Privacy protection close connection track mining method based on grid coding

Abstract

The invention belongs to the field of data mining, and discloses a privacy protection close connection track mining method based on grid coding, which comprises two stages of object track security preprocessing and privacy protection close connection track query, in the object track security preprocessing stage, the object track is subjected to grid coding processing to obtain an object track security code, and the privacy protection close connection track query stage is subjected to privacy protection close connection track query. Carrying out encryption processing on the object track; in a privacy protection close connection track query stage, same grid coding processing is performed on a query track to obtain a query track security code, track mining is performed based on an object track security code according to a close connection judgment condition, and finally a close connection track mining result set is obtained. According to the method, on the premise of ensuring privacy security, various scenes and requirements can be compatible, and efficient and reliable close contact track mining is realized.

Description

Technical Field

[0001] The present invention belongs to the field of data mining, and specifically relates to a privacy-preserving close-connected trajectory mining method based on grid coding. Background Art

[0002] With the rapid development of big data and artificial intelligence technologies, application scenarios based on data processing and analysis are constantly expanding. Especially in the fields of trajectory data analysis, privacy protection and public safety, how to efficiently and securely mine data value has become an important research direction and an urgent practical need. In today's society, with the popularization of mobile devices, IoT sensors and positioning technology, massive trajectory data are widely collected, and these data play an important role in transportation planning, logistics management and other fields. However, trajectory data has the characteristics of high dimensionality, temporal and spatiality, and its analysis process faces technical challenges such as high computational complexity and high storage pressure. At the same time, trajectory data contains sensitive information such as users' travel habits and location records, which may lead to the risk of privacy leakage if not handled properly.

[0003] Most current research solutions for privacy-preserving close-contact trajectory mining methods are difficult to balance efficiency and accuracy. Chinese patent application: ZL2024102645673, discloses a privacy-preserving close-contact object detection method based on trajectory coding, which mentions close-contact object detection. However, this detection method based on trajectory coding has low detection accuracy, is prone to missed solutions, and cannot achieve high-precision close-contact object detection. Summary of the invention

[0004] In order to address the defects of the prior art, the present invention provides a privacy-preserving close-connected trajectory mining method based on grid coding. This method supports high-precision close-connected trajectory mining with privacy protection capability without leaking plaintext trajectory data by performing grid coding and encryption processing on trajectory data.

[0005] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is a privacy-preserving close-connected trajectory mining method based on grid coding. The privacy-preserving close-connected trajectory mining method consists of two stages: object trajectory security preprocessing and privacy-preserving close-connected trajectory query. In the object trajectory security preprocessing stage, the object trajectory is subjected to grid coding to obtain the object trajectory security code, and the object trajectory is encrypted; in the privacy-preserving close-connected trajectory query stage, the query trajectory is subjected to the same grid coding to obtain the query trajectory security code, and then the close-connected trajectory mining is performed according to the close-connected judgment condition, and finally the close-connected trajectory mining result set is obtained. Specifically:

[0007] The object trajectory safety preprocessing stage specifically includes the following steps:

[0008] Step 1-1: Use a uniform grid segmentation method to spatially divide the area Z where the object trajectory and the query trajectory are located to generate a basic grid set G, merge four adjacent basic grids into a grid group, and all grid groups constitute a grid group set G. s , assign a unique code to each grid group, and assign each track u in the object track set U h ∈U is mapped to the corresponding grid group code, and the object trajectory security code sec is obtained h , where both the object trajectory and the query trajectory are obtained through n position samplings, and the sampling time point set is T = {t1, t2, v, t n}, object trajectory set U = {u1,u2,…,u m},u h ={(l h,1 ,t1),(l h,2 ,t2),…,(l h,n ,t n )},l h,p Represents the trajectory u h At sampling time t p The two-dimensional latitude and longitude position coordinates of ;

[0009] Step 1-2: Generate a key K, and for each trajectory u in the object trajectory set U h ∈U performs symmetric encryption to obtain the encrypted trajectory Finally, the encrypted object trajectory dataset is generated

[0010] The privacy-preserving close contact trajectory query phase specifically includes the following steps:

[0011] Step 2-1: query trajectory u q The trajectory points in are mapped to the corresponding grid group code, and the query trajectory security code sec is obtained. q , where the query trajectory is denoted as u q ={(l q,1 ,t1),(l q,2 ,t2),…,(l q,n ,t n )};

[0012] Step 2-2: Based on the distance threshold d determined by close contact, the encrypted object trajectory dataset All object trajectories in the , are securely encoded for close trajectory query, and all records u related to the query trajectory are mined q The object trajectories with close connection relationship are finally obtained, and the close connection trajectory mining result set R is obtained.

[0013] A further improvement of the present invention is that step 1-1 specifically includes the following steps:

[0014] Step 1-1-1, the area Z where the object trajectory and the query trajectory are located is evenly divided into square basic grids of equal size, and the basic grid set G = {g 1,1 ,g 1,2 ,…,g α,β}, where α is the number of grid rows and β is the number of grid columns;

[0015] Step 1-1-2: Merge four adjacent basic grids into one grid group a , and the diagonal length of each grid group is d, the grid group s a = {g i,j ,g i,j+1 ,g i+1,j ,g i+1,j+1}, suppose there are k grid groups in total, and the grid group set is recorded as G s ={s1,s2,…,s k};

[0016] Step 1-1-3, construct 2 σ The set C consists of binary codes of length σ, where The generation rules are as follows:

[0017]

[0018] Randomly select k codes from C and randomly map them to the grid group set G s k grid groups in the grid group s a The assigned code is denoted as c a , ensuring that each grid group s a Have a unique code;

[0019] Step 1-1-4: For any grid group s a , are composed of four basic grids, and there is an overlapping relationship between adjacent grid groups. Suppose four grid groups s a 、s b 、s c and d There are overlapping base grids g i,j , i.e. g i,j =s a ∩s b ∩s c ∩s d , for any base grid g i,j =s a ∩s b ∩s c ∩s d, which is uniquely represented as the set e i,j ={c a ,c b ,c c ,c d}, where c a 、c b 、c c and c d Grid groups s a 、s b 、s c and d The grid group code of

[0020] Step 1-1-5: For the object trajectory u h ∈U, let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid group encoding set is

[0021] Step 1-1-6: Set the object trajectory u h The trajectory points are represented by grid group coding, and the object trajectory security coding obtained after grid coding is

[0022] A further improvement of the present invention is that in step 1-1-1, in the square basic grids of equal size, the diagonal length of each grid is d is the distance threshold for close contact determination.

[0023] A further improvement of the present invention is that step 2-1 specifically includes the following steps:

[0024] Step 2-1-1: For the query trajectory u q , let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid group encoding set is

[0025] Step 2-1-2: query trajectory u q The trajectory points are represented by grid group coding, and the query trajectory coding obtained after grid coding is

[0026] A further improvement of the present invention is that: Step 2-2 is specifically: given a detection time range [t u ,t v ], for query trajectory security code sec q , examine the dense object trajectory dataset Each object trajectory in is securely encoded as sec h , let the sliding window W = {t l+1 ,t l+2 ,…,t l+δ} consists of δ continuous time sampling points. For any t p ∈W, if the object trajectory security code sec h In t p The grid code set at the moment Query track security code sec q In t p The grid code set at the moment satisfy Then encrypt the track Add the close-connected trajectory mining result set R, where δ is the sliding window width.

[0027] The beneficial effects of the present invention are:

[0028] The present invention performs trajectory mining based on the security coding of object trajectories in combination with the security coding of query trajectories, and realizes a trajectory mining method with privacy protection capability when the security coding does not contain trajectory information.

[0029] In the process of grid coding the track according to the present invention, the gridding method is fine and has a simple structure, is easy to implement and apply, and has high query accuracy.

[0030] The mining results of the present invention are returned in the form of trajectory ciphertext, without directly exposing the plaintext trajectory, and have strong security.

[0031] In summary, the present invention improves query accuracy while achieving efficient privacy-preserving close-connected trajectory mining. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a grid defined in the present invention.

[0033] Figure 2 Schematic diagram of the close contact determination conditions of the present invention.

[0034] Figure 3 This is a flow chart of the trajectory data mining method in the present invention. DETAILED DESCRIPTION

[0035] The following will disclose the embodiments of the present invention with drawings. For the purpose of clear description, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present invention. That is to say, in some embodiments of the present invention, these practical details are not necessary.

[0036] First, the definition of the close connection relationship of the query trajectory is given:

[0037] Assume that both the object trajectory and the query trajectory are obtained through n position samplings, and the sampling time point set is T = {t1, t2, …, t n}. The query trajectory is recorded as u q ={(l q,1 ,t1),(l q,2 ,t2),…,(l q,n ,t n )}, where l q,p Represents the query trajectory u q At sampling time t p The two-dimensional latitude and longitude coordinates of the location.

[0038] Definition 1 Closely connected trajectories: Given an object trajectory set, denoted as U = {u1,u2,…,u m}, where u h ={(l h,1 ,t1),(l h,2 ,t2),…,(l h,n ,t n )},l h,p Represents the trajectory u h At the sampling point t p The two-dimensional latitude and longitude coordinates of the location.

[0039] Given a detection time range [t u ,t v ], for the query trajectory u q , the set of object trajectories U = {u1,u2,…,u m Each trajectory u in h ∈U, if there is a sliding window W consisting of several continuous time sampling points = {t l+1 ,t l+2 ,…,t l+δ ,}If the following conditions are met, the object trajectory is called a close trajectory.

[0040] Condition 1: |W| = δ

[0041] Condition 2:

[0042] Where δ is the width of the sliding window W, that is, the number of continuous time sampling points in the window, l h,p is the object trajectory u h In t p The two-dimensional latitude and longitude coordinates at the time, l q,p To query the trajectory u q In t p The two-dimensional longitude and latitude coordinates at the time. Δ(l h,p ,l q,p ) indicates tp The Euclidean distance between the object trajectory and the query trajectory coordinate point at the moment. d is the distance threshold for close contact determination.

[0043] In the above definition, the mining of closely connected trajectories is performed in plain text, without considering the privacy security of trajectory data. In order to protect the privacy of trajectory data, the trajectory data needs to be grid-encoded and encrypted, and the mining of closely connected trajectories is supported.

[0044] like Figure 3 As shown, the present invention is a privacy-preserving close-connected trajectory mining method based on grid coding, and the privacy-preserving close-connected trajectory mining method consists of two stages: object trajectory security preprocessing and privacy-preserving close-connected trajectory query. In the object trajectory security preprocessing stage, the object trajectory is grid-coded to obtain the object trajectory security code, and the object trajectory is encrypted; in the privacy-preserving close-connected trajectory query stage, the query trajectory is subjected to the same grid coding to obtain the query trajectory security code, and according to the close connection determination distance threshold d, trajectory mining is performed based on the object trajectory security code, and finally a close-connected trajectory mining result set is obtained.

[0045] The object trajectory safety preprocessing stage specifically includes the following steps:

[0046] Step 1-1: Use a uniform grid segmentation method to spatially divide the area Z where the object trajectory and the query trajectory are located to generate a basic grid set G, merge four adjacent basic grids into a grid group, and all grid groups constitute a grid group set G. s , assign a unique code to each grid group, and assign each track u in the object track set U h ∈U is mapped to the corresponding grid group code, and the object trajectory security code sec is obtained h , where both the object trajectory and the query trajectory are obtained through n position samplings, and the sampling time point set is T = {t1, t2, …, t n}, object trajectory set U = {u1,u2,…,u m},u h ={(l h,1 ,t1),(l h,2 ,t2),…,(l h,n ,t n )},l h,p Represents the trajectory u h At sampling time t p The two-dimensional latitude and longitude coordinates of the location.

[0047] The specific steps include:

[0048] Step 1-1-1, evenly divide the area Z where the object trajectory and the query trajectory are located into α×β square basic grids of equal size, and divide the generated basic grid set G = {g 1,1 ,g 1,2 ,…,g α,β}, where α is the number of grid rows and β is the number of grid columns;

[0049] Step 1-1-2: Merge four adjacent basic grids into one grid group a , and the diagonal length of each grid group is d, the grid group s a = {g i,j ,g i,j+1 ,g i+1,j ,g i+1,j+1}, suppose there are k grid groups in total, and the grid group set is recorded as G s ={s1,s2,…,s k};

[0050] Step 1-1-3, construct 2 σ The set C consists of binary codes of length σ, where The generation rules are as follows:

[0051]

[0052] Randomly select k codes from C and randomly map them to the grid group set G s k grid groups in the grid group s a The assigned code is denoted as c a , ensuring that each grid group s a Have a unique code;

[0053] Step 1-1-4: For any grid group s a , are composed of four basic grids, and there is an overlapping relationship between adjacent grid groups. Suppose four grid groups s a 、s b 、s c and d There are overlapping base grids g i,j , i.e. g i,j =s a ∩s b ∩s c ∩s d Since each grid group is uniquely encoded and each basic grid is uniquely represented by four grid groups, for any basic grid g i,j =s a ∩s b ∩s c ∩s d , which is uniquely represented as the set ei,j ={c a ,c b ,c c ,c d}, where c a 、c b 、c c and c d Grid groups s a 、s b 、s c and d The grid group code of

[0054] Step 1-1-5: For the object trajectory u h ∈U, let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid code set is

[0055] Step 1-1-6: Set the object trajectory u h The trajectory points are represented by grid coding, and the object trajectory security coding obtained after grid coding is

[0056] Step 1-2: Generate a key K, and for each trajectory u in the object trajectory set U h ∈U performs symmetric encryption to obtain the encrypted trajectory Finally, the encrypted object trajectory dataset is generated

[0057] The privacy protection close contact trajectory query stage specifically includes the following steps:

[0058] Step 2-1: query trajectory u q The trajectory points in are mapped to the corresponding grid group code, and the query trajectory security code sec is obtained. q , where the query trajectory is denoted as u q ={(l q,1 ,t1),(l q,2 ,t2),…,(l q,n ,t n )}, specifically including the following steps:

[0059] Step 2-1-1: For the query trajectory u q , let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid code set is

[0060] Step 2-1-2: query trajectory u q The trajectory points are represented by grid coding, and the query trajectory coding obtained after grid coding is

[0061] Figure 2 The diagram is a schematic diagram of the close contact determination conditions of the present invention. The trajectory with the circle as the trajectory point represents the query trajectory u q , the trajectory with asterisks as trajectory points represents the object trajectory u h , d is the distance threshold for determining close contact, the rectangular box represents the sliding time window W, and δ is the minimum sliding window threshold for determining close contact, that is, the sliding window contains at least δ consecutive sampling points.

[0062] Step 2-2: Based on the distance threshold d determined by close contact, the encrypted object trajectory dataset All object trajectories in the , are securely encoded for close trajectory query, and all records u related to the query trajectory are mined q The object trajectories with close connection relationship are finally obtained, and the close connection trajectory mining result set R is obtained. Specifically, the close connection trajectory query method is: given the detection time range [t u ,t v ], for query trajectory security code sec q , examine the dense object trajectory dataset Each object trajectory in is securely encoded as sec h , let the sliding window W = {t l+1 ,t l+2 ,…,t l+δ} consists of δ continuous time sampling points. For any t p ∈W, if the object trajectory security code sec h In t p The grid code set at the moment Query track security code sec q In t p The grid code set at the moment satisfy Then encrypt the track Add the close-connected trajectory mining result set R, where δ is the sliding window width.

[0063] In order to verify the present invention, the present invention is compared with the other two methods, and the results are shown in Table 1.

[0064] Table 1

[0065] method Accuracy (%) Time(s) Method 1 92.54 115.05 Method 2 87.7 477.4 This method 93 8.74

[0066] Among them, method 1 is a Chinese patent application: ZL2024102645673. Method 2 is Li, M., Zeng, Y., Zheng, L., Chen, L., Li, Q.: Accurate and efficient trajectory-based contact tracing with secure computation and geo-indistinguishability. In: International Conference on Database Systems for Advanced Applications. pp. 300-316. Springer (2023)

[0067] As shown in Table 1, the method of the present invention has high accuracy and short time. The present invention improves the query accuracy while realizing efficient privacy-preserving close-connected trajectory mining.

[0068] The above description is only the embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A privacy-preserving close-connected trajectory mining method based on grid coding, characterized by: The privacy-preserving close-connected trajectory mining method comprises two stages: object trajectory security preprocessing and privacy-preserving close-connected trajectory query. In the object trajectory security preprocessing stage, the object trajectory is grid-coded to obtain the object trajectory security code, and the object trajectory is encrypted. In the privacy-preserving close-connected trajectory query stage, the query trajectory is processed with the same grid coding to obtain the query trajectory security code, and then the close-connected trajectory mining is carried out according to the close-connected judgment conditions, and finally the close-connected trajectory mining result set is obtained. Specifically: The object trajectory safety preprocessing stage specifically includes the following steps: Step 1-1: Use a uniform grid segmentation method to spatially divide the area Z where the object trajectory and the query trajectory are located to generate a basic grid set G, merge four adjacent basic grids into a grid group, and all grid groups constitute a grid group set G. s , assign a unique code to each grid group, and assign each track u in the object track set U h ∈U is mapped to the corresponding grid group code, and the object trajectory security code sec is obtained h , where both the object trajectory and the query trajectory are obtained through n position samplings, and the sampling time point set is T = {t1, t2, …, t n }, object trajectory set U = {u1,u2,…,u m },u h ={(l h,1 ,t1),(l h,2 ,t2),…,(l h,n ,t n )},l h,p Represents the trajectory u h At sampling time t p The two-dimensional latitude and longitude position coordinates of ; Step 1-2: Generate a key K for each trajectory u in the object trajectory set U h ∈U performs symmetric encryption to obtain the encrypted trajectory Finally, the encrypted object trajectory dataset is generated The privacy protection close contact trajectory query stage specifically includes the following steps: Step 2-1: query trajectory u q The trajectory points in are mapped to the corresponding grid group code, and the query trajectory security code sec is obtained. q , where the query trajectory is denoted as u q ={(l q,1 ,t1),(l q,2 ,t2),…,(l q,n ,t n )}; Step 2-2: Based on the distance threshold d determined by close contact, the encrypted object trajectory dataset All object trajectories in the , are securely encoded for close trajectory query, and all records u related to the query trajectory are mined q The object trajectories with close connection relationship are finally obtained, and the close connection trajectory mining result set R is obtained.

2. The privacy-preserving close-connected trajectory mining method based on grid coding according to claim 1, characterized in that: The step 1-1 specifically includes the following steps: Step 1-1-1, the area Z where the object trajectory and the query trajectory are located is evenly divided into square basic grids of equal size, and the basic grid set G = {g 1,1 ,g 1,2 ,…,g α,β }, where α is the number of grid rows and β is the number of grid columns; Step 1-1-2: Merge four adjacent basic grids into one grid group a , and the diagonal length of each grid group is d, the grid group s a = {g i,j ,g i,j+1 ,g i+1,j ,g i+1,j+1 }, suppose there are k grid groups in total, and the grid group set is recorded as G s ={s1,s2,…,s k }; Step 1-1-3, construct 2 σ The binary code set C consists of binary codes of length σ, where The generation rules are as follows: Randomly select k codes from the binary code set C and randomly map them to the grid group set G s k grid groups in the grid group s a The assigned code is denoted as c a , ensuring that each grid group s a Have a unique code; Step 1-1-4: For any grid group s a , are composed of four basic grids, and there is an overlapping relationship between adjacent grid groups. Suppose four grid groups s a 、s b 、s c and d There are overlapping base grids g i,j , i.e. g i,j =s a ∩s b ∩s c ∩s d , for any base grid g i,j =s a ∩s b ∩s c ∩s d , which is uniquely represented as the set e i,j ={c a ,c b ,c c ,c d }, where the grid group s b = {g i,j+1 ,g i,j+2 ,g i+1,j+1 ,g i+1,j+2 }, grid groups c = {g i+1,j ,g i+1,j+1 ,g i+2,j ,g i+2,j+1 }, grid groups d = {g i+1,j+1 ,g i+1,j+2 ,g i+2,j+1 ,g i+2,j+2 }, c a 、c b 、c c and c d Grid groups s a 、s b 、s c and d The grid group code of Step 1-1-5: For the object trajectory u h ∈U, let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid group encoding set is Step 1-1-6: Set the object trajectory u h The trajectory points are represented by grid group coding, and the object trajectory security coding obtained after grid coding is 3. The privacy-preserving close-connected trajectory mining method based on grid coding according to claim 2, characterized in that: In step 1-1-1, in the square basic grids of equal size, the diagonal length of each grid is d is the distance threshold for close contact determination.

4. The privacy-preserving close-connected trajectory mining method based on grid coding according to claim 2, characterized in that: In step 2-1, the query trajectory u q The trajectory points in are mapped to the corresponding grid group code, and the query trajectory security code sec is obtained. q , specifically including the following steps: Step 2-1-1: For the query trajectory u q , let t p The basic grid where the moment trajectory point is located is Through steps 1-1-4 The grid group encoding set is Step 2-1-2: query trajectory u q The trajectory points are represented by grid group coding, and the query trajectory coding obtained after grid coding is 5. The privacy-preserving close-connected trajectory mining method based on grid coding according to claim 1, characterized in that: The step 2-2 is specifically as follows: given a detection time range [t u ,t v ], for query trajectory security code sec q , examine the trajectory dataset of closely connected objects Each object trajectory in is securely encoded as sec h , let the sliding window W = {t l+1 ,t l+2 ,…,t l+δ } consists of δ continuous time sampling points. For any t p ∈W, if the object trajectory security code sec h In t p The grid group code set at the moment Query track security code sec q In t p The grid group code set at the moment satisfy Then encrypt the track Add the close-connected trajectory mining result set R, where δ is the sliding window width.

Images