Smart community policing data processing method and system based on artificial intelligence

Abstract

The present invention relates to the field of data processing, and in particular to a method and system for processing police data in a smart community based on artificial intelligence. The method comprises the following steps: obtaining a number of police data; adjusting the relative positions between the police data; performing multi-layer classification processing using the distance relationship between the police data after the relative position adjustment, and constructing an encrypted binary tree according to the category relationship obtained by the classification; encoding the police data using the encrypted binary tree to obtain encrypted data of the police data; so as to realize encrypted storage of the police data. By encoding and encrypting the similarity relationship between the data after the position adjustment, the similarity relationship between the police data is effectively destroyed, thereby improving the security of the police data.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a smart community policing data processing method and system based on artificial intelligence. Background Art

[0002] Community policing data is the basis for community policing services and needs to be effectively managed. Community policing data carries a lot of sensitive information, such as the file information of each resident. Once the community policing data is read by someone with ulterior motives, it is easy to threaten the property safety of community citizens. Therefore, community policing data needs to be encrypted.

[0003] Residents with close relationships generally have more intersections, and the similarity of the files of residents with close relationships is higher. Therefore, in order to prevent someone from mining the relationship between residents through the similarity of files, the similarity relationship between the file data needs to be destroyed when encrypting the files. Therefore, how to effectively destroy the similarity relationship of police data through encryption processing becomes the research focus of this invention.

[0004] The patent application document with publication number CN111639146A discloses a geospatial information system suitable for police management. The patent application document involves an encryption and decryption module, but the encryption and decryption method used in the encryption and decryption module fails to show better performance when destroying the similarity relationship between police data. Therefore, the method in the patent application document cannot solve the problem in the present invention well. Summary of the invention

[0005] In order to solve the problem of using encryption processing to effectively destroy the similarity relationship of police data, the present invention provides an artificial intelligence-based smart community police data processing method and system.

[0006] In the first aspect, the present invention provides a method for processing smart community policing data based on artificial intelligence, which adopts the following technical solutions:

[0007] The method for processing smart community policing data based on artificial intelligence includes the following steps:

[0008] obtain certain police data;

[0009] Adjust the relative position of a police data and the geometric center of all other police data, so that after the relative position adjustment, the distance between the police data and the geometric center is negatively correlated with the distance before the adjustment, and the relative direction remains unchanged; perform relative position adjustment processing on other police data in turn;

[0010] All police data after relative position adjustment are taken as parent nodes, and based on the distance between the data in the parent nodes, the data in the parent nodes are divided into two categories, and each category is respectively taken as the child node of the parent node; in response to the number of data in the child node being greater than 1, the child node is taken as a new parent node, the data in the new parent node is divided into two categories, and each newly obtained category is taken as the child node of the new parent node; in response to the number of data in the child node of the new parent node being less than 1, the classification is completed, and the parent node is connected with the corresponding child node to obtain an encrypted binary tree;

[0011] The mark value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree is set to 0, and the mark value of the connection path between the parent node and the corresponding right child node is set to 1; the binary number composed of the mark value of the connection path from the root node to the leaf node is used as the encryption data of the police data in the leaf node; so as to realize the encrypted storage of police data.

[0012] The present invention adjusts the position of police data to increase the distance between police data with greater similarity and decrease the distance between police data with less similarity, thereby effectively destroying the similarity relationship between police data; further, an encrypted binary tree is constructed for the police data after the adjustment of the position, so that there are more intersection paths between the connection paths of police data with less similarity, and there are fewer intersection paths between the connection paths of police data with greater similarity, and then using the constructed encrypted binary tree, the difference in coding values ​​of police data with greater similarity is greater, and the difference in coding values ​​of police data with less similarity is smaller, thereby effectively destroying the similarity relationship between police data.

[0013] Preferably, the step of adjusting the relative position of a police data with respect to the geometric center of all other police data includes:

[0014] The mean of the distances between all two police data is taken as the benchmark length;

[0015] Obtaining the distance between the police data and the geometric center; multiplying the inverse of the distance between the police data and the geometric center by the reference length to obtain an adjusted distance, and drawing a circle with the geometric center as the center and the adjusted distance as the radius;

[0016] The intersection point of the line connecting the geometric center and the police data and the circle is taken as the adjusted position of the police data.

[0017] The present invention reflects the overall position characteristics of other police data through the geometric center of other police data, and adjusts the relative distance between the police data and the geometric center so that when the similarity between the police data and other police data is large, the distance between the police data and other police data is increased, and when the similarity between the police data and other police data is small, the distance between the police data and other police data is reduced, thereby effectively destroying the similarity relationship of the police data.

[0018] Preferably, the relative position adjustment processing of other police data in sequence includes:

[0019] Obtain the remaining police data except the police data, and multiply the distance between one remaining police data and the geometric center of all other remaining police data by the reference length as the adjusted distance of the remaining police data; adjust the relative position of the remaining police data and the corresponding geometric center according to the geometric centers of other remaining police data and the adjusted distance of the remaining police data to obtain the adjusted position of the remaining police data;

[0020] And so on, complete the relative position adjustment processing of other remaining police data.

[0021] The present invention performs relative position adjustment processing on the remaining police data in turn, realizes traversal adjustment of each remaining police data, changes the relative position relationship of the police data more comprehensively, and destroys the similarity relationship of the police data more thoroughly.

[0022] Preferably, the method for obtaining the left child node includes:

[0023] Calculate the mean of all data in the child nodes, and obtain the child node with the smaller mean of all data in the two child nodes of the parent node as the left child node.

[0024] Preferably, the method for obtaining the right child node includes:

[0025] Among the two child nodes of the parent node, the child node with the larger mean value of all data is obtained as the right child node.

[0026] The present invention distinguishes the left child node and the right child node by the data size relationship, and the implementation method is simpler and more efficient.

[0027] Preferably, the method for obtaining the root node includes:

[0028] The topmost node is recorded as the root node.

[0029] Preferably, the method for obtaining the leaf node includes:

[0030] Nodes that do not have child nodes are considered leaf nodes.

[0031] Preferably, the method for obtaining the connection path includes:

[0032] The connection between the parent node and the corresponding child node is recorded as the connection path.

[0033] Preferably, the method of realizing encrypted storage of police data includes:

[0034] The police data is stored in encrypted form.

[0035] The present invention prevents information in police data from being leaked by encrypting police data, thereby effectively improving the security of police data.

[0036] In a second aspect, the present invention provides an intelligent community policing data processing system based on artificial intelligence, which adopts the following technical solutions:

[0037] The smart community policing data processing system based on artificial intelligence includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned smart community policing data processing method based on artificial intelligence is implemented.

[0038] By adopting the above technical solution, the above-mentioned artificial intelligence-based smart community policing data processing method is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0039] The present invention has the following technical effects:

[0040] The present invention adjusts the position of the police data to increase the distance between police data with a greater degree of similarity and decrease the distance between police data with a lesser degree of similarity, thereby effectively destroying the similarity relationship between the police data;

[0041] Furthermore, an encrypted binary tree is constructed for the police data after the adjustment, so that there are more intersection paths between the connection paths of the police data with less similarity, and fewer intersection paths between the connection paths of the police data with greater similarity. Then, the coding value differences of the police data with greater similarity obtained by the encrypted binary tree are greater, and the coding value differences of the police data with less similarity are smaller, thereby effectively destroying the similarity relationship between the police data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0043] Figure 1 It is a flow chart of a method in a smart community policing data processing method based on artificial intelligence according to an embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of an encrypted binary tree provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0047] The embodiment of the present invention discloses a method for processing smart community policing data based on artificial intelligence, referring to Figure 1 , comprising steps S1 to S5:

[0048] S1: Obtain some police data.

[0049] Specifically, the archives of each resident are obtained, and non-digital information such as characters and symbols in the archives of each resident are converted into digital information, and the sequence of all archive data of each resident after digital conversion is recorded as a police data; several residents obtain several police data. This embodiment uses the ASCII table to convert non-digital information in the archives into digital information, and other embodiments can use other methods for digital conversion, which is not specifically limited in this embodiment.

[0050] S2: Adjust the relative position of a police data and the geometric center of all other police data. After the relative position adjustment, the distance between the police data and the geometric center is negatively correlated with the distance before the adjustment, and the relative direction remains unchanged; perform relative position adjustment processing on other police data in turn.

[0051] It should be noted that in order to destroy the similarity relationship of police data, the distance between police data with greater similarity needs to be increased, and the distance between police data with less similarity needs to be decreased.

[0052] Preferably, as an example, the relative position of a police data and the geometric center of all other police data is adjusted, and after the relative position adjustment, the distance between the police data and the geometric center is negatively correlated with the distance before the adjustment, and the relative direction remains unchanged; the relative position adjustment processing is performed on other police data in turn, including:

[0053] The average of the distances between all two police data is used as the reference length; the distance between the police data and the geometric center is obtained; the inverse of the distance between the police data and the geometric center is multiplied by the reference length to obtain the adjusted distance, and a circle is drawn with the geometric center as the center and the adjusted distance as the radius; the intersection of the line connecting the geometric center and the police data and the circle is used as the adjusted position of the police data.

[0054] Obtain the remaining police data except the police data, and multiply the distance between one remaining police data and the geometric center of all other remaining police data by the reference length as the adjusted distance of the remaining police data; draw a circle with the geometric center of all other remaining police data as the center and the adjusted distance of the remaining police data as the radius, and record it as a new circle; and take the intersection of the line connecting the geometric center of all other remaining police data and the remaining police data and the new circle as the adjusted position of the remaining police data.

[0055] And so on, complete the relative position adjustment processing of other remaining police data.

[0056] It can be seen that through the above distance adjustment, the distance between the police data with originally small distance intervals can be increased, and the distance between the police data with originally large distance intervals can be reduced, thereby effectively destroying the similarity relationship between the police data.

[0057] S3: Take all police data after relative position adjustment as parent nodes, divide the data in the parent nodes into two categories based on the distance between the data in the parent nodes, and use each category as the child node of the parent node; in response to the number of data in the child node being greater than 1, use the child node as a new parent node, divide the data in the new parent node into two categories, and use each newly obtained category as the child node of the new parent node; in response to the number of data in the child node of the new parent node being not greater than 1, the classification is completed, and the parent node is connected to the corresponding child node to obtain an encrypted binary tree.

[0058] It should be noted that, in order to further destroy the similarity relationship, when encoding the police data, the difference in encoding settings between police data with greater similarity is greater, and the difference in encoding settings between police data with less similarity is smaller.

[0059] Preferably, as an example, all police data after relative position adjustment are used as parent nodes, and based on the distance between the data in the parent nodes, the data in the parent nodes are divided into two categories, and each category is used as a child node of the parent node; in response to the number of data in the child node being greater than 1, the child node is used as a new parent node, the data in the new parent node is divided into two categories, and each newly obtained category is used as a child node of the new parent node; in response to the number of data in the child node of the new parent node being not greater than 1, the classification is completed, and the parent node is connected to the corresponding child node to obtain an encrypted binary tree, including:

[0060] All police data after relative position adjustment are taken as parent nodes, and based on the distance between the data in the parent nodes, the data in the parent nodes are divided into two categories. This embodiment uses the K-means clustering algorithm to classify the data in the parent node. Other embodiments may adopt classification methods. This embodiment does not make specific restrictions. Each category is taken as a child node of the parent node; in response to the number of data in the child node being greater than 1, the child node is taken as a new parent node, and the data in the new parent node is divided into two categories, and each newly obtained category is taken as a child node of the new parent node; in response to the number of data in the child node of the new parent node being not greater than 1, the classification is completed, and the parent node is connected to the corresponding child node to obtain an encrypted binary tree.

[0061] It should be added that the parent node will correspond to two child nodes, which are the left child node and the right child node respectively.

[0062] Among them, the method for obtaining the left child node is:

[0063] Calculate the mean of all dimensions of each data in the child node and record it as the representation value of each data in the child node, and record the mean of the representation values ​​of all data in the child node as the mean of all data in the child node. Obtain the child node with the smaller mean of all data in the two child nodes of the parent node as the left child node.

[0064] In addition, the method for obtaining the right child node is:

[0065] Among the two child nodes of the parent node, the child node with the larger mean value of all data is obtained as the right child node.

[0066] S4: Set the mark value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree to 0, and set the mark value of the connection path between the parent node and the corresponding right child node to 1; use the binary number composed of the mark value of the connection path from the root node to the leaf node as the encryption data of the police data in the leaf node; so as to realize the encrypted storage of police data.

[0067] S40: Set the mark value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree to 0, and set the mark value of the connection path between the parent node and the corresponding right child node to 1; use the binary number composed of the mark value of the connection path from the root node to the leaf node as the encrypted data of the police data in the leaf node.

[0068] Preferably, as an example, the tag value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree is set to 0, and the tag value of the connection path between the parent node and the corresponding right child node is set to 1; the binary number composed of the tag value of the connection path from the root node to the leaf node is used as the encrypted data of the police data in the leaf node, including:

[0069] The mark value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree is set to 0, and the mark value of the connection path between the parent node and the corresponding right child node is set to 1; the binary number composed of the mark value of the connection path from the root node to the leaf node is used as the encrypted data of the police data in the leaf node.

[0070] For ease of understanding, the following diagram is used to illustrate the encryption of police data. Figure 2 The encrypted binary tree diagram is shown below. Figure 2 It contains 7 leaf nodes, and the serial numbers of the leaf nodes increase from left to right. The data without brackets in each leaf node is the police data schematic value, and the data with brackets is the encrypted data of the police data schematic value. The connection path from the root node to the leaf node 3 is bolded, and the binary data composed of the mark values ​​of all the connection paths from the root node to the leaf node 3 is 100, which is the encrypted data of the police data in the leaf node 3.

[0071] It should be added that, in this embodiment, the connection between the parent node and the corresponding child node is recorded as a connection path, the top node is recorded as a root node, and the node without a child node is recorded as a leaf node.

[0072] It can be seen that the police data with large distance differences have more intersection connection paths, so the difference in the encrypted data of the police data with large distance differences is smaller, while the police data with small distance differences have fewer intersection connection paths, so the difference in the encrypted data of the police data with small distance differences is larger. Through this encoding method, the difference between similar police data can be made larger, and the difference between dissimilar police data can be made smaller, thereby effectively destroying the similarity relationship between police data.

[0073] S41: To achieve encrypted storage of police data.

[0074] Preferably, as an example, to realize encrypted storage of police data, the method includes:

[0075] The encrypted data of the police data is stored in the storage space.

[0076] S5: Decryption processing of police data.

[0077] Preferably, as an example, the decryption process of police data includes:

[0078] The encrypted binary tree is used as the secret key, and the secret key is stored in a storage space with a permission threshold.

[0079] The faces of authorized police officers are entered into the verification set. When police officers read police data, they need to match their faces with the faces in the verification set. If the match is successful, the secret key in the storage space with a permission threshold is called.

[0080] The encrypted police data is decrypted through the correspondence between the encrypted data in the secret key and the corresponding police data, and the police officers can read the decrypted police data.

[0081] An embodiment of the present invention also discloses an artificial intelligence-based smart community policing data processing system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an artificial intelligence-based smart community policing data processing method according to the present invention is implemented.

[0082] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0083] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0085] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart community policing data processing method based on artificial intelligence, characterized in that: Includes steps: obtain certain police data; Adjust the relative position of a police data and the geometric center of all other police data, so that after the relative position adjustment, the distance between the police data and the geometric center is negatively correlated with the distance before the adjustment, and the relative direction remains unchanged; perform relative position adjustment processing on other police data in turn; All police data after relative position adjustment are taken as parent nodes, and based on the distance between the data in the parent nodes, the data in the parent nodes are divided into two categories, and each category is respectively taken as the child node of the parent node; in response to the number of data in the child node being greater than 1, the child node is taken as a new parent node, the data in the new parent node is divided into two categories, and each newly obtained category is taken as the child node of the new parent node; in response to the number of data in the child node of the new parent node being less than 1, the classification is completed, and the parent node is connected with the corresponding child node to obtain an encrypted binary tree; The mark value of the connection path between the parent node and the corresponding left child node in the encrypted binary tree is set to 0, and the mark value of the connection path between the parent node and the corresponding right child node is set to 1; the binary number composed of the mark value of the connection path from the root node to the leaf node is used as the encryption data of the police data in the leaf node; so as to realize the encrypted storage of police data.

2. The method for processing smart community policing data based on artificial intelligence according to claim 1 is characterized in that: The adjusting of the relative position of the geometric center of a police data and all other police data includes: The mean of the distances between all two police data is taken as the benchmark length; Obtaining the distance between the police data and the geometric center; multiplying the inverse of the distance between the police data and the geometric center by the reference length to obtain an adjusted distance, and drawing a circle with the geometric center as the center and the adjusted distance as the radius; The intersection point of the line connecting the geometric center and the police data and the circle is taken as the adjusted position of the police data.

3. The method for processing smart community policing data based on artificial intelligence according to claim 2 is characterized in that: The relative position adjustment processing of other police data in sequence includes: Obtain the remaining police data except the police data, and multiply the distance between one remaining police data and the geometric center of all other remaining police data by the reference length as the adjusted distance of the remaining police data; adjust the relative position of the remaining police data and the corresponding geometric center according to the geometric centers of other remaining police data and the adjusted distance of the remaining police data to obtain the adjusted position of the remaining police data; And so on, complete the relative position adjustment processing of other remaining police data.

4. The method for processing smart community policing data based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining the left child node includes: Calculate the mean of all data in the child nodes, and obtain the child node with the smaller mean of all data in the two child nodes of the parent node as the left child node.

5. The method for processing smart community policing data based on artificial intelligence according to claim 4 is characterized in that: The method for obtaining the right child node includes: Among the two child nodes of the parent node, the child node with the larger mean value of all data is obtained as the right child node.

6. The method for processing data of smart community policing based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining the root node includes: The topmost node is recorded as the root node.

7. The method for processing smart community policing data based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining the leaf node includes: Nodes that do not have child nodes are considered leaf nodes.

8. The method for processing smart community policing data based on artificial intelligence according to claim 1 is characterized in that: The method for obtaining the connection path includes: The connection between the parent node and the corresponding child node is recorded as the connection path.

9. The method for processing smart community policing data based on artificial intelligence according to claim 1 is characterized in that: The method for realizing encrypted storage of police data includes: The police data is stored in encrypted form.

10. The smart community policing data processing system based on artificial intelligence is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the artificial intelligence-based smart community policing data processing method according to any one of claims 1 to 9 is implemented.

Images