Desensitization data collection method, apparatus, device, and storage medium

Abstract

This application discloses a method, apparatus, device, and storage medium for collecting anonymized data, relating to the field of data processing technology. The disclosed method includes: upon receiving a vehicle locking command, shutting down the vehicle's internal processes and disconnecting the vehicle's communication channel to put the vehicle into an offline state; when the vehicle is offline and data to be anonymized is detected, anonymizing the data to obtain target data; storing the target data in the vehicle's internal storage system and controlling the vehicle to power off; and when the vehicle is powered on again and reconnected to the network, uploading the target data to the cloud. This solution uses offline anonymization to collect anonymized data to avoid excessive consumption of computing power and load during vehicle operation, reducing system stability risks and ensuring the stability of anonymized data collection on low-computing-power platforms.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device and storage medium for de-identified data acquisition. Background Technology

[0002] The competition in the intelligent driving industry has shifted from algorithms and hardware to data. The ability to accumulate high-quality data is a crucial advantage in gaining a competitive edge. Among the vast amounts of driving data, in-vehicle camera data is key to accelerating the iteration of intelligent driving models, providing a superior driving experience, and enhancing brand competitiveness. However, with the development of national data security, the requirements for vehicle-side data are becoming increasingly stringent. Automakers must comply with legal and regulatory requirements to anonymize in-vehicle camera data before acquiring it.

[0003] Currently, the industry primarily uses online real-time data masking for vehicle camera data processing, running a single target detection model to mask data from cameras of different specifications. Online data masking leads to a significant increase in load, resulting in decreased system stability, especially for low-computing-power platforms.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a method, apparatus, device and storage medium for collecting de-identified data, aiming to solve the technical problem of how to ensure the stability of a low-computing-power platform during the collection of de-identified data.

[0006] To achieve the above objectives, this application proposes a method for collecting de-identified data, the method comprising:

[0007] Upon receiving a vehicle lock command, the vehicle's internal processes are shut down and the vehicle's communication channels are disconnected to put the vehicle into an offline state.

[0008] When the vehicle is offline and the data to be de-identified is detected, the data to be de-identified is de-identified to obtain the target data;

[0009] The target data is stored in the vehicle's internal storage system, and the vehicle is powered off.

[0010] When the vehicle is powered on again and is connected to the network again, the target data will be uploaded to the cloud.

[0011] In one embodiment, before the step of shutting down the vehicle's internal processes and disconnecting the vehicle's communication channel to put the vehicle into an offline state upon receiving a vehicle lock command, the method further includes:

[0012] When the vehicle is in a preset scenario, obtain the camera flag position corresponding to the preset scenario;

[0013] Based on the camera flag, the corresponding vehicle camera is controlled to collect video data to obtain the data to be de-identified.

[0014] In one embodiment, the step of desensitizing the data to be desensitized to obtain the target data when the vehicle is offline and the data to be desensitized is detected includes:

[0015] When the vehicle is offline and the data to be de-identified is detected, the camera flag bit of the data to be de-identified is obtained;

[0016] The data to be de-identified is de-identified based on the camera flag to obtain the target data.

[0017] In one embodiment, the step of desensitizing the data to be desensitized based on the camera flag bit to obtain the target data includes:

[0018] The corresponding target detection model is obtained based on the camera flags;

[0019] Based on the target detection model, the sensitive information regions of the data to be de-identified are identified, and the data in the sensitive information regions is de-identified to obtain the target data.

[0020] In one embodiment, the step of desensitizing the data to be desensitized to obtain the target data when the vehicle is offline and the data to be desensitized is detected includes:

[0021] When the vehicle is offline and data to be desensitized is detected, the power-down delay duration is obtained;

[0022] The data to be desensitized is desensitized within the specified power-off delay period to obtain the target data.

[0023] In one embodiment, the step of desensitizing the data to be desensitized within the delayed power-off time to obtain the target data includes:

[0024] When all the data to be desensitized is desensitized within the specified power-down delay period, the desensitized data to be desensitized will be used as the target data.

[0025] When the time for desensitizing the data to be desensitized reaches the power-down delay time, the data to be desensitized after desensitization is taken as the target data, and the data to be desensitized before desensitization is saved.

[0026] In one embodiment, the step of uploading the target data to the cloud when the vehicle is powered on again and the vehicle is connected to the network again includes:

[0027] Iterate through the list of camera flags and obtain the current camera flag based on the list of camera flags;

[0028] When the vehicle is powered on again and the vehicle is connected to the network again, the current upload event data is obtained from the target data based on the current camera flag, and the current upload event data is uploaded to the cloud;

[0029] When the current upload event data is completed, the next camera flag is obtained based on the camera flag list, the next upload event data is obtained from the target data based on the next camera flag, and the next upload event data is uploaded to the cloud, until all the target data is uploaded.

[0030] Furthermore, to achieve the above objectives, this application also proposes a de-identified data acquisition device, which includes:

[0031] The offline control module is used to shut down the vehicle's internal processes and disconnect the vehicle's communication channel to put the vehicle into an offline state when a vehicle lock command is received.

[0032] The data desensitization module is used to desensitize the data to be desensitized when the vehicle is offline and the data to be desensitized is detected, so as to obtain the target data.

[0033] The vehicle power-off module is used to store the target data in the vehicle's internal storage system and control the vehicle to power off.

[0034] The data upload module is used to upload the target data to the cloud when the vehicle is powered on again and the vehicle is connected to the network again.

[0035] In addition, to achieve the above objectives, this application also proposes a de-identified data acquisition device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the de-identified data acquisition method described above.

[0036] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the de-identified data acquisition method described above.

[0037] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the de-identified data acquisition method described above.

[0038] One or more technical solutions proposed in this application have at least the following technical effects:

[0039] This embodiment provides a method for collecting anonymized data. Upon receiving a vehicle lock command, the vehicle's internal processes are shut down and its communication channels are disconnected to put the vehicle into an offline state. When the vehicle is offline and data to be anonymized is detected, the data to be anonymized is anonymized to obtain target data. The target data is stored in the vehicle's internal storage system, and the vehicle is powered off. When the vehicle is powered on again and reconnected to the network, the target data is uploaded to the cloud. This offline anonymization method avoids excessive consumption of computing power and load during vehicle operation, reduces system stability risks, and ensures the stability of anonymized data collection on low-computing-power platforms. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart illustrating an embodiment of the data anonymization collection method of this application.

[0043] Figure 2 This is a flowchart illustrating Embodiment 2 of the data anonymization collection method of this application.

[0044] Figure 3 This is a schematic diagram of the module structure of the data desensitization acquisition device according to an embodiment of this application;

[0045] Figure 4 This is a schematic diagram of the hardware operating environment involved in the data desensitization acquisition method in the embodiments of this application.

[0046] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0047] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0048] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0049] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or intelligent driving domain controller capable of performing the above functions. The following description uses an intelligent driving domain controller as an example to illustrate this embodiment and the subsequent embodiments.

[0050] Based on this, the embodiments of this application provide a method for collecting de-identified data, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the data desensitization acquisition method of this application.

[0051] In this embodiment, the de-identified data acquisition method includes steps S10 to S40:

[0052] Step S10: Upon receiving a vehicle lock command, shut down the vehicle's internal processes and disconnect the vehicle's communication channel to put the vehicle into an offline state;

[0053] It's important to note that when a vehicle lock command is received, it indicates that the vehicle has been locked by either the key or the application (APP). At this point, all the vehicle's controllers will gradually cease communication. During this process, the intelligent driving domain controller will monitor the application message transmission status of other units. When it detects that other units are no longer sending application messages, it will kill various internal processes of the vehicle and disconnect external communication, effectively shutting down the vehicle's internal processes and disconnecting its communication channels to put the vehicle into an offline state. Specifically, a unit refers to the ECU (Electronic Control Unit) in the vehicle, which is responsible for different functions such as engine control and the braking system. Application messages refer to the data information transmitted between these units through the vehicle bus system.

[0054] It should be understood that when the intelligent driving domain controller detects that the ECUs are no longer sending data, directly shutting down the vehicle's internal processes and putting the vehicle into an offline state can quickly release computing resources, reduce system load, and allow the vehicle to quickly enter the desensitized data acquisition state, thereby improving data acquisition efficiency.

[0055] In one feasible implementation, before step S10, the following steps may be included: when the vehicle is in a preset scenario, obtaining the camera flag corresponding to the preset scenario; controlling the corresponding vehicle camera to collect video data based on the camera flag to obtain the data to be desensitized.

[0056] It should be noted that the preset scenarios refer to the trigger scenarios for video recording set in specific scenario triggers pre-configured on the vehicle during the vehicle's development phase. These scenarios include automatic emergency braking, vehicle collisions, and abnormal exits of high-speed NOA (Navigate on Autopilot), which would cause abnormalities in vehicle status data. Furthermore, since different vehicle cameras have different field of view and resolution, camera markers are needed to identify different vehicle cameras. Specifically, camera markers can include forward-looking markers, side-looking markers, and surround-view markers; this embodiment does not impose limitations on these.

[0057] Additionally, it should be noted that during vehicle operation, the triggering module of the intelligent driving domain controller monitors the vehicle's operating status data in real time. When an abnormal event is triggered, the triggering module identifies the preset scenario the vehicle is in from the operating status data, activates the corresponding scenario trigger, obtains the camera flag corresponding to the scenario trigger, and sends the flag to the data recording module. The data recording module then controls the corresponding onboard camera to record data from the corresponding viewpoint based on the flag, obtaining the raw video data corresponding to the preset scenario, i.e., the data to be anonymized. Specifically, NOA-type scenario triggers mainly collect video data from the front-view camera and side / rear-view cameras, while HPP (Home-zone ParkingPilot, Memory Parking Assist)-type triggers mainly collect video data from the surround-view camera.

[0058] It should be understood that after obtaining the data to be anonymized, the data will be saved to the vehicle's internal storage system, and the camera flags that recorded the data will be recorded.

[0059] Step S20: When the vehicle is offline and the data to be de-identified is detected, the data to be de-identified is de-identified to obtain the target data;

[0060] It should be noted that after the intelligent driving domain controller detects that the vehicle has entered an offline state, it will activate the state management module to detect the status of video data in the vehicle's internal storage system. When it detects that there is recorded video data that has not yet been de-identified, it will treat this data as data to be de-identified, read the data to be de-identified, and perform the de-identification process to obtain the de-identified video data, i.e., the target data.

[0061] In one feasible implementation, step S20, which involves desensitizing the data to be desensitized when the vehicle is offline and the data to be desensitized is detected, to obtain the target data, may include steps A11 to A12:

[0062] Step A11: When the vehicle is offline and the data to be de-identified is detected, obtain the camera flag bit of the data to be de-identified;

[0063] It should be understood that desensitizing data in offline mode can avoid impacting the performance of the intelligent driving system by processing large amounts of data during normal vehicle operation, ensuring that the system focuses on driving tasks. When the vehicle enters offline mode, the intelligent driving domain controller will be in a domain idle period. At this time, the intelligent driving domain controller will initiate the desensitization process to perform data desensitization. Since different scenario data may be collected by different vehicle cameras, and the video data recorded by different vehicle cameras has different fields of view and different resolutions, different desensitization methods need to be used for the video data collected by different vehicle cameras to ensure the accuracy of data desensitization. Therefore, after detecting the data to be desensitized, before performing desensitization processing on the data, it is necessary to obtain the camera flag bit corresponding to the data to determine the vehicle camera used to record the data.

[0064] Step A12: Desensitize the data to be desensitized based on the camera flag bit to obtain the target data.

[0065] It should be understood that after obtaining the camera flag corresponding to the data to be de-identified, the corresponding data de-identification method can be determined based on the camera flag. The data to be de-identified is then processed based on the corresponding data de-identification method to obtain the de-identified data, i.e., the target data.

[0066] In one feasible implementation, step A12 may include steps B11 to B12:

[0067] Step B11: Obtain the corresponding target detection model based on the camera flags;

[0068] It should be noted that different vehicle cameras have different fields of view and resolutions, resulting in different target recognition models being used during data anonymization. Before deploying the target recognition model to the vehicle software, it is trained based on the characteristics of the data collected by different vehicle cameras. Specifically, a front-view target detection model is obtained by inputting front, side, oblique, and blurred faces from a front-view vehicle camera, along with blue, yellow, and green license plates. Similarly, a side-view target detection model is obtained by inputting front, side, oblique, and blurred faces from a side-view vehicle camera, along with blue, yellow, and green license plates. Likewise, a surround-view target detection model is obtained by inputting front, side, oblique, and blurred faces from a surround-view vehicle camera, along with blue, yellow, and green license plates.

[0069] Step B12: Based on the target detection model, identify the sensitive information region of the data to be de-identified, and de-identify the data in the sensitive information region to obtain the target data.

[0070] It should be understood that after determining the target detection model corresponding to the data to be desensitized based on the camera markers, sensitive information such as faces and license plate information in the data to be desensitized will be identified based on this target detection model, and the area where the sensitive information is located, i.e., the sensitive information region, will be output. The data to be desensitized in the sensitive information region will then be processed to obtain the desensitized video data, i.e., the target data. Specifically, the sensitive information region will be determined by the coordinate values ​​of the corresponding frame image in the data to be desensitized. After obtaining the coordinate values, irreversible mosaic processing can be performed on the original camera image corresponding to the corresponding frame in the data to be desensitized to cover or blur the sensitive information. After the mosaic-processed video data is H264 encoded and compressed, the desensitized video data, i.e., the target data, will be obtained.

[0071] It should be noted that the resolution and field of view of the front-view, surround-view, and side-view cameras of autonomous vehicles vary. A single target detection model has limited accuracy in identifying sensitive information from all vehicle cameras, posing a risk to data privacy and security. This implementation uses different target detection models to anonymize sensitive information such as faces and license plates from the collected front-view, side-view, and surround-view video data. This ensures the accuracy of anonymization for each vehicle camera and satisfies data privacy and security requirements. Furthermore, during data anonymization, the target detection models corresponding to the camera flags are run in parallel during domain controller idle periods. This ensures anonymization efficiency while saving computing power costs during the operation of the autonomous driving domain controller, achieving cost reduction and efficiency improvement. It also ensures secure data collection even on low-computing-power platforms with limited resources.

[0072] In another feasible implementation, step S20 may include steps A21 to A22:

[0073] Step A21: When the vehicle is offline and the data to be de-identified is detected, obtain the delayed power-down duration;

[0074] It should be noted that the intelligent driving domain controller is equipped with a timer to control the delayed power-down. When the vehicle is detected to be offline and the data to be de-identified exists in the vehicle's internal storage system, the timer setting duration of the intelligent driving domain controller, i.e., the delayed power-down duration, will be obtained to de-identify the data within the timer setting duration. This timer setting duration should be set according to the computing power of the intelligent driving domain controller's data acquisition system to ensure that even low-computing-power platforms can achieve secure data acquisition under limited resources.

[0075] Step A22: Desensitize the data to be desensitized within the delayed power-off time to obtain the target data.

[0076] It should be understood that regardless of whether the desensitization process of all data to be desensitized is completed within the delayed power-down period, the desensitized video data will be saved as the target data to the vehicle's internal storage system and the vehicle will be powered down. At the same time, the desensitization status of the target data will be marked as completed to prevent the data from being desensitized repeatedly.

[0077] In one feasible implementation, step A22 may include steps B21 to B22:

[0078] Step B21: When all the data to be desensitized is desensitized within the power-down delay period, the desensitized data to be desensitized is taken as the target data.

[0079] It should be understood that when the amount of data in the next ignition cycle is small, the time to complete the desensitization will be less than the timer setting time. That is, the desensitization process of all data to be desensitized can be completed within the delayed power-down time. At this time, the intelligent driving domain controller will not control the vehicle to power down after the delayed power-down time is reached, but will immediately go into complete sleep mode and power down when the data desensitization is completed, in order to save vehicle energy and computing resources.

[0080] Step B22: When the time for desensitizing the data to be desensitized reaches the power-down delay time, the data to be desensitized after desensitization is taken as the target data, and the data to be desensitized before desensitization is saved.

[0081] It should be understood that when the amount of data in a given ignition cycle is large, the time required to complete the desensitization process may exceed the timer's set duration. In other words, the desensitization process for all data to be desensitized cannot be completed within the delayed power-down time. In this case, the intelligent driving domain controller will control the vehicle to power down and enter a complete sleep state when the delayed power-down time is reached. The desensitization status of the target data will be marked as completed and saved to the vehicle's internal storage system. The video data that has not yet been desensitized will be marked as pending desensitization and saved to the vehicle's internal storage system. This will allow the desensitized video data to be desensitized during the next power-down period before the vehicle is fully locked and in sleep mode.

[0082] Step S30: Save the target data in the vehicle's internal storage system and control the vehicle to power off;

[0083] It should be noted that upon obtaining the target data, i.e., the data that has already been anonymized, the target data will be marked as processed and stored in the vehicle's internal storage system to avoid repeated anonymization processing of the target data before uploading it to the cloud. Immediately powering down the vehicle after obtaining the target data to put the intelligent driving domain controller into complete sleep mode can reduce the exposure time of the data in an unprotected state and reduce the risk of data leakage or unauthorized access.

[0084] Step S40: When the vehicle is powered on again and the vehicle is connected to the network again, the target data is uploaded to the cloud.

[0085] It should be noted that because the data anonymization process is conducted offline, the anonymized video data is not immediately uploaded to the cloud, but is stored in the vehicle's internal storage system. Once the vehicle is powered on, a new communication connection is established, at which point the anonymized data is uploaded to the cloud. Backing up the anonymized data facilitates further analysis and processing.

[0086] It should be understood that, in order to ensure the stability of data upload, when the vehicle is detected to be powered on and connected to the network, the network status at this time will be checked first. Only when the network status is good will the intelligent driving domain controller initiate a communication request to the cloud. After establishing a communication connection with the cloud, the de-identified and compressed data, i.e., the target data, will be uploaded to the cloud.

[0087] This embodiment provides a method for collecting anonymized data. Upon receiving a vehicle lock command, the vehicle's internal processes are shut down and its communication channels are disconnected to put the vehicle into an offline state. When the vehicle is offline and data to be anonymized is detected, the data to be anonymized is anonymized to obtain target data. The target data is stored in the vehicle's internal storage system, and the vehicle is powered off. When the vehicle is powered on again and reconnected to the network, the target data is uploaded to the cloud. This solution uses offline anonymization to collect anonymized data to avoid excessive consumption of computing power and load during vehicle operation, reducing system stability risks and ensuring the stability of anonymized data collection on low-computing-power platforms.

[0088] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S40 also includes steps S41 to S43:

[0089] Step S41: Traverse the camera flag list and obtain the current camera flag based on the camera flag list;

[0090] It should be noted that the vehicle's internal storage system maintains a list of camera flags. The list stores, in chronological order, the camera flags corresponding to the video data recorded for each event within the current ignition cycle, as well as the time period node corresponding to that camera flag.

[0091] Step S42: When the vehicle is powered on again and the vehicle is connected to the network again, the current upload event data is obtained from the target data based on the current camera flag, and the current upload event data is uploaded to the cloud.

[0092] It should be understood that when the vehicle is detected to be powered on and in a stable network connection state, the anonymized data will be uploaded to the cloud. To ensure data integrity and continuity, when uploading target data, events will be divided based on camera markers. Data for the same event will be uploaded first, followed by the data for the next event. Specifically, if the current upload event is a high-speed NOA abnormal exit, the camera markers traversed will be the forward-looking marker and the side-rear marker. Based on the camera marker list, the time period information corresponding to the forward-looking marker and the side-rear marker can be obtained. At this time, the video data that was first anonymized based on the forward-looking marker and the side-rear marker will be read from the target data based on this time period information, and used as the current upload event data. This current upload event data will be uploaded to the cloud, and the uploaded target data status will be marked as uploaded successfully.

[0093] Step S43: When the current upload event data is completed, obtain the next camera flag based on the camera flag list, obtain the next upload event data from the target data based on the next camera flag, and upload the next upload event data to the cloud until all the target data is uploaded.

[0094] It should be understood that when all currently uploaded event data read from the target data based on the current camera flag has been uploaded, the next camera flag will be obtained from the camera flag list, along with the corresponding time period information. The video data that was first anonymized based on the next camera flag from the unuploaded target data will be read as the next uploaded event data and uploaded to the cloud. The status of the target data that has been uploaded will then be marked as "uploaded successfully." This process continues until all target data has been marked as "uploaded successfully," at which point the original data (i.e., data to be anonymized) and the anonymized and compressed data (i.e., target data) will be cleared to free up space for new data recording.

[0095] In this embodiment, the anonymized data is divided into different events based on camera flags. After the data for the same event is uploaded, the data for the next event is uploaded, ensuring the integrity and continuity of the data during the upload process.

[0096] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the data collection method for de-identification in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0097] This application also provides a de-identified data acquisition device; please refer to [reference needed]. Figure 3 The de-identified data acquisition device includes:

[0098] The offline control module 10 is used to shut down the vehicle's internal processes and disconnect the vehicle's communication channel to put the vehicle into an offline state when a vehicle lock command is received.

[0099] The data desensitization module 20 is used to desensitize the data to be desensitized when the vehicle is offline and the data to be desensitized is detected, so as to obtain the target data.

[0100] The power-down control module 30 is used to store the target data in the vehicle's internal storage system and control the vehicle to power down.

[0101] The data upload module 40 is used to upload the target data to the cloud when the vehicle is powered on again and the vehicle is connected to the network again.

[0102] The anonymized data acquisition device provided in this application, employing the anonymized data acquisition method described in the above embodiments, can solve the technical problem of ensuring the stability of low-computing-power platforms during the acquisition of anonymized data. Compared with the prior art, the beneficial effects of the anonymized data acquisition device provided in this application are the same as those of the anonymized data acquisition method provided in the above embodiments, and other technical features in the anonymized data acquisition device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0103] This application provides a de-identified data acquisition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the de-identified data acquisition method in the above embodiment 1.

[0104] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a data acquisition device suitable for implementing embodiments of this application. The data acquisition device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The desensitized data acquisition device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0105] like Figure 4As shown, the desensitized data acquisition device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the desensitized data acquisition device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the de-identified data acquisition device to communicate wirelessly or wiredly with other devices to exchange data. Although de-identified data acquisition devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0106] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0107] The de-identified data acquisition device provided in this application, employing the de-identified data acquisition method described in the above embodiments, can solve the technical problem of ensuring the stability of low-computing-power platforms during the acquisition of de-identified data. Compared with the prior art, the beneficial effects of the de-identified data acquisition device provided in this application are the same as those of the de-identified data acquisition method provided in the above embodiments, and other technical features of this de-identified data acquisition device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0108] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0109] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0110] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the de-identified data acquisition method in the above embodiments.

[0111] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0112] The aforementioned computer-readable storage medium may be included in the desensitized data acquisition device; or it may exist independently and not be assembled into the desensitized data acquisition device.

[0113] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the data desensitization acquisition device, the data desensitization acquisition device: upon receiving a vehicle lock command, shuts down the vehicle's internal processes and disconnects the vehicle's communication channel to put the vehicle into an offline state; when the vehicle is offline and data to be desensitized is detected, desensitizes the data to obtain target data; stores the target data in the vehicle's internal storage system and controls the vehicle to power off; and when the vehicle is powered on again and reconnected to the network, uploads the target data to the cloud.

[0114] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0116] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0117] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described de-identified data acquisition method. This solves the technical problem of ensuring the stability of low-computing-power platforms during the acquisition of de-identified data. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the de-identified data acquisition method provided in the above embodiments, and will not be repeated here.

[0118] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the de-identified data acquisition method described above.

[0119] The computer program product provided in this application can solve the technical problem of ensuring the stability of low-computing-power platforms during the collection of anonymized data. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the anonymized data collection method provided in the above embodiments, and will not be repeated here.

[0120] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for collecting anonymized data, characterized in that, The de-identified data collection method includes: Upon receiving a vehicle lock command, the vehicle's internal processes are shut down and the vehicle's communication channels are disconnected to put the vehicle into an offline state. When the vehicle is offline and the data to be de-identified is detected, the data to be de-identified is de-identified to obtain the target data; The target data is stored in the vehicle's internal storage system, and the vehicle is powered off. When the vehicle is powered on again and is connected to the network again, the target data will be uploaded to the cloud. The step of uploading the target data to the cloud when the vehicle is powered on again and the vehicle is connected to the network again includes: Iterate through the list of camera flags and obtain the current camera flag based on the list of camera flags; When the vehicle is powered on again and the vehicle is connected to the network again, the current upload event data is obtained from the target data based on the current camera flag, and the current upload event data is uploaded to the cloud; When the current upload event data is completed, the next camera flag is obtained based on the camera flag list, the next upload event data is obtained from the target data based on the next camera flag, and the next upload event data is uploaded to the cloud, until all the target data is uploaded.

2. The method as described in claim 1, characterized in that, Before the step of shutting down the vehicle's internal processes and disconnecting the vehicle's communication channel to put the vehicle into an offline state upon receiving a vehicle lock command, the method further includes: When the vehicle is in a preset scenario, obtain the camera flag position corresponding to the preset scenario; Based on the camera flag, the corresponding vehicle camera is controlled to collect video data to obtain the data to be de-identified.

3. The method as described in claim 1, characterized in that, The step of desensitizing the data to be desensitized to obtain the target data when the vehicle is offline and the data to be desensitized is detected includes: When the vehicle is offline and the data to be de-identified is detected, the camera flag bit of the data to be de-identified is obtained; The data to be de-identified is de-identified based on the camera flag to obtain the target data.

4. The method as described in claim 3, characterized in that, The step of desensitizing the data to be desensitized based on the camera flag bit to obtain the target data includes: The corresponding target detection model is obtained based on the camera flags; Based on the target detection model, the sensitive information regions of the data to be de-identified are identified, and the data in the sensitive information regions is de-identified to obtain the target data.

5. The method as described in claim 1, characterized in that, The step of desensitizing the data to be desensitized to obtain the target data when the vehicle is offline and the data to be desensitized is detected includes: When the vehicle is offline and data to be desensitized is detected, the power-down delay duration is obtained; The data to be desensitized is desensitized within the specified power-off delay period to obtain the target data.

6. The method as described in claim 5, characterized in that, The step of desensitizing the data to be desensitized within the delayed power-off time to obtain the target data includes: When all the data to be desensitized is desensitized within the specified power-down delay period, the desensitized data to be desensitized will be used as the target data. When the time for desensitizing the data to be desensitized reaches the power-down delay time, the data to be desensitized after desensitization is completed is used as the target data, and the data to be desensitized before desensitization is completed is saved.

7. A de-identified data acquisition apparatus for performing the de-identified data acquisition method as described in any one of claims 1 to 6, characterized in that, The device includes: The offline control module is used to shut down the vehicle's internal processes and disconnect the vehicle's communication channel to put the vehicle into an offline state when a vehicle lock command is received. The data desensitization module is used to desensitize the data to be desensitized when the vehicle is offline and the data to be desensitized is detected, so as to obtain the target data. A power-down control module is used to store the target data in the vehicle's internal storage system and control the vehicle to power down. The data upload module is used to upload the target data to the cloud when the vehicle is powered on again and the vehicle is connected to the network again.

8. A data desensitization acquisition device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the de-identified data acquisition method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the de-identified data acquisition method as described in any one of claims 1 to 6.

Images