Data backup method and device, vehicle and readable storage medium
By receiving vehicle-side driving operation information to judge abnormal events and sending data backup instructions to related equipment, the problem of insufficient data backup in the existing technology is solved, the timeliness and completeness of data backup is realized, and the accuracy of data reference is improved. efficiency.
Patent Information
- Application Number
- CN202411031687.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-12
AI Technical Summary
The existing data backup methods focus more on bicycle data. The backup data is not enough to restore exceptions, and data backup cannot be performed in advance, affecting the integrity of data reference.
By receiving the driving operation information sent by the vehicle end, we can determine whether there is a driving operation abnormal event. If it exists, send data backup instructions to the relevant equipment, control data storage and send it to the cloud, store backup in advance, and improve the timeliness and integrity of data backup. .
It realizes timely and complete backup of vehicle operation data, improves the accuracy and efficiency of data reference, and can identify and handle abnormal driving events in advance.
Smart Images

Figure CN118939479A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving technology, and in particular to a data backup method, device, vehicle and readable storage medium. Background Art
[0002] During the operation of autonomous driving, backing up vehicle operation data helps to restore the scene and debug and analyze problems. In addition, for autonomous driving scenarios with mixed traffic, data backup is also used to record the behavior of people and vehicles that do not drive according to regulations, in order to improve operational efficiency, identify human interference, and improve data reference.
[0003] Existing data backup methods focus more on the data of a single vehicle. The backed-up data is not sufficient to restore anomalies. In addition, data backup is not performed in advance for possible anomalies, which affects the integrity of data references. Summary of the invention
[0004] In view of this, the present invention provides a data backup method, device, vehicle and readable storage medium to solve the problem that the existing data backup method focuses more on the data of a single vehicle, the backed up data is not sufficient to restore the anomaly, and in addition, no data backup is performed in advance for possible anomalies, affecting the integrity of data references.
[0005] In a first aspect, the present invention provides a data backup method, which is applied to the cloud, and the method includes: receiving driving operation information sent by the current vehicle end during driving, and judging whether the current vehicle end may have an abnormal driving operation event based on the driving operation information; if it is determined that the current vehicle end may have an abnormal driving operation event, sending a data backup instruction to the current vehicle end and / or a device end associated with the current vehicle end with the abnormal driving operation, controlling the current vehicle end and / or a device associated with the current vehicle end with the abnormal driving operation to store and send its own monitored data to the cloud; storing and backing up the monitored data sent by the current vehicle end and / or a device associated with the current vehicle end with the abnormal driving operation and the judged possible abnormal driving operation event.
[0006] The data backup method provided in this embodiment determines in advance whether the current vehicle side may have an abnormal driving operation event based on the driving operation information sent by the current vehicle side. If it is determined that an abnormal driving operation event may exist, a data backup instruction is sent to the current vehicle side and the device side associated with the abnormal driving operation of the current vehicle side to control the current vehicle side and the device side to store and send their own monitored data to the cloud. The cloud side can then store and back up the monitored data and the determined possible abnormal driving operation events in advance, thereby improving the timeliness and completeness of data backup.
[0007] In an optional implementation, the driving operation information at least includes the current vehicle-side operation scene, the current vehicle-side driving environment information and the status information of each module on the current vehicle-side. The cloud pre-stores an operation scene database that requires vehicle-side data backup and the status data of each module on the vehicle-side corresponding to normal driving of the vehicle. The driving operation abnormal event at least includes an operation failure event, a vehicle-side module abnormal event and an accident fault event. The judging whether the current vehicle-side may have a driving operation abnormal event based on the driving operation information includes: matching the current vehicle-side operation scene with a pre-stored operation scene database that requires vehicle-side data backup, and if the match is successful, determining that the current vehicle-side may have an operation failure event; comparing the status information of each module on the current vehicle-side with the status data of each module on the vehicle-side corresponding to normal driving of the vehicle, and determining that the current vehicle-side has a vehicle-side module abnormal event with a data difference; judging whether the dynamic obstacle driving information in the current vehicle-side driving environment information has a collision risk with the vehicle-side driving trajectory sent by the current vehicle, and / or judging whether the current vehicle has a violation, and if there is a collision risk, and / or if the current vehicle has a violation, determining that the current vehicle may have an accident fault event.
[0008] The present invention determines whether abnormal driving operation events may occur on the vehicle side by considering the vehicle side's own factors and external factors. Different data backup events are defined corresponding to system abnormalities caused by different factors. The factors considered are more comprehensive, and possible abnormal driving operation events can be predicted in advance, vehicle data backup can be triggered in advance, and risks can be identified in advance.
[0009] In an optional embodiment, the sending of data backup instructions to the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormalities includes: based on different key field information that needs to be detected and stored corresponding to different driving operation abnormal events, the key fields corresponding to the determined driving operation abnormalities that may exist in the current vehicle end are sent to the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormalities, so that the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormalities perform data monitoring based on the key fields, and fill in the corresponding field information and upload it to the cloud.
[0010] The cloud of the present invention can send the key fields corresponding to the abnormal driving operation events that may exist on the current vehicle side to the current vehicle side and / or the device side, so that the current vehicle side and / or the device side can directly monitor the data based on the key fields and fill in the field information and then upload it to the cloud, which can not only reduce the data backed up in the cloud, but also ensure that the data backed up in the cloud are all key information corresponding to the abnormal event.
[0011] In an optional embodiment, the method also includes: when it is detected that there are other real-time data monitoring devices in the current vehicle-side operation scene other than the current vehicle-side and / or the device side associated with the current vehicle-side with abnormal driving operation, obtaining the identification information of the other real-time data monitoring devices, and storing and backing up the possible abnormal driving operation events in the current vehicle-side operation scene, so that the cloud can obtain the data monitored by the other real-time data monitoring devices and restore the data based on the identification information of the other real-time data monitoring devices stored corresponding to the abnormal driving operation events occurring on the current vehicle-side.
[0012] The cloud of the present invention only needs to save the identification information of other devices. When restoring abnormal events, the original data of other sensors can be obtained through the tag information of other sensors for data restoration. This not only saves storage space in the cloud, but also takes into account not only the vehicles and equipment ends related to the abnormal events, but also the data collected by other sensors and other devices, thereby improving the integrity of data restoration.
[0013] In an optional embodiment, the monitoring data sent by the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormality and the judged possible driving operation abnormality events are stored and backed up, including: based on the influence of the monitoring data sent by the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormality on the judged possible driving operation abnormality events, determining the influence level of different monitored data; storing and backing up the data and the judged possible driving operation abnormality events according to the influence level of different monitored data.
[0014] The present invention stores the data stored in the event in a hierarchical manner, wherein the hierarchical levels are set according to the magnitude of the impact of the data on the abnormal driving operation event. When the data is subsequently restored, it can be retrieved according to the hierarchical levels, and key influencing factors can be extracted efficiently.
[0015] In an optional embodiment, the method also includes: in response to an abnormal driving operation event actually occurring during the driving process of the current vehicle, taking the actual abnormal driving operation event as a dimension, and restoring the data according to the impact level of each data when the backup is stored, so that the user can handle the abnormal driving operation event based on the restored data.
[0016] The cloud of the present invention restores data according to the impact level when the data is backed up, which not only improves the efficiency of data restoration, but also ensures that the abnormal situation of the current event can be fully and accurately restored.
[0017] In an optional embodiment, the cloud side and the vehicle side are pre-set with target data type conversion rules, and the method also includes: sending the target data type corresponding to the set key field information to the current vehicle side and / or the device side associated with the current vehicle side with driving operation abnormality, so that the current vehicle side and / or the device side associated with the current vehicle side with driving operation abnormality will perform target data type conversion based on the data monitored by the key fields, and fill in the field information after the target data type conversion and upload it to the cloud side.
[0018] The vehicle side and the cloud side of the present invention predefine the conversion rules of the target data type. After the vehicle side monitors the data, the monitored data is first converted into the target data type and then reported to the cloud side, which can effectively reduce the amount of reported data and improve the efficiency of data reporting.
[0019] In a second aspect, the present invention provides a data backup device, which is applied to the cloud, and the device includes: a vehicle-side operation judgment module, which is used to receive driving operation information sent by the current vehicle-side during driving, and judge whether the current vehicle-side may have an abnormal driving operation event based on the driving operation information; a data monitoring module, which is used to send a data backup instruction to the current vehicle-side and / or a device side associated with the current vehicle-side with abnormal driving operation if it is determined that the current vehicle-side may have an abnormal driving operation event, and control the current vehicle-side and / or a device associated with the current vehicle-side with abnormal driving operation to store and send its own monitored data to the cloud; a data backup module, which is used to store and back up the monitoring data sent by the current vehicle-side and / or a device associated with the current vehicle-side with abnormal driving operation and the judged possible abnormal driving operation event.
[0020] In a third aspect, the present invention provides a vehicle, comprising a vehicle end.
[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the data backup method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0023] Figure 1 is a flow chart of a data backup method according to an embodiment of the present invention;
[0024] Figure 2 is a flow chart of another data backup method according to an embodiment of the present invention;
[0025] Figure 3 is a structural block diagram of a vehicle according to an embodiment of the present invention;
[0026] Figure 4 is a structural block diagram of a data backup device according to an embodiment of the present invention;
[0027] Figure 5 Schematic diagram of the hardware structure of the cloud in an embodiment of the present invention. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0029] According to an embodiment of the present invention, a data backup method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0030] In this embodiment, a data backup method is provided, which can be used in the above-mentioned cloud. Figure 1 is a flow chart of a data backup method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0031] Step S101, receiving driving operation information sent by the current vehicle end during driving, and judging whether there may be an abnormal driving operation event on the current vehicle end based on the driving operation information.
[0032] The embodiments of the present invention do not limit the type of vehicle, which may be an operating vehicle such as a forklift, or a driving vehicle with passengers such as a car. The corresponding vehicle driving operation scenario may be a scenario for performing task operations or a normal driving scenario. For example, the vehicle side may send driving operation information to the cloud during driving, wherein the content of the driving operation information is not limited, and the driving operation information corresponding to different driving operation scenarios may be different. For example, the driving operation information sent in the scenario for performing task operations may include but is not limited to the operation task, the current operation network signal, etc. The driving operation information sent in the normal driving scenario may include but is not limited to the vehicle's driving trajectory, and the vehicles and obstacle information around the vehicle. This is for example only.
[0033] The cloud of an embodiment of the present invention can pre-set and store which driving operation scenarios may be prone to driving operation abnormality events, and can also pre-set event rules for obstacles in normal vehicle driving scenarios and the dynamic reference driving state of the current vehicle that may cause driving operation abnormality. After receiving the driving operation information sent by the current vehicle during driving, the cloud can determine whether there is an abnormal driving operation event on the current vehicle and possible abnormal driving operation events based on the driving operation information. For example, determine whether the operation scene of the current vehicle is among the operation scenes that may be prone to driving operation abnormality events that have been pre-stored by itself, as an example only.
[0034] Step S102, if it is determined that the current vehicle end may have an abnormal driving operation event, send a data backup instruction to the current vehicle end and / or the device end associated with the abnormal driving operation of the current vehicle end, control the current vehicle end and / or the device associated with the abnormal driving operation of the current vehicle end to store and send its own monitoring data to the cloud.
[0035] The embodiment of the present invention does not limit the device side associated with the current vehicle side where the driving operation is abnormal, and is related to the current vehicle side driving scene, and may include but is not limited to cameras on the road, and other vehicles that have a risk of vehicle collision with the current vehicle side, as an example only; after the cloud determines that the current vehicle side may have an abnormal driving operation event, it can send a data backup instruction to the current vehicle side and the device side associated with the current vehicle side where the driving operation is abnormal. After receiving the data backup instruction, the vehicle side and the device side can turn on the data backup function, store the data monitored by themselves and send it to the cloud.
[0036] Step S103, storing and backing up the monitoring data sent by the current vehicle end and / or the equipment associated with the current vehicle end having abnormal driving operation and the possible abnormal driving operation events determined.
[0037] After the cloud in the embodiment of the present invention receives the monitored data sent by the vehicle and other equipment ends, it can store and back up the data and the possible abnormal driving operation events that may be judged to record the abnormalities.
[0038] The data backup method provided in this embodiment determines in advance whether the current vehicle side may have an abnormal driving operation event based on the driving operation information sent by the current vehicle side. If it is determined that an abnormal driving operation event may exist, a data backup instruction is sent to the current vehicle side and the device side associated with the abnormal driving operation of the current vehicle side to control the current vehicle side and the device side to store and send their own monitored data to the cloud. The cloud side can then store and back up the monitored data and the determined possible abnormal driving operation events in advance, thereby improving the timeliness and completeness of data backup.
[0039] In this embodiment, a data backup method is provided, which can be used in the above-mentioned cloud. Figure 2 is a flow chart of a data backup method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0040] Step S201, receiving the driving operation information sent by the current vehicle end during driving, and judging whether there may be an abnormal driving operation event on the current vehicle end based on the driving operation information.
[0041] Specifically, the driving operation information includes at least the current vehicle-side operation scene, the current vehicle-side driving surrounding environment information and the current status information of each module on the vehicle-side; the cloud pre-stores the operation scene database that requires vehicle-side data backup and the corresponding vehicle-side module status data when the vehicle is driving normally; the driving operation abnormal events include at least operation failure events, vehicle-side module abnormal events and accident failure events.
[0042] The cloud matches the current vehicle-side operation scene with a pre-stored operation scene database that requires vehicle-side data backup. If the match is successful, it is determined that the current vehicle-side may have an operation failure event, and the status information of each module on the current vehicle-side is compared with the corresponding status data of each module on the vehicle-side when the vehicle is driving normally, to determine the abnormal event of the vehicle-side module with data difference on the current vehicle-side, to determine whether there is a collision risk between the dynamic obstacle driving information in the current vehicle-side driving environment information and the vehicle-side driving trajectory sent by the current vehicle-side, and / or to determine whether the current vehicle-side has any violation. If there is a collision risk, and / or the current vehicle-side has any violation, it is determined that the current vehicle-side may have an accident failure event.
[0043] The abnormal operation of the automatic driving system in the embodiment of the present invention is caused by the abnormality of the automatic driving system itself on the one hand, and the other part is caused by external factors. The abnormality of the automatic driving itself includes the algorithm, sensor, operation scene or hardware, etc. The external factors include weather, illegal driving of other vehicles or users in the system, and increased abnormal risk of the automatic driving system. The state of the automatic driving system mainly includes four aspects, namely, the operation state, the vehicle state, the sensor state, and the accident risk, which cause abnormality. According to these four aspects, different events are divided, and the data association model is defined for different events, that is, which data needs to be paid attention to, and the data that needs to be paid attention to is backed up as much as possible, and the scene can be restored. When the abnormality is detected, the data backup is triggered. The data may include the data of each module on the vehicle side, and may also include the data of the vehicle side camera, v2x and other equipment. The external factors mainly refer to the safety risks caused by the illegal driving of other traffic participants in the system. Illegal driving will affect multiple automatic driving vehicles in the area. We can define data backup events for illegal traffic participants. When illegal behavior is detected, the data backup event can be triggered to send to the vehicle side. In addition, for blind spots, turns and other locations, the cloud control platform can also use v2x detection to identify risks in advance and trigger data backup events.
[0044] The cloud can define different data backup events for system anomalies caused by different factors: When the autonomous driving system is operating in certain operating scenarios or certain operating locations, operating identification events will occur due to technical or environmental influences. The cloud has pre-stored an operating scenario database that requires vehicle-side data backup. After receiving the driving operation information sent by the user, it can determine whether the vehicle-side operating scenario in the driving operation information is matched with the pre-stored operating scenario database that requires vehicle-side data backup. If it is determined that the current vehicle may have an operating failure event, the cloud can define a data backup event for a single vehicle and send a data backup instruction to the current vehicle. The current vehicle can then back up information on modules such as planning, positioning and perception to the cloud. In some optional implementations, poor network signals or GPS signals may occur at certain work locations. When the cloud determines that the current vehicle is about to enter the area, it can send a data backup instruction to the current vehicle in advance, so that the current vehicle can report the vehicle network information to the cloud in advance. When the vehicle is performing a task or driving to a certain area, an event is sent to the vehicle to trigger a vehicle data backup. After receiving the event, the vehicle reports it to the cloud in real time according to the frequency of the cloud. After receiving the event, the cloud will store the reported data, event type, location, task and other key information in the cloud. When restoring the event, it can efficiently restore the abnormal scene based on these key information. This is just an example.
[0045] For the scenario where the current vehicle's own status is abnormal, the vehicle-side program includes but is not limited to multiple modules such as positioning, perception, and planning. When the vehicle is online, the status information of each module can be sent to the cloud. The cloud can compare the status information of each module on the current vehicle with the corresponding status data of each module on the vehicle when the vehicle is driving normally. After determining that a certain module is abnormal, the cloud can control the current vehicle to upload the backup event of the status of the abnormal module to the cloud. If the module abnormality is caused by the sensor, the sensor data needs to be backed up. If the module abnormality is caused by other modules, the status of the data interaction channel between modules needs to be backed up.
[0046] During the operation of the vehicle, there may be obstacles of different types and locations. Obstacles will increase the risk of accidents such as scratches and collisions. In addition, accidents may occur between autonomous driving vehicles due to abnormal vehicle driving. When an obstacle is detected by the vehicle-side or v2x sensor, as well as the path planned for the vehicle-side or the local path reported by the vehicle-side, it is determined whether there is a risk of collision between the vehicle-side trajectory and the obstacle or the obstacle's running trajectory. If so, a data backup event is triggered. In addition, it can also be determined whether there are any illegal driving behaviors. If so, data backup can also be triggered. In a specific embodiment, the cloud determines whether there is a risk of collision between vehicles based on the position and local trajectory reported by the vehicles. If there is a risk of collision, the size of the risk is obtained based on the position of the collision point between the vehicles and the distance between the vehicles. When the risk of collision is greater than a set threshold, the data backup event will be triggered to the dispatching end, and the vehicle data backup will be triggered in advance; or the cloud predicts the obstacle driving trajectory based on the position and driving trajectory reported by the vehicle and the obstacle information reported in the system, and calculates whether each obstacle will conflict with the driving trajectory of vehicles in the area. If there is a conflict, the size of the collision risk between each obstacle and the vehicle is obtained based on how long the predicted trajectory will collide with the vehicle. When the risk of collision is greater than a set threshold, the data backup instruction will be triggered to the dispatching end, and the vehicle data backup will be triggered in advance; in addition, the cloud determines whether the obstacle is detected to be driving illegally based on the obstacle information and lane line information, and calculates the distance between the obstacle and the vehicle position. However, when the distance is less than the threshold, the data backup instruction is triggered to the dispatching end. This is just an example.
[0047] The present invention determines whether abnormal driving operation events may occur on the vehicle side by considering the vehicle side's own factors and external factors. Different data backup events are defined corresponding to system abnormalities caused by different factors. The factors considered are more comprehensive, and possible abnormal driving operation events can be predicted in advance, vehicle data backup can be triggered in advance, and risks can be identified in advance.
[0048] In step S202, if it is determined that an abnormal driving operation event may occur on the current vehicle side, a data backup instruction is sent to the current vehicle side and / or a device side associated with the abnormal driving operation on the current vehicle side, and the current vehicle side and / or a device associated with the abnormal driving operation on the current vehicle side are controlled to store their own monitored data and send it to the cloud.
[0049] Specifically, the above step S202 includes:
[0050] Step S2021, based on the different key field information that needs to be detected and stored corresponding to different abnormal driving operation events, the key fields corresponding to the abnormal driving operation events that may exist on the current vehicle side are sent to the current vehicle side and / or the device side associated with the current vehicle side where the abnormal driving operation exists, so that the current vehicle side and / or the device side associated with the current vehicle side where the abnormal driving operation exists performs data monitoring based on the key fields, and fills in the corresponding field information and uploads it to the cloud.
[0051] The cloud in the embodiment of the present invention can define the data content to be reported associated with each abnormal driving operation event, and the message definition format can be defined using protobuf without limitation. Among them, the monitoring data content that the cloud needs to upload by the vehicle side is not limited. It can be that all monitored data associated with the abnormal driving operation event is uploaded to the cloud, that is, the abnormal related topic data is fully reported to the cloud. When the protobuf message is sent to the cloud, the protobuf contains the topic information associated with the event that needs to be backed up. After the vehicle side receives it, it reports each topic data to the cloud according to the topic information; it can also be that the cloud in this embodiment pre-defines different key field information that needs to be detected and stored corresponding to different abnormal driving operation events. Based on the abnormal driving operation event that may exist in the current vehicle side, the corresponding key field can be sent to the current vehicle side and / or the device side associated with the abnormal driving operation of the current vehicle side. The current vehicle side can monitor the data corresponding to the key field based on the sent key field information, and report the monitored data to the cloud after filling the field. That is, when the cloud sends the protobuf message, the protobuf contains the field that needs to be backed up. After the vehicle side receives it, it fills the field and reports it to the cloud. This is just an example.
[0052] The cloud of the present invention can send the key fields corresponding to the abnormal driving operation events that may exist on the current vehicle side to the current vehicle side and / or the device side, so that the current vehicle side and / or the device side can directly monitor the data based on the key fields and fill in the field information and then upload it to the cloud, which can not only reduce the data backed up in the cloud, but also ensure that the data backed up in the cloud are all key information corresponding to the abnormal event.
[0053] In some optional embodiments, the cloud and the vehicle side are pre-set with target data type conversion rules, and the cloud side sends the target data type corresponding to the set key field information to the current vehicle side and / or the device side associated with the current vehicle side with driving operation abnormalities, so that the current vehicle side and / or the device side associated with the current vehicle side with driving operation abnormalities will perform target data type conversion based on the data monitored by the key fields, and fill in the field information after the target data type conversion and upload it to the cloud.
[0054] The cloud side and vehicle side of the embodiment of the present invention can pre-set the transformation rules of the target data type. When the cloud side sends the key fields corresponding to the possible abnormal driving operation events to the vehicle side and / or other device sides, for example, the location-related data can be defined as integer. After the vehicle side and / or other device sides monitor the data based on the key fields, the monitored data can be first converted to the target data type, and then the automatic data serialization after the target data type conversion is reported to the cloud side, as an example only.
[0055] The vehicle side and the cloud side of the present invention predefine the conversion rules of the target data type. After the vehicle side monitors the data, the monitored data is first converted into the target data type and then reported to the cloud side, which can effectively reduce the amount of reported data and improve the efficiency of data reporting.
[0056] Step S203, storing and backing up the monitoring data sent by the current vehicle end and / or the equipment associated with the current vehicle end having abnormal driving operation and the possible abnormal driving operation events determined.
[0057] Specifically, the above step S203 includes:
[0058] Step S2031, based on the influence of the monitoring data sent by the current vehicle end and / or the device end associated with the current vehicle end where the driving operation abnormality exists on the judged possible driving operation abnormality events, determine the impact level of different monitored data; store and back up the data and the judged possible driving operation abnormality events according to the impact level of different monitored data.
[0059] After the cloud in an embodiment of the present invention detects that an abnormal driving operation event may occur on the current vehicle side, it will send a data backup instruction to the vehicle side. After receiving the data backup instruction, the vehicle side monitors the data and reports the monitored data to the cloud. When storing the backup data, the cloud will classify the backed up data based on the determined abnormal driving operation event as a dimension. Each event will have a unique identifier, wherein the method for classifying the backup data is not limited. For example, three levels of high, medium, and low can be defined. After receiving the data, the data can be classified and stored according to the impact of different data on the triggering of abnormal driving operation events. Among them, determining the impact of different data on the triggering of abnormal driving operation events can be that the cloud side pre-stores the corresponding relationship between the impact of different factors on the event, which is only used as an example.
[0060] The present invention stores the data stored in the event in a hierarchical manner, wherein the hierarchical levels are set according to the magnitude of the impact of the data on the abnormal driving operation event. When the data is subsequently restored, it can be retrieved according to the hierarchical levels, and key influencing factors can be extracted efficiently.
[0061] Step S204, in response to the abnormal driving operation event actually occurring during the driving process of the current vehicle, the data is restored according to the impact level of each data when the backup is stored, based on the actual abnormal driving operation event. This allows the user to handle the abnormal driving operation event based on the restored data.
[0062] The cloud in an embodiment of the present invention responds to the abnormal driving operation event actually occurring during the driving process of the current vehicle, and can read the data related to the dimension of the abnormal driving operation event. There is no limitation on the method of restoring the data according to the impact level of each data when it is stored and backed up. The high-level data can be restored in advance, and the key marked data can be restored, and then the medium-level and low-level data can be restored in turn. It can also be based on the user's restoration needs. If the high-level data can directly restore the event abnormality, there is no need to display the restored medium-level and low-level data. Just as an example, the cloud can also mine the data to improve operating efficiency.
[0063] In one embodiment, the cloud can also generate an event map based on the events that have occurred and the related areas, marking the high-frequency events and the number of times that have occurred in each area. When issuing tasks, the cloud can use the event map as a reference. For certain locations, if the number of events is too high, they can be avoided when planning the route, thereby reducing system risks and providing data support for system operation.
[0064] The cloud of the present invention restores data according to the impact level when the data is backed up, which not only improves the efficiency of data restoration, but also ensures that the abnormal situation of the current event can be fully and accurately restored.
[0065] In some optional embodiments, when it is detected that there are other real-time data monitoring devices in the current vehicle-side operation scene other than the current vehicle-side and / or the device side associated with the current vehicle-side driving operation abnormality, the identification information of the other real-time data monitoring devices is obtained, and the abnormal driving operation events that may exist in the current vehicle-side operation scene are stored and backed up, so that the cloud can obtain the data monitored by other real-time data monitoring devices and restore the data based on the identification information of other real-time data monitoring devices stored corresponding to the abnormal driving operation events occurring on the current vehicle-side.
[0066] In the case of an accident, in an embodiment of the present invention, if the cloud detects that there is a camera in the area, it can simultaneously trigger the camera to save the video data locally, and the camera reports the information (tag) about the saved video to the cloud. When the cloud checks the event, if there is tag information, it triggers the video data to be reported to the cloud. When the tag information of the sensor's original data is read, the vehicle-to-cloud delivery is triggered, and the related data is reported to the cloud in real time. This is only an example and is not limited to the device.
[0067] The cloud of the present invention only needs to save the identification information of other devices. When restoring an abnormal event, the original data of other sensors can be obtained through the tag information of other sensors for data restoration, which not only saves the storage space of the cloud, but also improves the integrity of data restoration.
[0068] In the present embodiment, a data backup device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0069] This embodiment provides a vehicle, such as Figure 3 As shown, the vehicle includes a vehicle end, and the vehicle may be an autonomous driving vehicle.
[0070] This embodiment provides a data backup device, which is applied to the cloud. Figure 4As shown, it includes: a vehicle-side operation judgment module 401, which is used to receive the driving operation information sent by the current vehicle-side during driving, and judge whether the current vehicle-side may have an abnormal driving operation event based on the driving operation information; a data monitoring module 402, which is used to send a data backup instruction to the current vehicle-side and / or a device side associated with the current vehicle-side with abnormal driving operation if it is determined that the current vehicle-side may have an abnormal driving operation event, and control the current vehicle-side and / or the device associated with the current vehicle-side with abnormal driving operation to store and send its own monitored data to the cloud; a data backup module 403, which is used to store and back up the monitoring data sent by the current vehicle-side and / or the device associated with the current vehicle-side with abnormal driving operation and the judged possible abnormal driving operation event.
[0071] In some optional embodiments, the data monitoring module 402 includes: an operation scene matching unit, which is used to match the current vehicle-side operation scene with a pre-stored operation scene database that requires vehicle-side data backup. If the match is successful, it is determined that the current vehicle-side may have an operation failure event; a module status matching unit, which is used to compare the status information of each module on the current vehicle-side with the corresponding status data of each module on the vehicle-side when the vehicle is driving normally, to determine an abnormal vehicle-side module event with a data difference on the current vehicle-side, a collision accident judgment unit, which is used to judge whether there is a collision risk between the dynamic obstacle driving information in the current vehicle-side driving environment information and the vehicle-side driving trajectory sent by the current vehicle-side, and / or, to judge whether the current vehicle-side has any violation. If there is a collision risk, and / or the current vehicle-side has any violation, it is determined that the current vehicle-side may have an accident failure event.
[0072] In some optional embodiments, the data backup module 403 includes: a field filling unit, which is used to send the key fields corresponding to the possible abnormal driving operation events on the current vehicle side to the current vehicle side and / or the device side associated with the abnormal driving operation on the current vehicle side based on the different key field information that needs to be detected and stored corresponding to different abnormal driving operation events, so that the current vehicle side and / or the device side associated with the abnormal driving operation on the current vehicle side can perform data monitoring based on the key fields, and fill in the corresponding field information and upload it to the cloud.
[0073] In some optional embodiments, the data backup device also includes: a device identification storage module, which is used to obtain the identification information of other real-time data monitoring devices when it is detected that there are other real-time data monitoring devices in the current vehicle-side operation scene other than the current vehicle-side and / or the device side associated with the current vehicle-side driving operation abnormality, and store and back up the possible driving operation abnormality events in the current vehicle-side operation scene, so that the cloud can obtain the data monitored by other real-time data monitoring devices and restore the data based on the identification information of other real-time data monitoring devices stored corresponding to the driving operation abnormality events occurring on the current vehicle-side.
[0074] In some optional embodiments, the data backup module 403 includes: an impact level determination unit, which is used to determine the impact level of different monitored data based on the impact of the monitoring data sent by the current vehicle end and / or the device end associated with the current vehicle end with the driving operation abnormality on the judged possible driving operation abnormality events; a data backup unit, which is used to store and back up the data and the judged possible driving operation abnormality events according to the impact level of different monitored data.
[0075] In some optional embodiments, the data backup device also includes: a data restoration module, which is used to respond to abnormal driving operation events that actually occur during the driving process of the current vehicle end, and restore the data according to the impact level of each data when the backup is stored based on the actual abnormal driving operation events. This allows the user to handle the abnormal driving operation events based on the restored data.
[0076] In some optional embodiments, the data backup device also includes: a data conversion module, which is used to send the target data type corresponding to the set key field information to the current vehicle end and / or the device end associated with the current vehicle end with the driving operation abnormality, so that the current vehicle end and / or the device end associated with the current vehicle end with the driving operation abnormality will perform target data type conversion based on the data monitored by the key fields, and fill in the field information after the target data type conversion and upload it to the cloud.
[0077] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
[0078] The data backup device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0079] The embodiment of the present invention also provides a cloud having the above Figure 4 The data backup device shown.
[0080] See also Figure 5 , Figure 5 is a schematic diagram of a cloud structure provided by an optional embodiment of the present invention, such as Figure 5As shown, the cloud includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the cloud, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple clouds can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.
[0081] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0082] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.
[0083] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the cloud, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the cloud via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0084] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0085] The cloud also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5The example of connecting through bus is taken in the following.
[0086] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the cloud, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.
[0087] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0088] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A data backup method, characterized in that: Applied to the cloud, the method includes: Receiving driving operation information sent by the current vehicle end during driving, and judging whether there may be an abnormal driving operation event at the current vehicle end based on the driving operation information; If it is determined that the current vehicle end may have an abnormal driving operation event, a data backup instruction is sent to the current vehicle end and / or a device end associated with the abnormal driving operation of the current vehicle end, and the current vehicle end and / or a device associated with the abnormal driving operation of the current vehicle end are controlled to store their own monitoring data and send it to the cloud; The monitoring data sent by the current vehicle end and / or the equipment associated with the abnormal driving operation of the current vehicle end and the possible abnormal driving operation events that may be judged are stored and backed up.
2. The method according to claim 1, characterized in that The driving operation information at least includes the current vehicle-side operation scene, the current vehicle-side driving environment information and the current status information of each module on the vehicle-side. The cloud pre-stores the operation scene database that requires vehicle-side data backup and the corresponding vehicle-side module status data when the vehicle is driving normally. The driving operation abnormal event at least includes an operation failure event, a vehicle-side module abnormal event and an accident failure event. The judging whether the current vehicle-side may have a driving operation abnormal event based on the driving operation information includes: Match the current vehicle-side operation scene with the pre-stored operation scene database that requires vehicle-side data backup. If the match is successful, it is determined that there may be an operation failure event on the current vehicle-side; Compare the status information of each module on the current vehicle side with the status data of each module on the vehicle side corresponding to normal driving of the vehicle, and determine the abnormal events of the vehicle side modules with data differences on the current vehicle side; Determine whether there is a collision risk between the dynamic obstacle driving information in the current vehicle-side driving environment information and the vehicle-side driving trajectory sent by the current vehicle-side, and / or determine whether the current vehicle-side has any violations. If there is a collision risk, and / or the current vehicle-side has any violations, it is determined that the current vehicle-side may have an accident failure event.
3. The method according to claim 1 or 2, characterized in that: The sending of the data backup instruction to the current vehicle end and / or the device end associated with the current vehicle end having abnormal driving operation includes: Based on the different key field information that needs to be detected and stored corresponding to different abnormal driving operation events, the key fields corresponding to the abnormal driving operation events that may exist on the current vehicle side are sent to the current vehicle side and / or the device side associated with the current vehicle side with the abnormal driving operation, so that the current vehicle side and / or the device side associated with the current vehicle side with the abnormal driving operation performs data monitoring based on the key fields, and fills in the corresponding field information and uploads it to the cloud.
4. The method according to claim 2, characterized in that: The method further comprises: When it is detected that there are other real-time data monitoring devices in the current vehicle-side operation scene other than the current vehicle-side and / or the device side associated with the current vehicle-side driving operation abnormality, the identification information of the other real-time data monitoring devices is obtained, and the abnormal driving operation events that may exist in the current vehicle-side operation scene are stored and backed up, so that the cloud can obtain the data monitored by the other real-time data monitoring devices and restore the data based on the identification information of the other real-time data monitoring devices stored corresponding to the abnormal driving operation events occurring on the current vehicle-side.
5. The method according to claim 1, characterized in that The storing and backing up of the monitoring data sent by the current vehicle end and / or the device end associated with the current vehicle end having abnormal driving operation and the possible abnormal driving operation events determined include: Determine the influence level of different monitored data based on the influence of the monitored data sent by the current vehicle end and / or the device end associated with the current vehicle end having the abnormal driving operation on the determined possible abnormal driving operation event; The data and possible abnormal driving operation events that may exist are stored and backed up according to the impact level of different monitored data.
6. The method according to claim 1 or 5, characterized in that: The method further comprises: In response to abnormal driving operation events that actually occur during the driving process of the current vehicle, the data is restored according to the impact level of each data when the backup is stored, based on the actual abnormal driving operation events. This allows the user to handle the abnormal driving operation events based on the restored data.
7. The method according to claim 3, characterized in that The cloud and the vehicle are pre-set with target data type conversion rules, and the method further includes: The target data type corresponding to the set key field information is sent to the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormality, so that the current vehicle end and / or the device end associated with the current vehicle end with driving operation abnormality will convert the target data type based on the data monitored by the key fields, and fill in the field information after the target data type conversion and upload it to the cloud.
8. A data backup device, characterized in that: Applied to the cloud, the device includes: A vehicle operation judgment module is used to receive the driving operation information sent by the current vehicle during driving, and judge whether there is a possible driving operation abnormality event on the current vehicle based on the driving operation information; The data monitoring module is used to send a data backup instruction to the current vehicle end and / or a device end associated with the current vehicle end having the abnormal driving operation event if it is determined that the current vehicle end may have an abnormal driving operation event, and control the current vehicle end and / or a device associated with the current vehicle end having the abnormal driving operation event to store the data monitored by itself and send it to the cloud; The data backup module is used to store and back up the monitoring data sent by the current vehicle end and / or the equipment associated with the current vehicle end having abnormal driving operations and the possible abnormal driving operation events that may be judged.
9. A vehicle, characterized in that: The vehicle includes a vehicle end.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the data backup method according to any one of claims 1 to 7.
