A differential privacy trajectory similarity publishing method, program product and device

Abstract

The present invention provides a differentially private trajectory similarity publishing method, comprising: obtaining location data of multiple users at multiple times; constructing a similarity subgraph at each time, wherein the edge in the similarity subgraph indicates that the distance between two users connected by the edge is less than a distance threshold; merging the similarity subgraphs at multiple times to obtain a similarity composite graph; setting the weight of each edge according to the frequency of each edge appearing in the similarity subgraphs at multiple times in the similarity composite graph to obtain a trajectory similarity graph; adding noise to the weight of the edge in the trajectory similarity graph to obtain a noisy trajectory similarity graph; and publishing the noisy trajectory similarity graph. The present invention also discloses a differentially private trajectory similarity publishing device, a computer program product, an electronic device, and a user trajectory similarity analysis method and analysis system. The present invention intuitively reflects the trajectory similarity between users on the trajectory similarity graph, and at the same time adds noise to the weight of the edge, thereby achieving privacy protection.

Description

Technical Field

[0001] The present invention relates to the technical field of trajectory similarity publishing, and in particular to a differentially private trajectory similarity publishing method, program product and device. Background Art

[0002] In today's era of rapid development of smart devices and Internet of Things technology, the collection and analysis of user trajectory data provides important support for personalized services, traffic optimization, and smart city construction. Among them, the calculation of trajectory similarity has important applications in many fields. For example, in traffic planning, trajectory similarity can help analyze the travel patterns of different users, thereby optimizing the design of public transportation routes. However, the release of trajectory data inevitably involves the leakage of user privacy. With the widespread application of trajectory similarity data, the issue of user privacy protection has become increasingly prominent. Trajectory similarity data contains sensitive information such as user behavior patterns, interests and hobbies, and social networks. Therefore, how to safely publish trajectory similarity data while protecting user privacy has become an urgent problem to be solved.

[0003] Differential Privacy (DP), as an important research direction in the field of privacy protection in recent years, can provide quantitative privacy protection, but there is currently no direct method for publishing trajectory similarity based on differential privacy. Summary of the invention

[0004] The present invention aims to at least solve the technical problem that the existing trajectory similarity publishing method cannot safely publish trajectory similarity data under the premise of protecting user privacy, and provide a trajectory similarity publishing method, program product and device with differential privacy.

[0005] In order to achieve the above-mentioned purpose of the present invention, according to the first aspect of the present invention, the present invention provides a differential privacy trajectory similarity publishing method, comprising: obtaining location data of multiple users at multiple times; constructing a similarity subgraph at each time based on the location data of multiple users at each time, wherein the nodes in the similarity subgraph correspond to the users one by one, and any edge existing in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the time to which the similarity subgraph belongs is less than a preset distance threshold; merging the similarity subgraphs at multiple times to obtain a similarity composite graph; setting the weight of each edge in the similarity composite graph according to the frequency of each edge appearing in the similarity subgraphs at multiple times to obtain a trajectory similarity graph; adding noise to the weight of the edges in the trajectory similarity graph to obtain the noisy trajectory similarity graph; and publishing the noisy trajectory similarity graph.

[0006] In order to achieve the above-mentioned purpose of the present invention, according to the second aspect of the present invention, the present invention provides a differential privacy trajectory similarity publishing device, which is used to implement a differential privacy trajectory similarity publishing method described in the first aspect of the present invention, including: a location data acquisition module, which acquires location data of multiple users at multiple times; a similarity subgraph construction module, which constructs a similarity subgraph at each time based on the location data of multiple users at each time, wherein the nodes in the similarity subgraph correspond to the users one by one, and any edge existing in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the time to which the similarity subgraph belongs is less than a preset distance threshold; a merging module, which merges the similarity subgraphs at multiple times to obtain a similarity composite graph; a trajectory similarity graph generation module, which sets the weight of each edge in the similarity composite graph according to the frequency of each edge appearing in the similarity subgraphs at multiple times to obtain a trajectory similarity graph; a noise adding module, which adds noise to the weight of the edge of the trajectory similarity graph to obtain the noisy trajectory similarity graph; and a publishing module, which publishes the noisy trajectory similarity graph.

[0007] In order to achieve the above-mentioned purpose of the present invention, according to the third aspect of the present invention, the present invention provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the steps of a differential privacy trajectory similarity publishing method described in the first aspect of the present invention are implemented.

[0008] In order to achieve the above-mentioned purpose of the present invention, according to the fourth aspect of the present invention, the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a differentially private trajectory similarity publishing method described in the first aspect of the present invention.

[0009] In order to achieve the above-mentioned object of the present invention, according to a fifth aspect of the present invention, the present invention provides a user trajectory similarity analysis method, comprising: a server end publishes a noisy trajectory similarity graph to an analysis end, wherein the noisy trajectory similarity graph is obtained according to a differentially private trajectory similarity publishing method according to the first aspect of the present invention; and the analysis end identifies users with similar trajectories to target users based on the obtained noisy trajectory similarity graph.

[0010] In order to achieve the above-mentioned purpose of the present invention, according to the sixth aspect of the present invention, the present invention provides an analysis system based on the user trajectory similarity analysis method described in the fifth aspect of the present invention, including a server and one or more analysis terminals, and the server is respectively connected to communicate with the one or more analysis terminals.

[0011] The beneficial technical effect of the present invention is as follows: according to the distance between users at each moment, an edge set of the similarity subgraph at that moment is constructed; if the distance between two users at that moment is less than a preset distance threshold, an edge is generated in the similarity subgraph at that moment to connect the two nodes corresponding to the two users; and then multiple similarity subgraphs are merged to obtain a similarity composite graph; the weights of the edges in the similarity composite graph are set; and the similarity composite graph with the edge weights set is used as a trajectory similarity graph; the weights of the edges in the trajectory similarity graph represent the frequency of the edge appearing in the similarity subgraphs at multiple moments, that is, the number of moments when the two users connected by the edge are close; it can be seen that the trajectory similarity graph intuitively reflects the trajectory similarity between users on the graph; service providers (data analysts) can directly obtain the trajectory similarity between users through the edge weights; and use differential privacy technology to add noise to the edge weights of the trajectory similarity graph, thereby achieving privacy protection of trajectory similarity. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of a trajectory similarity publishing method in a preferred embodiment of the present invention;

[0013] Figure 2 is a schematic structural diagram of an electronic device in a preferred embodiment of the present invention;

[0014] Figure 3 is a flow chart of a method for analyzing user trajectory similarity in a preferred embodiment of the present invention;

[0015] Figure 4 It is a system block diagram of an analysis system in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0016] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0017] In the description of the present invention, it is necessary to understand that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0018] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0019] The execution subject of the differential privacy trajectory similarity publishing method includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the differential privacy trajectory similarity publishing method can be executed by software or hardware installed on the terminal device or the server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0020] The present invention discloses a differential privacy trajectory similarity publishing method. In a preferred embodiment, referring to Figure 1 As shown, including:

[0021] Step S1, obtaining location data of multiple users at multiple times.

[0022] The execution subject of this method can read the location data of multiple users at multiple times from its own trajectory database or extract the location data of multiple users at multiple times from the trajectory database of a trusted party. The location data can be location coordinates, and the multiple times are multiple discrete time points distributed within a preset time period. The trajectory database includes the trajectory data records of each user. For user i, there are a total of m times, and the location data D of user i at m times i It is expressed as: i represents the user index, m is a positive integer; Indicates the location coordinates of user i at time k, which can be latitude and longitude coordinates or plane coordinates. k is the index of the time, 1≤k≤m. In the traffic planning scenario, users can be pedestrians and various means of transportation.

[0023] Step S2, constructing a similarity subgraph at each moment based on the location data of multiple users at each moment, wherein the nodes in the similarity subgraph correspond to the users one-to-one, and any edge in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the moment to which the similarity subgraph belongs is less than a preset distance threshold.

[0024] The similarity subgraph at time k is represented as G k =(V,E k ), V represents G k Because the user is fixed, the node set of the similarity subgraph at each moment is the same.

[0025] Step S3, merging the similarity subgraphs at multiple moments to obtain a similarity composite graph.

[0026] Step S4, setting the weight of each edge in the similarity composite graph according to the frequency of each edge appearing in the similarity subgraphs at multiple times, and obtaining a trajectory similarity graph. Specifically, the frequency of each edge appearing in the similarity subgraphs at multiple times (i.e., the number of similarity subgraphs containing the edge) can be used as the weight of each edge, or the normalized value of the frequency can be used as the weight of the edge, or the linear mapping value of the frequency can be used as the weight of the edge.

[0027] Step S5, adding noise to the weights of the edges of the trajectory similarity graph to obtain a noisy trajectory similarity graph.

[0028] Step S6, publishing the trajectory similarity graph after adding noise.

[0029] In the field of traffic planning, the trajectory similarity of two users connected by the edge can be directly obtained through the weight of the edge of the trajectory similarity graph after adding noise, and the trajectory similarity between users can be mapped to the trajectory similarity graph, so as to capture the global trajectory similarity and greatly enhance the data value of trajectory similarity. In addition, by adding noise to the edge weight, differential privacy protection is achieved, avoiding the risk of privacy leakage of user trajectory data. Without leaking the real trajectory similarity, the trajectory similarity is released, so that even if a third-party malicious attacker obtains the similarity information, it is impossible to accurately infer the specific trajectory of the user, thereby effectively protecting user privacy.

[0030] In a preferred embodiment, in order to accurately mine the similarity between user trajectories within a time period, a similarity subgraph at each moment is creatively obtained first, and then the similarity subgraphs at all moments are merged to obtain a similarity composite graph and a trajectory similarity graph. In the process of constructing the similarity subgraph at each moment, in order to accurately mine the trajectory similarity, a similarity subgraph G at moment k is constructed based on the location data of multiple users at moment k. k =(V,E k ),include:

[0031] Step S21, similarity subgraph G k The node set V is the user set;

[0032] Step S22, repeat the following steps to construct a similarity subgraph G k The edge set E k :

[0033] Calculate the distance d between user i and user j based on the location data of user i and user j at time k ij ;

[0034] If the distance d ij is less than the preset distance threshold, then the edge set E k Add edge e ij ; If the distance d ij If the distance is not less than the preset threshold, then the edge set E is not added. k Add edge e ij ;

[0035] Where i≠j, i and j both represent the index of the user / node; k represents the time index.

[0036] In this embodiment, the distance d ij It can be obtained by calculating the Euclidean distance formula or the Haversine Formula.

[0037] Specifically, if the trajectory data is a two-dimensional coordinate on the plane, then the Euclidean distance calculation formula is used: the distance between node i and node j at time k is If the distance value d ij If the distance is less than the preset threshold T, then k Add edge e ij ;

[0038] If the trajectory data is the coordinate on the sphere, such as Indicates longitude, If it represents latitude, the distance d is calculated using the Haversine Formula ij :

[0039]

[0040] d ij =R·c

[0041] The latitude difference Longitude difference R is the radius of the earth. If dij If the distance is less than the threshold T, then go to E k Add edge e ij ; a represents the first intermediate quantity, and c represents the second intermediate quantity.

[0042] In this embodiment, the size of the preset distance threshold can be adaptively adjusted according to specific similarity measurement accuracy requirements. The larger the preset distance threshold, the higher the similarity measurement accuracy.

[0043] In this embodiment, for the construction of the similarity subgraph at time k, the node set of the similarity subgraph is first initialized as V, and the edge set E k is empty, and there are n users, then repeat step S22 for a total of times until the distance between each pair of nodes is calculated once. After the edge is added, the trajectory similarity subgraph G at time k is obtained. k It can be seen that there may be a situation in the similarity subgraph where there is no edge connection between two nodes.

[0044] In a preferred embodiment, the similarity subgraphs at all times are represented as a similarity subgraph set {G1, G2, ..., G m In order to quickly and accurately merge the similarity subgraphs at all times, preferably, in step S3, merging the similarity subgraphs at multiple times to obtain a similarity composite graph includes:

[0045] Step S31, obtaining the union of edge sets of similarity subgraphs at multiple moments to obtain an edge set of a similarity composite graph;

[0046] Step S32: Using the node set of the similarity subgraph as the node set of the similarity composite graph.

[0047] In this embodiment, the similarity composite graph is represented by G0=(V, E0), where the edge set E0=E1∪E2∪…∪E m-1 ∪E m It can be seen that there may be a situation where there is no edge connection between two nodes in the similarity composite graph.

[0048] In a preferred embodiment, the trajectory similarity graph is represented by G = (V, E, W), where the edge set E of the trajectory similarity graph includes the edge connecting any two nodes, that is, it includes all edge cases, W represents the weight set composed of the weights of all edges of the trajectory similarity graph, and the edge e connecting node i and node j ij The weight is represented by w ij , w ij ≥0. When w ij = 0, it means that there is no edge between node i and node j. In order to make the trajectory similarity graph accurately express the trajectory similarity between users, the process of generating the trajectory similarity graph through the similarity composite graph is as follows:

[0049] The statistical similarity subgraph set {G1,G2,…,G m}, the frequency range of frequency is [0,m]. Let w ij Represents edge e ij The frequency of occurrence, traversing {G1, G2, ..., G m}, if e ij appears in a similarity subgraph, then w ij Increase by 1, so w ij The value range of is [0,m], and finally we get the trajectory similarity graph G = (V,E,W), whose edge set E contains all possible edges, and W is the weight set on its edge. The weight set is w ij A collection of .

[0050] In a preferred embodiment, in order to better implement differential privacy protection for user trajectory data, in step S5, in the step of adding noise to the edge weights of the trajectory similarity graph, the edge e ij The weight w ij After adding noise,

[0051]

[0052] Among them, ∈ represents the privacy budget parameter; x represents the added noise.

[0053] In this embodiment, the added noise x is preferably but not limited to Gaussian noise or Laplace noise. When it is Laplace noise, the added noise x satisfies the following probability distribution, which is obtained by applying the following probability distribution.

[0054]

[0055] Wherein, b is a scale parameter, which can be set to: b=1.

[0056] In this implementation, by introducing the differential privacy mechanism, the goal of effectively balancing data availability and privacy protection in the process of trajectory similarity publication is achieved, solving the key problem of trajectory data privacy protection. An attacker cannot infer the trajectory path of a specific user by obtaining the published noisy trajectory similarity graph.

[0057] The present invention also discloses a differential privacy trajectory similarity publishing device, which is used to implement the above-mentioned differential privacy trajectory similarity publishing method. In a preferred embodiment, it includes:

[0058] A location data acquisition module, which acquires location data of multiple users at multiple times;

[0059] A similarity subgraph construction module is used to construct a similarity subgraph at each moment based on the location data of multiple users at each moment, wherein the nodes in the similarity subgraph correspond to the users one by one, and any edge in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the moment of the similarity subgraph is less than a preset distance threshold;

[0060] A merging module merges similarity subgraphs at multiple moments to obtain a similarity composite graph;

[0061] A trajectory similarity graph generation module sets the weight of each edge in the similarity composite graph according to the frequency of each edge appearing in the similarity subgraphs at multiple moments, thereby obtaining a trajectory similarity graph;

[0062] A noise adding module adds noise to the edge weights of the trajectory similarity graph to obtain a noisy trajectory similarity graph;

[0063] Release module, releases the trajectory similarity graph after adding noise.

[0064] In this embodiment, the position data acquisition module, the similarity subgraph construction module, the similarity subgraph construction module, the merging module, the trajectory similarity graph generation module, the noise addition module, and the publishing module correspond one-to-one to the above-mentioned steps S1, S2, S3, S4, S5, and S6, and are not repeated here.

[0065] The present invention also discloses a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the above-mentioned differential privacy trajectory similarity publishing method provided by the present invention are implemented. The computer program product should be understood as a software product that mainly implements its solution through a computer program, such as a program product integrated in the cloud or a software library.

[0066] The present invention also discloses an electronic device. In one embodiment, the electronic device includes at least one processor; and a memory connected to the at least one processor in communication; wherein:

[0067] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a differential privacy trajectory similarity publishing method provided by the present invention.

[0068] like Figure 2 , which is a schematic diagram of the structure of an electronic device of a differential privacy trajectory similarity publishing method provided by an embodiment of the present invention. The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a differential privacy trajectory similarity publishing method program.

[0069] Among them, the processor 10 can be composed of an integrated circuit in some embodiments, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the program or module stored in the memory 11 (for example, executing a differential privacy trajectory similarity publishing method, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device and process data.

[0070] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of a differential privacy trajectory similarity publishing method program, but also can be used to temporarily store data that has been output or is to be output.

[0071] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0072] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0073] Figure 2 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0074] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0075] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited by this structure.

[0076] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0077] The present invention also discloses a user trajectory similarity analysis method. In a preferred embodiment, referring to Figure 3 As shown, including:

[0078] Step 100: The server publishes a noisy trajectory similarity graph to the analysis end, where the noisy trajectory similarity graph is obtained according to the above-mentioned differential privacy trajectory similarity publishing method;

[0079] Step 200: The analysis end identifies users whose trajectories are similar to the target user based on the obtained noisy trajectory similarity graph.

[0080] In this embodiment, in step 200, the analysis end can read out the weight of the edge between two nodes (users) in the trajectory similarity graph after adding noise and use it as the trajectory similarity of the two users. Users whose trajectory similarity with the target user is greater than a preset weight threshold are regarded as users with similar trajectories to the target user, wherein the preset weight threshold can be customized according to the numerical range of the weight of the edge in the trajectory similarity graph, such as 1 / 2 to 4 / 5 times the weight of the largest edge, or the median of the weights of all edges.

[0081] In this embodiment, in order to facilitate intuitive observation of users with similar trajectories to the target user, the users with similar trajectories to the target user selected according to the above method are marked with the same label, and the label form is preferably but not limited to node color rendering or node highlighting or text label.

[0082] The above method of directly determining users with similar trajectories to the target user by edge weight is only suitable for users with direct edges connected to the target user, and cannot analyze the trajectory similarity between users with no direct edges connected to the target user and the target user. In order to fully obtain the trajectory similarity between the user and the target user, preferably, step 200 includes:

[0083] Step 201, replacing the weights of the edges in the noisy trajectory similarity graph with the inverse of the edge weights to obtain an updated trajectory similarity graph;

[0084] Step 202, obtaining the shortest path between the target user / target node and the remaining users / nodes (users / nodes other than the target user / target node in the update trajectory similarity graph) in the update trajectory similarity graph, where the length of the path is the sum of the weights of the edges it passes through;

[0085] Step 203, sort the remaining users / nodes from small to large according to their shortest paths to the target user / target node to obtain a user / node sequence;

[0086] Step 204: extract the first X users / nodes in the user / node sequence as users with similar trajectories to the target user and output them. X is a positive integer.

[0087] The present invention also discloses an analysis system based on the above-mentioned user trajectory similarity analysis method. In a preferred embodiment, referring to Figure 4 As shown, the analysis system includes a server and one or more analysis terminals, and the server is connected to communicate with the one or more analysis terminals respectively.

[0088] In this embodiment, the server may be a server, a personal computer, a cloud platform, etc., and may be the owner of user trajectory data (location data of multiple users at multiple times). The analysis end is an electronic device of a service provider (data analyst), and may be a server, a personal computer, a cloud platform, a terminal device, etc. The server and the analysis end may be connected via the Internet or a local area network.

[0089] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "an implementation", "a preferred implementation" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0090] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A differentially private trajectory similarity publishing method, characterized in that: include: Obtain location data of multiple users at multiple times; Based on the location data of multiple users at each moment, a similarity subgraph is constructed at each moment, wherein the nodes in the similarity subgraph correspond to the users one by one, and any edge in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the moment to which the similarity subgraph belongs is less than a preset distance threshold; Merge similarity subgraphs at multiple moments to obtain a similarity composite graph; The weight of each edge in the similarity composite graph is set according to the frequency of occurrence of each edge in the similarity subgraphs at multiple moments, so as to obtain a trajectory similarity graph; Add noise to the weights of the edges of the trajectory similarity graph to obtain a noisy trajectory similarity graph; Publish a similarity graph of the trajectories after adding noise.

2. A differential privacy trajectory similarity publishing method as claimed in claim 1, characterized in that: Construct a similarity subgraph G at time k based on the location data of multiple users at time k k =(V,E k ),include: Similarity subgraph G k The node set V is the user set; Repeat the following steps to construct the similarity subgraph G k The edge set E k : Calculate the distance d between user i and user j based on the location data of user i and user j at time k ij ; If the distance d ij is less than the preset distance threshold, then the edge set E k Add edge e ij ; If the distance d ij If the distance is not less than the preset threshold, then the edge set E is not added. k Add edge e ij ; Where i≠j, i and j both represent the index of the user / node; k represents the time index.

3. A differential privacy trajectory similarity publishing method as described in claim 1 or 2, characterized in that: The step of merging the similarity subgraphs at multiple moments to obtain a similarity composite graph includes: The edge set of the similarity composite graph is obtained by obtaining the union of the edge sets of the similarity subgraphs at multiple moments; The node set of the similarity subgraph is used as the node set of the similarity composite graph.

4. A differential privacy trajectory similarity publishing method as claimed in claim 3, characterized in that: The trajectory similarity graph is represented as G = (V, E, W), where the edge set E of the trajectory similarity graph includes the edges connecting any two nodes, W represents the weight set composed of the weights of all the edges of the trajectory similarity graph, and the edge e connecting node i and node j ij The weight is represented by w ij , w ij ≥0.

5. A differential privacy trajectory similarity publishing method as claimed in claim 4, characterized in that: In the step of adding noise to the edge weights of the trajectory similarity graph, the edge e ij The weight w ij After adding noise, Among them, ∈ represents the privacy budget parameter; x represents the added noise.

6. A differential privacy trajectory similarity publishing device, used to implement a differential privacy trajectory similarity publishing method according to any one of claims 1 to 5, characterized in that: include: A location data acquisition module, which acquires location data of multiple users at multiple times; A similarity subgraph construction module is used to construct a similarity subgraph at each moment based on the location data of multiple users at each moment, wherein the nodes in the similarity subgraph correspond to the users one by one, and any edge in the similarity subgraph indicates that the distance between the two users corresponding to the two nodes connected by the edge at the moment of the similarity subgraph is less than a preset distance threshold; A merging module merges similarity subgraphs at multiple moments to obtain a similarity composite graph; A trajectory similarity graph generation module sets the weight of each edge in the similarity composite graph according to the frequency of each edge appearing in the similarity subgraphs at multiple moments, thereby obtaining a trajectory similarity graph; A noise adding module adds noise to the edge weights of the trajectory similarity graph to obtain a noisy trajectory similarity graph; Release module, releases the trajectory similarity graph after adding noise.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a differentially private trajectory similarity publishing method as described in any one of claims 1 to 5.

9. A user trajectory similarity analysis method, characterized in that: include: The server publishes a noisy trajectory similarity graph to the analysis end, wherein the noisy trajectory similarity graph is obtained according to a differentially private trajectory similarity publishing method according to any one of claims 1 to 5; The analysis end identifies users whose trajectories are similar to the target user based on the obtained noisy trajectory similarity graph.

10. An analysis system based on the user trajectory similarity analysis method according to claim 9, characterized in that: It includes a server and one or more analysis terminals, wherein the server is connected to communicate with the one or more analysis terminals respectively.

Images