Credibility-based policy statement sorting method, system, device and storage medium

Through a reliability-based method, using accuracy evaluation vectors and reliability matrix to calculate the reliability scores of each state, the problem of not being able to obtain the true preference information of decision makers in the prior art is solved, and it is suitable for a wider range of conflict decision-making scenarios. Provide more predictive decision-making advice.

CN114969217BActive Publication Date: 2024-11-15NAT UNIV OF DEFENSE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210521482.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-13
Publication Date
2024-11-15
Estimated Expiration
2042-05-13

AI Technical Summary

Technical Problem

The existing strategy prioritization method cannot effectively obtain the real preference information of decision makers, resulting in deviations from the actual situation and cannot be applied to conflicting decision-making scenarios in uncertain situations.

Method used

Through a reliability-based method, using accuracy evaluation vectors and reliability matrix, calculate the reliability scores of each state, obtain the true preference information of decision makers, express the accuracy and relative importance of policy statements, and apply to a wider range of Conflict decision-making scenario.

Benefits of technology

It more realistically describes the psychological state of decision makers and provides more predictive strategic decision-making suggestions, which are suitable for decision-making scenarios in uncertain situations, improving the accuracy of model solution results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114969217B_ABST
    Figure CN114969217B_ABST
Patent Text Reader

Abstract

The present application relates to a credibility-based policy statement sorting method, system, device and storage medium. The method includes: determining different decision makers of the conflicting parties of the game, obtaining all policy statement statements Ω given by the decision makers according to the specifications of the policy statement statements; using credibility to model the accuracy of the policy statement statements, and calculating the accuracy evaluation vector of the policy statement statements through mutually exclusive evaluation levels; using credibility to model the relative importance of the policy statement statements, and constructing a credibility matrix of the importance of the policy statement statements through the credibility of the policy statement statements in the kth position in the importance sorting; according to the accuracy evaluation vector and the credibility matrix, calculating the credibility scores of each state and performing preference sorting, and obtaining the real preference information of the decision maker according to the preference sorting. The present application can obtain the real preference information of the decision maker under uncertainty, thereby providing decision makers with more predictable strategic decision suggestions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a credibility-based policy statement sorting method, system, device and storage medium. Background Art

[0002] Conflict analysis is a method for modeling and analyzing real conflicts. In the process of conflict analysis, it mainly involves modeling using data such as decision makers, feasible states, and decision makers' preference rankings for states. Then, by analyzing the stability of each state under different solution concept types, the individual stable state and global equilibrium state of the conflict event are determined, thereby identifying the possible outcomes of the conflict. Among them, preference is the most important factor in determining the calculation results of conflict analysis. Therefore, obtaining decision preferences that meet actual conditions is particularly critical for conflict analysis methods.

[0003] At present, the method for obtaining the preferences of decision makers in conflict events mainly adopts the strategy priority ranking method. When using the strategy priority ranking method to obtain a simple preference sequence, for each decision maker, the conflict analyst needs to give an ordered set consisting of some statements, which are composed of some strategy numbers and logical relationship symbols. Depending on whether the state s∈S satisfies the strategy statement Ω, the state will have a truth value T or F in the statement Ω. If Ω(s)=T, it means that the state s satisfies the statement; otherwise Ω(s)=F, it means that the state s does not satisfy the statement. In this strategy statement, the earlier the statement appears, the greater the priority will be. For decision makers, these states are sorted in order from large to small by setting a score for each state. However, this simple sorting cannot obtain the real preference information of the decision maker, resulting in deviations from the actual situation. Summary of the invention

[0004] Based on this, it is necessary to provide a credibility-based policy statement sorting method, system, device and storage medium to address the above technical issues.

[0005] In a first aspect, an embodiment of the present invention provides a method for sorting policy statements based on credibility, the method comprising:

[0006] Determine the different decision makers of the game conflict parties, and obtain all the strategy declaration statements Ω given by the decision makers according to the specifications of the strategy declaration statements;

[0007] Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0008] Modeling the relative importance of the policy statement using credibility, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0009] According to the accuracy evaluation vector and the credibility matrix, the credibility score of each state is calculated and a preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking.

[0010] Furthermore, the accuracy of the policy statement is modeled using the reliability, and the accuracy evaluation vector of the policy statement is calculated by mutually exclusive evaluation levels, including:

[0011] Through N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) Evaluate t policy statements;

[0012] Construct N evaluation levels to form a recognition framework H = {H 1 ,H 2 ,…,H N};

[0013] Give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0014] Evaluate the jth policy statement to level H n The reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0015] Furthermore, the relative importance of the policy statement is modeled using credibility, and a credibility matrix of the importance of the policy statement is constructed according to the credibility of the policy statement in the kth position in the importance ranking, including:

[0016] The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0017]

[0018] Among them, β 2 The elements in are confidence values, indicating the reliability of the policy statement in the importance ranking.

[0019] Furthermore, the calculating of the reliability scores of each state and performing preference sorting according to the accuracy evaluation vector and the reliability matrix, and obtaining the real preference information of the decision maker according to the preference sorting, include:

[0020] The added value given to state s is determined by the importance of the statements in the policy statement;

[0021] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0022] Define ψ j β2(s) is the added value given to state s by the policy statement. The preference for state s is the sum of the improvement given to state s by all policy statements.

[0023] The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

[0024] On the other hand, an embodiment of the present invention further provides a maintenance identification system based on deep learning, comprising:

[0025] The strategy statement module is used to determine the different decision makers of the game conflict parties and obtain all the strategy statement statements Ω given by the decision makers according to the specifications of the strategy statement statements;

[0026] An accuracy assessment module, used to model the accuracy of the policy statement using credibility, and calculate the accuracy assessment vector of the policy statement through mutually exclusive evaluation levels;

[0027] An importance evaluation module, used to model the relative importance of the policy statement using credibility, and to construct a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0028] The preference sorting module is used to calculate the credibility score of each state and perform preference sorting according to the accuracy evaluation vector and the credibility matrix, and obtain the real preference information of the decision maker according to the preference sorting.

[0029] Further, the accuracy assessment module includes an assessment vector unit, and the assessment vector unit is used to:

[0030] Through N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) Evaluate t policy statements;

[0031] Construct N evaluation levels to form a recognition framework H = {H1 ,H 2 ,…,H N};

[0032] Give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0033] Evaluate the jth policy statement to level H n The reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0034] Furthermore, the importance assessment module includes a credibility matrix unit, and the credibility matrix unit is used to:

[0035] The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0036]

[0037] Among them, β 2 The elements in are confidence values, indicating the reliability of the policy statement in the importance ranking.

[0038] Furthermore, the preference ranking module includes a score determination unit, and the score determination unit is used to:

[0039] The added value given to state s is determined by the importance of the statements in the policy statement;

[0040] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0041] definition Assign a score increase to state s for the policy statement, where the preference for state s is the sum of the improvement degrees given to state s by all policy statements;

[0042] The superiority and inferiority relationship between the states is determined by comparing the size of the state comprehensive scores. An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0043] Determine the different decision makers of the game conflict parties, and obtain all the strategy declaration statements Ω given by the decision makers according to the specifications of the strategy declaration statements;

[0044] Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0045] Modeling the relative importance of the policy statement using credibility, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0046] According to the accuracy evaluation vector and the credibility matrix, the credibility score of each state is calculated and a preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking.

[0047] The embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0048] Determine the different decision makers of the game conflict parties, and obtain all the strategy declaration statements Ω given by the decision makers according to the specifications of the strategy declaration statements;

[0049] Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0050] Modeling the relative importance of the policy statement using credibility, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0051] According to the accuracy evaluation vector and the credibility matrix, the credibility score of each state is calculated and a preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking.

[0052] The above-mentioned credibility-based policy statement sorting method, system, device and storage medium, the method includes: determining different decision makers of the game conflict parties, obtaining all policy statement statements Ω given by the decision makers according to the specifications of the policy statement statements; using credibility to model the accuracy of the policy statement statements, and calculating the accuracy evaluation vector of the policy statement statements through mutually exclusive evaluation levels; using credibility to model the relative importance of the policy statement statements, and constructing a credibility matrix of the importance of the policy statement statements through the credibility of the policy statement statements in the kth position in the importance sorting; according to the accuracy evaluation vector and the credibility matrix, calculating the credibility score of each state and performing preference sorting, and obtaining the decision maker's real preference information according to the preference sorting. This application is aimed at the situation where the decision maker is uncertain about the accuracy and relative importance of the policy statement statements when performing preference sorting in real situations. By using credibility to describe the accuracy and relative importance of the policy statement statements, the psychological state of the decision maker in the real-world conflict game process is more realistically described and the credibility score of each state is more accurately calculated. Compared with the simple strategy prioritization method, this method can be applied to a wider range of conflict decision-making scenarios, obtain the real preference information of decision makers under uncertain situations, make the model solution results more in line with the actual situation, and thus provide decision makers with more predictive strategic decision-making recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flowchart of a credibility-based policy statement sorting method in one embodiment;

[0054] Figure 2 is a structural block diagram of a credibility-based policy statement sorting system in one embodiment;

[0055] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] At present, the method for obtaining the preferences of decision makers in conflict events mainly adopts the strategy priority ranking method. When using the strategy priority ranking method to obtain a simple preference sequence, for each decision maker, the conflict analyst needs to give an ordered set consisting of some statements, which are composed of some strategy numbers and logical relationship symbols. Depending on whether the state s∈S satisfies the policy statement Ω, the state will have a truth value T or F in the statement Ω. If Ω(s)=T, it means that the state s satisfies the statement; otherwise Ω(s)=F, it means that the state s does not satisfy the statement. In this policy statement, the earlier the statement appears, the greater the priority will be. For the decision maker DMi, these states are sorted in order from large to small by setting a score ψ(s) for each state.

[0058] Therefore, in the strategy priority ranking method, the two major determining factors for whether the state preference ranking is consistent with the decision maker's ideas are: ① the accuracy of the strategy statement, that is, whether the strategy statement can accurately describe the decision maker's preferences; ② the importance of the strategy statement, that is, the ranking of the strategy statement from important to unimportant.

[0059] In one embodiment, Figure 1 As shown, a method for sorting policy statements based on credibility is provided, the method comprising:

[0060] Step 101, determine different decision makers of the game conflicting parties, and obtain all policy statement statements Ω given by the decision makers according to the specification of the policy statement statement;

[0061] Step 102, modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0062] Step 103, using credibility to model the relative importance of the policy statement, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0063] Step 104, calculating the credibility score of each state and performing preference sorting according to the accuracy evaluation vector and the credibility matrix, and obtaining the real preference information of the decision maker according to the preference sorting.

[0064] Specifically, this embodiment uses reliability to describe the accuracy and relative importance of policy statements in real-world conflict games, aiming at the situation where decision makers are uncertain about the accuracy and relative importance of policy statements when ranking preferences in real situations, thereby more realistically describing the psychological state of decision makers in real-world conflict games and more accurately calculating the reliability scores of each state. Compared with simple policy priority ranking methods, this method can be applied to a wider range of conflict decision-making scenarios, obtain the real preference information of decision makers under uncertain circumstances, make the model solution results more in line with the actual situation, and provide decision makers with more predictable strategic decision-making suggestions.

[0065] When using the credibility-based policy statement prioritization method, decision makers need to first clarify all policy statement statements Ω according to the specifications of policy statement statements. Each policy statement statement is a logical statement about the policy, which can be expressed as a combination of policy and logical connectives, including yes, no conditions, and biconditions. When describing preferences, logical words are usually used, such as logical AND ("and" and "&"), logical OR ("or" and "|"), logical NOT ("not" and "-"), condition ("if"), and bicondition ("iff"). Let the policy statement set φ of DMi be i ={Ω 1 ,Ω 2 ,…,Ω t}, and from Ω 1 to Ω t From most important to least important statement.

[0066] In one embodiment, determining the assertion statement accuracy assessment vector includes the following steps:

[0067] Step 201: collect N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) Evaluate t policy statements;

[0068] Step 202: construct N evaluation levels to form a recognition framework H = {H 1 ,H 2 ,…,H N};

[0069] Step 203, give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0070] Step 204: Evaluate the jth policy statement to level H n The reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0071] Specifically, in some situations, it is difficult for experts to determine the accuracy of policy statements. The credibility structure can well express the subjective judgment or evaluation of decision makers.

[0072] In simple preference, even when j=k+1,k+2,…,t, there is Ω j (s)=F and Ω j (s 1 )=T holds, but due to So ψ(s) is still greater than ψ(s 1 ), that is, s>s 1 But the preference based on credibility is not necessarily true, because the correctness of each statement is not certain, but has a certain credibility. j can add value to the state, but unlike simple preferences, the statement Ω j The score added to state s is not only related to Ω j The importance and status s of decision makers in Ω j The truth value Ω j (s), and also Ω j The reliability of β j related.

[0073] A total of t policy statements are collected by N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) evaluations, these N evaluation levels constitute the recognition framework H={H 1 ,H 2 ,…,H N}. At the same time, give H n Each level of is assigned a utility value u(H n ), represents the score of the corresponding level evaluation. The j-th policy statement is evaluated to level H n The reliability is β n (Ω j ). The statement accuracy evaluation vector is expressed as in when is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector. It shows complete ignorance.

[0074] In one embodiment, the uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0075]

[0076] Among them, β 2 The elements in are confidence values, indicating the reliability of the policy statement in the importance ranking.

[0077] Specifically, in some situations, it is difficult for experts to determine the relative importance of policy statement statements. The credibility structure can well express the subjective judgment or evaluation of decision makers. The decision maker's preference for a state depends on whether the state conforms to the decision maker's policy statement. If the state conforms to the policy statement, the decision maker's preference for the state will be increased, and vice versa. The specific degree of increase depends on the importance of the policy statement it satisfies to the decision maker. The position of the importance ranking reflects the relative importance of the policy statement to the decision maker. Since statements with high importance can give a higher added value to the state, the higher the statement ranking, the greater the influence of whether the state conforms to the statement on the preference for the state. In the real world, decision makers put forward their own policy statement statements, but they may be uncertain about the order of the statements.

[0078] In the policy statement set φ i ={Ω 1 ,Ω 2 ,…,Ω t} in the statement Ω j (j=1,2,…t) is deterministic, that is, each statement can correctly express the decision maker's strategic preference, but the set φ i The importance ranking of the statements in is unknown. In the real world, a decision maker has multiple policy statements, but he is not sure which statement is the most important to him.

[0079] The uncertainty of the importance of the policy statement can be expressed by the confidence, and the definition matrix is:

[0080]

[0081]

[0082] Element Beta jk (1≤j≤t,1≤k≤t) is the confidence value, indicating the statement Ω j The reliability of the kth position in the importance ranking. j must be somewhere in the importance ranking, that is, the sum of the elements in each row of the matrix is ​​1, so β jk The following formula should be satisfied.

[0083]

[0084] However, there can be multiple statements at the same position in the importance ranking, which means that these statements are equally important to the decision maker. Therefore, the number of non-zero elements in each column of β represents the number of statements at that importance ranking position with a certain credibility.

[0085] In one embodiment, the added value assigned to the state s is determined by the importance of the statements in the policy statement;

[0086] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0087] definition Assign a score increase to state s for the policy statement, where the preference for state s is the sum of the improvement degrees given to state s by all policy statements;

[0088] The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

[0089] In one embodiment, such as in a water export conflict example, in order to accurately represent the model of the conflict game, first determine the three decision makers in the conflict: the coalition government (F), the provincial government (GP), and the company (S) that wants to implement water export. The optional action strategy of the coalition government: continue to implement the ban; the optional action strategy of the provincial government: lift the ban; the optional action strategy of the company: file an appeal. This conflict event contains 3 strategies in total, and each decision maker makes a binary choice for their respective strategies, so there are 2 3 =8 states. In this embodiment, it is assumed that the local government policy statement set φ GP ={Ω 1 ,Ω 2 ,Ω 3}, where Ω 1 for Ω 2 for Ω 3 for And for the three statements of GP, Ω 1 To Ω 2 The importance decreases in turn. The truth value of each state under each policy statement is shown in the following table.

[0090]

[0091] In this embodiment, four mutually exclusive evaluation levels H are used for the accuracy of policy statements. n (n = 1, 2, 3, 4) evaluation. These 4 evaluation levels constitute the recognition framework H = {H 1 ,H2 ,H 3 ,H 4} = {completely certain, basically certain, basically uncertain, completely uncertain), and give H n Each level of is assigned a utility value u(H n )=(1,0.7,0.3,0). The j-th policy statement accuracy is evaluated to level H n The reliability is Then the statement accuracy evaluation vector can be expressed as

[0092] In the embodiment, because the GP has some uncertainty about whether it wants to lift the ban or not to insist on enforcing the ban, the GP's policy statement cannot fully and accurately express its true preference. Therefore, it is difficult to determine the accuracy of the GP's policy statement, so the reliability of Ω 1 ,Ω 2 ,Ω 3 The accuracy of n (Ω1)=[0.5,0.3,0.2,0],β n (Ω 2 )=[0.5,0.3,0.2,0],β n (Ω 3 )=[1,0,0,0]. Since GP does not want S to appeal anyway, it is considered that Ω 3 Able to accurately express GP's true preferences.

[0093] In an embodiment, the confidence matrix of the decision maker's relative importance of the policy statement is:

[0094]

[0095] Assume that the set of local government policy statements φ GP ={Ω 1 ,Ω 2 ,Ω 3}, where Ω 1 for Ω 2 for Ω 3 for In this example, the GP may be best placed to lift the ban. It is also possible that he would most like S not to appeal. Simple preference cannot express this uncertainty, so a confidence β is defined for the position of each statement in the relative ranking. jk . β jk For the decision maker statement Ω jThe credibility of the kth position in the importance ranking. All credibility values ​​constitute the credibility matrix β.

[0096] The confidence matrix β of GP in this example is 2 as follows.

[0097]

[0098] In an embodiment, the confidence score of each state can be obtained:

[0099]

[0100]

[0101] Comparing the scores, the preference ranking is: 3 >s 4 >s 1 >s 7 >s 2 >s 8 >s 5 >s 6

[0102] In order to verify the effectiveness of the present invention, the simple preference is compared with the preference obtained in the case. The simple preference cannot accurately reflect the fuzzy psychology of decision makers in real life when dealing with conflicts due to the fixed nature of the statement. For example, there is uncertainty between GP's hope to lift the ban and hope that the federal government will not insist on enforcing the ban; GP most hopes to lift the ban. It is also possible that he would most like S not to appeal. The present invention simulates the fuzzy psychology of decision makers in conflict events, adds credibility to the strategy priority ranking, and the obtained state ranking is more in line with the actual situation of the decision makers, which is convenient for analyzing the conflict events.

[0103] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0104] In one embodiment, Figure 2 As shown, a credibility-based policy statement ranking system is provided, comprising:

[0105] The strategy statement module 301 is used to determine different decision makers of the game conflict parties, and obtain all strategy statement statements Ω given by the decision makers according to the specification of the strategy statement statement;

[0106] An accuracy evaluation module 302, configured to model the accuracy of the policy statement using credibility, and calculate an accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0107] The importance evaluation module 303 is used to model the relative importance of the policy statement using credibility, and to construct a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0108] The preference ranking module 304 is used to calculate the credibility score of each state according to the accuracy evaluation vector and the credibility matrix and perform preference ranking, and obtain the real preference information of the decision maker according to the preference ranking.

[0109] In one embodiment, Figure 2 As shown, the accuracy evaluation module 302 includes an evaluation vector unit 3021, and the evaluation vector unit 3021 is used to:

[0110] Through N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) Evaluate t policy statements;

[0111] Construct N evaluation levels to form a recognition framework H = {H 1 ,H 2 ,…,H N};

[0112] Give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0113] Evaluate the jth policy statement to level H n The reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0114] In one embodiment, Figure 2 As shown, the importance evaluation module 303 includes a credibility matrix unit 3031, and the credibility matrix unit 3031 is used to:

[0115] The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0116]

[0117] Among them, β 2 The element β in jk (1≤j≤t,1≤k≤t) is the confidence value, which indicates the Ω in the policy statement. j The reliability of the kth position in the importance ranking;

[0118] The Ω in the policy statement j must be in a position in the importance ranking, the sum of the elements in each row of the credibility matrix is ​​1, and the β jk Satisfy the following formula:

[0119]

[0120] In one embodiment, Figure 2 As shown, the preference ranking module 304 includes a score determination unit 3041, and the score determination unit 3041 is used to:

[0121] The added value given to state s is determined by the importance of the statements in the policy statement;

[0122] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0123] definition Assign a score increase to state s for the policy statement, where the preference for state s is the sum of the improvement degrees given to state s by all policy statements;

[0124] The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

[0125] For the specific limitations of the credibility-based policy statement sorting system, please refer to the limitations of the credibility-based policy statement sorting method above, which will not be repeated here. Each module in the above credibility-based policy statement sorting system can be implemented in whole or in part through software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0126] Figure 3FIG. 2 shows an internal structure diagram of a computer device in one embodiment. Figure 3 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement a policy statement sorting method based on credibility. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute a policy statement sorting method based on credibility. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0127] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0129] Determine the different decision makers of the game conflict parties, and obtain all the strategy declaration statements Ω given by the decision makers according to the specifications of the strategy declaration statements;

[0130] Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0131] Modeling the relative importance of the policy statement using credibility, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0132] According to the accuracy evaluation vector and the credibility matrix, the credibility score of each state is calculated and a preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking.

[0133] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0134] Through N complete and mutually exclusive evaluation levels Hn (n=1,2,…,N) Evaluate t policy statements;

[0135] Construct N evaluation levels to form a recognition framework H = {H 1 ,H 2 ,…,H N};

[0136] Give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0137] Evaluate the jth policy statement to level H n The reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0140]

[0141] Among them, β 2 The element β in jk (1≤j≤t,1≤k≤t) is the confidence value, which indicates the Ω in the policy statement. j The reliability of the kth position in the importance ranking;

[0142] The Ω in the policy statement j must be in a position in the importance ranking, the sum of the elements in each row of the credibility matrix is ​​1, and the β jk Satisfy the following formula:

[0143]

[0144] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0145] The added value given to state s is determined by the importance of the statements in the policy statement;

[0146] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0147] definition Assign a score increase to state s for the policy statement, where the preference for state s is the sum of the improvement degrees given to state s by all policy statements;

[0148] The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

[0149] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0150] Determine the different decision makers of the game conflict parties, and obtain all the strategy declaration statements Ω given by the decision makers according to the specifications of the strategy declaration statements;

[0151] Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels;

[0152] Modeling the relative importance of the policy statement using credibility, and constructing a credibility matrix of the importance of the policy statement according to the credibility of the policy statement in the kth position in the importance ranking;

[0153] According to the accuracy evaluation vector and the credibility matrix, the credibility score of each state is calculated and a preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking.

[0154] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0155] Through N complete and mutually exclusive evaluation levels H n (n=1,2,…,N) Evaluate t policy statements;

[0156] Construct N evaluation levels to form a recognition framework H = {H 1 ,H 2 ,…,H N};

[0157] Give H n Each level of is assigned a utility value u(H n ), representing the score of the corresponding level evaluation;

[0158] Evaluate the jth policy statement to level H nThe reliability is β n (Ω j ), the statement accuracy evaluation vector is expressed as in when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

[0159] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0160] The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows:

[0161]

[0162] Among them, β 2 The element β in jk (1≤j≤t,1≤k≤t) is the confidence value, which indicates the Ω in the policy statement. j The reliability of the kth position in the importance ranking;

[0163] The Ω in the policy statement j must be in a position in the importance ranking, the sum of the elements in each row of the credibility matrix is ​​1, and the β jk Satisfy the following formula:

[0164]

[0165] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0166] The added value given to state s is determined by the importance of the statements in the policy statement;

[0167] When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement;

[0168] definition Assign a score increase to state s for the policy statement, where the preference for state s is the sum of the improvement degrees given to state s by all policy statements;

[0169] The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

[0170] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0171] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0172] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A credibility-based policy statement ranking method, characterized in that: The method comprises: Identify the different decision makers of the game conflicting parties, and obtain all the policy statements given by the decision makers according to the specifications of the policy statement ; Modeling the accuracy of the policy statement using the reliability, and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels; The relative importance of the policy statement is modeled using the confidence, and the policy statement is ranked first in the importance ranking. The credibility of the policy statement is constructed based on the credibility of the policy statement. According to the accuracy evaluation vector and the credibility matrix, the credibility scores of each state are calculated and preference ranking is performed, and the real preference information of the decision maker is obtained according to the preference ranking, including: The assigned status is determined by the importance of the statement in the policy statement The added value of When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement; definition Assign status to the policy statement The added value for status The preference level is the state given by all policy statements Comprehensive improvement level; The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

2. The credibility-based policy statement ranking method according to claim 1, characterized in that: The method of modeling the accuracy of the policy statement using the reliability and calculating the accuracy evaluation vector of the policy statement using mutually exclusive evaluation levels includes: Through N complete and mutually exclusive evaluation levels Evaluate t policy statements; Constructing N evaluation levels to form an identification framework ; Give Each level of , represents the score of the corresponding level evaluation; Evaluate the j-th policy statement to level The reliability is , by declaring the statement accuracy evaluation vector as , n=1,2,…,N, where ,when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

3. The credibility-based policy statement ranking method according to claim 1, characterized in that: The confidence is used to model the relative importance of the policy statement, and the policy statement is ranked first in the importance ranking. The credibility of the policy statement is constructed by calculating the credibility of the policy statement, including: The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows: in, The elements in are confidence values, indicating the reliability of the policy statement in the importance ranking.

4. A credibility-based policy statement sorting system according to the credibility-based policy statement sorting method according to any one of claims 1 to 3, characterized in that: include: The strategy statement module is used to identify the different decision makers of the game conflict parties and obtain all the strategy statements given by the decision makers according to the specifications of the strategy statement. ; An accuracy assessment module, used to model the accuracy of the policy statement using credibility, and calculate the accuracy assessment vector of the policy statement through mutually exclusive evaluation levels; An importance evaluation module is used to model the relative importance of the policy statement using the credibility, and to determine the policy statement in the order of importance. The credibility of the policy statement is constructed based on the credibility of the policy statement. A preference ranking module, used to calculate the credibility score of each state and perform preference ranking according to the accuracy evaluation vector and the credibility matrix, and obtain the real preference information of the decision maker according to the preference ranking; The preference ranking module includes a score determination unit, which is used to: The assigned status is determined by the importance of the statement in the policy statement The added value of When the reliability of the policy statement is zero, the policy statement itself loses its meaning, and the corresponding state's score is 0; when the reliability of the policy statement is non-zero, the policy statement can express policy preferences and can assign scores to states that meet the statement; definition Assign status to the policy statement The added value for status The preference level is the state given by all policy statements Comprehensive improvement level; The superiority and inferiority relationship between states is determined by comparing the size of the comprehensive scores of the states.

5. The credibility-based policy statement ranking system according to claim 4, characterized in that: The accuracy assessment module includes an assessment vector unit, which is used to: Through N complete and mutually exclusive evaluation levels Evaluate t policy statements; Constructing N evaluation levels to form an identification framework ; Give Each level of , represents the score of the corresponding level evaluation; Evaluate the j-th policy statement to level The reliability is , by declaring the statement accuracy evaluation vector as , n=1,2,…,N, where ,when When , it is called a complete statement accuracy evaluation vector, otherwise it is called an incomplete statement accuracy evaluation vector.

6. The credibility-based policy statement ranking system according to claim 4, characterized in that: The importance assessment module includes a credibility matrix unit, and the credibility matrix unit is used to: The uncertainty of the importance of the policy statement is expressed by credibility, and the credibility matrix is ​​constructed as follows: in, The elements in are confidence values, indicating the reliability of the policy statement in the importance ranking.

7. A computer 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 3 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, 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 3 are implemented.