Unmanned cluster reputation value measurement and evaluation method and system

Abstract

The invention discloses an unmanned cluster reputation value measurement and evaluation method and system, and the method comprises the steps: introducing credible service persistence evaluation according to a task completion degree, a quotation gain and a cumulative reputation value of a reputation value matrix participation unit, giving a higher reputation gain to a unit which stably provides high-quality service for a long time, and also setting a reputation punishment mechanism. And forcefully constraining the unit of the continuous untrusted service, and finally forming a global reputation value. An accurate and reliable basis is provided for refining of feasible alliances, a task initiator can select a more appropriate participation unit and construct an optimal alliance execution task accordingly, the task execution efficiency and quality are greatly improved, the credibility of different participation units can be clearly defined, the situation that a low-reputation unit interferes with normal operation of a system is prevented, and the system reliability is improved. Each unit is stimulated to actively show good behaviors, the reputation of the unit is improved, and the reputation value is measured and calculated more comprehensively.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned cluster task allocation, and relates to an unmanned cluster reputation value calculation and evaluation method and system. Background Art

[0002] In the process of unmanned swarms performing tasks, reputation value calculation is crucial for task allocation, partner selection, and the overall stable and efficient operation of the system. Accurate reputation values ​​can help task initiators screen out reliable participating units, refine feasible alliances, optimize task allocation plans, and improve the success rate and quality of task execution.

[0003] However, the existing unmanned cluster reputation value calculation methods have many defects and shortcomings. On the one hand, the existing calculation methods often only consider a single factor, such as evaluating reputation based only on task completion or quotation rationality, ignoring other important influencing factors, resulting in the reputation value being unable to fully and accurately reflect the true credibility of the participating units. On the other hand, there is a lack of effective consideration of the sustainability of trusted services, which cannot motivate participating units to provide high-quality services in a long-term and stable manner. When facing the dishonest behavior of participating units, the punishment mechanism of the existing methods is not perfect, and it is difficult to effectively constrain continuous untrustworthy services, so that some bad behaviors do not receive the due punishment, affecting the fairness and stability of the system. In addition, the existing methods have not fully integrated and utilized the indirect reputation evaluation from other task participants, resulting in the one-sidedness of the reputation value calculation, and unable to provide a comprehensive and accurate decision-making basis for the task initiator. These problems have seriously affected the task execution efficiency and overall performance of the unmanned cluster system and need to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that in the process of unmanned cluster executing tasks in the prior art, only a single factor is considered, which cannot fully and accurately reflect the true credibility of the participating units, resulting in the one-sidedness of the reputation value calculation, and cannot provide a comprehensive and accurate decision-making basis for the task initiator, thereby reducing the task execution efficiency and overall performance. A method and system for measuring and evaluating the reputation value of an unmanned cluster is provided.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for calculating and evaluating the reputation value of an unmanned cluster comprises the following steps:

[0007] Acquire historical data of participating units, the historical data including task completion, bid gain, reputation value matrix, continuous trust times and continuous untrust times;

[0008] The cumulative reputation value is calculated based on the task completion, quotation gain and reputation value matrix;

[0009] Calculate the direct reputation value gain based on the continuous trust times and the cumulative reputation value;

[0010] Construct a penalty function based on the continuous untrust times and the direct reputation value gain, and calculate the penalty value based on the penalty function;

[0011] Calculate the indirect reputation value gain based on the direct reputation value gain;

[0012] Calculate the global reputation value gain of the participating unit based on the direct reputation value gain and the indirect reputation value gain;

[0013] Calculate the global reputation value of each participating unit based on the global reputation value gain of the participating unit and the penalty value.

[0014] A further improvement of the present invention lies in:

[0015] The calculation of the cumulative reputation value includes:

[0016] Calculate the cumulative reputation value according to the task completion degree, the quotation gain and the reputation value matrix:

[0017]

[0018] Wherein, Represents the task completion degree of the participating unit r j In the kth historical cooperation with the task initiator s i ; Represents the participating unit r j In the kth cooperation with the task initiator s i The reputation gain brought by the rationality evaluation result of the quotation, wherein

[0019] The calculation of the direct reputation value gain includes:

[0020] Define a sustainability factor according to the continuous trust times:

[0021]

[0022] Wherein, d represents the minimum number of trust times to establish reputation; x j Represents the continuous trust times of the participating unit;

[0023] Calculate the direct reputation value gain according to the sustainability factor and the cumulative reputation value:

[0024]

[0025] Wherein, Represents the cumulative reputation value.

[0026] The calculation of the penalty value includes:

[0027] Define the penalty factor for continuous untrustworthy behavior according to the number of continuous untrustworthy times as follows:

[0028]

[0029] Among them, y j represents the number of continuous untrustworthy times of participating unit r j .

[0030] Let represent the penalty function of task publisher s i and participating unit r j in the past k historical interactions as follows:

[0031]

[0032] Among them, ω is the reputation threshold; represents the reputation value before the kth interaction;

[0033] The penalty value measured by initiator i for task participating unit j in the kth cooperation is:

[0034]

[0035] Among them, y j represents the number of continuous untrustworthy times of participating unit r j .

[0036] The indirect reputation value gain is obtained through the following formula:

[0037]

[0038] Among them, N is the number of other task participants, and R i,s is the trust value of task publisher i for other task participants.

[0039] The global reputation value gain of the participating unit is obtained through the following formula:

[0040]

[0041] Among them, represents the trust coefficient of the task initiator for direct and indirect reputations.

[0042] The calculated global reputation values of each participating unit include

[0043] Obtain the reputation measurement model of multiple participating units according to the global reputation value gain and penalty value:

[0044]

[0045] Set the constraint conditions of the model to obtain the feasible coalition set:

[0046]

[0047] Among them, δ A represents the cumulative global reputation value; represents the average global reputation value; c A represents the value of redundant resources; represents the relative redundant resources; δ 0 represents the threshold of the cumulative global reputation value; represents the threshold of the average global reputation value.

[0048] An unmanned cluster reputation value measurement and evaluation system, comprising:

[0049] A historical data acquisition module, configured to acquire the historical data of participating units, where the historical data includes task completion degree, quotation gain, reputation value matrix, continuous trustworthy times, and continuous untrustworthy times;

[0050] A direct reputation value gain acquisition module, configured to calculate the cumulative reputation value according to the task completion degree, quotation gain, and reputation value matrix, and calculate the direct reputation value gain according to the continuous trustworthy times and the cumulative reputation value;

[0051] A penalty mechanism acquisition module, configured to construct a penalty function according to the continuous untrustworthy times and the direct reputation value gain, and calculate the penalty value based on the penalty function;

[0052] An indirect reputation acquisition module, configured to calculate the indirect reputation value gain according to the direct reputation value gain;

[0053] A global reputation value acquisition module for each participating unit, configured to calculate the global reputation value gain of the participating unit according to the direct reputation value gain and the indirect reputation value gain, and calculate the global reputation value of each participating unit according to the global reputation value gain of the participating unit and the penalty value.

[0054] A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of the present inventions when executing the computer program.

[0055] A computer-readable storage medium, storing a computer program, where the computer program implements the steps of the method according to any one of the present inventions when executed by a processor.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] This application discloses a method for calculating and evaluating the reputation value of an unmanned cluster. According to the task completion rate, quotation gain, and the cumulative reputation value of the participating units in the reputation value matrix, and by introducing the evaluation of reliable service sustainability, higher reputation gain is given to the units that can stably provide high-quality services for a long time. A reputation penalty mechanism is also established to strongly constrain the units that continuously provide untrustworthy services, and finally a global reputation value is formed. It provides an accurate and reliable basis for the refinement of feasible coalitions. The task initiator can select more suitable participating units based on this to construct an optimal coalition to execute tasks, greatly improving the task execution efficiency and quality. This application can clearly define the credibility of different participating units, prevent low-reputation units from interfering with the normal operation of the system, encourage each unit to actively demonstrate good behavior and improve its own reputation. The calculation of the reputation value is more comprehensive, comprehensively weighing various factors, achieving a scientific and fair calculation of the reputation value of the participating units, laying a reliable foundation for system decisions such as task allocation and resource allocation, and thus comprehensively improving the operation efficiency and overall performance of the unmanned cluster system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1 It is the system flowchart of the present invention;

[0060] Figure 2 It is the flowchart of the method for refining the feasible coalition of the unmanned cluster of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention usually described and shown in the drawings here can be arranged and designed in various different configurations.

[0062] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0063] It should be noted that like reference numerals and letters refer to like items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0064] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper", "lower", "horizontal", "inner", etc. are used to indicate the orientation or positional relationship, it is based on the orientation or positional relationship shown in the figures, or the orientation or positional relationship in which the product of the invention is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0065] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but it can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but it can be slightly inclined.

[0066] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, if terms such as "set", "installed", "connected", "coupled" are used, they 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 directly connected or indirectly connected through an intermediate medium, and it can be the communication inside 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 specific situations.

[0067] The present invention will be further described in detail below with reference to the accompanying drawings:

[0068] See Figures 1 to 2 , an embodiment of the present invention discloses a method for calculating and evaluating the reputation value of an unmanned cluster, which comprehensively integrates multi-dimensional reputation evaluation elements, deeply considers the task completion degree, historical reputation value, and quotation reasonableness, and at the same time focuses on the sustainable credibility service and the reputation penalty mechanism, aiming to make the calculated reputation value accurately reflect the true level of participating units, so as to refine a feasible coalition set. Through such a design, the credibility of different participating units can be clearly defined, preventing low-reputation units from interfering with the normal operation of the system, and motivating each unit to actively demonstrate good behavior and improve its own reputation.

[0069] The present invention constructs an optimized model for calculating reputation values based on edge self-organization, comprehensively weighs various factors, and achieves a scientific and fair calculation of the reputation values of participating units. The model can flexibly adjust the calculation rules and index weights of reputation values according to task characteristics, environmental changes, and the real-time status of participating units, ensuring the accuracy and timeliness of reputation value calculation, laying a reliable foundation for system decisions such as task allocation and resource allocation, and thus comprehensively improving the operation efficiency and overall performance of the unmanned cluster system.

[0070] Specifically, it includes the following steps:

[0071] Step 1: Obtain the historical data of the participating units, where the historical data includes task completion degree, quotation gain, reputation value matrix, continuous credible times, and continuous non-credible times;

[0072] During the implementation of edge self-organization based on tasks, the task publisher needs to calculate the reputation value of the participating units according to three factors: task completion degree, historical reputation value, and quotation rationality.

[0073] Among them:

[0074] The task completion degree and historical reputation value are known data obtained according to past task completion situations,

[0075] The quotation rationality only considers the price differences between participating units and does not involve task completion situations.

[0076] In addition, according to different measuring units, the reputation needs to be divided into direct reputation and indirect reputation. At the same time, a penalty factor is added on this basis, and a complete reputation measurement model is comprehensively analyzed to evaluate the reputation value of the participating units, so that the task publisher can select the most suitable participating unit.

[0077] Step 2: Calculate the direct reputation value gain

[0078] Calculate the cumulative reputation value according to the task completion degree, quotation gain, and reputation value matrix;

[0079] Specifically, the direct reputation evaluation refers to the reputation evaluation of the historical performance behavior of the participating units of the task by the task initiator. Therefore, the reputation value is obtained by analyzing historical cooperation behaviors.

[0080] Let represent the historical reputation value of the task initiator s i accumulated about r j in the past k interactions with the task participating unit r j where

[0081] represent the participating unit r jIn the k-th historical cooperation of the task initiator s i The task completion rate.

[0082] Among them Indicates the reputation gain brought by the rationality evaluation result of the quote of the participating unit r j In the k-th cooperation of the task initiator s i When the quote of the participating unit is within the interval [p, q], it means the quote is reasonable. If it is not within the interval, it means the quote is unreasonable and the participating unit set is excluded.

[0083] When the quote of the participating unit is within the interval [p, q], it means the quote is reasonable. If it is not within the interval, it means the quote is unreasonable and the participating unit set is excluded.

[0084] The update formula for the cumulative reputation value is:

[0085]

[0086] Among them, α represents the historical factor, which is used to adjust the evaluation proportion of historical reputation, and β is the weight of quote rationality. When k = 0, it means there is no historical cooperation record between the two.

[0087] The above update formula realizes the reputation value update of the participating unit r i by the initiator s according to the historical reputation of the task participating unit and the completion rate of the current task. j The reputation value update.

[0088] Step 3: Reliable service persistence evaluation

[0089] Calculate the direct reputation gain based on the continuous reliable times and the cumulative reputation value;

[0090] When conducting reputation evaluation, it is also necessary to consider the persistence of the reliable services provided by the task participating units, and give higher reputation gains to the participating units with higher persistence.

[0091] Let a thereshold be a threshold of the task completion rate. When the task completion rate exceeds this threshold, it is called a reliable service. Assume that the continuous reliable times of the task participating unit r j is x j , and define the following continuous factor f(x j ):

[0092]

[0093] Among them, d represents the minimum reliable times to establish reputation. When x j is less than d, the continuous factor grows slowly. When x j exceeds d, the continuous factor grows rapidly and finally converges to 1.

[0094] Furthermore, combining the persistence factor, the formula for the reputation value gain of the initiator i for the task participation unit j in the k-th cooperation can be obtained, that is, the direct reputation value gain:

[0095]

[0096] Some task participation units may have a low task completion rate due to their own mistakes when participating in a certain task, but their overall past reputation value is relatively high. At this time, due to the persistence factor becoming 0, their reputation value will be reduced to the initial value R 0 , where R 0 represents the initial value of the direct reputation value, and the initial value + value gain = cumulative value.

[0097] Step 4: Reputation penalty mechanism

[0098] Construct a penalty function based on the number of consecutive untrustworthy times and the direct reputation value gain, and calculate the penalty value based on the penalty function.

[0099] Specifically, when some task units continuously provide untrustworthy services, they should receive a reputation penalty value. Therefore, a penalty factor is introduced. Let the number of consecutive untrustworthy times of the participation unit r j be y j , and the penalty factor for consecutive untrustworthy behaviors be p(y j ):

[0100]

[0101] In actual situations, there will be two phenomena: dishonesty and mistakes. Therefore, it is necessary to introduce a penalty function to make a judgment according to different situations. Let represent the penalty function of the task publisher s i and the participation unit r j in the past k historical interactions:

[0102]

[0103] Among them, ω is the reputation threshold. When the task initiator and the task participation unit r j have their most recent interaction, if r j provides an untrustworthy service, then calculate the reputation value before the k-th interaction and judge the behavior type of the participation unit accordingly. If then it is considered that the participation unit continuously provides untrustworthy services, and at this time the penalty function will be a value less than 0; if then it can be considered that the participation unit caused this untrustworthy behavior due to a mistake, and at this time no additional penalty value is added.

[0104] Furthermore, after considering the penalty factor, the formula for calculating the penalty value of the initiator i for the task participation unit j in the k-th cooperation is as follows:

[0105]

[0106] Step 5: Recommendation reputation evaluation, i.e., indirect reputation evaluation

[0107] Calculate the indirect reputation value gain based on the direct reputation value gain, and calculate the global reputation value gain of the participation unit based on the direct reputation value gain and the indirect reputation value gain.

[0108] Specifically, in the process of reputation value evaluation, the reputation evaluation of the historical behavior of the participation unit from other task participants belongs to indirect reputation and is part of the entire reputation value evaluation.

[0109] Based on the direct reputation evaluation process, the recommended reputation value can be obtained:

[0110] Then, the recommended reputation value gain, i.e., the indirect reputation value gain, is obtained through the following formula:

[0111]

[0112] Among them, N is the number of other task participants, and R i,s is the trust value of the task publisher i for other task participants.

[0113] Furthermore, the global reputation value of the participation unit r j can be obtained:

[0114] Then, the global reputation value gain:

[0115]

[0116] Among them, represents the trust coefficient of the task initiator for direct reputation and recommended reputation.

[0117] Step 6: Calculate the global reputation value of each participation unit based on the global reputation value gain and the penalty value.

[0118] Obtain the reputation measurement model for multiple participation units:

[0119]

[0120] Furthermore, reputation application decision:

[0121] For a feasible coalition, it can be evaluated from multiple perspectives such as reputation value and redundant resources:

[0122] Cumulative global reputation value, δ A =∑ i∈A δ i;

[0123] Average global reputation value

[0124] Redundant resource value

[0125] Relative redundant resources

[0126] By further setting the constraint conditions of the evaluation parameters, the feasible coalition set can be further refined to cope with the complex battlefield environment, that is:

[0127]

[0128] Among them, the cumulative global reputation value δ A is greater than the threshold δ 0 , and the average global reputation value is greater than the threshold Then A is screened out as a feasible coalition

[0129] Specifically, in this embodiment, the algorithm flow for calculating the reputation value of the task participation unit is as follows:

[0130]

[0131] By comprehensively considering multi-dimensional factors such as task completion degree, historical reputation value, and quotation rationality, combined with the continuous trusted service evaluation and reputation penalty mechanism, the accuracy and reliability of the reputation value calculation of the unmanned cluster are significantly improved, and at the same time, the constraints and incentives for the behavior of the participation units are enhanced. The reputation evaluation system that adopts comprehensive multi-source information effectively differentiates the credibility of different participation units, solves the problems existing in the existing reputation value calculation methods, such as single consideration factors, lack of dynamic adjustment, and inability to effectively restrain bad behaviors, and improves the overall operation efficiency of the unmanned cluster.

[0132] This embodiment also discloses an unmanned cluster reputation value calculation and evaluation system, including:

[0133] Historical data acquisition module, used to acquire the historical data of the participation unit, and the historical data includes task completion degree, quotation gain, reputation value matrix, continuous trusted times, and continuous untrusted times;

[0134] Direct reputation value gain acquisition module, used to calculate the cumulative reputation value according to the task completion degree, quotation gain, and reputation value matrix, and calculate the direct reputation value gain according to the continuous trusted times and the cumulative reputation value;

[0135] Penalty mechanism acquisition module, used to construct a penalty function according to the continuous untrusted times and the direct reputation value gain, and calculate the penalty value based on the penalty function;

[0136] An indirect reputation acquisition module, configured to calculate an indirect reputation value gain based on a direct reputation value gain;

[0137] A global reputation value acquisition module for each participating unit, configured to calculate a global reputation value gain of the participating unit based on the direct reputation value gain and the indirect reputation value gain, and calculate the global reputation value of each participating unit according to the global reputation value gain and a penalty value

[0138] It is committed to overcoming the problems existing in the existing alliance screening methods, such as fuzzy criteria, low efficiency, and difficulty in adapting to dynamic environments. To achieve precise screening of feasible alliances, the present invention establishes a comprehensive reputation value measurement and evaluation system. It fully considers core elements such as task completion degree, historical reputation value, and quotation reasonableness, comprehensively measures the past performance of participating units; integrates a credible service persistence evaluation and a reputation penalty mechanism to effectively evaluate the stability of the services of participating units and restrain bad behaviors. It can accurately identify the reputation status of different participating units and provide solid and reliable reputation data support for the refinement of feasible alliances.

[0139] A schematic diagram of a terminal device provided by an embodiment of the present invention. The terminal device in this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0140] The computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention.

[0141] The terminal device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0142] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0143] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory, the processor implements various functions of the terminal device.

[0144] If the modules / units integrated in the terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0145] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for calculating and evaluating the reputation value of an unmanned cluster, characterized in that: The following steps are involved: Acquire historical data of participating units, the historical data including task completion, bid gain, reputation value matrix, continuous trust times and continuous untrust times; The cumulative reputation value is calculated based on the task completion, quotation gain and reputation value matrix; Direct reputation gain is calculated based on the number of continuous trustworthiness and the accumulated reputation value; A penalty function is constructed based on the number of continuous untrustworthiness and the direct reputation value gain, and the penalty value is calculated based on the penalty function; The indirect reputation value gain is calculated based on the direct reputation value gain; Calculate the global reputation gain of the participating unit according to the direct reputation gain and the indirect reputation gain; The global reputation value of each participating unit is calculated based on the global reputation value gain and penalty value of the participating unit.

2. The unmanned cluster reputation value calculation and evaluation method according to claim 1 is characterized in that: The calculation of the accumulated reputation value includes: The cumulative reputation value is calculated based on the task completion, quotation gain and reputation value matrix: in, Represents participating unit r j In the task initiator i The task completion degree in the k-th historical cooperation; Represents participating unit r j In the task initiator i The reputation gain brought by the rationality evaluation result of the quotation in the k-th cooperation, where 3. The unmanned cluster reputation value calculation and evaluation method according to claim 1 is characterized in that: The calculation to obtain a direct reputation gain includes: The sustainability factor is defined based on the number of continuous trustworthy times: Where d represents the minimum number of credible times to establish credibility; x j Indicates the number of continuous trustworthy times of participating units; Direct reputation gain is calculated based on the sustainable factor and the accumulated reputation: in, Indicates the accumulated reputation value.

4. The unmanned cluster reputation value calculation and evaluation method according to claim 1 is characterized in that: The penalty value is obtained by calculating, including: The penalty factor for continuous untrustworthy behavior is defined according to the number of continuous untrustworthy behaviors: Among them, y j Represents participating unit r j The number of times the continuous untrustworthiness is set up Indicates the task publisher s i and participation unit j The penalty function in the past k historical interactions is: Where, ω is the reputation threshold; represents the reputation value before the kth interaction; The penalty value of the initiator i to the task participant j in the kth cooperation is calculated as: Among them, y j Represents participating unit r j The number of continuous untrustworthy times.

5. The unmanned cluster reputation value calculation and evaluation method according to claim 1 is characterized in that: The indirect reputation gain is obtained by the following formula: Where N is the number of other task participants, R i,s is the trust value of task publisher i to other task participants.

6. The unmanned cluster reputation value calculation and evaluation method according to claim 5 is characterized in that: The global reputation gain of the participating unit is obtained by the following formula: Among them, γ represents the trust coefficient of the task initiator for direct reputation and indirect reputation.

7. The unmanned cluster reputation value calculation and evaluation method according to claim 1 is characterized in that: The calculation obtains the global reputation value of each participating unit, including The reputation calculation model of multiple participating units is obtained based on the global reputation gain and penalty value: Set the constraints of the model and obtain the feasible alliance set: Among them, δ A Indicates the accumulated global reputation value; represents the average global reputation value; c A Indicates the value of redundant resources; represents the relative redundant resources; δ0 represents the threshold of the cumulative global reputation value; Represents the threshold of the average global reputation value.

8. An unmanned cluster reputation value calculation and evaluation system, characterized in that: include: A historical data acquisition module is used to acquire historical data of participating units, wherein the historical data includes task completion, quotation gain, reputation value matrix, continuous trust times and continuous untrust times; A direct reputation gain acquisition module is used to calculate the cumulative reputation value based on the task completion degree, the quotation gain and the reputation value matrix, and to calculate the direct reputation gain based on the continuous trust times and the cumulative reputation value; A penalty mechanism acquisition module is used to construct a penalty function based on the number of continuous untrustworthiness and the direct reputation value gain, and calculate the penalty value based on the penalty function; An indirect reputation acquisition module, used to calculate an indirect reputation value gain based on the direct reputation value gain; The global reputation value acquisition module of each participating unit is used to calculate the global reputation value gain of the participating unit according to the direct reputation value gain and the indirect reputation value gain, and calculate the global reputation value of each participating unit according to the global reputation value gain and penalty value of the participating unit.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images