Crowdsourcing object evaluation method and device for security detection tasks

Abstract

The present application discloses a crowdsourcing object evaluation method and device for security detection tasks, including quantifying the influencing factor information corresponding to each attribute information in response to obtaining multiple attribute information of the crowdsourcing object for security detection tasks, wherein the influencing factor includes the factor information influencing the execution and motivation of the security detection task in crowdsourcing; determining the weight of the influencing factor information based on the hierarchical analysis method; performing consistency verification on the weight of the influencing factor information; and determining the evaluation score of the crowdsourcing object in response to the consistency verification result indicating that the consistency verification is satisfied. This solves the technical problem of poor completion quality of crowdsourcing tasks in related technologies.

Description

Technical Field

[0001] The present application relates to the technical field of network detection crowdsourcing, and in particular to a crowdsourcing object evaluation method and device for security detection tasks. Background Art

[0002] Crowdsourcing of security detection tasks can effectively solve the problems of high construction cost, insufficient monitoring points, uneven distribution of detection areas, and biased data samples in the centralized detection mode. In related technologies, crowdsourcing platforms often use value means such as points to measure crowdsourcing objects, but the point method seriously affects the completion quality of crowdsourcing tasks. Related technologies also use historical data to establish a preference model for crowdsourcing objects and use the method of building a recommendation matrix to achieve personalized recommendations for crowdsourcing. The above method only realizes the recommendation of crowdsourcing tasks and cannot be used to evaluate crowdsourcing objects.

[0003] In view of the poor completion quality of crowdsourcing tasks in related technologies, no effective solution has been proposed so far. Summary of the invention

[0004] The main purpose of this application is to provide a crowdsourcing object evaluation method and device for security detection tasks to solve the problem of poor completion quality of crowdsourcing tasks.

[0005] In order to achieve the above objectives, in a first aspect, the present application provides a crowdsourcing object evaluation method for security detection tasks.

[0006] The crowdsourcing object evaluation method for security detection tasks according to the present application includes: in response to obtaining multiple attribute information of the crowdsourcing object for the security detection task, quantifying the influencing factor information corresponding to each attribute information, wherein the influencing factor includes the factor information that affects the execution and motivation of the security detection task in the crowdsourcing; based on the hierarchical analysis method, determining the weight of the influencing factor information; performing consistency verification on the weight of the influencing factor information; and determining the evaluation score of the crowdsourcing object in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied.

[0007] In some embodiments, based on the hierarchical analysis method, determining the weight of the influencing factor information includes: establishing a hierarchical model for multiple attribute information, determining the correlation information of the influencing factor information corresponding to each attribute information; establishing a multi-dimensional comparison matrix for the influencing factors; calculating the maximum eigenvalue and corresponding eigenvector of the comparison matrix; normalizing the eigenvector to obtain the influence weight value of the influencing factor.

[0008] In some embodiments, consistency verification of the weight of the influencing factor information includes: determining a calculated consistency value based on the feature vector and the number of influencing factors; in response to obtaining a random consistency value, determining a ratio of the calculated consistency value to the random consistency value; and determining whether the weight of the influencing factor information satisfies consistency based on a judgment result of whether the ratio is within a preset value range.

[0009] In some embodiments, in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, determining the weight value of the detection point includes: in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, performing dimensionless processing on the quantified influencing factor information; calculating the value of the dimensionless processed influencing factor information based on the fuzzy integral method, and determining it as the evaluation score of the crowdsourcing object.

[0010] In the second aspect, the present application also provides a crowdsourcing object evaluation device for security detection tasks, including: a quantification unit, configured to quantify the influencing factor information corresponding to each attribute information in response to obtaining multiple attribute information of the crowdsourcing object for the security detection task, wherein the influencing factor includes the factor information that affects the execution and motivation of the security detection task in the crowdsourcing; a first determination unit, configured to determine the weight of the influencing factor information based on the hierarchical analysis method; a verification unit, configured to perform consistency verification on the weight of the influencing factor information; a second determination unit, configured to determine the evaluation score of the crowdsourcing object in response to the consistency verification result indicating that the consistency verification is satisfied.

[0011] In some embodiments, the first determination unit is further configured to: establish a hierarchical model about the multiple attribute information to determine the correlation information of the influencing factor information corresponding to each attribute information; establish a multi-dimensional comparison matrix about the influencing factors; calculate the maximum eigenvalue and corresponding eigenvector of the comparison matrix; normalize the eigenvector to obtain the influence weight value of the influencing factor.

[0012] In some embodiments, the verification unit is further configured to: determine a calculated consistency value based on the feature vector and the number of influencing factors; determine a ratio of the calculated consistency value to the random consistency value in response to obtaining a random consistency value; and determine whether the weight of the influencing factor information satisfies consistency based on a judgment result of whether the ratio is within a preset value range.

[0013] In some embodiments, the second determination unit is further configured to: perform dimensionless processing on the quantified influencing factor information in response to a consistency verification result indicating that the consistency verification is satisfied; calculate the value of the dimensionless processed influencing factor information based on the fuzzy integral method, and determine it as the evaluation score of the crowdsourcing object.

[0014] In a third aspect, the present application also provides a computer processing device, comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement a method as in any one of the embodiments in the first aspect.

[0015] In a fourth aspect, the present application further provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method of any embodiment of the first aspect is implemented.

[0016] In an embodiment of the present application, a crowdsourcing object evaluation method and device for a security detection task is provided. In response to obtaining multiple attribute information of a crowdsourcing object for a security detection task, the influencing factor information corresponding to each attribute information is quantified, wherein the influencing factor includes the factor information that affects the execution and motivation of the security detection task in crowdsourcing; based on the hierarchical analysis method, the weight of the influencing factor information is determined; the weight of the influencing factor information is verified for consistency; and in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, the evaluation score of the crowdsourcing object is determined. This solves the technical problem of poor completion quality of crowdsourcing tasks in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0018] Figure 1 It is a flow chart of a crowdsourcing object evaluation method for security detection tasks provided in an embodiment of the present application;

[0019] Figure 2 This is a diagram of a crowdsourcing object evaluation device for security detection tasks provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0023] In addition, the term "plurality" shall mean two or more.

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] Figure 1 An embodiment of a crowdsourcing object evaluation method for a security detection task is shown, comprising:

[0026] Step 101, in response to obtaining multiple attribute information of crowdsourcing objects for security detection tasks, quantify influencing factor information corresponding to each attribute information, wherein the influencing factor includes factor information that affects the execution and motivation of the security detection task in crowdsourcing.

[0027] In this embodiment, the executing entity obtains multiple attribute information of the crowdsourcing object for the security detection task, such as the community loyalty information, monitoring point resource information and participation activity information of the crowdsourcing object, and then quantifies the influencing factors corresponding to each attribute information. The quantification process can be the definition of the calculation method of each influencing factor information.

[0028] The influencing factors corresponding to the community loyalty information may include task effective completion rate information, personal integrity index information, and the number of points held. The effective completion rate information can be quantified as The personal integrity index can be quantified as A2. The initial integrity index of A2 is 1. The percentage is used and the number of dishonest behaviors is counted. Each dishonest behavior will be calculated as 90% of the previous one. At the same time, the user's performance is counted. For every 5 successful performances, 1% of the integrity value will be restored (the above weights can be adjusted according to actual needs); the holding points value is quantified as A3. Points are obtained by completing tasks and can be exchanged.

[0029] The influencing factors corresponding to the monitoring point resource information may include the network area information, the number of supported task types, the average availability of the execution results, and the task-specific weight. To quantify the network area information, the network area can be defined as B1; to quantify the supported task types, the number of task types that can be executed by the monitoring point can be quantified as B2; to quantify the average availability of the execution results, the average availability can be quantified as Where N effective It is the number of tasks available for execution results; the task-specific weight is quantified, which can be the definition of the task-specific weight, which can be defined according to the difficulty of task execution and the demand for resources, and is defined as B4.

[0030] The influencing factors corresponding to the participation activity information may include the number of tasks participated in, the number of task types, the acceptance rate of assigned tasks, the response speed of assigned tasks, and the average participation in the tasks.

[0031] The number of participating tasks can be quantified as C1=N accepted , where N accepted is the number of dispatched tasks that the monitoring point agrees to perform. The number of participating task types can be defined as C2, that is, the task types performed by the monitoring point. The acceptance rate can be quantified as Among them, N assigned The number of tasks dispatched by the scheduling mechanism to the monitoring point; the response speed of dispatching tasks is quantified as Where T start and T end are the start and end time of the task validity period, T accepted is the time when the monitoring point accepts the assigned task; the average participation rate of the task can be Where N all is the number of all scheduled tasks.

[0032] Step 102: Determine the weight of the influencing factor information based on the hierarchical analysis method.

[0033] As an optional implementation method of this embodiment, based on the hierarchical analysis method, determining the weight of the influencing factor information includes: establishing a hierarchical model for multiple attribute information, determining the correlation information of the influencing factor information corresponding to each attribute information; establishing a multi-dimensional comparison matrix for the influencing factors; calculating the maximum eigenvalue and the corresponding eigenvector of the comparison matrix; normalizing the eigenvector to obtain the influence weight value of the influencing factor.

[0034] In this embodiment, it can be known from step 101 that the attribute information of the crowdsourcing object can be constructed from bottom to top into three levels: community loyalty information (A layer), monitoring point resource information (B layer) and participation activity information (C layer). A hierarchical model can be constructed based on the n influencing factors corresponding to the attribute information of the crowdsourcing object to determine the mutual influence relationship between the factors, which can include: constructing an n-dimensional influencing factor comparison matrix based on the n influencing factors, with each influencing factor as the row and column of the matrix, and comparing the factors that influence each other at the same level in pairs; calculating the maximum eigenvalue λ of the comparison matrix Λ and its corresponding eigenvector w, w is normalized to obtain the influence weight value of each factor norm(w)={w1,…w n}.

[0035] Step 103: verify the consistency of the weights of the influencing factor information.

[0036] In some optional implementations of the present embodiment, consistency verification of the weight of the influencing factor information includes: determining a calculated consistency value based on the number of feature vectors and influencing factors; determining a ratio of the calculated consistency value to the random consistency value in response to obtaining a random consistency value; and determining whether the weight of the influencing factor information satisfies consistency based on a judgment result of whether the ratio is within a preset value range.

[0037] In this embodiment, the implementation of consistency comparison may include: calculating consistency and obtaining Look up the table to obtain random consistency RI; if The calculated weights meet the consistency requirements; if the weights do not meet the consistency requirements, modify the influencing factors and comparison matrix until the consistency verification meets the requirements.

[0038] Step 104 , in response to the weight of the influencing factor information, a consistency verification result indicates that the consistency verification is satisfied, and an evaluation score of the crowdsourcing object is determined.

[0039] In some optional implementations of the present embodiment, in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, determining the weight value of the detection point includes: in response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, performing dimensionless processing on the quantified influencing factor information; calculating the value of the influencing factor information after dimensionless processing based on the fuzzy integral method, and determining it as the evaluation score of the crowdsourcing object.

[0040] In this embodiment, based on the weight values ​​that meet the consistency, the fuzzy integral method can be used to calculate the weight values ​​of the monitoring points. For example, it may include: using the Karsa method to calculate the weight values ​​of each quantitative factor p i Dimensionless processing is performed to make each factor comparable. Where max and min are the upper and lower bounds of the integral domain. Fuzzy integral calculation factor values, Among them, g(.) is a fuzzy measure, which is calculated using the Sugeon measure. R is the crowdsourcing evaluation score that combines all factors.

[0041] The method of nonlinear calculation of fuzzy integral based on Sugeon fuzzy measure avoids the assumption that evaluation indicators are independent of each other. It not only comprehensively considers the fuzzy strength of indicator factors, but also considers the importance of evaluation factors. It also emphasizes the influence of the relationship between factors on the evaluation results, and improves the crowdsourcing user evaluation mechanism with certain subjective value evaluation.

[0042] The present embodiment discloses a crowdsourcing object evaluation method for security detection tasks. In response to obtaining multiple attribute information of crowdsourcing objects for security detection tasks, the influencing factor information corresponding to each attribute information is quantified, wherein the influencing factor includes the factor information that affects the execution and incentive of the security detection task in crowdsourcing; based on the hierarchical analysis method, the weight of the influencing factor information is determined; the weight of the influencing factor information is verified for consistency; and the evaluation score of the crowdsourcing object is determined in response to the consistency verification result indicating that the consistency verification is satisfied. It can avoid the bias problem existing in the scoring mechanism that relies solely on the weight of each factor, thereby realizing an effective evaluation mechanism that comprehensively considers the contribution and positive incentives of the participants in the crowdsourcing task.

[0043] refer to Figure 2 , Figure 2 An embodiment of a crowdsourcing object evaluation device for a security detection task is shown, and the device includes:

[0044] The quantification unit 201 is configured to, in response to obtaining multiple attribute information of a crowdsourcing object for a security detection task, quantify the influencing factor information corresponding to each attribute information, wherein the influencing factor includes the factor information that affects the execution and motivation of the security detection task in the crowdsourcing;

[0045] A first determining unit 202 is configured to determine the weight of the influencing factor information based on a hierarchical analysis method;

[0046] As an optional implementation method of this embodiment, the first determination unit is further configured to: establish a hierarchical model for multiple attribute information, determine the correlation information of the influencing factor information corresponding to each attribute information; establish a multi-dimensional comparison matrix for the influencing factors; calculate the maximum eigenvalue and corresponding eigenvector of the comparison matrix; normalize the eigenvector to obtain the influence weight value of the influencing factor.

[0047] A verification unit 203, configured to perform consistency verification on the weight of the influencing factor information;

[0048] As an optional implementation method of this embodiment, the verification unit is further configured to: determine a calculated consistency value based on the number of feature vectors and influencing factors; in response to obtaining a random consistency value, determine a ratio of the calculated consistency value to the random consistency value; based on a judgment result of whether the ratio is within a preset value range, determine whether the weight of the influencing factor information satisfies consistency.

[0049] The second determining unit 204 is configured to determine the evaluation score of the crowdsourcing object in response to the consistency verification result indicating that the consistency verification is satisfied in response to the weight of the influencing factor information.

[0050] As an optional implementation method of this embodiment, the second determination unit is further configured to: perform dimensionless processing on the quantified influencing factor information in response to a consistency verification result indicating that the consistency verification is satisfied in response to the weight of the influencing factor information; calculate the value of the dimensionless processed influencing factor information based on the fuzzy integral method, and determine it as the evaluation score of the crowdsourcing object.

[0051] This embodiment is aimed at the evaluation of crowdsourcing of network detection tasks. The interaction between different levels of influencing factors is determined by the hierarchical analysis method, and the task requirement list is matched and optimized by the consistency test method. The influence of uncertain multi-objectives and subjective information on user evaluation is mixed by fuzzy integral method to avoid the bias problem existing in the single reliance on the weight scoring mechanism of each factor, thereby realizing an effective evaluation mechanism that comprehensively considers the contribution and positive incentives of the participants in the crowdsourcing task. It avoids the problem of not being able to accurately reflect the user participation caused by relying solely on user points, as well as malicious fraud caused by points; the introduction of fuzzy integral method avoids the assumption of independence between evaluation indicators, and more accurately evaluates the problem of subjective value evaluation of the design.

[0052] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A crowdsourcing object evaluation method for security detection tasks, comprising: In response to obtaining multiple attribute information of crowdsourcing objects for security detection tasks, the influencing factor information corresponding to each attribute information is quantified, wherein the influencing factors include the factor information that affects the execution and incentive of the security detection task in crowdsourcing, wherein the community loyalty information, monitoring point resource information and participation activity information of the crowdsourcing object; the influencing factor information corresponding to the community loyalty information includes the effective completion rate information of the task, the personal integrity index information, and the number of points held, and the effective completion rate information is quantified as The personal integrity index is quantified as A2. The initial integrity index of A2 is 1. The percentage of use is calculated according to the number of dishonest behaviors. Each dishonest behavior will be calculated as 90% of the previous one. At the same time, the user's performance is counted. After every 5 successful performances, 1% of the integrity value is restored; the holding points are quantified as A3. Points are obtained by completing tasks and can be exchanged; the influencing factors corresponding to the monitoring point resource information include the network area information, the number of supported task types, the average availability of execution results and the task-specific weight. The network area information is quantified, which is to define the network area, which is defined as B1; the supported task types are quantified as the number of task types that can be executed by the monitoring point B2; the average availability of execution results is quantified as Where N effective is the number of tasks available for execution results; task-specific weights are quantified, which is the definition of task-specific weights, defined according to the difficulty of task execution and the demand for resources, and defined as B4; the influencing factors corresponding to the participation activity information include the number of participating tasks, the number of task types, the acceptance rate of assigned tasks, the response speed of assigned tasks, and the average participation of participating tasks; the number of participating tasks is quantified as C1=N accepted , where N accepted is the number of dispatched tasks that the monitoring point agrees to perform, the number of participating task types is defined as C2, that is, the type of tasks performed by the monitoring point; the acceptance rate is quantified as Among them, N assigned The number of tasks dispatched by the scheduling mechanism to the monitoring point; the response speed of dispatching tasks is quantified as Where T start and T end are the start and end time of the task validity period, T accepted is the time when the monitoring point accepts the assigned task; the average participation rate of the task Where N all is the number of all scheduled tasks; Based on the hierarchical analysis method, the weight of the influencing factor information is determined. Based on the attribute information of the crowdsourcing object, three levels are constructed from bottom to top, namely, the community loyalty information A layer, the monitoring point resource information B layer and the participation activity information C layer. Based on the n influencing factors corresponding to the attribute information of the crowdsourcing object, a hierarchical model is constructed to determine the mutual influence relationship between the factors, including: constructing an n-dimensional influencing factor comparison matrix based on the n influencing factors, with each influencing factor as the row and column of the matrix, and comparing the factors that influence each other at the same level in pairs; calculating the maximum eigenvalue λ of the comparison matrix Λ and its corresponding eigenvector w, w is normalized to obtain the influence weight value of each factor norm(w)={w1,…w n }; The consistency of the weight of the influencing factor information is verified, and the implementation of consistency comparison includes: calculating the consistency Look up the table to obtain random consistency RI; if If the weights do not meet the consistency requirements, modify the influencing factors and comparison matrix until the consistency verification meets the requirements. In response to the weight of the influencing factor information, a consistency verification result indicates that the consistency verification is satisfied, and an evaluation score of the crowdsourcing object is determined.

2. The crowdsourcing object evaluation method for security detection tasks according to claim 1 is characterized in that: The consistency verification of the weight of the influencing factor information includes: Determine and calculate a consistency value based on the feature vector and the number of influencing factors; In response to obtaining the random consistency value, determining a ratio of the calculated consistency value to the random consistency value; Based on the judgment result of whether the ratio is within a preset numerical range, it is determined whether the weight of the influencing factor information satisfies consistency.

3. The crowdsourcing object evaluation method for security detection tasks according to claim 1 is characterized in that: In response to the consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, determining the weight value of the detection point includes: In response to a consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, performing dimensionless processing on the quantified influencing factor information; The value of the dimensionless processed influencing factor information is calculated based on the fuzzy integral method, and is determined as the evaluation score of the crowdsourcing object.

4. A crowdsourcing object evaluation device for security detection tasks, comprising: The quantification unit is configured to quantify the influencing factor information corresponding to each attribute information in response to obtaining multiple attribute information of the crowdsourcing object for the security detection task, wherein the influencing factor includes the factor information that affects the execution and incentive of the security detection task in the crowdsourcing, wherein the community loyalty information, monitoring point resource information and participation activity information of the crowdsourcing object; the influencing factor information corresponding to the community loyalty information includes the effective completion rate information of the task, the personal integrity index information, and the number of points held, and the effective completion rate information is quantified to be The personal integrity index is quantified as A2. The initial integrity index of A2 is 1. The percentage of use is calculated according to the number of dishonest behaviors. Each dishonest behavior will be calculated as 90% of the previous one. At the same time, the user's performance is counted. After every 5 successful performances, 1% of the integrity value is restored; the holding points are quantified as A3. Points are obtained by completing tasks and can be exchanged; the influencing factors corresponding to the monitoring point resource information include the network area information, the number of supported task types, the average availability of execution results and the task-specific weight. The network area information is quantified, which is to define the network area, which is defined as B1; the supported task types are quantified as the number of task types that can be executed by the monitoring point B2; the average availability of execution results is quantified as Where N effective is the number of tasks available for execution results; task-specific weights are quantified, which is the definition of task-specific weights, which can be defined according to the difficulty of task execution and the demand for resources, and is defined as B4; the influencing factors corresponding to the participation activity information include the number of participating tasks, the number of task types, the acceptance rate of assigned tasks, the response speed of assigned tasks, and the average participation of participating tasks; the number of participating tasks is quantified as C1=N accepted , where N accepted is the number of dispatched tasks that the monitoring point agrees to perform, the number of participating task types is defined as C2, that is, the type of tasks performed by the monitoring point; the acceptance rate is quantified as Among them, N assigned The number of tasks dispatched by the scheduling mechanism to the monitoring point; the response speed of dispatching tasks is quantified as Where T start and T end are the start and end time of the task validity period, T accepted is the time when the monitoring point accepts the assigned task; the average participation rate of the task Where N all is the number of all scheduled tasks; The first determination unit is configured to determine the weight of the influencing factor information based on the hierarchical analysis method, construct three levels from bottom to top, namely, the community loyalty information A level, the monitoring point resource information B level, and the participation activity information C level, based on the attribute information of the crowdsourcing object, and construct a hierarchical model based on the n influencing factors corresponding to the attribute information of the crowdsourcing object to determine the mutual influence relationship between the factors, including: constructing an n-dimensional influencing factor comparison matrix based on the n influencing factors, each influencing factor being a row and a column of the matrix, and comparing the factors that influence each other at the same level in pairs; calculating the maximum eigenvalue λ of the comparison matrix Λ and its corresponding eigenvector w, w is normalized to obtain the influence weight value of each factor norm(w)={w1,…w n }; The verification unit is configured to verify the consistency of the weight of the influencing factor information, and the implementation of the consistency comparison includes: calculating the consistency Look up the table to obtain random consistency RI; if If the weights do not meet the consistency requirements, modify the influencing factors and comparison matrix until the consistency verification meets the requirements. The second determining unit is configured to determine the evaluation score of the crowdsourcing object in response to the consistency verification result indicating that the consistency verification is satisfied in response to the weight of the influencing factor information.

5. The crowdsourcing object evaluation device for security detection tasks according to claim 4 is characterized in that: The verification unit is further configured to: Determine and calculate a consistency value based on the feature vector and the number of influencing factors; In response to obtaining the random consistency value, determining a ratio of the calculated consistency value to the random consistency value; Based on the judgment result of whether the ratio is within a preset numerical range, it is determined whether the weight of the influencing factor information satisfies consistency.

6. The crowdsourcing object evaluation device for security detection tasks according to claim 4 is characterized in that: The second determining unit is further configured to: In response to a consistency verification result of the weight of the influencing factor information indicating that the consistency verification is satisfied, performing dimensionless processing on the quantified influencing factor information; The value of the dimensionless processed influencing factor information is calculated based on the fuzzy integral method, and is determined as the evaluation score of the crowdsourcing object.

7. A computer processing device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

8. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images