artificial neural network methods to construct a digital evaluation model for human resources positions, establishing a data set by combining the objective evaluation indicators of digital evaluation of human resources positions with the subjective evaluation scores of experts, which is used to train and verify the systematic model established by the artificial neural network, and verify the performance of the evaluation model, and finally establish a digital evaluation model for human resources positions based on psychometrics.

[0009] Furthermore, the indicator system method is to evaluate human resource positions by comprehensively applying multiple types of indicators to reflect human resource position information from different angles and depths. The multiple types of indicators include financial indicators, customer-oriented indicators, internal process indicators, and learning, innovation and growth indicators.

[0010] Furthermore, the driving force in the improved DPSIR model refers to the fundamental reason that causes changes in job evaluation, the pressure in the improved DPSIR model refers to the direct or indirect impact of human activities on job evaluation, the state in the improved DPSIR model refers to the current evaluation of the job, the impact in the improved DPSIR model refers to the impact of human activities on job evaluation, and the response in the improved DPSIR model refers to the countermeasures taken to address job problems.

[0011] Furthermore, the step A2 specifically includes the following steps:

[0012] B1, determine the purpose and evaluation object of digital evaluation of human resources positions through data determination model;

[0013] B2, based on the digital evaluation references of human resources positions, and using the Zotero plug-in to build an entry library based on the large language model;

[0014] B3, based on the item list established in step B2, compile an initial digital evaluation scale for human resources positions;

[0015] B4, perform scale pre-verification on the initial human resource position digital evaluation scale generated in step B3, wherein the initial human resource position digital evaluation scale that passes the pre-verification is sent to step B6, and the initial human resource position digital evaluation scale that fails the pre-verification is sent to perform the following steps:

[0016] B41, reliability test of pre-test was conducted by using factor analysis method;

[0017] B42, the validity test of the pre-test was conducted by Cronbach's coefficient method;

[0018] B5, for those initial digital evaluation scales for human resources positions that fail the reliability test in step B41 and the validity test in step B42, revise the initial digital evaluation scales for human resources positions;

[0019] B6. Mark the initial human resources position digital evaluation scale that passed the pre-verification in step B4 and the initial human resources position digital evaluation scale that was revised in step B5 as the official human resources position digital evaluation scale.

[0020] Furthermore, the factor analysis method in step B41 specifically includes the following steps:

[0021] C1, collect factors through the data collection model. The factors are the factors in the initial human resources position digital evaluation scale:

[0022] C2, judging whether the factors collected in step C1 are suitable for factor analysis through a data judgment model, and sending the factor set judged to be suitable for factor analysis to step C3, wherein the data judgment model includes a Bartlett sphericity test model and a KOM test model;

[0023] C3, determine the factors that have passed the test in the factor set through the data detection model;

[0024] C4, set the number of factors according to the number of secondary dimensions under the primary dimension in the indicator system valve, and convert the collected factors into a factor loading matrix;

[0025] C5, use the orthogonal matrix to multiply the factor loading matrix in step C4 on the right to realize the rotation of the factor loading matrix, that is, an orthogonal transformation corresponds to a rotation of the coordinate system;

[0026] C6. After determining the number of factors and the rotation method, interpret the factor loading matrix and understand the relationship between each factor;

[0027] C7, combines the extracted factors with the domain knowledge of digital evaluation of human resources positions, and gives each factor an explanation of digital evaluation of human resources positions.

[0028] Furthermore, the step C3 determines the qualified factors through the data detection model, which specifically includes the following steps:

[0029] D1, data preprocessing, let the percentage of abnormal data in the factor set be μ1 and μ2, where μ1 represents the probability that the abnormal data is lower than the first dimension standard, and μ2 represents the probability that the abnormal data is lower than the second dimension standard.

[0030] D2, extract the factor data value vector G from the factor set e ;

[0031] D3, find the factor mean n and the total factor data volume m;

[0032] D4, get G e The Euclidean distance vector G from n euc =|G e -n|;

[0033] D5, against G euc Sort in descending order to get the sorted distance vector G s;

[0034] D6, get the threshold: d1 = G s (round(m·μ1)),d2=G s (round(m·μ2)),

[0035] Where d1 represents the threshold of the first-level dimension standard, d2 represents the threshold of the second-level dimension standard, and round represents the rounding function;

[0036] D7, mark abnormal data, and G euc (i) Compare with the threshold, where G euc (i) represents the Euclidean distance vector between the i-th factor data vector and n, when G euc (i)≥d1, indicating that the i-th factor is abnormal data, when d1≥G euc (i)≥d2, indicating that the i-th factor is suspicious data, when G euc (i)≤d2, indicating that the i-th factor is normal data;

[0037] D8, eliminating the factors marked as abnormal data in step D7, retaining the factors marked as normal data in step D7, and screening the factors marked as suspicious data in step D7.

[0038] Furthermore, in step D8, the factors marked as suspicious data in step D7 are screened, which specifically includes the following steps:

[0039] E1, let the set of digital evaluation of human resources positions be T = {T1, T2, T3, ..., T n}, all factor data sets are D(T) = {d1, d2, d3, ..., d N(D(T))}, where N(D(T)) is the total amount of factor data;

[0040] E2, let the evaluation factor data set under the i-th human resources position be D(T i )={d i1 , d i2 , d i3 ,…,d iN(D(Tn))}, where N(D(T n )) represents the total amount of factor data under the i-th human resources position;

[0041] E3, the calculation formula for the evaluation value Z of the suspicious data factor is:

[0042] Z=αE i +βA i

[0043] Where α and β represent parameters, and α+β=1, and the calculation formula of α is:

[0044]

[0045] Among them A i Indicates the number of standard quantities of suspicious data factors, E in Indicates the number of times the suspicious data factor is marked;

[0046] E4. Set a selection threshold and compare it with the evaluation value Z of the suspicious data factor. Suspicious data factors whose evaluation value Z is greater than the selection threshold are retained, and suspicious data factors whose evaluation value Z is less than the selection threshold are deleted.

[0047] Compared with the existing technology, the present invention provides a digital evaluation model for human resources positions based on big data. It uses factor analysis and Cronbach coefficient method to test the reliability and validity of customized scales to test the reliability and validity of the scales. By establishing a digital detection system, the position evaluation operation is simple and intuitive, which is suitable for the evaluation of all positions. In addition, by determining the qualified factors through the data detection model and screening the factors marked as suspicious data, the accuracy and effectiveness of the position evaluation are guaranteed, which has broad market prospects and social value. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 This is a system structure block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0051] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention.

[0052] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a communication between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0053] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0054] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0055] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0056] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0057] The embodiments described herein may be described with reference to plan views and / or cross-sectional views, with the aid of idealized schematic diagrams of the present disclosure. Thus, the example illustrations may be modified based on manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings are schematic in nature, and the shapes of the regions shown in the drawings illustrate specific shapes of the regions of the elements, but are not intended to be limiting.

[0058] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined as such herein.

[0059] See also Figure 1 , a digital evaluation model for human resource positions based on big data, including the following generation steps:

[0060] A1. Based on the characteristics and evaluation requirements of human resources positions, a digital evaluation index system for human resources positions is established by combining the index system method with the improved DPSIR model;

[0061] A2: Develop a digital evaluation scale for human resources positions and conduct reliability and validity tests on the customized scale using factor analysis and Cronbach coefficient method to verify the reliability and effectiveness of the scale;

[0062] A3, using artificial neural network methods to construct a digital evaluation model for human resources positions, establishing a data set by combining the objective evaluation indicators of digital evaluation of human resources positions with the subjective evaluation scores of experts, which is used to train and verify the systematic model established by the artificial neural network, and verify the performance of the evaluation model, and finally establish a digital evaluation model for human resources positions based on psychometrics.

[0063] The indicator system method evaluates human resource positions by comprehensively applying various types of indicators to reflect human resource position information from different angles and depths. Various types of indicators include financial indicators, customer-oriented indicators, internal process indicators, and learning, innovation and growth indicators.

[0064] In the improved DPSIR model, driving force refers to the fundamental cause of changes in job evaluation; pressure in the improved DPSIR model refers to the direct or indirect impact of human activities on job evaluation; state in the improved DPSIR model refers to the current evaluation of the job; impact in the improved DPSIR model refers to the impact of human activities on job evaluation; response in the improved DPSIR model refers to the response measures taken to address job problems.

[0065] Step A2 specifically includes the following steps:

[0066] B1, determine the purpose and evaluation object of digital evaluation of human resources positions through data determination model;

[0067] B2, based on the digital evaluation references of human resources positions, and using the Zotero plug-in to build an entry library based on the large language model;

[0068] B3, based on the item list established in step B2, compile an initial digital evaluation scale for human resources positions;

[0069] B4, perform scale pre-verification on the initial human resource position digital evaluation scale generated in step B3, wherein the initial human resource position digital evaluation scale that passes the pre-verification is sent to step B6, and the initial human resource position digital evaluation scale that fails the pre-verification is sent to perform the following steps:

[0070] B41, reliability test of pre-test was conducted by using factor analysis method;

[0071] B42, the validity test of the pre-test was conducted by Cronbach's coefficient method;

[0072] B5, for those initial digital evaluation scales for human resources positions that fail the reliability test in step B41 and the validity test in step B42, revise the initial digital evaluation scales for human resources positions;

[0073] B6. Mark the initial human resources position digital evaluation scale that passed the pre-verification in step B4 and the initial human resources position digital evaluation scale that was revised in step B5 as the official human resources position digital evaluation scale.

[0074] The factor analysis method in step B41 specifically includes the following steps:

[0075] C1, collect factors through the data collection model. The factors are the factors in the initial human resources position digital evaluation scale:

[0076] C2, judging whether the factors collected in step C1 are suitable for factor analysis through a data judgment model, and sending the factor set that is judged to be suitable for factor analysis to step C3. The data judgment model includes a Bartlett sphericity test model and a KOM test model;

[0077] C3, determine the factors in the factor set that have passed the test through the data detection model;

[0078] C4, set the number of factors according to the number of secondary dimensions under the primary dimension in the indicator system valve, and convert the collected factors into a factor loading matrix;

[0079] C5, use the orthogonal matrix to multiply the factor loading matrix in step C4 on the right to realize the rotation of the factor loading matrix, that is, an orthogonal transformation corresponds to a rotation of the coordinate system;

[0080] C6. After determining the number of factors and the rotation method, interpret the factor loading matrix and understand the relationship between each factor;

[0081] C7, combines the extracted factors with the domain knowledge of digital evaluation of human resources positions, and gives each factor an explanation of digital evaluation of human resources positions.

[0082] Step C3 determines the qualified factors through the data detection model, which specifically includes the following steps:

[0083] D1, data preprocessing, let the percentage of abnormal data in the factor set be μ1 and μ2, where μ1 represents the probability that the abnormal data is lower than the first dimension standard, and μ2 represents the probability that the abnormal data is lower than the second dimension standard.

[0084] D2, extract the factor data value vector G from the factor set e ;

[0085] D3, find the factor mean n and the total factor data volume m;

[0086] D4, get G e The Euclidean distance vector G from n euc =|G e -n|;

[0087] D5, against G euc Sort in descending order to get the sorted distance vector G s ;

[0088] D6, get the threshold: d1 = G s (round(m·μ1)),d2=G s (round(m·μ2)),

[0089] Where d1 represents the threshold of the first-level dimension standard, d2 represents the threshold of the second-level dimension standard, and round represents the rounding function;

[0090] D7, mark abnormal data, and G euc (i) Compare with the threshold, where G euc (i) represents the Euclidean distance vector between the i-th factor data vector and n, when G euc (i)≥d1, indicating that the i-th factor is abnormal data, when d1≥G euc (i)≥d2, indicating that the i-th factor is suspicious data, when G euc (i)≤d2, indicating that the i-th factor is normal data;

[0091] D8, eliminating the factors marked as abnormal data in step D7, retaining the factors marked as normal data in step D7, and screening the factors marked as suspicious data in step D7.

[0092] In step D8, the factors marked as suspicious data in step D7 are screened, which specifically includes the following steps:

[0093] E1, let the set of digital evaluation of human resources positions be T = {T1, T2, T3, ..., T n}, all factor data sets are D(T) = {d1, d2, d3, ..., d N(D(T))}, where N(D(T)) is the total amount of factor data;

[0094] E2, let the evaluation factor data set under the i-th human resources position be D(T i )={d i1 , d i2 , d i3 ,…,d iN(D(Tn))}, where N(D(T n )) represents the total amount of factor data under the i-th human resources position;

[0095] E3, the calculation formula for the evaluation value Z of the suspicious data factor is:

[0096] Z=αE i +βA i

[0097] Where α and β represent parameters, and α+β=1, and the calculation formula of α is:

[0098]

[0099] Among them A i Indicates the number of standard quantities of suspicious data factors, E in Indicates the number of times the suspicious data factor is marked;

[0100] E4. Set a selection threshold and compare it with the evaluation value Z of the suspicious data factor. Suspicious data factors whose evaluation value Z is greater than the selection threshold are retained, and suspicious data factors whose evaluation value Z is less than the selection threshold are deleted.

[0101] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A digital evaluation model for human resources positions based on big data, characterized by: The build steps include: A1. Based on the characteristics and evaluation requirements of human resources positions, a digital evaluation index system for human resources positions is established by combining the index system method with the improved DPSIR model; A2: Develop a digital evaluation scale for human resources positions and conduct reliability and validity tests on the customized scale using factor analysis and Cronbach coefficient method to verify the reliability and effectiveness of the scale; A3, using artificial neural network methods to construct a digital evaluation model for human resources positions, establishing a data set by combining the objective evaluation indicators of digital evaluation of human resources positions with the subjective evaluation scores of experts, which is used to train and verify the systematic model established by the artificial neural network, and verify the performance of the evaluation model, and finally establish a digital evaluation model for human resources positions based on psychometrics.

2. The human resources position digital evaluation model based on big data according to claim 1 is characterized by: The indicator system method is to evaluate human resource positions by comprehensively applying multiple types of indicators to reflect human resource position information from different angles and depths. The multiple types of indicators include financial indicators, customer-oriented indicators, internal process indicators, and learning, innovation and growth indicators.

3. The human resources position digital evaluation model based on big data according to claim 1 is characterized by: The driving force in the improved DPSIR model refers to the fundamental reason that causes changes in job evaluation, the pressure in the improved DPSIR model refers to the direct or indirect impact of human activities on job evaluation, the state in the improved DPSIR model refers to the current evaluation of the job, the impact in the improved DPSIR model refers to the impact of human activities on job evaluation, and the response in the improved DPSIR model refers to the countermeasures taken to address job problems.

4. The human resources position digital evaluation model based on big data according to claim 1 is characterized by: The step A2 specifically includes the following steps: B1, determine the purpose and evaluation object of digital evaluation of human resources positions through data determination model; B2, based on the digital evaluation references of human resources positions, and using the Zotero plug-in to build an entry library based on the large language model; B3, based on the item list established in step B2, compile an initial digital evaluation scale for human resources positions; B4, perform scale pre-verification on the initial human resource position digital evaluation scale generated in step B3, wherein the initial human resource position digital evaluation scale that passes the pre-verification is sent to step B6, and the initial human resource position digital evaluation scale that fails the pre-verification is sent to perform the following steps: B41, reliability test of pre-test was conducted by using factor analysis method; B42, the validity test of the pre-test was conducted by Cronbach's coefficient method; B5, for those initial digital evaluation scales for human resources positions that fail the reliability test in step B41 and the validity test in step B42, revise the initial digital evaluation scales for human resources positions; B6. Mark the initial human resources position digital evaluation scale that passed the pre-verification in step B4 and the initial human resources position digital evaluation scale that was revised in step B5 as the official human resources position digital evaluation scale.

5. The human resources position digital evaluation model based on big data according to claim 4 is characterized by: The factor analysis method in step B41 specifically includes the following steps: C1, collect factors through the data collection model. The factors are the factors in the initial human resources position digital evaluation scale: C2, judging whether the factors collected in step C1 are suitable for factor analysis through a data judgment model, and sending the factor set judged to be suitable for factor analysis to step C3, wherein the data judgment model includes a Bartlett sphericity test model and a KOM test model; C3, determine the factors in the factor set that have passed the test through the data detection model; C4, set the number of factors according to the number of secondary dimensions under the primary dimension in the indicator system valve, and convert the collected factors into a factor loading matrix; C5, use the orthogonal matrix to multiply the factor loading matrix in step C4 on the right to realize the rotation of the factor loading matrix, that is, an orthogonal transformation corresponds to a rotation of the coordinate system; C6. After determining the number of factors and the rotation method, interpret the factor loading matrix and understand the relationship between each factor; C7, combines the extracted factors with the domain knowledge of digital evaluation of human resources positions, and gives each factor an explanation of digital evaluation of human resources positions.

6. The human resources position digital evaluation model based on big data according to claim 5 is characterized by: The step C3 determines the qualified factors through the data detection model, specifically including the following steps: D1, data preprocessing, let the percentage of abnormal data in the factor set be μ1 and μ2, where μ1 represents the probability that the abnormal data is lower than the first dimension standard, and μ2 represents the probability that the abnormal data is lower than the second dimension standard. D2, extract the factor data value vector G from the factor set e ; D3, find the factor mean n and the total factor data volume m; D4, get G e The Euclidean distance vector G from n euc =|G e -n|; D5, against G euc Sort in descending order to get the sorted distance vector G s ; D6, get the threshold: d1 = G s (round(m·μ1)),d2=G s (round(m·μ2)), Where d1 represents the threshold of the first-level dimension standard, d2 represents the threshold of the second-level dimension standard, and round represents the rounding function; D7, mark abnormal data, and G euc (i) Compare with the threshold, where G euc (i) represents the Euclidean distance vector between the i-th factor data vector and n, when G euc (i)≥d1, indicating that the i-th factor is abnormal data, when d1≥G euc (i)≥d2, indicating that the i-th factor is suspicious data, when G euc (i)≤d2, indicating that the i-th factor is normal data; D8, eliminating the factors marked as abnormal data in step D7, retaining the factors marked as normal data in step D7, and screening the factors marked as suspicious data in step D7.

7. The human resources position digital evaluation model based on big data according to claim 6 is characterized by: In step D8, the factors marked as suspicious data in step D7 are screened, which specifically includes the following steps: E1, let the set of digital evaluation of human resources positions be T = {T1, T2, T3, ..., T n }, all factor data sets are D(T) = {d1, d2, d3, ..., d N(D(T)) }, where N(D(T)) is the total amount of factor data; E2, let the evaluation factor data set under the i-th human resources position be D(T i )={d i1 , d i2 , d i3 ,…,d iN(D(Tn)) }, where N(D(T n )) represents the total amount of factor data under the i-th human resources position; E3, the calculation formula for the evaluation value Z of the suspicious data factor is: Z=αE i +βA i Where α and β represent parameters, and α+β=1, and the calculation formula of α is: Among them A i Indicates the number of standard quantities of suspicious data factors, E in Indicates the number of times the suspicious data factor is marked; E4. Set a selection threshold and compare it with the evaluation value Z of the suspicious data factor. Suspicious data factors whose evaluation value Z is greater than the selection threshold are retained, and suspicious data factors whose evaluation value Z is less than the selection threshold are deleted.

Images