A method, device, equipment and medium for identifying illegal organizations

Abstract

The present application discloses a method, device, equipment and medium for identifying illegal organizations. In the embodiments of the present application, when determining whether any two target illegal numbers belong to the same illegal organization, not only the location information of the target base station used when the two target illegal numbers communicate is referenced, but also the type allocation code corresponding to the communication device used by the target illegal numbers is referenced, which effectively improves the accuracy of determining whether each illegal number belongs to the same illegal organization, and is more conducive to maintaining people's property safety.

Description

Technical Field

[0001] The present application relates to the field of security identification technology, and in particular to a method, device, equipment and medium for identifying illegal organizations. Background Art

[0002] At present, it is becoming more and more common for violators to commit violations based on the Internet or telephone. There is even a trend of team-based violations. Specifically, team-based violations are usually initiated by organized, disciplined, large-scale professional violation organizations composed of multiple violators, and such team-based violations have seriously endangered the property safety of the people and endangered people's normal production and living order.

[0003] In the prior art, each illegal number is often classified into a corresponding illegal organization based on the indicator of base station identification. Specifically, all illegal numbers with the same identification information are classified into one illegal organization based on whether the identification information of the base stations used by each illegal person to communicate when committing illegal acts is consistent. However, in fact, in order to evade risks, some illegal organizations often disperse multiple illegal persons in different places, so that when each illegal person uses the illegal number to commit illegal acts, they can communicate based on base stations with different identification information. Therefore, identifying illegal organizations based on the indicator of the identification information of the base station will cause multiple illegal numbers that clearly belong to one illegal organization to belong to multiple different illegal organizations, thereby affecting the accuracy of determining whether each illegal number belongs to the same illegal organization, which is not conducive to maintaining people's property safety. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for identifying illegal organizations, so as to solve the problem in the prior art that the accuracy of determining whether various illegal numbers belong to the same illegal organization is low, which is not conducive to maintaining people's property safety.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying an illegal organization, the method comprising:

[0006] For each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within the preset time length; and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector;

[0007] For any two target illegal numbers, the target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0008] Furthermore, the method further comprises:

[0009] Based on a preset priority traversal algorithm and the undirected graph, determining at least one connected component;

[0010] For each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0011] Furthermore, if the target similarity is not greater than a preset similarity threshold, the method further includes:

[0012] In the undirected graph, the nodes corresponding to the two target violation numbers are not connected.

[0013] Furthermore, before determining the target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector, the method further includes:

[0014] Determine a communication time feature vector corresponding to the target illegal number according to the communication record corresponding to the target illegal number within the preset time length;

[0015] The determining, according to the communication device feature vector and the communication location feature vector, a target feature vector corresponding to the target illegal number comprises:

[0016] A target feature vector corresponding to the target illegal number is determined according to the communication device feature vector, the communication location feature vector and the time feature vector.

[0017] Further, the determining the communication device feature vector corresponding to the target illegal number according to the type allocation code corresponding to the communication device used by the target illegal number within the set time length includes:

[0018] Sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length;

[0019] The communication device feature vector corresponding to the target illegal number is determined according to the type allocation codes corresponding to a first number of communication devices that are preset in sequence.

[0020] Further, the determining, based on the location information of the target base station used by the target illegal number when communicating within the preset time length, a communication location feature vector corresponding to the target illegal number includes:

[0021] According to the number of times the target illegal number uses each target base station when communicating within a preset time length, the target base stations are sorted;

[0022] The communication location feature vector corresponding to the target illegal number is determined according to the location information corresponding to a preset second number of target base stations in the preceding order.

[0023] Further, the determining, according to the communication record corresponding to the illegal number within the preset time length, the communication time feature vector corresponding to the illegal number includes:

[0024] According to the number of communications of the target illegal number in each sub-time period within a preset time length, the sub-time periods are sorted;

[0025] The communication time feature vector corresponding to the target illegal number is determined according to a third number of sub-time periods that are preset in sequence.

[0026] In a second aspect, an embodiment of the present application further provides a device for identifying illegal organizations, the device comprising:

[0027] A determination module is used to establish, for each target illegal number, a node corresponding to the target illegal number in an undirected graph, determine a communication device feature vector corresponding to the target illegal number according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; determine a communication location feature vector corresponding to the target illegal number according to location information of a target base station used by the target illegal number when communicating within the preset time length; and determine a target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector;

[0028] The processing module is used to determine the target similarity between any two target illegal numbers according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0029] Furthermore, the processing module is also used to determine at least one connected component based on a preset priority traversal algorithm and the undirected graph; for each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0030] Furthermore, the processing module is further configured to not connect the nodes corresponding to the two target illegal numbers in the undirected graph if the target similarity is not greater than a preset similarity threshold.

[0031] Furthermore, the determination module is further configured to determine a communication time feature vector corresponding to the target illegal number according to the communication records corresponding to the target illegal number within the preset time length;

[0032] The determination module is specifically configured to determine a target feature vector corresponding to the target illegal number according to the communication device feature vector, the communication location feature vector and the time feature vector.

[0033] Furthermore, the determination module is specifically used to sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length; and determine the communication device feature vector corresponding to the target illegal number according to the type allocation codes corresponding to a preset first number of communication devices in the preceding order.

[0034] Furthermore, the determination module is specifically used to sort the target base stations according to the number of times the target illegal number uses each target base station when communicating within a preset time length; and determine the communication position feature vector corresponding to the target illegal number according to the position information corresponding to a preset second number of target base stations in the previous order.

[0035] Furthermore, the determination module is specifically used to sort the sub-time periods according to the number of communications of the target illegal number in each sub-time period within a preset time length; and determine the communication time feature vector corresponding to the target illegal number according to a preset third number of sub-time periods in the preceding order.

[0036] In a third aspect, an embodiment of the present application further provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of any of the above-mentioned methods for identifying illegal organizations when executing a computer program stored in the memory.

[0037] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for identifying illegal organizations.

[0038] In an embodiment of the present application, for each target illegal number, nodes corresponding to the two target illegal numbers are established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length, and a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within a preset time length, and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector, and for any two target illegal numbers, a target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers, and if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization. Because in the embodiment of the present application, when determining whether any two target illegal numbers belong to the same illegal organization, not only the location information of the target base station used by the two target illegal numbers when communicating is referenced, but also the type allocation code corresponding to the communication device used by the target illegal numbers is referenced, which effectively improves the accuracy of determining whether each illegal number belongs to the same illegal organization, and is more conducive to maintaining people's property safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0040] Figure 1 A schematic diagram of a process for identifying illegal organizations provided in some embodiments of the present application;

[0041] Figure 2 A detailed process diagram of identifying an illegal organization provided in some embodiments of the present application;

[0042] Figure 3 A schematic diagram showing target similarity between target illegal numbers provided in some embodiments of the present application;

[0043] Figure 4 A schematic diagram showing an undirected graph constructed according to the similarities of various targets provided in some embodiments of the present application;

[0044] Figure 5 A display schematic diagram of determining a target illegal organization corresponding to each target illegal number provided in some embodiments of the present application;

[0045] Figure 6 A schematic diagram of the structure of an illegal organization identification device provided in some embodiments of the present application;

[0046] Figure 7 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0048] In an embodiment of the present application, for each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length, and a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within a preset time length, and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector, and for any two target illegal numbers, a target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers, and if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0049] In order to improve the accuracy of determining whether each illegal number belongs to the same illegal organization, the embodiments of the present application provide a method, device, equipment and medium for identifying an illegal organization.

[0050] Embodiment 1:

[0051] Figure 1 A schematic diagram of a process for identifying an illegal organization provided in some embodiments of the present application, the process includes the following steps:

[0052] S101: For each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within the preset time length; and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector.

[0053] The illegal organization identification method provided in the embodiment of the present application is applied to an electronic device, which may be a smart terminal, a PC, a server or other device.

[0054] The electronic device may obtain multiple target illegal numbers in advance, and determine which target illegal numbers belong to the same illegal organization based on the multiple target illegal numbers. The target illegal numbers may be numbers with illegal marks filtered out from all numbers recorded in the operator's voice call bill.

[0055] Specifically, in order to determine which numbers are marked as illegal numbers (target illegal numbers), in one possible implementation, for each number among all numbers, the voice call or traffic consumption information corresponding to the number can be input into a pre-trained voice traffic anomaly model to determine whether the voice calls or traffic consumption of the number occur in different geographical locations within the same time period. If so, the number is determined to be an illegal number.

[0056] Specifically, the process of identifying which numbers are marked as illegal numbers is a prior art and will not be described in detail here.

[0057] In order to facilitate the subsequent determination of whether each illegal number belongs to the same illegal organization, in an embodiment of the present application, an undirected graph that can characterize the relationship between each target illegal number can be pre-constructed, and based on the constructed undirected graph, it is determined whether each target illegal number belongs to the same illegal organization.

[0058] In the process of constructing an undirected graph, a node corresponding to each target illegal number can be first established in the undirected graph, wherein one target illegal number corresponds to one node. In order to facilitate determining whether it is necessary to connect the nodes corresponding to each target illegal number in the undirected graph to characterize the association relationship between each target illegal number, so as to subsequently determine whether each target illegal number belongs to the same illegal organization, in an embodiment of the present application, a feature vector corresponding to each target illegal number can be first determined, wherein, since the communication devices generally used by the illegal personnel belonging to the same illegal organization are of the same brand and model, and since the geographical locations of the illegal personnel belonging to the same illegal organization are generally fixed and very close, the locations of the base stations used by the illegal numbers corresponding to each illegal personnel for communication are generally also very close, so the feature vector corresponding to the target illegal number can include: a communication device feature vector corresponding to the target illegal number and a communication location feature vector corresponding to the target illegal number.

[0059] Specifically, in order to determine the communication device feature vector corresponding to each target illegal number, for each target illegal number, the communication device feature vector corresponding to the target illegal number can be determined according to the type allocation code (TAC) corresponding to the communication device used by the target illegal number within a set time length.

[0060] In a possible implementation, for each target illegal number, the set time length may be first divided into a preset number of sub-time periods, and for each sub-time period, the type allocation code corresponding to the communication device most frequently used by the target illegal number in the sub-time period is determined, and the type allocation code corresponding to the communication device frequently used by the target illegal number in each sub-time period is determined as each component in the communication device feature vector corresponding to the target illegal number, wherein the number of components included in the communication device feature vector corresponding to the target illegal number is the set number.

[0061] In order to determine the communication location feature vector corresponding to each target illegal number, the communication location feature vector corresponding to each target illegal number can be determined according to the location information of the target base station used by the target illegal number when communicating within a preset time length.

[0062] In a possible implementation, for each target illegal number, the set time length may be first divided into a preset number of sub-time periods, and for each sub-time period, the location information of the target base station most frequently used by the target illegal number in the sub-time period is determined, and the location information of the target base station most frequently used by the target illegal number in each sub-time period is determined as each component in the target communication location feature vector corresponding to the target illegal number. The number of components included in the communication location feature vector corresponding to the target illegal number is the set number.

[0063] For each target illegal number, after determining the communication device feature vector and the communication location feature vector corresponding to the target illegal number, in an embodiment of the present application, the target feature vector corresponding to the target illegal number can be determined based on the communication device feature vector and the communication location feature vector. Specifically, the communication device feature vector and the communication location feature vector can be spliced ​​according to the preset first vector splicing rule to obtain the target feature vector corresponding to the target illegal number. The number of components contained in the target feature vector is equal to the sum of the number of components contained in the communication device feature vector and the number of components contained in the communication location feature vector. The lengths of the target feature vectors corresponding to each target illegal number are the same.

[0064] Among them, the preset first vector splicing rule can be that after the first set position of the communication device feature vector, each component in the communication position feature vector is sequentially spliced ​​behind the first set position of the communication device feature vector, and the first set position can be the position where the last component of the communication device feature vector is located, etc. Specifically, how to splice the communication device feature vector and the communication position feature vector is not limited here.

[0065] For example, if the communication device feature vector corresponding to the target illegal number A is (a1, a2, a3, a4), and the corresponding communication location feature vector is (b1, b2, b3, b4), then the target feature vector can be (a1, a2, a3, a4, b1, b2, b3, b4).

[0066] S102: For any two target illegal numbers, determine the target similarity between the two target illegal numbers according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, connect the nodes corresponding to the two target illegal numbers in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0067] In order to determine whether the target illegal numbers in the undirected graph are connected according to the target feature vectors corresponding to the target illegal numbers, so as to subsequently determine whether the target illegal numbers belong to the same illegal organization, in the embodiment of the present application, after determining the target feature vector corresponding to each target illegal number, the target similarity between the two target illegal numbers can be determined for every two target illegal numbers according to the target feature vectors corresponding to the two target illegal numbers, wherein the higher the target similarity, the higher the correlation between the two target illegal numbers, and the greater the possibility that the two target illegal numbers belong to the same illegal organization.

[0068] Specifically, the target similarity corresponding to the two illegal numbers can be determined by determining the Euclidean distance between the target feature vectors corresponding to the two target illegal numbers, wherein the smaller the Euclidean distance, the greater the corresponding target similarity. Specifically, the reciprocal of the Euclidean distance between the target feature vectors corresponding to the two target illegal numbers can be determined as the target similarity corresponding to the two illegal numbers.

[0069] In order to represent the relationship between each target illegal number in an undirected graph, in an embodiment of the present application, for any two target illegal numbers, it can be determined whether the target similarity between the two target illegal numbers is greater than a preset similarity threshold, and whether to connect the nodes corresponding to the two target illegal numbers. The preset similarity threshold can be 90%, 80%, etc. Specifically, the preset similarity threshold can be set according to requirements.

[0070] If the target similarity is greater than the preset similarity threshold, it means that the two target illegal numbers are highly correlated, and it is very likely that the two target illegal numbers belong to the same illegal organization. Therefore, the nodes corresponding to the two target illegal numbers can be connected in the undirected graph, and it can be determined that the two target illegal numbers belong to the same illegal organization.

[0071] S103: If the target similarity is not greater than a preset similarity threshold, then in the undirected graph, the nodes corresponding to the two target illegal numbers are not connected.

[0072] In the embodiment of the present application, for any two target illegal numbers, if it is determined that the target similarity between the two target illegal numbers is not greater than a preset similarity threshold, it means that the correlation between the two target illegal numbers is not high, and the possibility that the two target illegal numbers belong to the same illegal organization is small. Therefore, in order to represent the relationship between the two target illegal numbers in an undirected graph, the nodes corresponding to the two target illegal numbers may not be connected.

[0073] Because in the embodiment of the present application, when determining whether any two target illegal numbers belong to the same illegal organization, not only the location information of the target base station used by the two target illegal numbers when communicating is referenced, but also the type allocation code corresponding to the communication device used by the target illegal numbers is referenced, which effectively improves the accuracy of determining whether each illegal number belongs to the same illegal organization, and is more conducive to maintaining people's property safety.

[0074] Embodiment 2:

[0075] In order to further determine to which target violation group each target violation number belongs, based on the above embodiment, in the embodiment of the present application, the method further includes:

[0076] Based on a preset priority traversal algorithm and the undirected graph, determining at least one connected component;

[0077] For each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0078] In order to determine how many illegal organizations can be identified based on the undirected graph and which target illegal numbers are assigned to which illegal organization, in an embodiment of the present application, at least one connected component can be determined based on a preset priority traversal algorithm and the undirected graph.

[0079] Among them, the preset priority traversal algorithm can be Robert Tarjan algorithm, or breadth-first traversal algorithm, or depth-first traversal algorithm, etc., and the process of determining at least one connected component based on the preset priority traversal algorithm and undirected graph is a prior art and will not be elaborated here.

[0080] In order to determine which target illegal numbers are assigned to which illegal organization, after the undirected graph is constructed, for each connected component, the target illegal numbers corresponding to the target nodes of all target illegal numbers contained in the connected component can be attributed to the same illegal organization. For easy distinction, a corresponding target illegal organization can be set for each connected component, and for each connected component, the target illegal numbers corresponding to the target nodes of all target illegal numbers contained in the connected component can be assigned to the corresponding target illegal organization.

[0081] For example, if three connected components are determined, namely connected component 1, connected component 2 and connected component 3, and three target violation organizations are set in advance for the three connected components, connected component 1 corresponds to target violation organization 1, connected component 2 corresponds to target violation organization 2, and connected component 3 corresponds to target violation organization 3, then the target violation numbers corresponding to all target nodes contained in the connected component 1 are divided into the corresponding target violation organization 1, the target violation numbers corresponding to all target nodes contained in the connected component 2 are divided into the corresponding target violation organization 2, and the target violation numbers corresponding to all target nodes contained in the connected component 3 are divided into the corresponding target violation organization 3.

[0082] Figure 2 A detailed process diagram of identifying illegal organizations provided in some embodiments of the present application is now directed to Figure 2 Provide explanation.

[0083] First, illegal number identification is performed to determine each target illegal number, and nodes corresponding to each target illegal number are established in an undirected graph. Then, a target feature vector corresponding to each target illegal number is determined. Then, for every two target illegal numbers, the target similarity corresponding to the two target illegal numbers is determined according to the target feature vectors corresponding to the two target illegal numbers. Based on the target similarity and a preset similarity threshold, it is determined whether to connect the nodes corresponding to the two target illegal numbers in the undirected graph. If the target similarity is greater than the preset similarity threshold, the two target illegal numbers are connected. Otherwise, the two target illegal numbers are not connected.

[0084] Finally, based on the constructed undirected graph and the preset priority traversal algorithm, at least one connected component is determined, and for each connected component, the target nodes of all target illegal numbers contained in the connected component are determined, and the target illegal numbers corresponding to the target nodes corresponding to the connected component are divided into corresponding target illegal organizations.

[0085] Figure 3 A schematic diagram showing target similarity between target illegal numbers provided in some embodiments of the present application, Figure 4 A schematic diagram showing an undirected graph constructed according to the similarities of various targets provided in some embodiments of the present application, Figure 5 A display schematic diagram of determining a target illegal organization corresponding to each target illegal number provided in some embodiments of the present application is now directed to Figure 3 , Figure 4 as well as Figure 5 Provide explanation.

[0086] Take five target illegal numbers as an example, namely target illegal number 1, target illegal number 2, target illegal number 3, target illegal number 4 and target illegal number 5. Among the five target illegal numbers, the target similarity between any two target illegal numbers is shown in Figure 3 For example, the target similarity between target violation number 1 and target violation number 2 is 0.8, the target similarity between target violation number 1 and target violation number 3 is 0.5, and so on.

[0087] If the preset similarity threshold is 0.6, the target similarities greater than the preset similarity threshold include: target violation number 1 and target violation number 2 target similarity, target violation number 1 and target violation number 4 target similarity, and target violation number 3 and target violation number 5 target similarity. Then, the node corresponding to target violation number 1 is connected to the node corresponding to target violation number 2, the node corresponding to target violation number 1 is connected to the node corresponding to target violation number 4, and the node corresponding to target violation number 3 is connected to the node corresponding to target violation number 5. For specific connection conditions, see Figure 4 .

[0088] Based on the preset priority traversal algorithm and Figure 4 The undirected graph constructed in , two connected components are determined. The first connected component contains nodes: the node corresponding to the target violation number 1, the node corresponding to the target violation number 2 and the node corresponding to the target violation number 4. Then the target violation number 1, the target violation number 2 and the target violation number 4 are divided into the target violation organization 1. The second connected component contains nodes: the node corresponding to the target violation number 3 and the node corresponding to the target violation number 5. Then the target violation number 3 and the target violation number 5 are divided into the target violation organization 2. See Figure 5 .

[0089] Embodiment 3:

[0090] In order to improve the accuracy of determining whether each target illegal number belongs to the same illegal organization, based on the above embodiments, in the embodiment of the present application, before determining the target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector, the method further includes:

[0091] Determine a communication time feature vector corresponding to the target illegal number according to the communication record corresponding to the target illegal number within the preset time length;

[0092] The determining, according to the communication device feature vector and the communication location feature vector, a target feature vector corresponding to the target illegal number comprises:

[0093] A target feature vector corresponding to the target illegal number is determined according to the communication device feature vector, the communication location feature vector and the time feature vector.

[0094] In the embodiment of the present application, since there is a certain regularity in the time when the violating members of the same violating organization commit violations, that is, the violating members of the same violating organization may concentrate on committing violations in a certain time period. Therefore, in order to improve the accuracy of determining whether each target violating number belongs to the same violating organization, before determining the target feature vector corresponding to the target violating number for each target violating number based on the communication device feature vector and the communication position feature vector corresponding to the target violating number, the communication time feature corresponding to the target violating number can also be considered. Specifically, the communication time corresponding to the target violating number within the preset time length can be determined based on the communication record corresponding to the target violating number within the preset time length, and then the communication time feature vector corresponding to the target violating number can be determined.

[0095] In a possible implementation, the set time length can be first divided into a preset number of sub-time periods, and for each sub-time period, the number of times the target illegal number communicates in the sub-time period is determined, and the number of times the target illegal number communicates in each sub-time period is determined as each component in the communication time feature vector.

[0096] After determining the communication time feature vector, determine the target feature vector corresponding to the target illegal number according to the communication device feature vector, the communication location feature vector and the communication time feature vector. Specifically, the communication device feature vector and the communication location feature vector may be spliced ​​according to a preset first vector splicing rule to obtain a spliced ​​vector, and then the spliced ​​vector and the communication time feature vector may be spliced ​​according to a preset second vector splicing rule to obtain a target feature vector. The number of components contained in the target feature vector is equal to the sum of the number of components contained in the communication device feature vector, the number of components contained in the communication location feature vector and the number of components contained in the communication time feature vector.

[0097] Among them, the preset first vector splicing rule can be that after the first set position of the communication device feature vector, each component in the communication position feature vector is sequentially spliced ​​behind the first set position of the communication device feature vector, and the first set position can be the position where the last component of the communication device feature vector is located, etc. Among them, the preset second vector splicing rule can be that after the second set position of the splicing vector, each component in the communication time feature vector is sequentially spliced ​​behind the second set position of the splicing vector, and the second set position can be the position where the last component of the splicing vector is located, etc. Specifically, how to splice each feature vector is not limited here.

[0098] For example, if the communication device feature vector corresponding to the target illegal number A is (a1, a2, a3, a4), the corresponding communication position feature vector is (b1, b2, b3, b4), and the corresponding communication time feature vector is (c1, c2, c3, c4), then the target feature vector can be (a1, a2, a3, a4, b1, b2, b3, b4, c1, c2, c3, c4).

[0099] Embodiment 4:

[0100] In order to accurately determine the communication device feature vector corresponding to the target illegal number, based on the above embodiments, in the embodiment of the present application, the communication device feature vector corresponding to the target illegal number is determined according to the type allocation code corresponding to the communication device used by the target illegal number within the set time length. The feature vector includes:

[0101] Sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length;

[0102] The communication device feature vector corresponding to the target illegal number is determined according to the type allocation codes corresponding to a first number of communication devices that are preset in sequence.

[0103] In order to determine the communication device feature vector corresponding to each target illegal number, in a possible implementation, for each target illegal number, the set time length can be first divided into a preset number of sub-time periods, and for each sub-time period, the type allocation code corresponding to the communication device that is more frequently used by the target illegal number in the sub-time period is determined, and the type allocation code corresponding to the communication device that is more frequently used by the target illegal number in each sub-time period is determined as each component in the target communication device feature vector corresponding to the target illegal number.

[0104] In another possible implementation, for each target illegal number, each communication device may be sorted according to the number of times the target illegal number uses each communication device within a preset time length, and then the type allocation codes corresponding to a preset first number of communication devices in the front order are determined as the components in the communication device feature vector corresponding to the target illegal number.

[0105] It should be noted that, since different target illegal numbers may use different numbers of communication devices within a preset time length, and there may be a situation where the number of communication devices used by one or some target illegal numbers within the preset time length is less than the preset first number, in order to ensure that the lengths of communication device feature vectors corresponding to various target illegal numbers are consistent, for any target illegal number whose number of communication devices used within the preset time length is less than the preset first number, the communication device feature vector corresponding to the target illegal number can be determined based on the type allocation codes corresponding to all communication devices used by the target illegal number within the preset time length and the preset target type allocation code. That is to say, at this time, some components of the communication device feature vector corresponding to the target illegal number are the type allocation codes corresponding to all communication devices used by the target illegal number within the preset time length, and some components are the preset target type allocation code.

[0106] In order to accurately determine the communication location feature vector corresponding to each target illegal number, based on the above embodiments, in the embodiment of the present application, the communication location feature vector corresponding to the target illegal number is determined according to the location information of the target base station used by the target illegal number when communicating within the preset time length, including:

[0107] According to the number of times the target illegal number uses each target base station when communicating within a preset time length, the target base stations are sorted;

[0108] The communication location feature vector corresponding to the target illegal number is determined according to the location information corresponding to a preset second number of target base stations in the preceding order.

[0109] In order to determine the communication location feature vector corresponding to each target illegal number, in a possible implementation, for each target illegal number, the set time length can be first divided into a preset number of sub-time periods, and for each sub-time period, the location information of the target base station that the target illegal number uses more frequently in the sub-time period is determined, and the location information of the target base station that the target illegal number uses more frequently in each sub-time period is determined as each component in the target communication device feature vector.

[0110] In another possible implementation, for each target illegal number, each target base station can also be sorted according to the number of times the target illegal number uses each target base station when communicating within a preset time length, and the location information corresponding to a preset second number of target base stations in the front sequence can be determined as each component in the communication location feature vector corresponding to the target illegal number.

[0111] It should be noted that, since different target illegal numbers may use different numbers of target base stations for communication within a preset time length, and there may be one or some target illegal numbers that use less than the preset second number for communication within a preset time length, in order to ensure that the lengths of communication position feature vectors corresponding to each target illegal number are consistent, for any target illegal number that uses less than the preset first number of target base stations for communication within a preset time length, the communication position feature vector corresponding to the target illegal number can be determined based on the location information of all target base stations used by the target illegal number for communication within the preset time length and the preset target base station location information. That is to say, at this time, some components of the communication position feature vector corresponding to the target illegal number are the location information of all target base stations used by the target illegal number for communication within the preset time length, and some components are the preset target base station location information.

[0112] In order to accurately determine the communication time feature vector corresponding to the target illegal number, based on the above embodiments, in the embodiment of the present application, the communication time feature vector corresponding to the illegal number is determined according to the communication record corresponding to the illegal number within the preset time length, including:

[0113] According to the number of communications of the target illegal number in each sub-time period within a preset time length, the sub-time periods are sorted;

[0114] The communication time feature vector corresponding to the target illegal number is determined according to a third number of sub-time periods that are preset in sequence.

[0115] In order to determine the communication time feature vector corresponding to each target illegal number, in a possible implementation manner, for each target illegal number, the set time length can be first divided into a preset number of sub-time periods, and for each sub-time period, the number of times the target illegal number communicates within the sub-time period is determined, and the number of times the target illegal number communicates within each sub-time period is determined as each component in the communication time feature vector.

[0116] In another possible implementation, for each target illegal number, the sub-time periods may be sorted according to the number of communications of the target illegal number in each sub-time period within a preset time length, and a preset third number of sub-time periods in front of the sequence may be determined as the components in the communication time feature vector corresponding to the target illegal number.

[0117] Embodiment 5:

[0118] Figure 6 A schematic diagram of a device for identifying illegal organizations provided in some embodiments of the present application, the device comprising:

[0119] The determination module 601 is used to establish, for each target illegal number, a node corresponding to the target illegal number in an undirected graph, determine a communication device feature vector corresponding to the target illegal number according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; determine a communication location feature vector corresponding to the target illegal number according to location information of a target base station used by the target illegal number when communicating within the preset time length; and determine a target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector;

[0120] Processing module 602, for any two target illegal numbers, determines the target similarity between the two target illegal numbers according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0121] In a possible implementation, the processing module 602 is further used to determine at least one connected component based on a preset priority traversal algorithm and the undirected graph; for each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0122] In a possible implementation, the processing module 602 is further configured to not connect the nodes corresponding to the two target illegal numbers in the undirected graph if the target similarity is not greater than a preset similarity threshold.

[0123] In a possible implementation manner, the determination module 601 is further configured to determine a communication time feature vector corresponding to the target illegal number according to the communication records corresponding to the target illegal number within the preset time length;

[0124] The determination module 601 is specifically configured to determine a target feature vector corresponding to the target illegal number according to the communication device feature vector, the communication location feature vector and the time feature vector.

[0125] In a possible implementation, the determination module 601 is specifically used to sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length; and determine the communication device feature vector corresponding to the target illegal number according to the type allocation codes corresponding to a preset first number of communication devices in the preceding order.

[0126] In a possible implementation, the determination module 601 is specifically used to sort the target base stations according to the number of times the target illegal number uses each target base station when communicating within a preset time length; and determine the communication position feature vector corresponding to the target illegal number according to the position information corresponding to a preset second number of target base stations in the preceding order.

[0127] In a possible implementation, the determination module 601 is specifically used to sort the sub-time periods according to the number of communications of the target illegal number in each sub-time period within a preset time length; and determine the communication time feature vector corresponding to the target illegal number according to a preset third number of sub-time periods that come first in order.

[0128] Embodiment 6:

[0129] Based on the above embodiments, some embodiments of the present application further provide an electronic device, such as Figure 7 As shown, it includes: a processor 701 , a communication interface 702 , a memory 703 and a communication bus 704 , wherein the processor 701 , the communication interface 702 , and the memory 703 communicate with each other via the communication bus 704 .

[0130] The memory 703 stores a computer program. When the program is executed by the processor 701, the processor 701 performs the following steps:

[0131] For each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within the preset time length; and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector;

[0132] For any two target illegal numbers, the target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0133] Furthermore, the processor 701 is also used to determine at least one connected component based on a preset priority traversal algorithm and the undirected graph; for each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0134] Furthermore, the processor 701 is further configured to, if the target similarity is not greater than a preset similarity threshold, not connect the nodes corresponding to the two target illegal numbers in the undirected graph.

[0135] Further, the processor 701 is further configured to determine a communication time feature vector corresponding to the target illegal number according to the communication record corresponding to the target illegal number within the preset time length;

[0136] The processor 701 is specifically configured to determine a target feature vector corresponding to the target illegal number according to the communication device feature vector, the communication location feature vector, and the time feature vector.

[0137] Further, the processor 701 is specifically configured to sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length; and determine the communication device feature vector corresponding to the target illegal number according to the type allocation codes corresponding to a preset first number of communication devices in the preceding order.

[0138] Further, the processor 701 is specifically configured to sort the target base stations according to the number of times the target illegal number uses the target base stations when communicating within a preset time length;

[0139] The communication location feature vector corresponding to the target illegal number is determined according to the location information corresponding to a preset second number of target base stations in the preceding order.

[0140] Furthermore, the processor 701 is specifically configured to sort the sub-time periods according to the number of communications of the target illegal number in each sub-time period within a preset time length; and determine the communication time feature vector corresponding to the target illegal number according to a preset third number of sub-time periods in the preceding order.

[0141] The communication bus mentioned in the above server can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0142] The communication interface 702 is used for communication between the electronic device and other devices.

[0143] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0144] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0145] Embodiment 7:

[0146] On the basis of the above embodiments, some embodiments of the present application further provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program executable by an electronic device, and when the program is run on the electronic device, the electronic device implements the following steps when executing:

[0147] For each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within the preset time length; and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector;

[0148] For any two target illegal numbers, the target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

[0149] Furthermore, the method further comprises:

[0150] Based on a preset priority traversal algorithm and the undirected graph, determining at least one connected component;

[0151] For each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

[0152] Furthermore, if the target similarity is not greater than a preset similarity threshold, the method further includes:

[0153] In the undirected graph, the nodes corresponding to the two target violation numbers are not connected.

[0154] Furthermore, before determining the target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector, the method further includes:

[0155] Determine a communication time feature vector corresponding to the target illegal number according to the communication record corresponding to the target illegal number within the preset time length;

[0156] The determining, according to the communication device feature vector and the communication location feature vector, a target feature vector corresponding to the target illegal number comprises:

[0157] A target feature vector corresponding to the target illegal number is determined according to the communication device feature vector, the communication location feature vector and the time feature vector.

[0158] Further, the determining the communication device feature vector corresponding to the target illegal number according to the type allocation code corresponding to the communication device used by the target illegal number within the set time length includes:

[0159] Sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length;

[0160] The communication device feature vector corresponding to the target illegal number is determined according to the type allocation codes corresponding to a first number of communication devices that are preset in sequence.

[0161] Further, the determining, based on the location information of the target base station used by the target illegal number when communicating within the preset time length, a communication location feature vector corresponding to the target illegal number includes:

[0162] According to the number of times the target illegal number uses each target base station when communicating within a preset time length, the target base stations are sorted;

[0163] The communication location feature vector corresponding to the target illegal number is determined according to the location information corresponding to a preset second number of target base stations in the preceding order.

[0164] Further, the determining, according to the communication record corresponding to the illegal number within the preset time length, the communication time feature vector corresponding to the illegal number includes:

[0165] According to the number of communications of the target illegal number in each sub-time period within a preset time length, the sub-time periods are sorted;

[0166] The communication time feature vector corresponding to the target illegal number is determined according to a third number of sub-time periods that are preset in sequence.

[0167] Because in the embodiment of the present application, when determining whether any two target illegal numbers belong to the same illegal organization, not only the location information of the target base station used by the two target illegal numbers when communicating is referenced, but also the type allocation code corresponding to the communication device used by the target illegal numbers is referenced, which effectively improves the accuracy of determining whether each illegal number belongs to the same illegal organization, and is more conducive to maintaining people's property safety.

[0168] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0169] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0172] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for identifying illegal organizations, characterized in that: The method comprises: For each target illegal number, a node corresponding to the target illegal number is established in an undirected graph, and a communication device feature vector corresponding to the target illegal number is determined according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; a communication location feature vector corresponding to the target illegal number is determined according to location information of a target base station used by the target illegal number when communicating within the preset time length; and a target feature vector corresponding to the target illegal number is determined according to the communication device feature vector and the communication location feature vector; For any two target illegal numbers, the target similarity between the two target illegal numbers is determined according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

2. The method according to claim 1, characterized in that The method further comprises: Based on a preset priority traversal algorithm and the undirected graph, determining at least one connected component; For each connected component, according to the target nodes of all target illegal numbers contained in the connected component, the target illegal numbers corresponding to the target nodes are divided into corresponding target illegal organizations.

3. The method according to claim 1, characterized in that If the target similarity is not greater than a preset similarity threshold, the method further includes: In the undirected graph, the nodes corresponding to the two target violation numbers are not connected.

4. The method according to claim 1, characterized in that: Before determining the target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector, the method further includes: Determine a communication time feature vector corresponding to the target illegal number according to the communication record corresponding to the target illegal number within the preset time length; Determining the target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector includes: A target feature vector corresponding to the target illegal number is determined according to the communication device feature vector, the communication location feature vector and the time feature vector.

5. The method according to claim 1 or 4, characterized in that: The determining, according to the type allocation code corresponding to the communication device used by the target illegal number within the set time length, the communication device feature vector corresponding to the target illegal number comprises: Sort the communication devices according to the number of times the target illegal number uses each communication device within a preset time length; The communication device feature vector corresponding to the target illegal number is determined according to the type allocation codes corresponding to a first number of communication devices that are preset in sequence.

6. The method according to claim 1 or 4, characterized in that: The determining, according to the location information of the target base station used by the target illegal number when communicating within the preset time length, the communication location feature vector corresponding to the target illegal number comprises: According to the number of times the target illegal number uses each target base station when communicating within a preset time length, the target base stations are sorted; The communication location feature vector corresponding to the target illegal number is determined according to the location information corresponding to a preset second number of target base stations in the preceding order.

7. The method according to claim 4, characterized in that The determining, according to the communication record corresponding to the illegal number within the preset time length, the communication time feature vector corresponding to the illegal number comprises: According to the number of communications of the target illegal number in each sub-time period within a preset time length, the sub-time periods are sorted; The communication time feature vector corresponding to the target illegal number is determined according to a third number of sub-time periods that are preset in sequence.

8. A device for identifying illegal organizations, characterized in that: The device comprises: A determination module is used to establish, for each target illegal number, a node corresponding to the target illegal number in an undirected graph, determine a communication device feature vector corresponding to the target illegal number according to a type allocation code corresponding to a communication device used by the target illegal number within a set time length; determine a communication location feature vector corresponding to the target illegal number according to location information of a target base station used by the target illegal number when communicating within the preset time length; and determine a target feature vector corresponding to the target illegal number according to the communication device feature vector and the communication location feature vector; The processing module is used to determine the target similarity between any two target illegal numbers according to the target feature vectors respectively corresponding to the two target illegal numbers; if the target similarity is greater than a preset similarity threshold, the nodes corresponding to the two target illegal numbers are connected in the undirected graph to determine that the two target illegal numbers belong to the same illegal organization.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to implement the steps of the illegal organization identification method described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the illegal organization identification method described in any one of claims 1 to 7.

Images