Trajectory data desensitization method and device, electronic equipment and readable storage medium

Abstract

The application provides a trajectory data desensitization method and device, electronic equipment and a readable storage medium, and relates to the technical field of data processing. A source coordinate data set is obtained, the source coordinate data set represents a driving trajectory and includes at least one sensitive coordinate data, and the sensitive coordinate data has a sensitive mark generated when data is collected. Then, based on a preset data construction rule and the sensitive mark of the sensitive coordinate data, the source coordinate data set is desensitized to obtain a target desensitized data set that retains trajectory features of the driving trajectory. In this way, manpower can be saved, and desensitization efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, apparatus, electronic device, and readable storage medium for de-identifying trajectory data. Background Technology

[0002] Data, as a resource, possesses unique significance for humanity due to its universality, shareability, value-added nature, processability, and versatility. However, during storage, processing, and exchange, data is susceptible to leakage, interception, eavesdropping, tampering, and forgery. Data anonymization, as an important data security measure, can effectively reduce the exposure of sensitive data during collection, transmission, and use, thereby mitigating the risk of sensitive data leakage and ensuring data security and compliance.

[0003] For example, driving trajectory data may contain some personal privacy data or sensitive data that cannot be published. Current technology typically involves manually searching for sensitive data in the trajectory data and replacing or deleting it to achieve desensitization. However, this is extremely labor-intensive and inefficient. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, electronic device, and readable storage medium for desensitizing trajectory data, so as to improve the problems existing in the prior art.

[0005] The embodiments of the present invention can be implemented as follows:

[0006] In a first aspect, the present invention provides a method for de-identifying trajectory data, comprising:

[0007] Obtain a source coordinate data set, which represents the driving trajectory and includes at least one sensitive coordinate data, which carries a sensitive marker generated during data acquisition;

[0008] Based on preset data construction rules and sensitive markers of the sensitive coordinate data, the source coordinate data set is desensitized to obtain a target desensitized data set, which retains the trajectory features of the driving trajectory.

[0009] In an optional implementation, the step of desensitizing the source coordinate data set based on preset data construction rules and sensitive tags of the sensitive coordinate data to obtain the target desensitized data set includes:

[0010] Perform coordinate transformation on each coordinate data in the source coordinate data set to convert it from the geodetic coordinate system to the Cartesian coordinate system, and obtain the first coordinate data set after transformation;

[0011] The first coordinate data set is deduplicated to obtain a deduplicated coordinate data set.

[0012] Based on each of the sensitive markers and the data construction rules, the de-identified coordinate data set is de-identified to obtain at least one target de-identified data set.

[0013] In an optional implementation, before the step of deduplicating the first coordinate data set to obtain a deduplicated coordinate data set, the method further includes:

[0014] Calculate the expected value and variance of the first coordinate data set.

[0015] In an optional implementation, the step of deduplicating the first coordinate data set to obtain a deduplicated coordinate data set includes:

[0016] Perform a Discrete Fourier Transform on the first coordinate data set, and perform windowing processing on the time-domain sampling of the continuous signal to obtain a discrete deduplicated coordinate data set.

[0017] In an optional implementation, the step of desensitizing the deduplicated coordinate data set based on each of the sensitive markers and the data construction rules to obtain at least one of the target desensitized data sets includes:

[0018] Find the sensitive coordinate data corresponding to the sensitive marker from the de-identified coordinate data set, and remove the sensitive coordinate data to obtain the de-identified coordinate data set after anonymization.

[0019] Based on the data construction rules and the de-identified and deduplicated coordinate data set, at least one second coordinate data set is constructed using an interpolation method; wherein, the data construction rule is that the expected value and variance of the second coordinate data set are equal to the expected value and variance of the first coordinate data set, respectively;

[0020] Each of the second coordinate data sets is used as the target de-identified data set.

[0021] In an optional implementation, the interpolation method is Lagrange interpolation or spline interpolation.

[0022] In a second aspect, the present invention provides a trajectory data desensitization device, comprising:

[0023] The data acquisition module is used to acquire a source coordinate data set, which represents the driving trajectory and includes at least one sensitive coordinate data, which carries a sensitive marker generated during data acquisition.

[0024] The data processing module is used to perform desensitization processing on the source coordinate data set based on preset data construction rules and sensitive tags of the sensitive coordinate data to obtain a target desensitized data set, wherein the target desensitized data set retains the trajectory features of the driving trajectory.

[0025] In an optional implementation, the data processing module is specifically used for:

[0026] Perform coordinate transformation on each coordinate data in the source coordinate data set to convert it from the geodetic coordinate system to the Cartesian coordinate system, and obtain the first coordinate data set after transformation;

[0027] The first coordinate data set is deduplicated to obtain a deduplicated coordinate data set.

[0028] Based on each of the sensitive markers and the data construction rules, the de-identified coordinate data set is de-identified to obtain at least one target de-identified data set.

[0029] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor executes the machine-readable instructions to implement the trajectory data desensitization method as described in any of the foregoing embodiments.

[0030] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the trajectory data desensitization method described in any of the foregoing embodiments.

[0031] Compared with existing technologies, embodiments of the present invention provide a trajectory data anonymization method, apparatus, electronic device, and readable storage medium. The method involves acquiring a source coordinate data set, which represents a driving trajectory and includes at least one sensitive coordinate data point with a sensitive marker generated during data acquisition. Then, based on preset data construction rules and the sensitive markers of the sensitive coordinate data, the source coordinate data set is anonymized to obtain a target anonymized data set that retains the trajectory characteristics of the driving trajectory. This approach saves manpower and improves anonymization efficiency. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0034] Figure 2 This is one of the flowcharts illustrating a trajectory data desensitization method provided in an embodiment of the present invention.

[0035] Figure 3 This is a second schematic flowchart of a trajectory data desensitization method provided in an embodiment of the present invention.

[0036] Figure 4 This is a schematic diagram of a data processing procedure provided in an embodiment of the present invention.

[0037] Figure 5 This is a schematic diagram showing the trajectory comparison before and after desensitization provided in an embodiment of the present invention.

[0038] Figure 6 This is a schematic diagram of a trajectory data desensitization device provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0040] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0041] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0042] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0043] This invention provides a trajectory data anonymization method, which can anonymize a source coordinate data set based on preset data construction rules and sensitive markers for sensitive coordinate data, thereby obtaining a target anonymized data set that retains the trajectory features of the driving trajectory. This saves manpower and improves anonymization efficiency. The following detailed description, through embodiments and in conjunction with the accompanying drawings, illustrates this method.

[0044] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes a processor 110, a memory 120, and a bus 130, with the processor 110 connected to the memory 120 via the bus 130.

[0045] The memory 120 can be used to store software programs and modules, such as the program instructions / modules corresponding to the trajectory data desensitization device 200 provided in the embodiments of the present invention. The processor 110 executes various functional applications and data processing, such as the trajectory data desensitization method provided in the embodiments of the present invention, by running the software programs and modules stored in the memory 120.

[0046] The memory 120 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0047] The processor 110 can be an integrated circuit chip with signal processing capabilities. The processor 110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0048] Optionally, the electronic device 100 may be, but is not limited to, a personal computer, a server, a smart car, etc.

[0049] Understandable. Figure 1 The structure shown is for illustrative purposes only; the electronic device 100 may also include components that are more advanced than those shown. Figure 1The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0050] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a trajectory data anonymization method provided in an embodiment of the present invention. The execution subject of this method can be the aforementioned electronic device, and the method includes the following steps:

[0051] S100, Obtain the source coordinate data set.

[0052] In this embodiment, the source coordinate data set can represent the driving trajectory and includes at least one sensitive coordinate data, each of which may carry a sensitive marker generated during data acquisition.

[0053] It is understood that the source coordinate dataset may include several coordinate data points, at least one of which is a sensitive coordinate data point with a sensitive label. Each coordinate data point in the source coordinate dataset may include latitude and longitude.

[0054] S200. Based on preset data construction rules and sensitive markers for sensitive coordinate data, the source coordinate data set is desensitized to obtain the target desensitized data set.

[0055] In this embodiment, the target desensitized data set retains the trajectory features of the driving trajectory, which are the shape features of the driving trajectory.

[0056] The trajectory data anonymization method provided in this invention obtains a source coordinate data set, which represents a driving trajectory and includes at least one sensitive coordinate data point. This sensitive coordinate data point carries a sensitive marker generated during data acquisition. Then, based on preset data construction rules and the sensitive markers of the sensitive coordinate data, the source coordinate data set is anonymized to obtain a target anonymized data set that retains the trajectory characteristics of the driving trajectory. This method saves manpower and improves anonymization efficiency.

[0057] In an optional implementation, to protect the data, the coordinate data needs to be transformed before the anonymization process. For the corresponding details, please refer to [link to relevant documentation]. Figure 3 The sub-steps of step S200 above may include S210 to S240.

[0058] S210. Perform coordinate transformation on each coordinate data in the source coordinate data set to convert it from the geodetic coordinate system to the Cartesian coordinate system, and obtain the first coordinate data set after transformation.

[0059] It can be understood that each coordinate data point in the source coordinate dataset is located in a geodetic coordinate system, while each coordinate data point in the first coordinate dataset is located in a Cartesian coordinate system. Converting common geodetic coordinate data to Cartesian coordinate data in this way can, to some extent, protect the data from being identified as specific location coordinates.

[0060] S220. Calculate the expected value and variance of the first coordinate data set.

[0061] S230. Perform deduplication on the first coordinate data set to obtain a deduplicated coordinate data set.

[0062] In an optional example, the driving trajectory may contain duplicate trajectories. Deduplication can remove the coordinate data corresponding to duplicate trajectories to avoid data redundancy. Sub-steps of S230 may include:

[0063] S231. Perform a discrete Fourier transform on the first coordinate data set, and perform windowing processing on the time-domain sampling of the continuous signal to obtain a discrete deduplicated coordinate data set.

[0064] In this embodiment, after performing a discrete Fourier transform on the first coordinate data set, there may be periodically changing discrete signals corresponding to the repeating trajectories. Windowing can remove the repeating periodically changing discrete signals.

[0065] S240. Based on each sensitive marker and data construction rule, desensitize the deduplicated coordinate data set to obtain at least one target desensitized data set.

[0066] In an optional example, the sub-steps of S240 may include S241 to S243:

[0067] S241. Find the sensitive coordinate data corresponding to the sensitive marker from the de-identified coordinate data set, and remove the sensitive coordinate data to obtain the de-identified coordinate data set.

[0068] S242. Based on the data construction rules and the de-identified and deduplicated coordinate data set, at least one second coordinate data set is constructed using the interpolation method.

[0069] In this embodiment, the data construction rule can be that the expected value and variance of the second coordinate data set are equal to the expected value and variance of the first coordinate data set, respectively.

[0070] In optional examples, the interpolation method can be Lagrange interpolation or spline interpolation.

[0071] S243. Treat each second coordinate data set as the target desensitized data set.

[0072] The second coordinate dataset that meets the data construction rules can guarantee the retention of trajectory features of the driving trajectory, so the second coordinate dataset can be used as the target de-identified dataset.

[0073] Please refer to Figure 4 The data desensitization process involved in steps S210-240 above can be as follows: Figure 4 As shown.

[0074] Combination Figure 4 The source coordinate data set, the first coordinate data set, the deduplicated coordinate data set, the anonymized deduplicated coordinate data set, and the second coordinate data set are respectively... Figure 4 Given sets A, B, B′, B″, and C, the data processing procedure for this scheme is as follows:

[0075] A coordinate transformation is performed on set A to obtain set B. A Fourier transform is then performed on set B to obtain set B′. Sensitive coordinates are then removed from set B′ to obtain set B″. Finally, set C is constructed using interpolation. The expected value E(C) and variance D(C) of set C are equal to the expected value E(B) and variance D(B) of set B, respectively.

[0076] exist Figure 4 Based on, combined Figure 5 , Figure 5 This is a schematic diagram comparing the trajectories before and after desensitization. Figure 5 The driving trajectory S1 corresponding to the source coordinate data set and the driving trajectory S2 corresponding to the target desensitized data set show that S2 retains the trajectory characteristics of S1, namely the trajectory shape.

[0077] Therefore, this solution starts with the data itself, employing Discrete Fourier Transform and data interpolation. First, a Fourier Transform is performed on the coordinate-transformed set, then sensitive coordinates are removed. Finally, a new set (i.e., the target-desensitized data set) is constructed through interpolation. This target-desensitized data set eliminates sensitive coordinates and, while preserving the trajectory characteristics of the driving trajectory, protects data security, making it usable for subsequent applications. Furthermore, the target-desensitized data set is irreversible; that is, the source coordinate data set cannot be derived from this new set.

[0078] To facilitate the explanation of the embodiments of this solution, combined with Figure 4 Here is a specific example.

[0079] Suppose set A (the source coordinate data set) contains a total of 62 coordinate data points, separated by commas. Data points marked with a sensitivity flag are sensitive coordinate data. Set A can be represented as follows:

[0080] [(114.266434 30.527505), (114.266670 30.527325), (114.26692230.527145), (114.267185 30.527357), (114.267485 30.527671), (114.26760330.527829), (114.267759 30.528060), (114.267855 30.528175 Sensitive (Main Water Gate)), (114.26807530.528078), (114.268274] 30.527972), (114.26849930.528328), (114.26874030.528720), (114.269014 30.529118), (114.26959330.529977 Sensitive (Dock)), (114.26933030.530102), (114.269668 30.530629), (114.269990 30.531165), (114.27032330.531678), (114.266434 30.527505), (114.266670) 30.527325), (114.26679330.527228), (114.266932 30.527145), (114.267179 30.527353), (114.26742130.527588), (114.267662 30.527907), (114.267855 30.528175 Sensitive (Main Water Gate)), (114.268097 30.528060), (114.268274 30.527972), (114.268483 30.528300), (114.268805 30.528813), (114.269159 30.529330), (114.269405 30.529686), (114.269593 30.529977 Sensitive (Dock)), (114.269502 30.530023), (114.26934130.530107), (114.26968430.530647), (114.269899 30.530961), (114.27013030.531382), (114.27032330.531678), (114.266434 30.527505), (114.26661630.527371), (114.26676130.527256), (114.266932 30.527145), (114.26716830.527339), (114.26740530.527574), (114.267598 30.527787), (114.26770030.527953), (114.26785530.528175 Sensitive (Water Main Gate)), (114.268080 30.528073), (114.26827930.527967), (114.268440 30.528231), (114.268633) 30.528540), (114.26886930.528896), (114.269186 30.529358), (114.269405 30.529686), (114.26959330.529977 Sensitive (Dock)), (114.269513 30.530023), (114.26934130.530107), (114.269636 30.530550), (114.269883 30.530971), (114.27011430.531350), (114.270323 30.531678)].

[0081] Perform coordinate transformation on each coordinate data in set A (from geodetic coordinate system to Cartesian coordinate system) to obtain set B (the first set of coordinate data). Set B can be represented as follows:

[0082] [(3381781.020690023 813443.2639875237)，(3381761.714707957813466.5010014758)，(3381742.453308832 813491.2742572038)，(3381766.697289668813515.8430988832)，(3381802.3566504447813543.636129179)，(3381820.2081693523813554.4570600989)，(3381846.2615704113 813568.6914936386)，(3381859.2829502556813577.5384511084)，(3381849.137800718 813598.9724471516)，(3381837.936062353813618.4192479695)，(3381878.044853337813638.875966588)，(3381922.1908421577813660.7528212012)，(3381967.094247505 813685.7784357041)，(3382063.974678638813738.6024436688)，(3382077.1050741477 813712.950264751)，(3382136.493725397813743.7044538299)，(3382196.8360571135813772.8932013756)，(3382254.6583380485813803.2116921693)，(3381781.020690023 813443.2639875237)，(3381761.714707957813466.5010014758)，(3381751.2993173953 813478.622097058)，(3381742.4811461284813492.2343561716)，(3381766.236966449813515.2799041519)，(3381792.9733558963813537.7584663709)，(3381829.0230292333 813559.8707274897)，(3381859.2829502556813577.5384511084)，(3381847.202777053 813601.1425489266)，(3381837.936062353813618.4192479695)，(3381874.8949527126813637.429908662)，(3381932.686054899813666.694131446)，(3381991.0100302976 813699.0173864777)，(3382031.1775360405813721.4896124864)，(3382063.974678638 813738.6024436688)，(3382068.8227724084813729.71773956)，(3382077.690244655813713.9902513853)，(3382138.5345963873813745.1826233624)，(3382173.957851916 813764.8133066269)，(3382221.292584894813785.6354943675)，(3382254.6583380485 813803.2116921693)，(3381781.020690023813443.2639875237)，(3381766.666021605813461.1685731541)，(3381754.3155776813475.4597508293)，(3381742.4811461284 813492.2343561716)，(3381764.6536748605813514.2688193796)，(3381791.3761408543 813536.2673402147)，(3381815.5362420906813554.1120994114)，(3381834.2304624673813563.3711202543)，(3381859.2829502556813577.5384511084)，(3381848.597199923 813599.4685764181)，(3381837.3954623323813618.9153787384)，(3381867.122752053 813633.5235158161)，(3381901.9299203474813651.0590563683)，(3381942.0694367695813672.5715977013), (3381994.1905859467813701.5194931328), (3382031.1775360405 813721.4896124864), (3382063.974678638813738.6024436688), (3382068.8534194157 813730.773818465), (3382077.690244655813713.9902513853), (3382127.6430676556813740.8865128392), (3382175.0223189276813763.2450175718), (3382217.6990356008 813784.2024133983), (3382254.6583380485813803.2116921693)].

[0083] Next, we can calculate the expected value E(B) and variance D(B) of set B. Then, we perform a discrete Fourier transform on set B, and window the time-domain samples of the continuous signal once. This gives us a discrete signal data set B′ of finite length, as shown below:

[0084] [(3381781.020690023 813443.2639875237), (3381761.714707957813466.5010014758), (3381742.453308832 813491.2742572038), (3381766.697289668813515.8430988832), (3381802.3566504447813543.636129179), (3381820.2081693523813554.4570600989), (3381846.2615704113] 813568.6914936386), (3381859.2829502556813577.5384511084), (3381849.137800718 813598.9724471516), (3381837.936062353813618.4192479695), (3381878.044853337813638.875966588), (3381922.1908421577813660.7528212012), (3381967.094247505 813685.7784357041), (3382063.974678638813738.6024436688), (3382077.1050741477 813712.950264751), (3382136.493725397813743.7044538299), (3382196.8360571135813772.8932013756), (3382254.6583380485813803.2116921693)]

[0085] Then, data replacement is required: Based on set B′, sensitive coordinates are removed to obtain set B″. Then, based on set B″, interpolation is used to obtain set C, ensuring that the expected value E(C) and variance D(C) of set C are equal to the expected value E(B) and variance D(B) of set B, respectively. Set C can be shown as follows:

[0086] [(813443.2639875237 3381781.020690023), (813466.50100147583381761.714707957), (813491.2742572038 3381742.453308832), (813515.84309888323381766.697289668), (813543.6361291793381802.3566504447), (813554.45706009893381820.2081693523), (813564.8011233893 3381837.9348752997), (813576.28137665733381833.050915622), (813590.3345896639 3381828.9075825433), (813615.7560100563381820.432086304), (813634.0035602873381867.136677474), (813651.05905636833381901.9299203474), (813666.7102195035 3381932.1315300474), (813684.76739692013381965.5109359445), (813696.122124282 3381984.8211118965), (813683.49898535283381992.668729379), (813680.54052032273382021.7754576323), (813696.7744000193382048.442104805), (813733.998210032 3382116.6763148573), (813756.43080504963382161.504730725), (813789.0846966497 3382224.944655625), (813803.21169216933382254.6583380485)]

[0087] Therefore, the above set C is the target de-identified data set corresponding to set A (source coordinate data set).

[0088] It should be noted that the above examples are merely illustrative and are not intended to be limiting. Furthermore, the execution order of each step in the above method embodiments is not limited to what is shown in the accompanying drawings; the execution order of each step depends on the actual application.

[0089] In order to perform the corresponding steps in the above method embodiments and various possible implementations, an implementation method of the trajectory data desensitization device is given below.

[0090] Please see Figure 6 , Figure 6 A schematic diagram of the trajectory data desensitization device provided in an embodiment of the present invention is shown. The trajectory data desensitization device 200 includes: a data acquisition module 210 and a data processing module 220.

[0091] The data acquisition module 210 is used to acquire a source coordinate data set, which represents the driving trajectory and includes at least one sensitive coordinate data, which carries a sensitive marker generated during data acquisition.

[0092] The data processing module 220 is used to perform desensitization processing on the source coordinate data set based on preset data construction rules and sensitive markers of sensitive coordinate data to obtain the target desensitized data set, which retains the trajectory features of the driving trajectory.

[0093] In an optional implementation, the data processing module 220 may be specifically used to: perform coordinate transformation on each coordinate data of the source coordinate data set to transform it from the geodetic coordinate system to the Cartesian coordinate system, to obtain a first coordinate data set after transformation; calculate the mathematical expectation and variance of the first coordinate data set; perform deduplication processing on the first coordinate data set to obtain a deduplicated coordinate data set; and desensitize the deduplicated coordinate data set based on each sensitive marker and data construction rule to obtain at least one target desensitized data set.

[0094] In an optional implementation, the data processing module 220 is used to perform deduplication processing on the first coordinate data set. Specifically, when obtaining the deduplicated coordinate data set, it can be used to: perform a discrete Fourier transform on the first coordinate data set, and perform windowing processing on the time-domain sampling of the continuous signal to obtain a discrete deduplicated coordinate data set.

[0095] In an optional implementation, when the data processing module 220 desensitizes the deduplicated coordinate data set based on each sensitive marker and data construction rule to obtain at least one target desensitized data set, it can specifically be used to: find the sensitive coordinate data corresponding to the sensitive marker in the deduplicated coordinate data set, and remove the sensitive coordinate data to obtain the desensitized deduplicated coordinate data set; construct at least one second coordinate data set using interpolation based on the data construction rule and the desensitized deduplicated coordinate data set; wherein the data construction rule is that the expected value and variance of the second coordinate data set are equal to the expected value and variance of the first coordinate data set, respectively; and use each second coordinate data set as a target desensitized data set.

[0096] In an optional implementation, the interpolation method is either Lagrange interpolation or spline interpolation.

[0097] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the trajectory data desensitization device 200 described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0098] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the trajectory data desensitization method disclosed in the above embodiments. The computer-readable storage medium can be, but is not limited to, various media capable of storing program code, such as a USB flash drive, portable hard drive, ROM, RAM, PROM, EPROM, EEPROM, FLASH disk, or optical disk.

[0099] In summary, this invention provides a trajectory data anonymization method, apparatus, electronic device, and readable storage medium. It acquires a source coordinate data set, which represents a driving trajectory and includes at least one sensitive coordinate data point with a sensitive marker generated during data acquisition. Then, based on preset data construction rules and the sensitive markers of the sensitive coordinate data, the source coordinate data set is anonymized to obtain a target anonymized data set that retains the trajectory characteristics of the driving trajectory. This approach saves manpower and improves anonymization efficiency.

[0100] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for desensitizing trajectory data, characterized in that, include: Obtain a source coordinate data set, which represents the driving trajectory and includes at least one sensitive coordinate data, which carries a sensitive marker generated during data acquisition; Each coordinate data in the source coordinate data set is transformed from the geodetic coordinate system to the Cartesian coordinate system to obtain the first transformed coordinate data set. After calculating the expected value and variance of the first coordinate data set, the first coordinate data set is deduplicated to obtain a deduplicated coordinate data set. Find each sensitive coordinate data containing the sensitive marker from the de-identified coordinate data set, and remove each sensitive coordinate data to obtain the de-identified coordinate data set after anonymization. Based on the preset data construction rules and the de-identified and deduplicated coordinate data set, at least one second coordinate data set is constructed using an interpolation method; wherein, the data construction rule is that the expected value and variance of the second coordinate data set are equal to the expected value and variance of the first coordinate data set, respectively; Each of the second coordinate data sets is used as a target desensitized data set, which retains the trajectory features of the driving trajectory.

2. The method according to claim 1, characterized in that, The step of deduplicating the first coordinate data set to obtain a deduplicated coordinate data set includes: Perform a Discrete Fourier Transform on the first coordinate data set, and perform windowing processing on the time-domain sampling of the continuous signal to obtain a discrete deduplicated coordinate data set.

3. The method according to claim 1, characterized in that, The interpolation method is either Lagrange interpolation or spline interpolation.

4. A trajectory data desensitization device, characterized in that, include: The data acquisition module is used to acquire a source coordinate data set, which represents the driving trajectory and includes at least one sensitive coordinate data, which carries a sensitive marker generated during data acquisition. The data processing module is used for: Each coordinate data in the source coordinate data set is transformed from the geodetic coordinate system to the Cartesian coordinate system to obtain the first transformed coordinate data set. After calculating the expected value and variance of the first coordinate data set, the first coordinate data set is deduplicated to obtain a deduplicated coordinate data set. Find each sensitive coordinate data containing the sensitive marker from the de-identified coordinate data set, and remove each sensitive coordinate data to obtain the de-identified coordinate data set after anonymization. Based on the preset data construction rules and the de-identified and deduplicated coordinate data set, at least one second coordinate data set is constructed using an interpolation method; wherein, the data construction rule is that the expected value and variance of the second coordinate data set are equal to the expected value and variance of the first coordinate data set, respectively; Each of the second coordinate data sets is used as a target desensitized data set, and the target desensitized data set retains the trajectory features of the driving trajectory.

5. An electronic device, characterized in that, include: The electronic device includes a memory and a processor, the memory storing machine-readable instructions executable by the processor, which, when the electronic device is in operation, are executed by the processor to implement the trajectory data desensitization method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the trajectory data desensitization method according to any one of claims 1-3.

Images