Automatic driving data recording method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an automatic driving data recording method and device, equipment and a storage medium, and the method comprises the steps: obtaining multiple pieces of driving description information in response to a triggering event of automatic driving data recording; wherein the types of the driving description information comprise vehicle basic information, vehicle state information, automatic driving system operation information, driving environment information and driver operation information; column vectors corresponding to all types of driving description information are constructed, and a vehicle data matrix is generated according to all the column vectors; label information used for describing the column vector position of each type of driving description information in the vehicle data matrix is constructed; and according to the type of the trigger event, the vehicle data matrix and the label information are stored in the target partition of the target database in an associated manner for a user to read and analyze, so that the data acquisition range can be expanded, the data transmission efficiency can be improved, and a data basis is provided for vehicle accident reason analysis and responsibility definition.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving data recording method, device, equipment and storage medium. Background Art

[0002] At present, with the development of vehicle intelligent technology, the number of autonomous driving accidents is gradually increasing. Since autonomous driving vehicles generate massive amounts of data all the time, it is difficult to quickly locate the data when the accident occurred, making accident analysis difficult.

[0003] In the prior art, driving description information is usually collected through a driving recorder or an event data recording system, and the driving description information is directly uploaded to a data receiving end.

[0004] However, since the dashcam can only collect external video and vehicle positioning information, and the event data recording system can only collect key operating information of the vehicle, the data collected by the existing technology is small, making it difficult to accurately determine the responsibility for the accident. Secondly, since the collected driving description information is usually large, directly uploading the driving description information to the data receiving end will result in a slow transmission rate of the driving description information. Summary of the invention

[0005] The present invention provides an automatic driving data recording method, device, equipment and storage medium, which can expand the scope of data collection, improve data transmission efficiency, and provide a data basis for vehicle accident cause analysis and responsibility definition.

[0006] In a first aspect, an embodiment of the present invention provides an automatic driving data recording method, the method comprising:

[0007] Responsive to a triggering event recorded by the autonomous driving data, obtaining a plurality of driving description information;

[0008] The types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information;

[0009] Constructing column vectors corresponding to each type of driving description information, and generating a vehicle data matrix according to each column vector;

[0010] Constructing label information for describing the column vector position of each type of driving description information in the vehicle data matrix;

[0011] According to the type of triggering event, the vehicle data matrix and tag information are associated and stored in the target partition of the target database for users to read and parse.

[0012] Optionally, after generating a vehicle data matrix according to each column vector, it also includes: fitting and determining a weight matrix between each column vector in the vehicle data matrix, wherein the weight matrix is ​​used to describe the data correlation between each vector element in the two column vectors; according to the type of triggering event, storing the vehicle data matrix in a target partition of a target database, further including: according to the type of triggering event, storing the vehicle data matrix and the weight matrix between each column vector in the vehicle data matrix in a target partition of a target database.

[0013] Optionally, according to the type of triggering event, the vehicle data matrix and the weight matrix between each pair of column vectors in the vehicle data matrix are stored in the target partition of the target database, further including: encrypting the vehicle data matrix and the weight matrix between each pair of column vectors in the vehicle data matrix according to a pre-generated symmetric key to obtain a content encryption result; encrypting the symmetric key according to a pre-generated asymmetric public key to obtain a key encryption result, and storing the content encryption result and the key encryption result in the target partition of the target database.

[0014] Optionally, the method further includes: storing event data corresponding to the triggering event in an event database; and storing the symmetric key, the asymmetric public key, and the asymmetric key corresponding to the asymmetric public key in a security database.

[0015] Optionally, depending on the type of triggering event, the vehicle data matrix is ​​stored in a target partition of a target database, including: if the storage capacity in the target partition is greater than or equal to a preset storage capacity threshold, then after uploading the data stored in the target partition to the target storage space, the vehicle data matrix is ​​stored in the target partition of the target database; or, after deleting the historical data in the target partition that is farthest from the storage time of the vehicle data matrix, the vehicle data matrix is ​​stored in the target partition of the target database.

[0016] In a second aspect, an embodiment of the present invention provides a method for reading autonomous driving data, the method comprising: obtaining a vehicle data matrix of any embodiment of the present invention from a target partition of a target database; and reading column vectors corresponding to each type of driving description information from the vehicle data matrix according to label information associated with the vehicle data matrix.

[0017] Optionally, after reading the column vectors corresponding to each type of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix, the method further includes: if it is determined that the target column vector corresponding to the driving description information of the target type is missing in the vehicle data matrix, detecting the vehicle data matrix to obtain at least one auxiliary recovery column vector; combining the target column vector with each auxiliary recovery column vector to obtain a column vector pair, and obtaining a target weight matrix corresponding to each column vector pair from the target partition of the target database; and restoring the target column vector according to each target weight matrix and the auxiliary recovery column vector matching each target weight matrix.

[0018] In a third aspect, an embodiment of the present invention further provides an automatic driving data recording device, the device comprising:

[0019] A driving information acquisition module, configured to acquire a plurality of driving description information in response to a triggering event recorded by the autonomous driving data;

[0020] The types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information;

[0021] A data matrix generation module is used to construct column vectors corresponding to various types of driving description information, and generate a vehicle data matrix according to each column vector;

[0022] A label information construction module, used to construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix;

[0023] The data storage module is used to associate and store the vehicle data matrix and tag information in the target partition of the target database according to the type of triggering event, so that users can read and parse it.

[0024] In a fourth aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0025] at least one processor; and

[0026] a memory communicatively connected to at least one processor; wherein,

[0027] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the autonomous driving data recording method or the autonomous driving data reading method provided by any embodiment of the present invention.

[0028] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the autonomous driving data recording method or the autonomous driving data reading method provided by any embodiment of the present invention when executed.

[0029] The technical solution of the embodiment of the present invention solves the problem of small data range collected by the existing technology by acquiring basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information, and can fully acquire the data required for accident cause analysis. Secondly, by constructing column vectors corresponding to each type of driving description information, and transmitting data according to the vehicle data matrix generated by each column vector, the data transmission efficiency is improved.

[0030] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 is a flowchart of an automatic driving data recording method provided according to Embodiment 1 of the present invention;

[0033] Figure 2 is a flowchart of another method for recording automatic driving data provided according to Embodiment 2 of the present invention;

[0034] Figure 3 is a flow chart of a data encryption method provided according to an embodiment of the present invention;

[0035] Figure 4 is a flowchart of an automatic driving data reading method provided according to Embodiment 3 of the present invention;

[0036] Figure 5 is a schematic diagram of the structure of an automatic driving data recording device provided according to a fourth embodiment of the present invention;

[0037] Figure 6 is a schematic diagram of the structure of an automatic driving data reading device provided according to Embodiment 5 of the present invention;

[0038] Figure 7It is a schematic diagram of the structure of an electronic device provided by Embodiment 6 of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] Embodiment 1

[0042] Figure 1 This is a flowchart of an autonomous driving data recording method provided according to Embodiment 1 of the present invention. This embodiment is applicable to the case of recording autonomous driving data. The method can be executed by an autonomous driving data recording device. The autonomous driving data recording device can be implemented in the form of hardware and / or software. The autonomous driving data recording device can be configured in an electronic device.

[0043] like Figure 1 As shown, an automatic driving data recording method disclosed in this embodiment includes:

[0044] S110. In response to a triggering event recorded by the autonomous driving data, obtain multiple pieces of driving description information.

[0045] In this embodiment, the trigger event may be an event that can trigger the automatic driving description information acquisition operation. There may be multiple trigger events, such as a collision event, a collision risk event, an automatic driving system state change event, and a system failure event.

[0046] In this step, specifically, after receiving the trigger event, it is possible to obtain basic vehicle information, vehicle status information collected in real time through vehicle sensors and bus network signals, autonomous driving system operation information collected in real time through the vehicle autonomous driving domain control system, driving environment information collected in real time through vehicle external cameras, millimeter-wave radars and other sensors, and driver operation information collected in real time through vehicle internal sensors or bus network signals.

[0047] Among them, the basic vehicle information may include the vehicle identification number (VIN), vehicle software version number, vehicle hardware version number, serial number, type code of the trigger event, complete flag of the trigger event, time, longitude and latitude, cumulative mileage and heading angle, etc. The vehicle status information may include dynamic information such as vehicle speed, lateral acceleration, longitudinal angular velocity, yaw angular velocity and roll angular velocity. The automatic driving system operation information may include the lateral control decision information of the automatic driving system, the longitudinal control decision information of the automatic driving system, the automatic driving system's decision information on lights and wipers, etc. The driving environment information may include relevant information of the perceived target such as the type of the perceived target, relative position and relative speed, and external image or video data such as images or videos of the vehicle forward, left, right and backward. The driver operation information may include the driver's operation information, the driver's safety status, the driver's ability to take over, whether the seat belt is fastened, whether the driver is in the driving position, etc. The above-mentioned driver's operation information may include the accelerator pedal opening, the brake pedal opening, the brake pedal status, the steering wheel angle and the steering torque, etc.

[0048] The advantage of this setting is that the use of an event-triggered mechanism can reduce the frequency of data transmission, reduce data redundancy, and ensure that data at critical moments is accurately recorded.

[0049] Optionally, after obtaining multiple driving description information, the multiple driving description information can be stored in a preset interactive information template in JavaScript Object Notation (JSON) format to obtain a vehicle interaction report, and the vehicle data report can be stored in an interactive report table of the event database.

[0050] S120, constructing column vectors corresponding to each type of driving description information, and generating a vehicle data matrix according to each column vector.

[0051] In this embodiment, each item of driving description information corresponds to at least one dimension. For example, vehicle status information may include dimensions such as position, speed, and acceleration.

[0052] In this step, specifically, for each trigger event, according to the number of types of driving description information, a multidimensional vector data chain including multiple nodes can be constructed. Among them, each node is used to process a corresponding type of driving description information. Then, a data vectorization method can be used to construct column vectors corresponding to each type of driving description information. Among them, there can be many data vectorization methods, such as principal component analysis and singular value decomposition. Finally, a vehicle data matrix can be generated based on each column vector and the processing priority of the node corresponding to each column vector. Optionally, a PID control algorithm (Proportion Integral Differential, PID) can be used to automatically adjust the processing priority of the node according to the node load and processing speed, and an optimization algorithm can be used so that the multidimensional vector data chain can achieve the best effect under different conditions.

[0053] For example, assuming that there are N nodes and each node contains data of M dimensions, an M×N vehicle data matrix can be generated. The specific formula of the vehicle data matrix is ​​as follows:

[0054]

[0055] Where A is the vehicle data matrix, [a1n, a2n, …, amn] T is the column vector of the nth column.

[0056] Optionally, a node may be added to the multidimensional vector data chain by adding a column vector to the vehicle data matrix; a node may be deleted from the multidimensional vector data chain by deleting a column vector from the vehicle data matrix.

[0057] S130: Construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix.

[0058] In this step, specifically, after each column vector is added to the vehicle data matrix, label information corresponding to each column vector may be generated.

[0059] S140. According to the type of the triggering event, the vehicle data matrix and the tag information are associated and stored in a target partition of the target database for the user to read and parse.

[0060] In this step, specifically, the type of the triggering event can be determined by identifying the identifier of the triggering event. Then, after obtaining the target database corresponding to the vehicle data matrix, the target partition corresponding to the type of the triggering event can be obtained, and the vehicle data matrix and the tag information can be associated and stored in the target partition of the target database. For example, the target partitions corresponding to the collision event and the collision risk event are different. Since the database is a non-volatile memory, by associating and storing the vehicle data matrix and the tag information in the target database, it is possible to ensure that the data is stored in an orderly manner while avoiding data loss after power failure.

[0061] In an optional implementation of an embodiment of the present invention, the vehicle data matrix is ​​stored in a target partition of a target database according to the type of triggering event, including: if the storage capacity in the target partition is greater than or equal to a preset storage capacity threshold, then after uploading the data stored in the target partition to the target storage space, the vehicle data matrix is ​​stored in the target partition of the target database; or, after deleting the historical data in the target partition that is farthest from the storage time of the vehicle data matrix, the vehicle data matrix is ​​stored in the target partition of the target database.

[0062] In a specific implementation, when the storage capacity in the target partition is greater than or equal to a preset storage capacity threshold, the type of data stored in the target partition can be determined. If all data are lock event data, all lock event data are uploaded to the target storage space.

[0063] The advantage of this setting is that by uploading the data stored in the target partition to the target storage space, the storage space can be flexibly used, the stability and reliability of the system using the target database can be guaranteed, and the basis for accident cause analysis and responsibility determination can be improved. Secondly, by overwriting data in the same target partition using the first-in-first-out principle, the latest data can be retained.

[0064] The technical solution of this embodiment obtains multiple driving description information in response to a triggering event recorded by the automatic driving data; wherein the types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information; constructs column vectors corresponding to each type of driving description information, and generates a vehicle data matrix according to each column vector; constructs label information for describing the column vector position of each type of driving description information in the vehicle data matrix; according to the type of triggering event, associates the vehicle data matrix and the label information and stores them in a target partition of the target database for users to read and parse. The technical solution solves the problem that data collection and transmission through existing technologies result in a small data collection range and low data transmission efficiency, expands the data collection range, improves data transmission efficiency, and provides a data basis for vehicle accident cause analysis and responsibility definition.

[0065] Embodiment 2

[0066] Figure 2 It is a flowchart of another method for recording autonomous driving data provided according to the second embodiment of the present invention. This embodiment is a further optimization and expansion based on the above embodiments, and can be combined with various optional technical solutions in the above implementation methods.

[0067] like Figure 2 As shown, an automatic driving data recording method disclosed in this embodiment includes:

[0068] S210: In response to a triggering event recorded in the autonomous driving data, obtain multiple pieces of driving description information.

[0069] Among them, the types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information.

[0070] Optionally, when acquiring multiple driving description information, for sensors that need to collect data at a high frequency, such as lidar and cameras, a high-speed data bus can be used for transmission to ensure high-precision collection of sensors that need to collect data at a high frequency.

[0071] Optionally, after obtaining multiple driving description information, the collected data can be temporarily stored so that when there is a problem or delay in network transmission, the data can still be recorded, thereby avoiding data loss.

[0072] Optionally, multiple pieces of driving description information corresponding to the triggering event may be uploaded to the remote monitoring center based on the severity level of the triggering event for real-time response and scheduling.

[0073] S220, constructing column vectors corresponding to each type of driving description information, and generating a vehicle data matrix according to each column vector.

[0074] Optionally, the similarity or difference of different driving description information in each dimension can be measured by a multi-dimensional Euclidean distance formula.

[0075] Optionally, the operation of acquiring multiple driving description information may be performed synchronously with the operation of generating the vehicle data matrix, that is, while collecting the driving description information corresponding to the current trigger event, the vehicle data matrix corresponding to another trigger event may be generated.

[0076] S230, fitting and determining a weight matrix between two column vectors in the vehicle data matrix, wherein the weight matrix is ​​used to describe the data correlation between each vector element in two column vectors.

[0077] In this step, specifically, two non-repeating column vectors can be obtained in the vehicle data matrix, and a weight matrix between the two column vectors can be determined. It is determined whether the processing of any two column vectors in the vehicle data matrix is ​​completed. If not, the operation of obtaining two non-repeating column vectors in the vehicle data matrix is ​​returned to execute until the processing of any two column vectors in the vehicle data matrix is ​​completed.

[0078] For example, assuming that there are N column vectors and the dimension of each column vector is 3, the following vehicle data matrix can be generated:

[0079]

[0080] Among them, A is the vehicle data matrix.

[0081] Then, the weight matrix between the two column vectors can be determined according to the following specific calculation formula:

[0082] Ai=W·Aj

[0083] Among them, Ai is the i-th column vector in the vehicle data matrix, Aj is the j-th column vector in the vehicle data matrix, and W is the weight matrix between the i-th column vector and the j-th column vector.

[0084] Specifically, W is a 3×3 matrix, and the specific formula of W is as follows:

[0085]

[0086] S240: Construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix.

[0087] S250. According to the type of the triggering event, the vehicle data matrix and the weight matrix between the column vectors in the vehicle data matrix are stored in the target partition of the target database for the user to read and parse.

[0088] In this step, specifically, after obtaining the target database corresponding to the vehicle data matrix, the target partition corresponding to the type of the triggering event can be obtained, and the vehicle data matrix, label information and each weight matrix are associated and stored in the target partition of the target database.

[0089] Figure 3 The present invention provides a flowchart of a data encryption method according to an embodiment of the present invention.

[0090] In an alternative implementation, Figure 3 As shown, S250 may specifically include:

[0091] S251. Encrypt the vehicle data matrix and the weight matrix between each pair of column vectors in the vehicle data matrix respectively according to the pre-generated symmetric key to obtain a content encryption result.

[0092] In this embodiment, the pre-generated symmetric key can be updated periodically according to user needs.

[0093] In this step, specifically, a symmetric key can be generated by a symmetric encryption algorithm (Advanced Encryption Standard, AES), and the vehicle data matrix and each weight matrix corresponding to the vehicle data matrix are encrypted according to the symmetric key to obtain a content encryption result. Optionally, when abnormal activities or malicious intrusions are detected, the data encryption operation can be interrupted in time to avoid leakage of sensitive information.

[0094] S252. Encrypt the symmetric key according to the pre-generated asymmetric public key to obtain a key encryption result, and store the content encryption result and the key encryption result in the target partition of the target database for users to read and parse.

[0095] In this embodiment, the pre-generated asymmetric public key can be updated regularly according to user needs.

[0096] In this step, specifically, an asymmetric public key and an asymmetric private key can be generated by an elliptic curve encryption algorithm. Then, the asymmetric public key can be used to encrypt the symmetric key to obtain a key encryption result. Optionally, after the content encryption result and the key encryption result are transmitted to the target database, the key encryption result can be decrypted using an asymmetric private key to obtain a symmetric key. Among them, the asymmetric private key can be updated regularly according to user needs. Then, decryption can be performed based on the symmetric key content encryption result, and the decrypted driving description information can be stored in different data tables of the target database. For example, the basic information of the vehicle can be stored in the basic information table of the vehicle, and the vehicle status information can be stored in the vehicle status information table.

[0097] The advantage of this setting is that, since symmetric encryption is faster, encrypting a large amount of data such as the vehicle data matrix and the weight matrix with a symmetric key can improve data encryption efficiency. Secondly, after encrypting the vehicle data matrix and the weight matrix with a symmetric key, encrypting the symmetric key with an asymmetric key can improve data security while ensuring data encryption efficiency.

[0098] In an optional implementation, the event data corresponding to the triggering event may be stored in an event database. The event data may include an event number, a vehicle identification code, an event type, event data, and a timestamp. The symmetric key, the asymmetric public key, and the asymmetric key corresponding to the asymmetric public key are stored in a security database; and the relevant information of the multidimensional vector data link is stored in a link database. The relevant information of the multidimensional vector data link may include a vehicle identification code, a data link identifier, and data link information.

[0099] In a specific implementation, the event data may be stored in an event data table of an event database. The symmetric key, the asymmetric public key, and the asymmetric key corresponding to the asymmetric public key may be stored in a security information table of a security database. The relevant information of the multidimensional vector data link may be stored in a data link information table of a link database. The target database is a first-layer database, the event database is a second-layer database, the security database is a third-layer database, and the link database is a fourth-layer database.

[0100] The advantage of this setting is that by storing different types of data in different databases, data can be classified and isolated, improving the stability and maintainability of the system. Secondly, by setting different uses for databases at different levels, efficient management and secure storage of data are ensured.

[0101] The technical solution of this embodiment is to determine the weight matrix between two column vectors in the vehicle data matrix by fitting, wherein the weight matrix is ​​used to describe the data correlation between each vector element in the two column vectors; construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix; according to the type of triggering event, the vehicle data matrix and the weight matrix between two column vectors in the vehicle data matrix are stored in the target partition of the target database for user reading and parsing. The technical means solves the problem of data collection and transmission through the existing technology, resulting in a small data collection range and low data transmission efficiency. The weight matrix between two column vectors in the vehicle data matrix is ​​determined by fitting, which facilitates the subsequent recovery of lost column vectors.

[0102] Embodiment 3

[0103] Figure 4 It is a flowchart of an autonomous driving data reading method provided according to the third embodiment of the present invention. This embodiment is applicable to the case of reading recorded autonomous driving data. The method can be executed by an autonomous driving data reading device. The autonomous driving data reading device can be implemented in the form of hardware and / or software. The autonomous driving data reading device can be configured in an electronic device.

[0104] like Figure 4 As shown, a method for reading autonomous driving data disclosed in this embodiment includes:

[0105] S310. Obtain the vehicle data matrix of any embodiment of the present invention from the target partition of the target database.

[0106] In this step, specifically, the vehicle data matrix can be obtained from the target partition of the target database through a unified data reading port and protocol that conforms to the technical specifications of the on-board diagnostic system management of light vehicles. Among them, the data reading port conforms to the preset international standard rules, and the protocol is the Diagnosis Over Internet Protocol (DoIP) based on IP.

[0107] The benefit of this setup is that by setting up a unified data reading port and protocol, the data reading process can be independent of the vehicle manufacturer, which means that third parties can extract data according to the standard without additional customized development, thereby improving the flexibility and portability of the system. Secondly, through a unified data extraction method, consistent extraction of vehicle and component-level data can be achieved, which reduces dependence on vehicle manufacturers while making data reading and analysis more convenient and reliable.

[0108] S320 . Read column vectors corresponding to each type of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix.

[0109] In an optional implementation of an embodiment of the present invention, after reading the column vectors corresponding to each type of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix, it also includes: if it is determined that the target column vector corresponding to the driving description information of the target type is missing in the vehicle data matrix, then detecting the vehicle data matrix to obtain at least one auxiliary recovery column vector; combining the target column vector with each auxiliary recovery column vector to obtain a column vector pair, and obtaining a target weight matrix corresponding to each column vector pair from the target partition of the target database; and restoring the target column vector according to each target weight matrix and the auxiliary recovery column vector matching each target weight matrix.

[0110] In a specific implementation, one of the target weight matrices corresponding to the target column vector may be selected as the current target weight matrix, and the target column vector may be recovered based on the current target weight matrix and the current auxiliary recovery column vector matching the current target weight matrix.

[0111] The advantage of this setting is that by restoring the target column vector through the target weight matrix, the vehicle data matrix can be accurately determined, thereby improving the accuracy of vehicle accident cause analysis and liability determination results.

[0112] In an optional implementation of an embodiment of the present invention, after reading the vehicle data matrix, each item of driving description information can be parsed by a parser with a predefined data format to obtain driving description information corresponding to each column vector in the vehicle data matrix. Exemplarily, the real-time state of the vehicle can be obtained by parsing the column vector corresponding to the vehicle state information. The driver's behavior and the driving state of the vehicle can be obtained by parsing the column vector corresponding to the driver's operation information. Optionally, considering the dynamic changes of factors such as vehicle type and sensor configuration, the parameters of the parser can be dynamically adjusted according to the specific configuration of the current vehicle to adapt to the data parsing requirements of different models.

[0113] The advantage of this setting is that by deeply analyzing each driving description information, it can provide a high-quality data foundation for subsequent data analysis and application, meeting the needs of different vehicles and application scenarios.

[0114] The technical solution of this embodiment obtains the vehicle data matrix of any embodiment of the present invention from the target partition of the target database; and reads the column vectors corresponding to each type of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix. This can analyze the cause of the vehicle accident and define the responsibility based on the various types of driving description information, thereby improving the accuracy of the vehicle accident cause analysis and responsibility definition results.

[0115] Based on the above embodiments, the present invention provides an autonomous driving data management system equipped with an autonomous driving data recording device and an autonomous driving data reading device. After receiving a trigger event, the system can collect, record, read and parse various driving description information, so that users can handle traffic accidents corresponding to the trigger event in a timely manner according to the various driving description information.

[0116] Embodiment 4

[0117] Figure 5 It is a structural diagram of an autonomous driving data recording device provided according to Embodiment 4 of the present invention. This embodiment can be applied to the situation of recording autonomous driving data. The autonomous driving data recording device can be implemented in the form of hardware and / or software and can be configured in an electronic device.

[0118] like Figure 5 As shown, the automatic driving data recording device disclosed in this embodiment includes:

[0119] A driving information acquisition module 51, for acquiring a plurality of driving description information in response to a triggering event recorded by the autonomous driving data;

[0120] The types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information;

[0121] A data matrix generation module 52 is used to construct column vectors corresponding to each type of driving description information, and generate a vehicle data matrix according to each column vector;

[0122] A label information construction module 53, used to construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix;

[0123] The data storage module 54 is used to associate and store the vehicle data matrix and tag information in a target partition of a target database according to the type of triggering event, so as to provide reading and analysis for users.

[0124] The technical solution in this embodiment solves the problem of data collection and transmission through existing technologies, resulting in a small data collection range and low data transmission efficiency, through the mutual cooperation of a driving information acquisition module, a data matrix generation module, a label information construction module and a data storage module. It expands the data collection range, improves the data transmission efficiency, and provides a data basis for vehicle accident cause analysis and responsibility definition.

[0125] Optionally, the device further includes a weight matrix determination module, which is specifically used to:

[0126] The weight matrix between two column vectors in the vehicle data matrix is ​​determined by fitting, wherein the weight matrix is ​​used to describe the data correlation between each vector element in the two column vectors.

[0127] Optionally, the data storage module 54 includes:

[0128] A matrix storage unit, used for storing the vehicle data matrix and the weight matrix between two column vectors in the vehicle data matrix into the target partition of the target database according to the type of the triggering event;

[0129] A content encryption unit, used for encrypting the vehicle data matrix and the weight matrix between two column vectors in the vehicle data matrix respectively according to a pre-generated symmetric key to obtain a content encryption result;

[0130] A key encryption unit is used to encrypt the symmetric key according to the pre-generated asymmetric public key to obtain a key encryption result, and store the content encryption result and the key encryption result in a target partition of the target database;

[0131] A storage space management unit is used to store the vehicle data matrix in the target partition of the target database after uploading the data stored in the target partition to the target storage space if the storage capacity in the target partition is greater than or equal to a preset storage capacity threshold; or to store the vehicle data matrix in the target partition of the target database after deleting the historical data in the target partition that is farthest away from the storage time of the vehicle data matrix.

[0132] Optionally, the device further includes a database storage module, which includes:

[0133] An event data storage unit, used for storing event data corresponding to a triggering event into an event database;

[0134] The key data storage unit is used to store the symmetric key, the asymmetric public key, and the asymmetric key corresponding to the asymmetric public key in a security database.

[0135] The automatic driving data recording device provided in the embodiment of the present invention can execute the automatic driving data recording method provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For the contents not described in detail in this embodiment, please refer to the description in any method embodiment of this application.

[0136] Embodiment 5

[0137] Figure 6 It is a structural diagram of an autonomous driving data reading device provided according to Embodiment 5 of the present invention. This embodiment can be applied to the case of reading recorded autonomous driving data. The autonomous driving data reading device can be implemented in the form of hardware and / or software and can be configured in an electronic device.

[0138] like Figure 6 As shown, the automatic driving data reading device disclosed in this embodiment includes:

[0139] A data matrix acquisition module 61 is used to acquire a vehicle data matrix according to any embodiment of the present invention from a target partition of a target database;

[0140] The column vector acquisition module 62 is used to read the column vectors corresponding to each type of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix.

[0141] The technical solution in this embodiment, through the mutual cooperation of the production load determination module and the production management prompt module, can analyze the cause of the vehicle accident and define the responsibility based on various types of driving description information, thereby improving the accuracy of the vehicle accident cause analysis and responsibility definition results.

[0142] Optionally, the device further includes a column vector recovery module, which is specifically used to:

[0143] If it is determined that the target column vector corresponding to the driving description information of the target type is missing in the vehicle data matrix, then detecting the vehicle data matrix to obtain at least one auxiliary recovery column vector;

[0144] The target column vector is combined with each auxiliary recovery column vector to obtain a column vector pair, and a target weight matrix corresponding to each column vector pair is obtained from the target partition of the target database;

[0145] According to each target weight matrix and the auxiliary recovery column vector matched with each target weight matrix, the target column vector is recovered.

[0146] The autonomous driving data reading device provided in the embodiment of the present invention can execute the autonomous driving data reading method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For the contents not described in detail in this embodiment, please refer to the description in any method embodiment of this application.

[0147] Embodiment 6

[0148] Figure 7 FIG. 1 is a schematic diagram showing the structure of an electronic device 10 that can be used to implement an embodiment of the present invention. Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0149] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0150] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as autonomous driving data recording or autonomous driving data reading methods.

[0151] In some embodiments, the autonomous driving data recording method or the autonomous driving data reading method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the autonomous driving data recording method or the autonomous driving data reading method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the autonomous driving data recording or autonomous driving data reading method in any other appropriate manner (e.g., by means of firmware).

[0152] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0157] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0158] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0159] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic driving data recording method, characterized in that: The method comprises: Responsive to a triggering event recorded by the autonomous driving data, obtaining a plurality of driving description information; The types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information; Constructing column vectors corresponding to each type of the driving description information, and generating a vehicle data matrix according to each of the column vectors; Constructing label information for describing the column vector position of each type of the driving description information in the vehicle data matrix; According to the type of triggering event, the vehicle data matrix and the tag information are associated and stored in a target partition of a target database for users to read and parse.

2. The method according to claim 1, characterized in that After generating a vehicle data matrix according to each of the column vectors, the method further includes: Fitting and determining a weight matrix between two column vectors in the vehicle data matrix, wherein the weight matrix is ​​used to describe the data correlation between each vector element in two column vectors; According to the type of triggering event, the vehicle data matrix is ​​stored in the target partition of the target database, further comprising: according to the type of triggering event, the vehicle data matrix and the weight matrix between each pair of column vectors in the vehicle data matrix are stored in the target partition of the target database.

3. The method according to claim 2, characterized in that According to the type of the triggering event, the vehicle data matrix and the weight matrix between the column vectors in the vehicle data matrix are stored in the target partition of the target database, further comprising: According to the pre-generated symmetric key, the vehicle data matrix and the weight matrix between two column vectors in the vehicle data matrix are encrypted respectively to obtain a content encryption result; The symmetric key is encrypted according to the pre-generated asymmetric public key to obtain a key encryption result, and the content encryption result and the key encryption result are stored in a target partition of a target database.

4. The method according to claim 3, characterized in that The method further comprises: storing event data corresponding to the trigger event in an event database; The symmetric key, the asymmetric public key, and the asymmetric key corresponding to the asymmetric public key are stored in a secure database.

5. The method according to claim 1, characterized in that According to the type of triggering event, the vehicle data matrix is ​​stored in a target partition of a target database, including: If the storage capacity in the target partition is greater than or equal to the preset storage capacity threshold, after uploading the data stored in the target partition to the target storage space, the vehicle data matrix is ​​stored in the target partition of the target database; or, After deleting the historical data in the target partition that is farthest away from the storage time of the vehicle data matrix, the vehicle data matrix is ​​stored in the target partition of the target database.

6. A method for reading data for autonomous driving, characterized in that: The method comprises: Obtaining the vehicle data matrix according to any one of claims 1 to 5 from a target partition of a target database; According to the label information associated with the vehicle data matrix, column vectors respectively corresponding to each type of driving description information are read from the vehicle data matrix.

7. The method according to claim 6, characterized in that After reading the column vectors corresponding to the various types of driving description information from the vehicle data matrix according to the label information associated with the vehicle data matrix, the method further includes: If it is determined that the target column vector corresponding to the driving description information of the target type is missing in the vehicle data matrix, detecting the vehicle data matrix to obtain at least one auxiliary recovery column vector; Combining the target column vector with each of the auxiliary recovery column vectors to obtain a column vector pair, and acquiring a target weight matrix corresponding to each column vector pair from a target partition of a target database; The target column vector is restored according to each of the target weight matrices and the auxiliary restored column vector matched with each of the target weight matrices.

8. An automatic driving data recording device, characterized in that: The device comprises: A driving information acquisition module, configured to acquire a plurality of driving description information in response to a triggering event recorded by the autonomous driving data; The types of driving description information include: basic vehicle information, vehicle status information, automatic driving system operation information, driving environment information and driver operation information; A data matrix generation module, used to construct column vectors corresponding to each type of driving description information, and generate a vehicle data matrix according to each column vector; A label information construction module, used to construct label information for describing the column vector position of each type of driving description information in the vehicle data matrix; The data storage module is used to associate and store the vehicle data matrix and the tag information in a target partition of a target database according to the type of triggering event, so as to provide reading and analysis for users.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the autonomous driving data recording method described in any one of claims 1-5 or the autonomous driving data reading method described in any one of claims 6-7.

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 processor to implement the autonomous driving data recording method described in any one of claims 1-5 or the autonomous driving data reading method described in any one of claims 6-7 when executed.

Images