False Information Detection Method in Multi-Agent System

Abstract

The present invention relates to the field of information detection, and particularly to a method for detecting false information in a multi-agent system. The present invention analyzes an agent cluster by invoking interaction data of historical tasks of a plurality of real information executed by the agent cluster; compares the values of the specific dimension features corresponding to each path segment with the standard range of the specific dimension features to determine the offset of the task execution path topology graph; evaluates the deviation tendency characterization coefficient of the received information according to the offset and the information reception frequency of the agent cluster; determines whether the corresponding rule execution path topology graph is consistent with the task execution path topology graph of the agent cluster, and detects and analyzes the received information of the agent cluster; marks the received information, identifies the sender corresponding to the received information, and traces the receiver of the information sent by the agent cluster. The present invention adopts a multi-dimensional evaluation method to detect false information more comprehensively and reliably.

Description

Technical Field

[0001] The present invention relates to the field of information detection, and particularly to a method for detecting false information in a multi-agent system. Background Art

[0002] An agent is a terminal that includes a server capable of performing corresponding computing tasks and data interaction. An agent cluster can process relatively complex tasks sent by a sender and send the relevant result information after processing to a receiver. Agent clusters are widely used in various fields. Therefore, security detection during the interaction process of agent clusters is crucial, for example, identifying false information, forged information, etc.

[0003] Chinese Patent Application Publication No.: CN117155616A, discloses a method for predicting deception attack intention in a multi-agent system based on inverse reinforcement learning, belonging to the field of information processing technology. This invention considers the existence of deception attack phenomena in a multi-agent system and proposes an effective method for detecting false information injection. A method of multi-sensor data fusion is used for positioning, making the positioning more accurate. A Kalman filter is added for distributed state estimation, which can solve the problems of sensor noise and system instability. Assisting state estimation through neighbor node information makes the estimation more accurate and also makes the impact of external attacks on system performance smaller. Based on the traditional false data injection attack detection method, inverse reinforcement learning technology is added to infer the attacker's attack intention, solving the problems of complex data encryption and decryption algorithms and attack hiding in traditional technologies, and effectively improving the effectiveness and accuracy of attack detection.

[0004] However, the following problems still exist in the prior art.

[0005] In the prior art, the identity of the sender may be disguised, and thus it is not easy to identify the authenticity of the sent information by only using a single method. The interaction rules of each node in the agent cluster are not considered, and the reliability of identifying false information is poor. Summary of the Invention

[0006] Therefore, the present invention provides a method for detecting false information in a multi-agent system to overcome the problems in the prior art that the identity of the sender may be disguised, and thus it is not easy to identify the authenticity of the sent information by only using a single method. The interaction rules of each node in the agent cluster are not considered, and the reliability of identifying false information is poor.

[0007] To achieve the above object, the present invention provides a method for detecting false information in a multi-agent system, which includes:

[0008] Invoke the interaction data of the historical tasks of the intelligent agent cluster for a number of real information to analyze the intelligent agent cluster, including determining the fluctuation value ranking of the corresponding dimensional features of each path segment of the task execution path topology graph after the intelligent agent cluster receives a number of real information, so as to determine the specific dimensional features and the standard range of the specific dimensional features corresponding to each path segment;

[0009] In response to the intelligent agent cluster receiving information, compare the specific dimensional features corresponding to each path segment with the standard range of the specific dimensional features to determine the offset of the task execution path topology graph;

[0010] Evaluate the deviation tendency characterization coefficient of the received information according to the offset and the information reception frequency of the intelligent agent cluster;

[0011] Based on the deviation tendency characterization coefficient, determine whether to invoke the operation rule file of the intelligent agent cluster to determine the corresponding rule execution path topology graph, and determine whether the rule execution path topology graph is consistent with the task execution path topology graph of the intelligent agent cluster, so as to detect and analyze the received information of the intelligent agent cluster, including,

[0012] Identify a number of nodes corresponding to the task execution path topology graph of the intelligent agent cluster to determine unexpected nodes, determine the task execution impact degree for the intelligent agent cluster based on the unexpected nodes, calculate the topology deviation characterization value in combination with the number of associated nodes of the unexpected nodes, and determine whether it meets the topology deviation standard;

[0013] In response to determining that it does not meet the topology deviation standard, mark the received information, identify the sender corresponding to the received information, and track the receiver of the information sent by the intelligent agent cluster.

[0014] Furthermore, the process of determining the specific dimensional features and the standard range of the specific dimensional features corresponding to each path segment includes,

[0015] Determine the dimensional features corresponding to the path segment of the task execution path topology graph, including the average load at both ends, the data transmission volume, and the transmission frequency;

[0016] Determine the fluctuation values of the dimensional features of each path segment and sort them respectively;

[0017] Determine the dimensional feature corresponding to the minimum fluctuation value, and determine the dimensional feature as the specific dimensional feature;

[0018] Record the maximum value and the minimum value of the specific dimensional feature in the path segment, and determine the standard range of the specific dimensional feature based on the maximum value and the minimum value;

[0019] Among them, the fluctuation value is the absolute variance of the dimensional feature at a number of time nodes.

[0020] Further, the process of determining the offset of the task execution path topology diagram includes

[0021] Determining the specific dimension features corresponding to each path segment respectively;

[0022] Determining the proportion of the specific dimension features corresponding to each of the path segments that exceed the standard range of the corresponding specific dimension features;

[0023] Determining the mean value of each of the proportions as the offset.

[0024] Further, the process of evaluating the deviation tendency characterization coefficient of the received information includes

[0025] Taking the ratio of the offset of the task execution path topology diagram to the offset threshold as the first deviation feature;

[0026] Taking the ratio of the information reception frequency to the information reception frequency threshold as the second deviation feature;

[0027] Taking the sum of the first deviation feature and the second deviation feature as the deviation tendency characterization coefficient.

[0028] Further, determining whether to call the operation rule file of the intelligent agent cluster based on the deviation tendency characterization coefficient includes

[0029] If the deviation tendency characterization coefficient is greater than or equal to the deviation tendency characterization coefficient threshold, then call the operation rule file of the intelligent agent cluster;

[0030] Wherein, the operation rule file records a rule execution path topology diagram.

[0031] Further, the process of determining whether the rule execution path topology diagram and the task execution path topology diagram of the intelligent agent cluster are consistent includes

[0032] Extracting the rule execution path topology diagram from the operation rule file;

[0033] Comparing the task execution path topology diagram with the rule execution path topology diagram and calculating the coincidence degree;

[0034] If the coincidence degree is greater than or equal to the preset coincidence degree threshold, then determine that they are consistent;

[0035] If the coincidence degree is less than the preset coincidence degree threshold, then determine that they are not consistent, and detect and analyze the received information of the intelligent agent cluster.

[0036] Further, the process of determining the task execution influence degree on the intelligent agent cluster based on the unexpected node includes

[0037] Determine unexpected nodes according to the task execution path topology graph and the rule execution path topology graph;

[0038] Determine the average actual in-degree and out-degree of each unexpected node to obtain the task execution influence degree;

[0039] Among them, if a node appears in the task execution path topology graph and does not appear in the rule execution path topology graph, then determine that the node is an unexpected node.

[0040] Furthermore, the process of calculating the topology deviation characterization value includes,

[0041] Determine the associated nodes of each unexpected node and determine the average value of the number of associated nodes;

[0042] Take the ratio of the task execution influence degree to the task execution influence degree threshold as the first topology deviation feature;

[0043] Take the ratio of the average value of the number of associated nodes to the associated node number threshold as the second topology deviation feature;

[0044] Perform weighted summation on the first topology deviation feature and the second topology deviation feature as the topology deviation characterization value.

[0045] Furthermore, determining whether to meet the topology deviation standard includes,

[0046] If the topology deviation characterization value is greater than or equal to the topology deviation characterization threshold, then determine that it does not meet the topology deviation standard.

[0047] Furthermore, it also includes, in response to not meeting the topology deviation standard, controlling the intelligent agent cluster to stop receiving information and stop sending information.

[0048] Compared with the prior art, the present invention analyzes the intelligent agent cluster by calling the historical task execution interaction data of the intelligent agent cluster for several real information; in response to the intelligent agent cluster receiving information, compares the specific dimension features corresponding to each path segment with the standard range of the specific dimension features to determine the offset of the task execution path topology graph; evaluates the deviation tendency characterization coefficient of the received information according to the offset and the information reception frequency of the intelligent agent cluster; determines whether to call the operation rule file of the intelligent agent cluster based on the deviation tendency characterization coefficient to determine the corresponding rule execution path topology graph, and determines whether the rule execution path topology graph is consistent with the task execution path topology graph of the intelligent agent cluster to detect and analyze the received information of the intelligent agent cluster; in response to determining that it does not meet the topology deviation standard, marks the received information, identifies the sender corresponding to the received information, and tracks the receivers of the information sent by the intelligent agent cluster. The present invention adopts a multi-dimensional evaluation method to more comprehensively and reliably detect false information and ensure the reliability of detecting false information.

[0049] In particular, the present invention determines the specific dimensional features corresponding to each path segment and the standard range of the specific dimensional features. In actual situations, the computing capabilities or functions of the nodes corresponding to different path segments are not exactly the same. Therefore, there are differences in the information transmission between the corresponding path segments when performing corresponding tasks. Furthermore, there are differences in the performance in terms of different dimensional features. Therefore, considering and identifying the specific dimensional features corresponding to the path segments, for the dimensional features with large fluctuation values, their regularity is poor, it is difficult to reflect the daily transmission law, and they do not have the value of observation. Therefore, identifying the specific dimensional features with strong data representativeness of the path segment data and determining the standard range of the specific dimensional features provide support for determining the deviation tendency characterization coefficient subsequently, improving the analysis efficiency and reliability.

[0050] In particular, the present invention considers calculating the deviation tendency characterization coefficient. In actual situations, for a given sender, when the intelligent agent executes a task for the received information, the nodes participating in the operation and the information interaction between the nodes are all related to the corresponding task, and there are usually certain historical laws. Based on this, the present invention determines the offset of the task execution path topology graph, considering the offset of the specific dimensional features corresponding to different path segments relative to the standard range of the specific dimensional features, that is, the situation of deviation from the historical law. At the same time, combining the information reception frequency of the intelligent agent cluster, the offset of the operation of the intelligent agent cluster relative to the historical law is comprehensively considered, which characterizes the potential risk that the information received by the intelligent agent cluster is tampered with or there is false information. Furthermore, it provides data support for subsequent determination of the consistency of the execution situation of the intelligent agent. The present invention adopts a multi-dimensional evaluation method to detect false information more comprehensively and reliably, ensuring the reliability of detecting false information.

[0051] In particular, in the case where the task execution path topology graph of the intelligent agent cluster does not conform to the consistency with the rule execution path topology graph, the present invention triggers further detection and analysis of the information received by the intelligent agent cluster, saving computing power and avoiding waste of computing power in traversing and in-depth analysis. When performing detection and analysis, an unexpected node means that this node does not belong to the rule execution path topology graph. Subsequently, the influence degree of the task execution is calculated. The in-degree and out-degree of the unexpected node characterize the proportion of this type of node participating in the operation. The more the proportion, the more it indicates that it is not an accidental event, and the more important the unexpected node is, which characterizes that more operations involved in the task executed by the current intelligent agent cluster do not conform to the historical law. By calculating the topological deviation characterization value and considering the number of associated nodes of the unexpected node, the importance degree of the unexpected node participating in the operation is further corroborated. Furthermore, it comprehensively reflects the situation of the task execution deviating from the historical law from the inside of the intelligent agent cluster, providing data support for subsequent determination of whether it conforms to the topological deviation standard. The present invention adopts a multi-dimensional evaluation method to detect false information more comprehensively and reliably, ensuring the reliability of detecting false information. Description of the Drawings

[0052] Figure 1 Schematic diagram of steps of the false information detection method in the multi-agent system according to the invention embodiment;

[0053] Figure 2 Logic decision diagram for determining whether to call the operation rule file of the agent cluster according to the invention embodiment;

[0054] Figure 3 Logic decision diagram for determining whether the topology of the rule execution path of the invention embodiment is consistent with the topology of the task execution path of the agent cluster;

[0055] Figure 4 Logic decision diagram for determining whether it meets the topology deviation standard according to the invention embodiment. Detailed implementation manners

[0056] In order to make the purpose and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0058] Please refer to Figure 1 as shown, which is a schematic diagram of steps of the false information detection method in the multi-agent system according to the invention embodiment. The false information detection method in the multi-agent system according to the invention embodiment includes:

[0059] Step S1, calling the historical task execution interaction data of the agent cluster for several real information to analyze the agent cluster, including determining the fluctuation value sorting of each dimension feature corresponding to each path segment of the task execution path topology diagram of the agent cluster after receiving several real information, so as to determine the specific dimension feature corresponding to each path segment and the standard range of the specific dimension feature;

[0060] Step S2, in response to the agent cluster receiving information, comparing the specific dimension feature corresponding to each path segment with the standard range of the specific dimension feature to determine the offset of the task execution path topology diagram;

[0061] Step S3, evaluating the deviation tendency characterization coefficient of the received information according to the offset and the information reception frequency of the agent cluster;

[0062] Step S4, determine whether to call the operation rule file of the intelligent agent cluster based on the deviation tendency characterization coefficient to determine the corresponding rule execution path topology graph, and determine whether the rule execution path topology graph is consistent with the task execution path topology graph of the intelligent agent cluster, so as to detect and analyze the received information of the intelligent agent cluster, including,

[0063] Identify several nodes corresponding to the task execution path topology graph of the intelligent agent cluster to determine unexpected nodes, determine the task execution influence degree on the intelligent agent cluster based on the unexpected nodes, calculate the topology deviation characterization value in combination with the number of associated nodes of the unexpected nodes, and determine whether it meets the topology deviation standard;

[0064] Step S5, in response to determining that the intelligent agent cluster does not meet the topology deviation standard, mark the received information, identify the sender corresponding to the received information, and track the receivers of the information sent by the intelligent agent cluster.

[0065] Specifically, an intelligent agent is a terminal that includes a server capable of executing corresponding computing tasks and capable of data interaction, and the intelligent agent cluster includes several intelligent agents.

[0066] Specifically, in implementation, the intelligent agent cluster establishes connections with the sender and the receiver. The information sent by the sender includes the tasks to be executed. After the intelligent agent cluster performs operations, the information containing the operation results is sent to the receiver.

[0067] Specifically, the real information received by the intelligent agent can be pre-verified and marked by those skilled in the art as real information.

[0068] Specifically, the historical task execution interaction data includes the operation records of the intelligent agent cluster within the historical period. To ensure that the historical task execution interaction data has data representativeness, the historical period should not be less than 10 days.

[0069] Specifically, the task execution path topology graph is determined through the operation records of the intelligent agent cluster. Obtain the intelligent agents participating in the operation in the intelligent agent cluster, use the intelligent agents participating in the operation as nodes, and connect the interacting intelligent agents as edges to obtain the task execution path topology graph.

[0070] Specifically, the path segment of the task execution path topology graph includes two interacting intelligent agents and the corresponding edge.

[0071] Specifically, the process of determining the specific dimension features and the standard range of specific dimension features corresponding to each of the path segments includes,

[0072] Determine the dimension features corresponding to the path segment of the task execution path topology graph, including the average load at both ends, the data transmission volume, and the transmission frequency;

[0073] Determine the fluctuation values of the dimensional features of each path segment respectively and sort them;

[0074] Determine the dimensional feature corresponding to the minimum fluctuation value, and determine the dimensional feature as the specific dimensional feature;

[0075] Record the maximum value and the minimum value of the specific dimensional feature in the path segment, and determine the standard range of the specific dimensional feature based on the maximum value and the minimum value. In implementation, the standard range of the specific dimensional feature is a closed interval, the lower limit of the interval is the minimum value, and the upper limit of the interval is the maximum value.

[0076] Wherein, the fluctuation value is the absolute variance of the dimensional feature at several time nodes.

[0077] In implementation, the average value of the loads at both ends is the average value of the loads corresponding to the two agents of the path segment, the data transmission volume is the average value of the data transmission volumes of the two agents corresponding to the path segment during several data interaction processes, and the transmission frequency is the transmission frequency between the two agents corresponding to the path segment.

[0078] It can be understood that the larger the fluctuation value, the worse the regularity of the corresponding dimensional feature, and it has strong volatility itself, and a relatively standard range cannot be determined.

[0079] Specifically, the present invention determines the specific dimensional features and the standard ranges of the specific dimensional features corresponding to each path segment. In actual situations, the computing capabilities or functions of the nodes corresponding to different path segments are not exactly the same. Therefore, there are differences in the information transmission between the corresponding path segments when performing corresponding tasks. Furthermore, the performance is different in different dimensional features. Therefore, considering and identifying the specific dimensional features corresponding to the path segments, for the dimensional features with large fluctuation values, their regularity is poor, it is difficult to reflect the daily transmission regularity, and they do not have the value of observation. Therefore, identifying the specific dimensional features with strong data representativeness of the path segments and determining the standard ranges of the specific dimensional features provide support for determining the deviation tendency representation coefficient later, and improve the analysis efficiency and reliability.

[0080] Specifically, the process of determining the offset of the task execution path topology graph includes,

[0081] Determine the specific dimensional features corresponding to each path segment respectively;

[0082] Determine the proportion of the specific dimensional features corresponding to each path segment that exceed the standard range of the specific dimensional features corresponding to them;

[0083] Determine the average value of each of the proportions as the offset.

[0084] It can be understood that exceeding the corresponding specific dimension feature standard range means not being within the corresponding interval of the specific dimension feature standard range, and the ratio is the ratio of the excess amount of the specific dimension feature exceeding the corresponding specific dimension feature standard range to the length of the corresponding interval of the specific dimension feature standard range.

[0085] In implementation, if the value of the specific dimension feature corresponding to any path segment does not exceed the specific dimension feature standard range, the corresponding ratio is determined to be 0.

[0086] Specifically, the process of evaluating the deviation tendency characterization coefficient of the received information includes

[0087] Taking the ratio of the offset of the task execution path topology graph to the offset threshold as the first deviation feature;

[0088] Taking the ratio of the information reception frequency to the information reception frequency threshold as the second deviation feature;

[0089] Taking the sum of the first deviation feature and the second deviation feature as the deviation tendency characterization coefficient.

[0090] In this embodiment, the purpose of setting the offset threshold is to characterize the situation where the specific dimension features corresponding to each path segment deviate relatively more from the specific dimension feature standard range. Therefore, the offset threshold should not be set too small. In implementation, it is selected within the interval [30%, 50%].

[0091] The information reception frequency threshold is determined based on the maximum value of the historical information reception frequency between the sender and the intelligent agent cluster, and is set as the product of the maximum value and the error coefficient. The error coefficient is selected within the interval [0.85, 0.95].

[0092] Specifically, the present invention considers calculating the deviation tendency characterization coefficient. In actual situations, for a given sender, when the intelligent agent executes tasks for the received information, the nodes participating in the operation and the information interaction between the nodes are all associated with the corresponding tasks, and there are usually certain historical laws. Based on this, the present invention determines the offset of the task execution path topology graph, considering the deviation of the specific dimension features corresponding to different path segments from the specific dimension feature standard range, that is, the situation of deviation from the historical laws. At the same time, combined with the information reception frequency of the intelligent agent cluster, the offset of the operation situation of the intelligent agent cluster relative to the historical laws is comprehensively considered, characterizing the potential risk that the information received by the intelligent agent cluster is tampered with or there is false information, and thus providing data support for subsequent determination of the consistency of the intelligent agent execution situation. The present invention adopts a multi-dimensional evaluation method to more comprehensively and reliably detect false information and ensure the reliability of false information detection.

[0093] Specifically, please refer to Figure 2As shown, it is a logical decision diagram for determining whether to call the operation rule file of the agent cluster in the embodiment of the present invention. Based on the deviation tendency characterization coefficient, it is determined whether to call the operation rule file of the agent cluster, including,

[0094] If the deviation tendency characterization coefficient is greater than or equal to the deviation tendency characterization coefficient threshold, then call the operation rule file of the agent cluster;

[0095] Among them, the rule execution path topology diagram is recorded in the operation rule file.

[0096] In implementation, the deviation tendency characterization coefficient threshold is selected within the interval [2.24, 2.35].

[0097] Specifically, the rule execution path topology diagram is pre-generated, and the operation records of the agent cluster after a number of real messages are sent by the same sender are pre-recorded. The agents participating in the operation are determined as nodes, and the agents generating interactions are connected as edges to obtain the rule execution path topology diagram.

[0098] Specifically, please refer to Figure 3 As shown, it is a logical decision diagram for determining whether the task execution path topology diagram of the agent cluster in the embodiment of the present invention is consistent. The process of determining whether the rule execution path topology diagram and the task execution path topology diagram of the agent cluster are consistent includes,

[0099] Extract the rule execution path topology diagram from the operation rule file;

[0100] Compare the task execution path topology diagram with the rule execution path topology diagram and calculate the coincidence degree;

[0101] If the coincidence degree is greater than or equal to the preset coincidence degree threshold, it is determined to be consistent;

[0102] If the coincidence degree is less than the preset coincidence degree threshold, it is determined to be inconsistent, and the received information of the agent cluster is detected and analyzed.

[0103] Specifically, the ratio of the number of overlapping nodes to the total number of nodes in the rule execution path topology diagram is used as the coincidence degree.

[0104] The coincidence degree threshold is preset. Among them, the task execution path topology diagrams corresponding to the agent cluster after a number of real messages are sent by the same sender are pre-statistically analyzed. The coincidence degrees of each task execution path topology diagram and the rule execution path topology diagram are respectively solved, and the average coincidence degree is calculated. The coincidence degree threshold is set as the product of the average coincidence degree and the precision coefficient, and the precision coefficient is selected within the interval [1.15, 1.3].

[0105] Specifically, the process of determining the task execution impact degree for the agent cluster based on the unexpected nodes includes

[0106] Determining the unexpected nodes according to the task execution path topology graph and the rule execution path topology graph;

[0107] Determining the average value of the actual in-degree and out-degree of each unexpected node to obtain the task execution impact degree;

[0108] Among them, if a node appears in the task execution path topology graph but does not appear in the rule execution path topology graph, then this node is determined as an unexpected node.

[0109] It can be understood that the in-degree and out-degree of a node is the average value of the data reception frequency and data transmission frequency of this node.

[0110] Specifically, the process of calculating the topology deviation characterization value includes

[0111] Determining the associated nodes of each unexpected node and determining the average value of the number of associated nodes;

[0112] Taking the ratio of the task execution impact degree to the task execution impact degree threshold as the first topology deviation feature;

[0113] Taking the ratio of the average value of the number of associated nodes to the associated node number threshold as the second topology deviation feature;

[0114] Performing weighted summation of the first topology deviation feature and the second topology deviation feature as the topology deviation characterization value.

[0115] In implementation, the task execution impact degree threshold is determined in advance. Among them, the average value of the in-degree and out-degree of the corresponding nodes in the rule execution path topology graph is used as the task execution impact degree threshold.

[0116] In implementation, the average value of the number of associated nodes corresponding to each node in the rule execution path topology graph is determined as the associated node number threshold.

[0117] Specifically, during the actual operation of the agent cluster, the deviation of the task execution impact degree evaluation operation determined according to the actual operation trajectory is more representative. Therefore, in implementation, the task execution impact degree is preferentially considered. Therefore, a slightly higher weight is assigned to the first topology deviation feature calculated based on the task execution impact degree. Therefore, when performing weighted summation, the weight of the first topology deviation feature is set to 0.6, and the weight of the second topology deviation feature is set to 0.4.

[0118] Specifically, in the case where the task execution path topology graph of the agent cluster does not conform to the consistency of the rule execution path topology graph, the present invention triggers further detection and analysis of the information received by the agent cluster, saving computing power and avoiding waste of computing power in traversal-depth analysis. When performing detection and analysis, an unexpected node means that the node does not belong to the rule execution path topology graph. Subsequently, the influence degree of the computing task execution is calculated. The in-degree and out-degree of the unexpected node characterize the proportion of this type of node participating in the operation. The more the proportion, the more it indicates that it is not an accidental event, and the more important the unexpected node is, which characterizes that the operations involved in the tasks executed by the current agent cluster do not conform to the historical law. By calculating the topology deviation characterization value and considering the number of associated nodes of the unexpected node, the importance degree of the unexpected node participating in the operation is further corroborated. Furthermore, the situation of the task execution deviation from the historical law is comprehensively reflected from the inside of the agent cluster, providing data support for subsequent determination of whether it conforms to the topology deviation standard. The present invention adopts a multi-dimensional evaluation method to detect false information more comprehensively and reliably, ensuring the reliability of false information detection.

[0119] Specifically, please refer to Figure 4 shown in the figure, which is the logic decision diagram for the present invention's embodiment to determine whether it conforms to the topology deviation standard. Determining whether it conforms to the topology deviation standard includes

[0120] If the topology deviation characterization value is greater than or equal to the topology deviation characterization threshold, it is determined that it does not conform to the topology deviation standard;

[0121] If the topology deviation characterization value is less than the topology deviation characterization threshold, it is determined that it conforms to the topology deviation standard.

[0122] It can be understood that the purpose of setting the topology deviation characterization threshold is to characterize that the abnormal deviation degree presented by the current agent cluster during the operation process is relatively large, that is, the situation where the topology deviation characterization value is relatively large. Due to the calculation method of the topology deviation characterization value, its ideal state should be around 1. The larger the topology deviation characterization value, the more serious the topology deviation. Therefore, the topology deviation characterization threshold is set as the product of 1 and the deviation coefficient, and the deviation coefficient is in the interval [1.3, 1.6].

[0123] Specifically, it further includes controlling the agent cluster to stop receiving information and stop sending information in response to not conforming to the topology deviation standard.

[0124] If the false information detection method in the multi-agent system of the present invention is implemented in the form of software functional units and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0125] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A method for detecting false information in a multi-agent system, characterized in that, Including: Invoking the interaction data of the historical tasks of a number of real information by the intelligent agent cluster to analyze the intelligent agent cluster, including determining the fluctuation value sorting of the corresponding dimensional characteristics of each path segment of the task execution path topology graph after the intelligent agent cluster receives a number of real information, so as to determine the specific dimensional characteristics and the standard range of the specific dimensional characteristics corresponding to each path segment; In response to the intelligent agent cluster receiving information, comparing the specific dimensional characteristics corresponding to each path segment with the standard range of the specific dimensional characteristics to determine the offset of the task execution path topology graph; Evaluating the deviation tendency characterization coefficient of the received information according to the offset and the information reception frequency of the intelligent agent cluster; Based on the deviation tendency characterization coefficient, determining whether to invoke the operation rule file of the intelligent agent cluster to determine the corresponding rule execution path topology graph, and determining whether the rule execution path topology graph is consistent with the task execution path topology graph of the intelligent agent cluster, so as to detect and analyze the received information of the intelligent agent cluster, Including, Identifying a number of nodes corresponding to the task execution path topology graph of the intelligent agent cluster to determine unexpected nodes, determining the task execution influence degree on the intelligent agent cluster based on the unexpected nodes, calculating the topology deviation characterization value by combining the number of associated nodes of the unexpected nodes, and determining whether it meets the topology deviation standard; In response to determining that it does not meet the topology deviation standard, marking the received information, identifying the sender corresponding to the received information, and tracking the receivers of the information sent by the intelligent agent cluster.

2. The method for detecting false information in a multi-agent system according to claim 1, characterized in that The process of determining the specific dimensional characteristics and the standard range of the specific dimensional characteristics corresponding to each path segment includes, Determining the dimensional characteristics corresponding to the path segments of the task execution path topology graph, including the average load at both ends, the data transmission volume, and the transmission frequency; Respectively determining the fluctuation values of the dimensional characteristics of each path segment and sorting them; Determining the dimensional characteristic corresponding to the minimum fluctuation value, and determining the dimensional characteristic as the specific dimensional characteristic; Recording the maximum value and the minimum value of the specific dimensional characteristic in the path segment, and determining the standard range of the specific dimensional characteristic based on the maximum value and the minimum value; Wherein, the fluctuation value is the absolute variance of the dimensional characteristic at a number of time nodes.

3. The false information detection method in the multi-agent system according to claim 2, characterized in that, The process of determining the offset of the task execution path topology graph includes, Respectively determining the specific dimensional characteristics corresponding to each path segment; Determining the proportion of the specific dimensional characteristics corresponding to each path segment exceeding the corresponding standard range of the specific dimensional characteristics; Determining the average value of each proportion as the offset.

4. The false information detection method in the multi-agent system according to claim 3, characterized in that The process of evaluating the deviation tendency characterization coefficient of the received information includes, Taking the ratio of the offset of the task execution path topology graph to the offset threshold as the first deviation characteristic; Taking the ratio of the information reception frequency to the information reception frequency threshold as the second deviation characteristic; Taking the sum of the first deviation characteristic and the second deviation characteristic as the deviation tendency characterization coefficient.

5. The false information detection method in the multi-agent system according to claim 4, characterized in that Determining whether to invoke the operation rule file of the intelligent agent cluster based on the deviation tendency characterization coefficient, including, If the deviation tendency characterization coefficient is greater than or equal to the deviation tendency characterization coefficient threshold, then invoking the operation rule file of the intelligent agent cluster; Among them, the rule execution path topology graph is recorded in the operation rule file.

6. The false information detection method in the multi-agent system according to claim 5, characterized in that, The process of determining whether the rule execution path topology graph is consistent with the task execution path topology graph of the agent cluster includes: extracting the rule execution path topology graph from the operation rule file; comparing the task execution path topology graph with the rule execution path topology graph and calculating the coincidence degree; if the coincidence degree is greater than or equal to the preset coincidence degree threshold, it is determined to be consistent; if the coincidence degree is less than the preset coincidence degree threshold, it is determined to be inconsistent, and the received information of the agent cluster is detected and analyzed.

7. The method for detecting false information in a multi-agent system according to claim 1, characterized in that The process of determining the task execution influence degree for the agent cluster based on the unexpected nodes includes: determining the unexpected nodes according to the task execution path topology graph and the rule execution path topology graph; determining the average value of the actual in-degree and out-degree of each unexpected node to obtain the task execution influence degree; wherein, if a node appears in the task execution path topology graph but does not appear in the rule execution path topology graph, it is determined that the node is an unexpected node.

8. The false information detection method in the multi-agent system according to claim 7, characterized in that The process of calculating the topology deviation characterization value includes: determining the associated nodes of each unexpected node and determining the average value of the number of associated nodes; taking the ratio of the task execution influence degree to the task execution influence degree threshold as the first topology deviation feature; taking the ratio of the average value of the number of associated nodes to the associated node number threshold as the second topology deviation feature; weighted summing the first topology deviation feature and the second topology deviation feature as the topology deviation characterization value.

9. The false information detection method in the multi-agent system according to claim 8, characterized in that, Determining whether it meets the topology deviation standard includes: if the topology deviation characterization value is greater than or equal to the topology deviation characterization threshold, it is determined not to meet the topology deviation standard.

10. The false information detection method in the multi-agent system according to claim 9, characterized in that It also includes, in response to not meeting the topology deviation standard, controlling the agent cluster to stop receiving information and stop sending information.

Images