Government Affairs Information Traceability Method and System Based on Big Data Analysis

Abstract

The present invention relates to the technical field of data processing, and specifically relates to a method and system for tracing government affairs information based on big data analysis. The method includes: obtaining a first knowledge graph of real government affairs information and a second knowledge graph of the government affairs information to be traced; determining the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information; dividing the real part and the tampered part in the government affairs information to be traced; marking the tampered part in the second knowledge graph, and taking all the nodes and edges associated with the tampered part as the influence information subgraph of the tampered part; determining the degree of tampering between the government affairs information to be traced and the real government affairs information. When the degree of tampering is greater than or equal to the first threshold, it is determined that there is a tampering relationship between the government affairs information to be traced and the real government affairs information, and the real government affairs information is used as the real information of the government affairs information to be traced. In this way, the present invention improves the success rate, efficiency and accuracy of tracing government affairs information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for tracing government affairs information based on big data analysis. Background Art

[0002] Government affairs information refers to various information generated in government affairs activities, which is the general term for various data materials reflecting government work and related things. It has the characteristics of timeliness, authenticity, and a certain degree of transparency, providing a basis for organizational decision-making and implementation. With the deep penetration and large-scale application of modern electronic information technologies such as computer technology and network communication technology in various fields, electronic storage materials have rapidly emerged as the main direction for the storage and dissemination of government affairs information. During the extensive dissemination of government affairs information through electronic channels such as the Internet, information security risks have become increasingly prominent. Due to the numerous and complex information dissemination links, some entities, for various improper purposes, beautify or maliciously tamper with government affairs information, distorting the original semantics of the information and seriously deviating from the true content, thereby resulting in information errors. Once such incorrect information flows into the decision-making level or the public eye, it may trigger a series of serious consequences such as decision-making mistakes, misleading public opinion, and undermining the credibility.

[0003] In some scenarios, to address the harm caused by false government affairs information, currently, the origin of government affairs information is traced based on the dissemination path. By tracking the dissemination path of government affairs information in the network, an attempt is made to find the source node where the information has been tampered with. At the same time, combined with semantic analysis technology, the false government affairs information is compared with possible original information samples, and the initial source of the correct government affairs information is inferred based on the semantic change situation. However, in actual application scenarios, these methods have exposed many problems. On the one hand, the modern network dissemination path is intricate and prone to losing the dissemination path, greatly increasing the difficulty of the information tracing method based on the dissemination path. On the other hand, for false government affairs information with a large degree of tampering, the semantic difference from the original text is significant, resulting in problems such as slow tracing and incorrect tracing. Therefore, the success rate, efficiency, and accuracy of tracing government affairs information in the above-mentioned manner are all relatively low. Summary of the Invention

[0004] In order to solve the technical problem of relatively low success rate, efficiency, and accuracy in tracing government affairs information, the purpose of the present invention is to provide a method and system for tracing government affairs information based on big data analysis. The specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for tracing government affairs information based on big data analysis, including: obtaining a first knowledge graph of real government affairs information and a second knowledge graph of government affairs information to be traced; determining the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information according to the consistency between the nodes and the consistency between the edges in the second knowledge graph and the first knowledge graph; matching the government affairs information to be traced with the real government affairs information to divide the real part and the tampered part in the government affairs information to be traced; marking the tampered part in the second knowledge graph, and taking all the nodes and edges associated with the tampered part as the influence information subgraph of the tampered part; determining the degree of tampering between the government affairs information to be traced and the real government affairs information according to the possibility, the consistency between the nodes and the consistency between the edges in the first knowledge graph and the influence information subgraph, and when the degree of tampering is greater than or equal to a first threshold, determining that there is a tampering relationship between the government affairs information to be traced and the real government affairs information, and taking the real government affairs information as the real information of the government affairs information to be traced.

[0006] Optionally, after determining that there is a tampering relationship between the government affairs information to be traced and the real government affairs information and taking the real government affairs information as the real information of the government affairs information to be traced when the degree of tampering is greater than or equal to a first threshold, the method further includes: marking the nodes and edges existing in the influence information subgraph in the first knowledge graph.

[0007] Optionally, determining the possibility of a tampering relationship between the government affairs information to be traced and the true government affairs information based on the consistency between the nodes and the consistency between the edges in the second knowledge graph and the first knowledge graph includes: determining the first quantity of the consistent nodes in the second knowledge graph and the first knowledge graph and the second quantity of the edges where the consistent nodes are located and having a consistent relationship in the first knowledge graph and the second knowledge graph; determining the semantic consistency between the first knowledge graph and the second knowledge graph according to the third quantity, the first quantity, the second quantity of the nodes in the second knowledge graph, and the fourth quantity of the edges where the consistent nodes are located; in the case where the semantic consistency does not meet the second threshold, determining that the government affairs information to be traced is false government affairs information; determining the third knowledge graph of the true government affairs information published before the publication time of the government affairs information to be traced, and calculating the time interval between the publication time of each true government affairs information in the third knowledge graph and the publication time of the government affairs information to be traced; determining the fifth quantity of the consistent edges in the first knowledge graph and the second knowledge graph; determining the remaining nodes and the remaining edges in the second knowledge graph except for the consistent nodes and the consistent edges with the first knowledge graph; determining the sixth quantity and the seventh quantity of the nodes and the edges different from the remaining nodes and the remaining edges from the first knowledge graph; determining the tampering connection situation between the government affairs information to be traced and the true government affairs information according to the semantic consistency, the time interval, the second quantity, the fifth quantity, the sixth quantity, the seventh quantity, the eighth quantity of the remaining nodes, and the ninth quantity of the remaining edges; performing a normalization process on the tampering connection situation to obtain the possibility of a tampering relationship between the government affairs information to be traced and the true government affairs information.

[0008] Optionally, determining the semantic consistency between the first knowledge graph and the second knowledge graph according to the third quantity, the first quantity, the second quantity of the nodes in the second knowledge graph, and the fourth quantity of the edges where the consistent nodes are located includes: calculating the first ratio between the third quantity and the first quantity, and the second ratio between the second quantity and the fourth quantity; determining the first product between the first ratio and the second ratio as the semantic consistency.

[0009] Optionally, determining the tampering connection situation between the government affairs information to be traced and the true government affairs information according to semantic consistency, time interval, the second quantity, the fifth quantity, the sixth quantity, the seventh quantity, the eighth quantity of the remaining nodes, and the ninth quantity of the remaining edges includes: calculating the first difference between the fifth quantity and the second quantity, and calculating the third ratio between the first difference and the fifth quantity, and taking the third ratio as the entity change situation between the government affairs information to be traced and the true government affairs information; calculating the second product between the third ratio and semantic consistency, and calculating the fourth ratio between the second product and the time interval; calculating the first sum value between the sixth quantity and the seventh quantity, and the second sum value between the eighth quantity and the ninth quantity, and calculating the fifth ratio between the first sum value and the second sum value; determining the third product between the fourth ratio and the fifth ratio as the tampering connection situation.

[0010] Optionally, determining the degree of tampering between the government affairs information to be traced and the true government affairs information according to the consistency between nodes and the consistency between edges in possibility, the first knowledge graph, and the influence information subgraph includes: determining the first total quantity of nodes and edges in the influence information subgraph that exist in the first knowledge graph, determining the second total quantity of nodes and edges in the influence information subgraph where the first total quantity of nodes and edges exist, and determining the degree to which the tampered part is disrupted during the tampering process according to the first distance between any two nodes or edges in the first knowledge graph and the second distance in the influence information subgraph; determining the degree of tampering between the government affairs information to be traced and the true government affairs information according to possibility, the first total quantity, the second total quantity, and the degree of disruption.

[0011] Optionally, determining the degree to which the tampered part is disrupted during the tampering process according to the first distance between any two nodes or edges in the first knowledge graph and the second distance in the influence information subgraph includes: calculating the absolute value of the second difference between each first distance and the corresponding second distance; superimposing the absolute values of each second difference to obtain the degree to which the tampered part is disrupted during the tampering process.

[0012] Optionally, determining the degree of tampering between the government affairs information to be traced and the true government affairs information according to possibility, the first total quantity, the second total quantity, and the degree of disruption includes: calculating the sixth ratio between the second total quantity and the first total quantity; determining the fourth product between possibility, the sixth ratio, and the degree of disruption as the degree of tampering between the government affairs information to be traced and the true government affairs information.

[0013] Optionally, the first knowledge graph for obtaining real government affairs information and the second knowledge graph for government affairs information to be traced include: identifying the content of real government affairs information and government affairs information to be traced based on a rule dictionary, and determining the entities and relationships in the real government affairs information and the government affairs information to be traced; using the entities as nodes, the relationships as edges, and recording the attribute data of the nodes or edges in the nodes or edges, to construct the first knowledge graph and the second knowledge graph.

[0014] In a second aspect, an embodiment of the present invention provides a government affairs information tracing system based on big data analysis, including: a processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; the processor is used to execute the program stored on the memory to implement the steps of the government affairs information tracing method based on big data analysis as mentioned in the first aspect.

[0015] The present invention has the following beneficial effects: First, obtain the first knowledge graph of real government affairs information and the second knowledge graph of government affairs information to be traced; then, according to the consistency between the nodes and the consistency between the edges in the second knowledge graph and the first knowledge graph, determine the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information; secondly, match the government affairs information to be traced with the real government affairs information, and divide the real part and the tampered part in the government affairs information to be traced; mark the tampered part in the second knowledge graph, and use all the nodes and edges associated with the tampered part as the influence information subgraph of the tampered part; and according to the possibility, the consistency between the nodes and the consistency between the edges in the first knowledge graph and the influence information subgraph, determine the degree of being tampered between the government affairs information to be traced and the real government affairs information; finally, when the degree of being tampered is greater than or equal to the first threshold, determine that there is a tampering relationship between the government affairs information to be traced and the real government affairs information, and use the real government affairs information as the real information of the government affairs information to be traced.

[0016] Thus, the embodiment of the present invention determines the synonymous part and the tampered part in the traceable government information according to the tampering relationship between the real government information and the traceable government information, determines the degree of tampering of the traceable government information for the influence information subgraph of the tampered part and the real government information, and thus determines whether there is a tampering relationship between the traceable government information and the real government information. If there is a tampering relationship, the real government information is used as the real information of the traceable government information. Thus, the embodiment of the present invention has a lower difficulty in tracing information through the knowledge graph, improving the tracing success rate. In addition, for false government information with a large degree of tampering, the real government information is determined by combining the semantics of the real part in the traceable government information, and the degree of tampering between the tampered part in the traceable government information and the real government information is determined, so as to determine whether there is a tampering relationship between the traceable government information and the real government information. If the degree of tampering is large, it indicates that there is a tampering relationship between the two, achieving the purpose of tracing. The above method improves the success rate, efficiency and accuracy of tracing government information. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 The flowchart of a government information tracing method based on big data analysis provided by an embodiment of the present invention;

[0019] Figure 2 The knowledge graph schematic diagram of real government information provided by an embodiment of the present invention;

[0020] Figure 3 The schematic diagram of a tampered traceable government information provided by an embodiment of the present invention;

[0021] Figure 4 The structural schematic diagram of a government information tracing system based on big data analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a government information tracing method and system based on big data analysis proposed according to the present invention, including its specific implementation manner, structure, features and effects, as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0024] The following specifically describes the specific solution of a government information tracing method based on big data analysis provided by the present invention in conjunction with the accompanying drawings.

[0025] Embodiment 1:

[0026] Please refer to Figure 1 , which shows the flowchart of the government information tracing method based on big data analysis provided by an embodiment of the present invention, including:

[0027] S101, obtaining the first knowledge graph of real government information and the second knowledge graph of the government information to be traced.

[0028] Specifically, after obtaining the existing public real government information resources in the embodiment of the present invention, the real government information is cleaned to remove noise and duplicate data therein, and then a knowledge extraction operation is performed on the cleaned real government information. Among them, as an optional embodiment of the present invention, obtaining the first knowledge graph of real government information and the second knowledge graph of the government information to be traced includes: identifying the content of the real government information and the government information to be traced based on a rule dictionary, and determining the entities and relationships in the real government information and the government information to be traced; using the entities as nodes, the relationships as edges, and recording the attribute data of the nodes or edges in the nodes or edges to construct the first knowledge graph and the second knowledge graph.

[0029] Specifically, for real government affairs information, in the embodiments of the present invention, based on the rule dictionary method, the real government affairs information is matched and semantically recognized to determine the entities and relationships therein. Among them, the entities include but are not limited to people, organizations, location units, time, policies, etc., and the relationships between entities refer to the association relationships between entities. For example, a real government affairs information is "Department A is responsible for the implementation of Policy B", and the entities "Department A" and "Policy B" and their relationship "implementation" are extracted from the real government affairs information. After obtaining the entities and the relationships between the entities, they are organized in the form of a graph. Specifically, the entities are used as nodes, the relationships between the entities are used as edges, and the attribute data of the nodes or edges are recorded in the nodes or edges to construct the knowledge graph of the real government affairs information and enter it into the system for subsequent traceability operations. Exemplarily, as Figure 2 shown, Figure 2 is a schematic diagram of the knowledge graph of a real government affairs information provided by an embodiment of the present invention. As can be seen from Figure 2 it, each node represents an entity, and the edge between each node represents the association relationship between two entities.

[0030] Furthermore, in the embodiments of the present invention, untrue government affairs information suspected of being rumors on the network is obtained as the government affairs information to be traced through various channels, and the channels include but are not limited to real-time hot spot detection, anonymous reporting, and manual discrimination methods. After obtaining the government affairs information to be traced, in the embodiments of the present invention, based on the rule dictionary method, the government affairs information to be traced is matched and semantically recognized to determine the entities and relationships therein. Among them, the entities include but are not limited to people, organizations, location units, time, policies, etc., and the relationships between entities refer to the association relationships between entities.

[0031] It should be noted that, according to the type of government affairs information, the entities and the relationships between the entities are not limited to the types mentioned in the above embodiments of the present invention.

[0032] S102. Determine the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information according to the consistency between the nodes and the consistency between the edges in the second knowledge graph and the first knowledge graph.

[0033] Specifically, during the dissemination process of real government affairs information, there are some untrue information maliciously tampered with or fabricated out of thin air, and there is also a possibility that the processed and beautified information may be regarded as untrue government affairs information. There is a fundamental semantic difference between the truly maliciously tampered or fabricated untrue government affairs information and the existing real government affairs information, while the processed and beautified information does not change the semantics of the real government affairs information. Since the knowledge graph contains the semantics represented by each government affairs information, the processed and beautified real government affairs information in the suspected untrue government affairs information can be excluded according to the matching of the knowledge graph of the suspected untrue government affairs information and the existing real government affairs information.

[0034] Furthermore, through the above embodiments, knowledge extraction is performed on the attributes and content of each real government affair information and the government affair information to be traced, and a number of knowledge graphs are constructed. In the embodiments of the present invention, it is assumed that a total of existing real government affair information items are used to obtain the first knowledge graph (sorted in the order of release time), where and and represent the node set (entity set) in the first knowledge graph obtained from the th existing real government affair information item, and represents the th node in the first knowledge graph obtained from the th existing real government affair information item. represents the edge set (relationship set) in the first knowledge graph obtained from the th existing real government affair information item, and represents the th edge in the first knowledge graph obtained from the th existing real government affair information item. Similarly, the knowledge graph obtained from the government affair information to be traced that needs to be discriminated is denoted as and represents the node set (entity set) in the second knowledge graph obtained from the th government affair information to be traced, and represents the edge set (relationship set) in the second knowledge graph obtained from the th government affair information to be traced.

[0035] Further, as an optional embodiment of the present invention, determining the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information according to the consistency between nodes and the consistency between edges in the second knowledge graph and the first knowledge graph includes: determining the first quantity of the consistent nodes in the second knowledge graph and the first knowledge graph, and the second quantity of the edges where the edges where the consistent nodes are located have a consistent relationship in the first knowledge graph and the second knowledge graph; determining the semantic consistency between the first knowledge graph and the second knowledge graph according to the third quantity, the first quantity, the second quantity of the nodes in the second knowledge graph, and the fourth quantity of the edges where the consistent nodes are located; determining that the government affairs information to be traced is false government affairs information when the semantic consistency does not meet the second threshold; determining the third knowledge graph of the real government affairs information published before the publication time of the government affairs information to be traced, and calculating the time interval between the publication time of each real government affairs information in the third knowledge graph and the publication time of the government affairs information to be traced; determining the fifth quantity of the consistent edges in the first knowledge graph and the second knowledge graph; determining the remaining nodes and remaining edges in the second knowledge graph except for the consistent nodes and consistent edges with the first knowledge graph; determining the sixth quantity and the seventh quantity of the nodes and edges different from the remaining nodes and remaining edges in the first knowledge graph; determining the tampering connection situation between the government affairs information to be traced and the real government affairs information according to the semantic consistency, the time interval, the second quantity, the fifth quantity, the sixth quantity, the seventh quantity, the eighth quantity of the remaining nodes, and the ninth quantity of the remaining edges; performing normalization processing on the tampering connection situation to obtain the possibility of a tampering relationship between the government affairs information to be traced and the real government affairs information.

[0036] Specifically, in the embodiment of the present invention, taking the second knowledge graph obtained from the government affairs information to be traced and the first knowledge graph obtained from a certain existing real government affairs information as an example to calculate the possibility of a tampering relationship between the two. Among them, the third quantity of the nodes in the second knowledge graph in the embodiment of the present invention is denoted as , and it is respectively determined whether each node in its node set exists in the node set of the first knowledge graph . Specifically, it is determined according to whether the stored entities and the attribute data of the entities in the nodes are consistent. If the stored entities and the attribute data of the entities in the nodes of the first knowledge graph and the second knowledge graph are consistent, it means that the nodes in the node set exist in the node set of the first knowledge graph . Mark the consistent nodes in the node set and the node set , and record the number of the marked nodes in the node set as , i.e., the first quantity.

[0037] Furthermore, in the first knowledge graph and the second knowledge graph in the edge set and among them, select the edges whose two end nodes are both or in the marked nodes and denote them as subset and , where is the edge whose two end nodes are in the marked nodes, is the edge whose two end nodes are in the marked nodes. Obtain the number of edges inside subset , i.e., the fourth quantity, and respectively determine whether each edge inside it exists in subset . Among them, it can be determined according to whether the relationship expressed by the edge and the relationship attribute data are consistent. If the relationship expressed by the edge in subset and the relationship attribute data are the same as those of the edge in subset , it means that the edge in subset exists in subset . Mark the consistent edges in subset and subset and record the number of marked edges in subset as , i.e., the second quantity.

[0038] Furthermore, as an optional embodiment of the present invention, according to the third quantity, the first quantity, the second quantity of the nodes in the second knowledge graph, and the fourth quantity of the edges where the consistent nodes are located, determining the semantic consistency between the first knowledge graph and the second knowledge graph includes: calculating the first ratio between the third quantity and the first quantity, and the second ratio between the second quantity and the fourth quantity; determining the first product between the first ratio and the second ratio as the semantic consistency.

[0039] Specifically, the embodiment of the present invention specifically calculates the semantic consistency using the following formula:

[0040]

[0041] In the above formula, represents the semantic consistency between the first knowledge graph and the second knowledge graph . represents the third quantity of the nodes in the node set of the second knowledge graph Represents the second knowledge graph Node set in the first knowledge graph of the node set The first quantity of nodes with a consistent relationship Represents the second knowledge graph Node set in the first knowledge graph of the node set The fourth quantity of the edges where the nodes with a consistent relationship are located Represents the second knowledge graph Edge subset in the edges and among them the edges in the first knowledge graph of the edge subset The second quantity of edges with a consistent relationship

[0042] Among them represents the ratio of the number of nodes with semantic consistency in the knowledge graph of the government affairs information to be traced and the real government affairs information to the total number of nodes represents the ratio of the number of consistent relationships in the knowledge graph of the government affairs information to be traced and the real government affairs information to its total number of relationships and The larger they are, the higher the semantic consistency between the government affairs information to be traced and the real government affairs information. In summary The larger the value, the higher the semantic consistency between the government affairs information to be traced and the real government affairs information, and the more consistent the semantics contained

[0043] Therefore, by calculating the semantic consistency between the government affairs information to be traced and all real government affairs information through the above method, they are respectively denoted as .

[0044] Furthermore, the second threshold can be set according to the actual situation, and the value in the embodiment of the present invention is 1. If the semantic consistency between the government affairs information to be traced and a certain real government affairs information among all real government affairs information satisfies , it indicates that the semantics expressed by the government affairs information to be traced and the rd real government affairs information correspond one-to-one and match, and it is considered not to be false government affairs information and is excluded. On the contrary, if are not all 1, it is considered that the government affairs information to be traced is false government affairs information, and the semantic consistency between it and each real government affairs information is recorded and the following operations in the embodiment of the present invention are performed

[0045] Furthermore, false government affairs information can be divided into two types: those tampered from true government affairs information and those fabricated out of thin air, hereinafter simply referred to as tampered false government affairs information and fabricated false government affairs information. For tampered false government affairs information, which is tampered from true government affairs information, there is still a certain connection with the true government affairs information. It is possible that only data such as entities, relationships, or attributes are tampered. In contrast, fabricated false government affairs information is completely fabricated out of thin air without any basis and has little connection with existing true government affairs information. Therefore, it is possible to determine whether there is a tampering relationship between the two based on the connection and difference between the false government affairs information and the existing true government affairs information.

[0046] First of all, government affairs information has timeliness, and tampered government affairs information is based on true government affairs information. Therefore, the release time of tampered false government affairs information must be after the release time of the true government affairs information it tampers with, and the interval will not be too long. Record the release time of this false government affairs information as , and screen out the existing true government affairs information (assuming there are a total of articles) released before this time point, and the obtained several knowledge graphs are recorded as . Record its release time as . Calculate the interval between the release time of the -th true government affairs information and the release time of this false government affairs information, and record it as . .

[0047] Secondly, consider the associated situation between the false government affairs information and the -th true government affairs information, and obtain the semantic consistency between the two according to the method of the above embodiment. However, the calculation logic of this value considers whether the relationships between entities are consistent on the premise of entity consistency. Although this does not affect the judgment of false government affairs information, it fails to consider the situation where the relationships are consistent but the entities have changed, that is, the situation where the relationships and entities do not correspond to the true government affairs information, and it is not applicable to the distinction between tampered information and fabricated information. Therefore, in the embodiment of the present invention, for each edge in the edge set of the second knowledge graph of the false government affairs information, find the edge that is consistent with it in the edge set of the first knowledge graph obtained from the -th true government affairs information and mark it. The number of edges that are consistent with the true government affairs information is recorded as , that is, the fifth quantity. Further calculate the proportion of the edges with entity changes among all the edges with consistent relationships between the false government affairs information and the true government affairs information as:

[0048]

[0049] In the above formula, ​Indicates the entity change situation between the i-th real government affair information and the government affair information to be traced back. Is the fifth quantity of the consistent edges in the first knowledge graph of the i-th real government affair information and the second knowledge graph of the government affair information to be traced back. Indicates the second knowledge graph Edge subset of Edges in it and those that have a consistent relationship with the edge subset of the first knowledge graph Edge subset of The second quantity of the edges that are in agreement.

[0050] Finally, the embodiments of the present invention consider the difference situation between the real government affair information and the government affair information to be traced back. Besides the part of information with semantic consistency, the tampered information is tampered from the real information, and there are some "local differences", such as changing some attribute data (such as the time and place attributes of an event), etc. In the set corresponding to the government affair information to be traced back And Remove the nodes and edges marked with semantic consistency with the real government affair information. For the remaining nodes and edges, record the number of the remaining nodes and the remaining edges as the eighth quantity And the ninth quantity . For the remaining nodes and remaining edges, look for "local differences" in the set corresponding to the first knowledge graph of the real government affair information And , that is, the nodes and edges where the entity or relationship data stored in the nodes or edges is consistent, but the attribute data is inconsistent. Record the number of the nodes and edges with local differences as And , where Indicates the sixth quantity of the nodes in the first knowledge graph of the i-th real government affair information that are different from the remaining nodes, Indicates the seventh quantity of the edges in the first knowledge graph of the i-th real government affair information that are different from the remaining edges.

[0051] Furthermore, as an optional embodiment of the present invention, according to the semantic consistency, time interval, second quantity, fifth quantity, sixth quantity, seventh quantity, eighth quantity of the remaining nodes, and ninth quantity of the remaining edges, determining the tampering connection situation between the government affair information to be traced back and the real government affair information includes: calculating the first difference between the fifth quantity and the second quantity, and calculating the third ratio between the first difference and the fifth quantity, and taking the third ratio as the entity change situation between the government affair information to be traced back and the real government affair information; calculating the second product between the third ratio and the semantic consistency, and calculating the fourth ratio between the second product and the time interval; calculating the first sum value between the sixth quantity and the seventh quantity, and the second sum value between the eighth quantity and the ninth quantity, and calculating the fifth ratio between the first sum value and the second sum value; determining that the third product between the fourth ratio and the fifth ratio is the tampering connection situation.

[0052] Specifically, the embodiments of the present invention specifically calculate the tampering connection situation by the following formula:

[0053]

[0054] In the above formula, represents the tampering connection situation between the i-th real government affair information and the government affair information to be traced. represents the first knowledge graph of the real government affair information and the semantic consistency between the second knowledge graph of the government affair information to be traced The larger this value is, the higher the semantic consistency between the two pieces of information, and the better the tampering connection situation between the two pieces of information. represents the entity change situation between the i-th real government affair information and the government affair information to be traced. The larger this value is, the more tampering behaviors where the relational entities in the i-th real government affair information and the government affair information to be traced do not correspond, and the better the tampering connection situation between the i-th real government affair information and the government affair information to be traced.

[0055] is the time interval between the release times of the i-th real government affair information and the government affair information to be traced. The smaller this value is, the stronger the timeliness of the tampered real government affair information, and the higher the possibility of its being tampered. represents the sixth quantity of the nodes in the first knowledge graph of the i-th real government affair information that are different from the remaining nodes, represents the seventh quantity of the edges in the first knowledge graph of the i-th real government affair information that are different from the remaining edges. is the eighth quantity of the remaining nodes, is the ninth quantity of the remaining edges.

[0056] Among them, is the situation where "locally different" appears in the semantic difference part between the i-th real government affair information and the government affair information to be traced. The larger this value is, the greater the connection still exists in the difference situation between the i-th real government affair information and the government affair information to be traced, and the better the tampering connection situation.

[0057] Furthermore, the embodiments of the present invention use the following formula to normalize the tampering connection situation:

[0058]

[0059] In the above formula, represents the possibility that there is a tampering relationship between the government affair information to be traced and the i-th real government affair information. represents the tampering connection situation between the i-th real government affair information and the government affair information to be traced. represents the normalization function, which is used to perform normalization processing.

[0060] S103. Match the to-be-traced government affairs information with the real government affairs information, and divide the real part and the tampered part in the to-be-traced government affairs information.

[0061] Specifically, in the above embodiments of the present invention, the possibilities of tampering and being tampered between the two are quantified according to the respective situations of the connection (real part) and difference (tampered part) between the false government affairs information and the real government affairs information. However, in the false government affairs information, the tampered part also has a certain impact on the real part. It is necessary to further consider the existence of the tampered part in the false government affairs information and the related real part in the real government affairs information, and comprehensively trace the part with the risk of tampering in the real government affairs information. Exemplarily, as Figure 3 shown, Figure 3 is a schematic diagram of the tampered to-be-traced government affairs information provided by an embodiment of the present invention. Figure 3 In it, when the real government affairs information "Department A manages Department B" is tampered with the false government affairs information "Department B manages Department A", the direction of the relationship of "management" (abstracted as an edge in the knowledge graph) is tampered with. However, the two entities of "Department A" and "Department B" related to "management" still belong to the real government affairs information, but these two are also affected by the tampering of the related "management" relationship. Therefore, in the embodiment of the present invention, it is necessary to first divide the tampered part in the to-be-traced government affairs information, and the to-be-traced government affairs information can be divided into the real part that matches the real government affairs information and the tampered part that does not match. And in the second knowledge graph corresponding to the to-be-traced government affairs information, divide the two.

[0062] S104. Mark the tampered part in the second knowledge graph, and take all the nodes and edges associated with the tampered part as the influence information subgraph of the tampered part.

[0063] Specifically, the part related to the tampered content in the real part of the to-be-traced government affairs information is also affected by the tampering. According to the marked tampered part in the second knowledge graph of the to-be-traced government affairs information, extend outward and mark all the associated nodes and edges together with itself as the tampering and its influence information subgraph. .

[0064] S105. Determine the degree of tampering between the to-be-traced government affairs information and the real government affairs information according to the consistency between the nodes and the consistency between the edges in the possibility, the first knowledge graph and the influence information subgraph. When the degree of tampering is greater than or equal to the first threshold, determine that the relationship between the to-be-traced government affairs information and the real government affairs information is a tampering relationship, and take the real government affairs information as the real information of the to-be-traced government affairs information.

[0065] Specifically, between the tampered part of the government affairs information to be traced, the real part related thereto, and the real government affairs information having a tampering relationship with the government affairs information to be traced, due to the tampering relationship, there are many common entities and relationships between the two. In the embodiment of the present invention, the obtained impact information sub-graph is compared with the first knowledge graph of the th real government affairs information to determine the consistency between the nodes and the consistency between the edges in the first knowledge graph and the impact information sub-graph.

[0066] Further, as an optional embodiment of the present invention, according to the possibility, the consistency between the nodes and the consistency between the edges in the first knowledge graph and the impact information sub-graph, determining the degree of tampering between the government affairs information to be traced and the real government affairs information includes: determining the first total number of nodes and edges in the impact information sub-graph that exist in the first knowledge graph, determining the second total number of nodes and edges in the impact information sub-graph where the first total number of nodes and edges exist, and determining the degree to which the tampered part is disrupted during the tampering process according to the first distance between any two nodes or edges in the first knowledge graph and the second distance in the impact information sub-graph; determining the degree of tampering existing between the government affairs information to be traced and the real government affairs information according to the possibility, the first total number, the second total number, and the disrupted degree.

[0067] Specifically, in the embodiment of the present invention, first record the total number of nodes and edges in the first knowledge graph of the th real government affairs information existing in the impact information sub-graph as , that is, the first total number. Then retrieve the total number of nodes and edges existing in the impact information sub-graph in the first knowledge graph of the th real government affairs information as , that is, the second total number.

[0068] Further, the tampering behavior may cause the entities and relationships in the real government affairs information to be disrupted during the tampering process. Take any two nodes or edges among the co-existing nodes and edges in the first knowledge graph and the impact information sub-graph . Take the th and the th nodes taken as an example. Denote the distances between the th and the th nodes in the first knowledge graph and the impact information sub-graph respectively. Among them, the distance can be the number of nodes or the number of edges separated by the fewest nodes between any two nodes or edges taken. Among them, in the embodiment of the present invention, the The first distance between the th node in the first knowledge graph is denoted as , the th and the th node in the influence information subgraph, and the second distance is denoted as .

[0069] Furthermore, as an optional embodiment of the present invention, determining the degree of disruption of the tampered part during the tampering process according to the first distance between any two nodes or edges in the second total quantity in the first knowledge graph and the second distance in the influence information subgraph includes: calculating the absolute value of the second difference between each first distance and the corresponding second distance; superimposing the absolute values of each second difference to obtain the degree of disruption of the tampered part during the tampering process.

[0070] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the degree of disruption of the tampered part during the tampering process:

[0071]

[0072] In the above formula, represents the degree of disruption of the tampered part corresponding to nodes or edges during the tampering process. represents the total number of nodes and edges retrieved from the first knowledge graph of the th real government information that exist in the influence information subgraph , that is, the second total quantity. represents the first distance between the th and the th node in the first knowledge graph, represents the second distance between the th and the th node in the influence information subgraph.

[0073] Furthermore, as an optional embodiment of the present invention, determining the degree of tampering between the to-be-traced government information and the real government information according to the possibility, the first total quantity, the second total quantity, and the degree of disruption includes: calculating the sixth ratio between the second total quantity and the first total quantity; determining the fourth product of the possibility, the sixth ratio, and the degree of disruption as the degree of tampering between the to-be-traced government information and the real government information.

[0074] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the degree of tampering between the to-be-traced government information and the real government information:

[0075]

[0076] In the above formula, Indicates the degree of tampering between the government affairs information to be traced and the th piece of authentic government affairs information. Is the possibility of a tampering relationship between the government affairs information to be traced and the th piece of authentic government affairs information. The larger this value, the greater the degree of tampering between the two. Indicates the first knowledge graph in the information sub-graph that contains the th piece of authentic government affairs information, which is the total number of nodes and edges in the first knowledge graph, that is, the first total quantity. Indicates the total number of nodes and edges retrieved in the first knowledge graph of the th piece of authentic government affairs information that exist in the information sub-graph that contains the information sub-graph, that is, the second total quantity. The ratio of the two represents the number of these abnormal entity relationships in the authentic government affairs information. The larger this value, the more entity relationships in the authentic government affairs information are tampered with, and the greater the degree of tampering between the two. Indicates the degree to which the tampered part corresponding to the i nodes or edges is disrupted during the tampering process. The larger this value, the greater the degree of tampering between the

[0077] th piece of authentic government affairs information and the government affairs information to be traced. In summary, indicates the degree of tampering between the obtained government affairs information to be traced and the th piece of authentic government affairs information. Calculating the degree of tampering between the government affairs information to be traced and all authentic government affairs information before its release is denoted as .

[0078] Furthermore, in the embodiments of the present invention, the first threshold can be determined according to actual situations. In the embodiments of the present invention, the value is 0.7. If , is the first threshold, it is considered that the government affairs information to be traced and the th piece of authentic government affairs information have a tampering and being tampered relationship, and the obtained authentic government affairs information is used as the authentic information for tracing the government affairs information to be traced.

[0079] Furthermore, in order to warn about the tampering risk part and prevent the negative impact brought by false government affairs information from occurring again in the future, as an optional embodiment of the present invention, when the degree of tampering is greater than or equal to the first threshold, it is determined that there is a tampering relationship between the government affairs information to be traced and the authentic government affairs information. After using the authentic government affairs information as the authentic information of the government affairs information to be traced, the method further includes: marking the nodes and edges in the first knowledge graph that exist in the information sub-graph.

[0080] Specifically, in the embodiments of the present invention, the nodes and edges obtained by marking the above steps are regarded as parts with the risk of tampering and marked to prevent the negative impact brought by the reappearance of false information subsequently. For the results obtained from the government affairs information to be traced, false government affairs information is promptly refuted, and the true government affairs information obtained by tracing is attached.

[0081] In the embodiments of the present invention, the synonymous part and the tampered part in the government affairs information to be traced are determined according to the tampering relationship between the true government affairs information and the government affairs information to be traced. For the influence information subgraph of the tampered part and the true government affairs information, the degree of tampering of the government affairs information to be traced is determined, so as to determine whether there is a tampering relationship between the government affairs information to be traced and the true government affairs information. If there is a tampering relationship, the true government affairs information is used as the true information of the government affairs information to be traced. In this way, the method of information tracing through the knowledge graph in the embodiments of the present invention has a lower difficulty and improves the tracing success rate. In addition, for false government affairs information with a large degree of tampering, the true government affairs information is determined by combining the semantics of the true part in the government affairs information to be traced, and the degree of tampering between the tampered part in the government affairs information to be traced and the true government affairs information is determined, so as to determine whether there is a tampering relationship between the government affairs information to be traced and the true government affairs information. If the degree of tampering is large, it means that there is a tampering relationship between the two, achieving the purpose of tracing. The above method improves the success rate, efficiency and accuracy of tracing government affairs information.

[0082] Embodiment 2:

[0083] Corresponding to the government affairs information tracing method based on big data analysis provided in the above embodiment, based on the same technical concept, the embodiments of the present invention also provide a government affairs information tracing system based on big data analysis. The government affairs information tracing system based on big data analysis is used to execute the above government affairs information tracing method based on big data analysis. Figure 4 is a schematic structural diagram of a government affairs information tracing system based on big data analysis provided by an embodiment of the present invention, as Figure 4 shown. The government affairs information tracing system based on big data analysis may vary greatly due to configuration or performance, and may include one or more processors 401 and a memory 402. The memory 402 is used to store a computer program that can run on the processor 401. The processor 401 is used to execute the program stored in the memory 402 to implement each step in the above Figure 1 method embodiments. Among them, the memory 402 can be short-term storage or persistent storage. The application program stored in the memory 402 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions for the government affairs information tracing system based on big data analysis.

[0084] Furthermore, the processor 401 can be configured to communicate with the memory 402 and execute a series of computer-executable instructions in the memory 402 on the government affairs information traceability system based on big data analysis. The government affairs information traceability system based on big data analysis may further include one or more power supplies 403, one or more wired or wireless network interfaces 404, one or more input / output interfaces 405, and one or more keyboards 406.

[0085] Specifically, in this embodiment, the government affairs information traceability system based on big data analysis includes a processor, a communication interface, a memory, and a communication bus; wherein, the processor, the communication interface, and the memory complete mutual communication through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored on the memory to implement each step in the above Figure 1 method embodiments, and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be elaborated herein.

[0086] It should be noted that the government affairs information traceability system based on big data analysis provided by the embodiments of the present invention and the government affairs information traceability method based on big data analysis provided by the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned government affairs information traceability method based on big data analysis and has the same or similar beneficial effects. The repeated parts will not be elaborated.

[0087] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A government affairs information tracing method based on big data analysis, characterized in that, The government affair information traceability method based on big data analysis includes: Obtaining a first knowledge graph of real government affair information and a second knowledge graph of the government affair information to be traced; Determining the possibility of a tampering relationship between the government affair information to be traced and the real government affair information according to the consistency between nodes and the consistency between edges in the second knowledge graph and the first knowledge graph; Matching the government affair information to be traced with the real government affair information to divide the real part and the tampered part in the government affair information to be traced; Marking the tampered part in the second knowledge graph, and taking all nodes and edges associated with the tampered part as the influence information subgraph of the tampered part; Determining the degree of tampering between the government affair information to be traced and the real government affair information according to the possibility, the consistency between nodes and the consistency between edges in the first knowledge graph and the influence information subgraph. When the degree of tampering is greater than or equal to a first threshold, determining that there is a tampering relationship between the government affair information to be traced and the real government affair information, and taking the real government affair information as the real information of the government affair information to be traced.

2. The method for tracing government affairs information based on big data analysis according to claim 1, wherein After determining that there is a tampering relationship between the government affair information to be traced and the real government affair information and taking the real government affair information as the real information of the government affair information to be traced when the degree of tampering is greater than or equal to the first threshold, the method further includes: Marking the nodes and edges existing in the influence information subgraph in the first knowledge graph.

3. The government affairs information traceability method based on big data analysis according to claim 1, wherein, The determining the possibility of a tampering relationship between the government affair information to be traced and the real government affair information according to the consistency between nodes and the consistency between edges in the second knowledge graph and the first knowledge graph includes: Determining a first quantity of nodes that are consistent in the second knowledge graph and the first knowledge graph and a second quantity of edges whose relationships are consistent in the first knowledge graph and the second knowledge graph among the edges where the consistent nodes are located; Determining the semantic consistency between the first knowledge graph and the second knowledge graph according to a third quantity of nodes in the second knowledge graph, the first quantity, the second quantity, and a fourth quantity of edges where the consistent nodes are located; When the semantic consistency does not meet a second threshold, determining that the government affair information to be traced is false government affair information; Determining a third knowledge graph of real government affair information published before the publishing time of the government affair information to be traced, and calculating the time intervals between the publishing times of the real government affair information in the third knowledge graph and the publishing time of the government affair information to be traced; Determining a fifth quantity of edges that are consistent in the first knowledge graph and the second knowledge graph; Determining the remaining nodes and remaining edges in the second knowledge graph except for the nodes and edges that are consistent in the first knowledge graph; Determining a sixth quantity and a seventh quantity of nodes and edges different from the remaining nodes and remaining edges in the first knowledge graph; Determine the tampering connection situation between the government affairs information to be traced and the true government affairs information according to the semantic consistency, the time interval, the second quantity, the fifth quantity, the sixth quantity, the seventh quantity, the eighth quantity of the remaining nodes, and the ninth quantity of the remaining edges; Perform normalization processing on the tampering connection situation to obtain the possibility of the existence of a tampering relationship between the government affairs information to be traced and the true government affairs information.

4. The government affairs information traceability method based on big data analysis according to claim 3, wherein, The determination of the semantic consistency between the first knowledge graph and the second knowledge graph according to the third quantity of the nodes in the second knowledge graph, the first quantity, the second quantity, and the fourth quantity of the edges where the consistent nodes are located includes: Calculate a first ratio between the third quantity and the first quantity, and a second ratio between the second quantity and the fourth quantity; Determine that the first product between the first ratio and the second ratio is the semantic consistency.

5. The government affairs information traceability method based on big data analysis according to claim 3, wherein The determination of the tampering connection situation between the government affairs information to be traced and the true government affairs information according to the semantic consistency, the time interval, the second quantity, the fifth quantity, the sixth quantity, the seventh quantity, the eighth quantity of the remaining nodes, and the ninth quantity of the remaining edges includes: Calculate a first difference between the fifth quantity and the second quantity, and calculate a third ratio between the first difference and the fifth quantity, and use the third ratio as the entity change situation between the government affairs information to be traced and the true government affairs information; Calculate a second product between the third ratio and the semantic consistency, and calculate a fourth ratio between the second product and the time interval; Calculate a first sum value between the sixth quantity and the seventh quantity, and a second sum value between the eighth quantity and the ninth quantity, and calculate a fifth ratio between the first sum value and the second sum value; Determine that the third product between the fourth ratio and the fifth ratio is the tampering connection situation.

6. The government affairs information traceability method based on big data analysis according to any one of claims 1-5, characterized in that, The determination of the degree of tampering between the government affairs information to be traced and the true government affairs information according to the possibility, the consistency between the nodes in the first knowledge graph and the influence information subgraph, and the consistency between the edges includes: Determine the first total quantity of the nodes and edges in the first knowledge graph that exist in the influence information subgraph, and determine the second total quantity of the nodes and edges in the influence information subgraph where the first total quantity of nodes and edges exist. The second total quantity represents the total number of nodes and edges retrieved in the first knowledge graph that exist in the influence information subgraph; Determine the degree to which the tampered part is disrupted during the tampering process according to the first distance between any two nodes or edges in the second total quantity in the first knowledge graph and the second distance in the influence information subgraph; Determine the degree of tampering that exists between the government affairs information to be traced and the true government affairs information according to the possibility, the first total quantity, the second total quantity, and the degree of disruption.

7. The government affairs information traceability method based on big data analysis according to claim 6, characterized in that, Determining the degree to which the tampered part is disrupted during the tampering process based on the first distance between any two nodes or edges in the second total quantity in the first knowledge graph and the second distance in the influence information sub-graph includes: Calculating the absolute value of the second difference between each of the first distances and the corresponding second distance; Superposing the absolute values of the second differences to obtain the degree to which the tampered part is disrupted during the tampering process.

8. The method for tracing government affairs information based on big data analysis according to claim 6, wherein Determining the degree of tampering existing between the to-be-traced government affairs information and the real government affairs information based on the possibility, the first total quantity, the second total quantity, and the disrupted degree includes: Calculating the sixth ratio between the second total quantity and the first total quantity; Determining that the fourth product among the possibility, the sixth ratio, and the disrupted degree is the degree of tampering existing between the to-be-traced government affairs information and the real government affairs information.

9. The government affairs information traceability method based on big data analysis according to claim 1, wherein, Obtaining the first knowledge graph of the real government affairs information and the second knowledge graph of the to-be-traced government affairs information includes: Identifying the content of the real government affairs information and the to-be-traced government affairs information based on a rule dictionary to determine the entities and relationships in the real government affairs information and the to-be-traced government affairs information; Taking the entities as nodes, the relationships as edges, and recording the attribute data of the nodes or edges in the nodes or edges to construct the first knowledge graph and the second knowledge graph.

10. A government affairs information traceability system based on big data analysis, characterized in that, Including: A processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; The processor is used to execute the program stored on the memory to implement the steps of the government affairs information tracing method based on big data analysis as described in any one of claims 1-9.

Images