Data optimization system, method and product of intelligent connected automobile

Abstract

The embodiment of the invention provides a data optimization system, method and product for an intelligent connected automobile, and the system comprises a simulation model module which is used for carrying out the simulation processing of historical operation data in a historical data storage unit through a simulation model, and obtaining simulation data which is the range data of the reasonable operation state of the current automobile; the data comparison module is used for comparing the original operation data collected in real time with the simulation data and determining whether the original operation data is abnormal or not; the data optimization module is used for optimizing and correcting the abnormal original operation data according to the historical operation data in the historical data storage unit under the condition that the original operation data is abnormal, and obtaining optimized and corrected target operation data; and the historical data storage unit is used for storing the normal original operation data and the abnormal optimized and corrected target operation data. The invention aims to improve the accuracy of abnormal operation data correction.

Description

Technical Field

[0001] This application relates to the technical field of data management, and particularly relates to a data optimization system, method and product for intelligent connected vehicles. Background Art

[0002] With the rapid development of automotive intelligent and connected technologies, data inside and outside the vehicle (such as sensor data, GPS positioning data, user behavior data, etc.) have become crucial for vehicle performance improvement, safety guarantee, and user experience optimization, providing important support for functions such as vehicle control, fault diagnosis, and navigation services. However, in practical applications, the quality of this data is often affected by various factors, such as sensor errors, signal interference, transmission delays, etc., resulting in abnormal or distorted data.

[0003] Currently, the methods for monitoring the quality of automotive data usually adopt a post - analysis approach, that is, after the data has been generated and stored, its quality is evaluated and processed. At the same time, the way to process abnormal data usually uses methods such as filtering outliers or interpolation for data filling. This method has deficiencies such as poor real - time performance and processing lag, and at the same time, the correction accuracy of this abnormal data correction method is insufficient. Summary of the Invention

[0004] In view of this, this application provides a data optimization system, method and product for intelligent connected vehicles, aiming to improve the accuracy of correcting abnormal operation data.

[0005] In the first aspect of this application, a data optimization system for intelligent connected vehicles is provided. The system includes:

[0006] A simulation model module, which is used to perform simulation processing on the historical operation data in the historical data storage unit through a simulation model to obtain simulation data, and the simulation data is the range data of the reasonable operation state of the current vehicle;

[0007] A data comparison module, which is used to compare the originally collected real - time operation data with the simulation data to determine whether the originally collected operation data is abnormal;

[0008] A data optimization module, which is used to optimize and correct the abnormal originally collected operation data according to the historical operation data in the historical data storage unit in the case where the originally collected operation data is abnormal, to obtain the target operation data after optimization and correction;

[0009] A historical data storage unit, which is used to store the normal originally collected operation data and the abnormal target operation data after optimization and correction.

[0010] Optionally, the system further includes:

[0011] A data acquisition module for real-time acquisition of the original operation data of a vehicle;

[0012] A data distribution module for distributing the acquired original operation data to a data comparison module and an original operation data storage unit, and synchronously sending an instruction to direct the simulation model module to work;

[0013] An original operation data storage unit for storing the originally acquired operation data in real time.

[0014] Optionally, the data comparison module includes an abnormal attribute recording module for recording attribute information of abnormal original operation data, and the attribute information at least includes a timestamp and an abnormal type;

[0015] The data optimization module includes a measure trigger module for determining and executing corresponding countermeasures according to the attribute information of the recorded abnormal original operation data;

[0016] An abnormal data recording and analysis module for recording abnormal original operation data, the attribute information of the abnormal original operation data, and the execution information of countermeasures.

[0017] Optionally, the simulation model module includes:

[0018] A simulation model determination module for determining, according to a target mapping relationship, the simulation models corresponding to the operation data of various data types in the historical operation data, where the target mapping relationship is a pre-established mapping relationship between data types and simulation models;

[0019] A simulation processing module for inputting the operation data of various data types in the historical operation data into their respective corresponding simulation models for simulation processing to obtain simulation data of various data types.

[0020] Optionally, the data comparison module includes:

[0021] A comparison strategy determination module for determining a target abnormal judgment strategy corresponding to the data type according to the data type of the simulation data;

[0022] An abnormal data determination module for obtaining original operation data of the same data type as the simulation data, and determining whether the original operation data is abnormal through the target abnormal judgment strategy based on the simulation data and the obtained original operation data.

[0023] Optionally, when the data type of the simulation data is numerical, the simulation model corresponding to the numerical simulation data in the simulation processing module includes:

[0024] The fractional digit data determination module is used to determine the first fractional digit value and the second fractional digit value of the first operating data input to the simulation model, where the first fractional digit value is less than the second fractional digit value, and the first operating data is data of the same data type as the simulation data input to the simulation model;

[0025] The constraint correction module is used to perform constraint correction on the first fractional digit value and the second fractional digit value through the input second operating data to obtain simulation data, where the second operating data is data of a different data type from the simulation data input to the simulation model.

[0026] Optionally, the fractional digit data determination module includes:

[0027] The first fractional digit data determination module is used to determine the short-term first fractional digit value, short-term second fractional digit value, long-term first fractional digit value, and long-term second fractional digit value of the first operating data input to the simulation model;

[0028] The second fractional digit data determination module is used to perform weighted fusion on the short-term first fractional digit value and the long-term first fractional digit value, and perform weighted fusion on the short-term second fractional digit value and the long-term second fractional digit value to obtain the fused first fractional digit value and second fractional digit value.

[0029] A second aspect of the present application provides a data optimization method for an intelligent connected vehicle, and the method includes:

[0030] Performing simulation processing on historical operating data through a simulation model to obtain simulation data, where the simulation data is range data of a reasonable operating state of the current vehicle, and the historical operating data is composed of normal original operating data stored in a historical data storage unit and abnormal target operating data after optimization and correction;

[0031] Comparing the originally collected operating data with the simulation data to determine whether the originally collected operating data is abnormal;

[0032] In the case where the originally collected operating data is abnormal, optimizing and correcting the abnormal originally collected operating data according to the historical operating data to obtain the optimized and corrected target operating data.

[0033] A third aspect of the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and running on the processor, and when the computer program is executed by the processor, it implements the steps in a data optimization method for an intelligent connected vehicle as described in the second aspect of the present application.

[0034] A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in a data optimization method for an intelligent connected vehicle as described in the second aspect of the present application are implemented.

[0035] The data optimization method for an intelligent connected vehicle provided by the present application has the following advantages:

[0036] An intelligent connected vehicle data optimization system provided by an embodiment of the present application includes a simulation model module for performing simulation processing on historical operation data in a historical data storage unit through a simulation model to obtain simulation data, where the simulation data is range data of a reasonable operation state of the current vehicle; a data comparison module for comparing the originally collected real-time operation data with the simulation data to determine whether the originally collected operation data is abnormal; a data optimization module for, in the case where the originally collected operation data is abnormal, optimizing and correcting the abnormal originally collected operation data according to the historical operation data in the historical data storage unit to obtain target operation data after optimization and correction; and a historical data storage unit for storing normal originally collected operation data and target operation data after optimization and correction of abnormal data. Thus, through the intelligent connected vehicle data optimization system provided by the present application, when it is determined that the vehicle operation data is abnormal, based on the past historical operation state, the reasonable range corresponding to various types of operation data in the current reasonable operation state is determined. When it is determined that the originally collected operation data of each type is abnormal based on the reasonable range of various types of operation data, more complex optimization and correction of the abnormal originally collected operation data are performed. This method of first determining the reasonable range of various types of operation data only depends on statistical laws and physical constraints to determine the reasonable range of various types of operation data, without complex modeling, has high real-time performance and limited resource consumption, and therefore can effectively improve the efficiency of data optimization. At the same time, when performing simulation processing in the present application, the historical operation data adopted are all operation data that can ensure normal operation (that is, the originally normal originally collected operation data and the target operation data that were originally abnormal and became correct data after optimization and correction), and therefore the accuracy of data optimization and correction can be effectively improved. At the same time, these modules are set in the cloud. After the intelligent connected vehicle communicates with the cloud and uploads its own originally collected operation data to the cloud, the simulation model module, data comparison module, and data optimization module in the cloud immediately start working to determine and optimize and correct the abnormal operation data, thereby effectively ensuring the real-time performance of data optimization and correction. Description of the Drawings

[0037] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0038] Figure 1 Schematic diagram of a data optimization system for an intelligent connected vehicle shown in an embodiment of the present application;

[0039] Figure 2 Structural diagram of a data optimization system for an intelligent connected vehicle shown in an embodiment of the present application;

[0040] Figure 3 Working flowchart of a simulation model module in a data optimization system for an intelligent connected vehicle shown in an embodiment of the present application;

[0041] Figure 4 Flowchart of a data optimization method for an intelligent connected vehicle shown in an embodiment of the present application. Detailed implementation manners

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0043] Refer to Figure 1 , Figure 1 Schematic diagram of a data optimization system for an intelligent connected vehicle shown in an embodiment of the present application. As Figure 1 shown, the system includes: a simulation model module 101, configured to perform simulation processing on historical operation data in a historical data storage unit through a simulation model to obtain simulation data, where the simulation data is range data of a reasonable operation state of the current vehicle; a data comparison module 102, configured to compare the originally collected real-time operation data with the simulation data to determine whether the originally collected operation data is abnormal; a data optimization module 103, configured to, when the originally collected operation data is abnormal, optimize and correct the abnormal originally collected operation data according to the historical operation data in the historical data storage unit to obtain target operation data after optimization and correction; and a historical data storage unit 104, configured to store normal originally collected operation data and target operation data after optimization and correction of the abnormal data.

[0044] In this embodiment, as Figure 2As shown, the historical data storage unit records historical operation data generated in the past. The historical operation data includes the original operation data of vehicles determined to be normal and the operation data that is no longer abnormal (i.e., target operation data) obtained after optimizing and correcting the original operation data determined to be abnormal. That is to say, the historical operation data in the historical data storage unit belongs to the normal operation data that is no longer abnormal. The historical operation data includes, but is not limited to, speed, acceleration, vehicle positioning data, in-vehicle temperature, out-of-vehicle temperature, steering angle, fuel consumption, data representing the operation state of the engine, data representing the operation state of the braking system, data representing the operation state of the suspension system, etc.

[0045] In this embodiment, the simulation data is range data, which represents the data range of various operation data corresponding to the reasonable operation state that the vehicle should be in under the operation state of the vehicle characterized by the historical operation data of the vehicle recorded in the historical data storage unit during a past continuous period starting from the current moment. For example, taking the data type of the simulation data as speed for exemplary explanation, based on the historical operation data of the vehicle recorded in the historical data storage unit during a past continuous period starting from the current moment, it is determined that the operation state of the vehicle during the past continuous period starting from the current moment is that the vehicle has been in uniform motion at 50 km / h and the acceleration has been fluctuating around 0. Therefore, through the corresponding simulation model, the data range of the speed simulation data corresponding to the reasonable operation state that the vehicle should be in currently is [45, 55], with the unit of km / h, and the data range of the acceleration simulation data corresponding is [0, 0.5], with the unit of m / s 2 . Among them, the data types of the simulation data include, but are not limited to, speed, acceleration, vehicle positioning data, in-vehicle temperature, out-of-vehicle temperature, steering angle, fuel consumption, data types representing the operation state of the engine, data types representing the operation state of the braking system, data types representing the operation state of the suspension system, etc.

[0046] In this embodiment, as Figure 3As shown, the simulation model module obtains the historical operation data recorded in the historical data storage unit during a continuous period of time in the past starting from the current moment, and then performs simulation processing on the obtained historical operation data during this continuous period of time through the pre-established simulation model in the simulation model module, so as to simulate and obtain the reasonable operation state range that the vehicle should be in under the operation state of the vehicle during a continuous period of time in the past starting from the current moment. The reasonable operation state range obtained by this simulation records the reasonable range values of various operation data, that is, the simulation data of various data types. For example, under the operation state of the vehicle during a continuous period of time in the past starting from the current moment, the reasonable range value of the data type of the speed that the vehicle should be in determined through the simulation model is [45, 55], and this reasonable range value is the simulation data of the data type of the speed; and, the reasonable range value of the data type of the acceleration that the vehicle should be in determined through the simulation model is [0, 0.5], and this reasonable range value is the simulation data of the data type of the acceleration. Among them, the duration of this continuous period of time in the past starting from the current moment can be set according to the actual application scenario, and no specific limitation is made here, such as the past 1 hour, half an hour, the past 1 minute, etc.

[0047] In this embodiment, after obtaining the simulation data of various data types through the simulation model module, the data comparison module obtains the simulation data of these data types, and at the same time obtains the current raw operation data collected in real time. The various data types included in the raw operation data are the same as the various data types included in the obtained simulation data. For example, when the simulation data includes data types such as speed data type, acceleration data type, and vehicle positioning data type, the raw operation data also includes speed data type, acceleration data type, and vehicle positioning data type. Then, the data comparison model compares the raw operation data and the simulation data belonging to the same data type, and determines whether the raw operation data belongs to abnormal data based on whether the raw operation data is within the data range of the simulation data. For example, through the simulation model module, it is determined that under the operation state of the vehicle during a continuous period of time in the past starting from the current moment, the reasonable range of the current vehicle speed is [45, 50], and this range data [45, 50] is the simulation data of the data type of the speed, while the result of the raw operation data of the data type of the speed obtained in real time currently is 60. Since the raw operation data is not within the range of the simulation data, it is determined that the raw operation data is abnormal. Among them, the raw operation data is the data obtained in real time from various sensors inside and outside the vehicle, GPS devices, and user interfaces, as well as some data that need to be calculated through corresponding algorithms based on sensor data (for example, the remaining driving range (Range Estimation) needs to be calculated through corresponding algorithms by comprehensively considering the current battery level, energy consumption rate, driving behavior, and environmental conditions (such as slope, temperature)).

[0048] In this embodiment, the simulation data obtained by simulation belongs to the reasonable data ranges that various data types should be in under the reasonable operating state that the current vehicle should be in under the operating state of the vehicle in the past period of time obtained by simple simulation. Its purpose is only to determine whether the original operating data is reasonable, and this process does not obtain accurate and correct results through complex algorithms and processing procedures. Therefore, when this application determines that the collected original operating data is abnormal through the data comparison module, it will optimize and correct the abnormal original operating data through complex algorithms and processing procedures based on the historical operating data recorded in the historical data storage unit for a continuous period of time starting from the current moment, so as to obtain the target operating data after correction and optimization corresponding to the original operating data. This target operating data is the normal operating data obtained after optimizing and correcting the abnormal original operating data.

[0049] For example, through the simulation model module, it is determined that under the operating state of the vehicle for a continuous period of time starting from the current moment, the reasonable range of the current vehicle speed is [45, 50]. This range data [45, 50] is also the simulation data of the data type of speed. The result of the original operating data of the data type of speed obtained in real time currently is 60. Since this original operating data is not within the range of the simulation data, it is determined that this original operating data is abnormal. Then, based on the historical operating data recorded in the historical data storage unit for a continuous period of time starting from the current moment, the abnormal original operating data with a value of 60 is optimized and corrected through complex algorithms and processing procedures to obtain the target operating data with an optimized and corrected value of 48. This target operating data with a value of 48 is the normal operating data with a value of 48 obtained after optimizing and correcting the abnormal original operating data with a value of 60.

[0050] In this embodiment, the target operating data obtained after optimizing and correcting the abnormal original operating data is stored in the historical data storage unit and participates in the subsequent simulation processing process. At the same time, the original operating data determined to be normal by the data comparison module is also stored in the historical data storage unit and participates in the subsequent simulation processing process.

[0051] A data optimization system for an intelligent connected vehicle provided by an embodiment of the present application. The system includes a simulation model module, which is used to perform simulation processing on historical operation data in a historical data storage unit through a simulation model to obtain simulation data, and the simulation data is range data of a reasonable operation state of the current vehicle; a data comparison module, which is used to compare the originally collected operation data collected in real time with the simulation data to determine whether the originally collected operation data is abnormal; a data optimization module, which is used to optimize and correct the abnormal originally collected operation data according to the historical operation data in the historical data storage unit in the case where the originally collected operation data is abnormal to obtain target operation data after optimization and correction; and a historical data storage unit, which is used to store normal originally collected operation data and abnormal target operation data after optimization and correction. Thus, through the data optimization system for an intelligent connected vehicle provided by the present application, when it is determined that the vehicle operation data is abnormal, based on the past historical operation state, the reasonable range corresponding to various operation data under the current reasonable operation state is determined, and when it is determined that the originally collected operation data of each type is abnormal based on the reasonable range of various operation data, more complex optimization and correction of the abnormal originally collected operation data are performed. This method of first determining the reasonable range of various operation data only relies on statistical laws and physical constraints to determine the reasonable range of various operation data, without complex modeling, has high real-time performance and limited resource consumption, and thus can effectively improve the efficiency of data optimization. At the same time, when the present application performs simulation processing, the historical operation data adopted are all operation data that can ensure normal operation (that is, the originally normal originally collected operation data and the target operation data that were originally abnormal and became normal data after optimization and correction), and thus the accuracy of data optimization and correction can be effectively improved. At the same time, these simulation model module, data comparison module, data optimization module and historical data storage unit are set in the cloud. After the intelligent connected vehicle communicates with the cloud and uploads the originally collected operation data of its own vehicle to the cloud, the simulation model module, data comparison module and data optimization module in the cloud immediately start to work to determine and optimize and correct the abnormal operation data, thereby effectively ensuring the real-time performance of data optimization and correction.

[0052] Combined with the above embodiments, in one implementation manner, the embodiment of the present application further provides a data optimization system for an intelligent connected vehicle. In this data optimization system for an intelligent connected vehicle, the system further includes: a data collection module, which is used to collect the originally collected operation data of the vehicle in real time; a data distribution module, which is used to distribute the collected originally collected operation data to the data comparison module and the originally collected operation data storage unit, and synchronously send an instruction to instruct the simulation model module to work; and an originally collected operation data storage unit, which is used to store the originally collected operation data collected in real time.

[0053] In this embodiment, a data optimization system for an intelligent connected vehicle provided by the present application further includes a data acquisition module, a data distribution module, and an original operation data storage unit. The data acquisition module obtains data in real time from various sensors, GPS devices, and user interfaces inside and outside the vehicle. These real-time obtained data are the originally operated data obtained in real time. Among them, only the data acquisition module in the present application is set on the intelligent connected vehicle side to collect the originally operated data. The data acquisition module sends the collected originally operated data to the data distribution module in the cloud through the communication connection with the cloud. The data distribution module distributes the currently received originally operated data to the data comparison module to determine whether the originally operated data is abnormal. At the same time, the currently received originally operated data is distributed to the original operation data storage unit, and the original operation storage unit saves the most original originally operated data that has not been determined to be abnormal and optimized and corrected, so as to facilitate subsequent data traceability and problem troubleshooting. While the data distribution module distributes the originally operated data sent by the data acquisition module to the data comparison module and the original operation data storage unit, the data distribution module synchronously sends an instruction to the simulation model module to control the simulation model module to start working, that is, the simulation model module responds to this instruction and starts to obtain historical operation data within a continuous period of time starting from the current moment from the historical data storage unit for simulation processing to obtain simulation data of various data types at the current moment.

[0054] Combined with the above embodiments, in one implementation manner, the embodiment of the present application further provides a data optimization system for an intelligent connected vehicle. In this data optimization system for an intelligent connected vehicle, the data comparison module includes an abnormal attribute recording module for recording attribute information of abnormal originally operated data, and the attribute information at least includes a timestamp and an abnormal type; the data optimization module includes a measure triggering module for determining and executing corresponding countermeasures according to the attribute information of the recorded abnormal originally operated data; and an abnormal data recording and analysis module for recording the abnormal originally operated data, the attribute information of the abnormal originally operated data, and the execution information of the countermeasures.

[0055] In this embodiment, the data comparison module set in the cloud in the present application includes an abnormal attribute recording module, and the data optimization module set in the cloud includes a measure triggering module, and the system further includes an abnormal data recording and analysis module set in the cloud.

[0056] In this embodiment, the abnormal attribute recording module is used to record the attribute information of the abnormal original operation data based on the determination result when the data comparison module determines that the original operation data belongs to abnormal operation data. The attribute information of the abnormal original operation data includes at least a time stamp and an abnormal type. Among them, the abnormal type includes at least a sensor abnormal type and an algorithm abnormal type. Sensor abnormality refers to abnormal sensor data. Algorithm abnormality means that the operation data input into the algorithm is normal, but the result obtained by comparing the output operation data of the algorithm with the simulation data of the same data type as the output operation data is that the output operation data is abnormal, then it is determined that the algorithm is abnormal. For example, an optional implementation manner for determining vehicle acceleration is to calculate the acceleration through the accelerometer and gyroscope data in the inertial measurement unit (IMU) and through a sensor fusion algorithm (such as Kalman filtering). This sensor fusion algorithm is an in-vehicle algorithm that may have abnormalities.

[0057] In this embodiment, the measure trigger module included in the data optimization module receives the attribute information of the abnormal original operation data recorded in the abnormal attribute recording module. The abnormal types in the attribute information of all the abnormal original operation data received by the measure trigger module are used to determine the number of times the same abnormal type appears in the same vehicle (such as determining the number of times the speed sensor is abnormal), while the timestamps in the attribute information of all the abnormal original operation data received by the measure trigger module and the respective acquisition time intervals of the original operation data of each data type originally recorded are used to determine whether the same abnormal type in the same vehicle appears continuously. Therefore, the measure trigger module will determine the number of times various abnormal types in the same vehicle appear continuously based on the abnormal types and timestamps in the attribute information of all the abnormal original operation data received, as well as the respective acquisition time intervals of the original operation data of each data type originally recorded. For example, the acquisition time interval of the original operation data of the speed data type is 100 ms, and based on the timestamps in the attribute information of all the abnormal original operation data, it is determined that the time intervals between the original operation data of the speed data type with 3 abnormalities are 100 ms, and the time intervals between these 3 original operation data and the original operation data of other abnormal speed data types exceed 100 ms. Therefore, it is determined that the number of times the abnormal type of speed sensor abnormality appears continuously is 3 times. At the same time, the degree of abnormality of this abnormal type is determined based on the number of times the same abnormal type appears continuously. The more times an abnormal type appears continuously, the higher the corresponding degree of abnormality. Based on the degree of abnormality of the same abnormal type, it is determined whether this abnormal type meets the trigger condition of its corresponding countermeasure. When the trigger condition of its corresponding countermeasure is met, the corresponding countermeasure is executed. Among them, when the abnormal type is sensor abnormality, the countermeasure to be executed is to prompt the engineering personnel through the human-machine interaction interface to determine that there is an abnormality in the corresponding sensor of the vehicle where this abnormal type is located and sensor calibration is required. For example, when the abnormal type is speed sensor abnormality, the engineering personnel are prompted through the human-machine interaction interface to determine that there is an abnormality in the corresponding speed sensor of the vehicle where this abnormal type is located and speed sensor calibration is required; when the abnormal type is algorithm abnormality, the countermeasure to be executed is to prompt the engineering personnel through the human-machine interaction interface to determine that there is an abnormality in the insufficient performance of the corresponding algorithm of the vehicle where this abnormal type is located and algorithm optimization and update are required.

[0058] In this embodiment, an alternative implementation manner for determining whether a certain type of abnormality meets the triggering condition of its corresponding countermeasure based on the degree of abnormality of the same type of abnormality is as follows: Set respective abnormality degree thresholds for each type of abnormality of the vehicle. As long as the degree of abnormality of the abnormality type is greater than or equal to its corresponding abnormality degree threshold, it is determined that the abnormality type meets the countermeasure triggering condition. For example, set the abnormality degree threshold of type a abnormality as 4. Therefore, when type a abnormality occurs continuously 4 times or more, it is determined that type a abnormality of the vehicle meets the triggering condition of its corresponding countermeasure; set the abnormality degree threshold of type b abnormality as 5. Therefore, when type b abnormality occurs continuously 5 times or more, it is determined that type b abnormality of the vehicle meets the triggering condition of its corresponding countermeasure.

[0059] Combined with the above embodiments, in one implementation manner, the embodiment of the present application further provides a data optimization system for an intelligent connected vehicle. In the data optimization system of the intelligent connected vehicle, the simulation model module includes: a simulation model determination module, configured to determine the simulation models corresponding to the operation data of various data types in the historical operation data according to the target mapping relationship, where the target mapping relationship is a mapping relationship established in advance between the data type and the simulation model; a simulation processing module, configured to input the operation data of various data types in the historical operation data into their respective corresponding simulation models for simulation processing to obtain simulation data of various data types.

[0060] In this embodiment, the present application, considering that different types of operation data are based on different physical constraints and the basic operation data of the vehicle during simulation, pre-establishes respective corresponding simulation models for the operation data of different data types, and at the same time pre-establishes a mapping relationship between the data type to be input into the simulation model and the simulation model for different simulation models. This mapping relationship is the target mapping relationship, and what is recorded in the target mapping relationship is the corresponding relationship between each type of historical operation data and which simulation model it should be input into. It should be understood that one type of historical operation data can be simultaneously input into multiple simulation models respectively. For example, the historical operation data corresponding to the simulation model for obtaining the current vehicle speed can include historical acceleration, and the historical operation data corresponding to the simulation model for obtaining the current vehicle position can also include historical acceleration. Among them, the basic operation data belongs to the operation data required for simulating the simulation data of a certain specific data type. For example, when simulating the positioning data of the vehicle, the historical positioning data, historical speed, historical longitudinal and lateral accelerations, and historical steering angle of the vehicle are used as the basic operation data for simulating the vehicle positioning simulation data at the current moment; when simulating the speed data of the vehicle, the historical speed and historical longitudinal and lateral accelerations of the vehicle are used as the basic operation data for simulating the vehicle speed simulation data at the current moment.

[0061] Specifically: In the data optimization system for intelligent connected vehicles provided by this application, the simulation model module includes a simulation model determination module and a simulation processing module. The simulation model determination module obtains various types of historical operation data stored in the historical data storage unit, and based on the pre-established target mapping relationship, determines which simulation model or models each type of historical operation data should be input into. Based on the determination result, the simulation model to which each type of historical operation data belongs is labeled. Among them, when obtaining various types of historical operation data stored in the historical data storage unit, the historical operation data within a continuous period from the current moment to the past is obtained. The duration within this continuous period can be set according to the actual application scenario and is not specifically limited here. For example, it can be taken as 5 minutes, 1 minute, etc. In the case where one type of historical operation data needs to be input into multiple simulation models, multiple labels are assigned to this type of historical operation data, and these multiple labels correspond to the multiple simulation models into which it will be input. For example, if type-a historical operation data needs to be input into simulation models x and y, then two labels x and y are assigned to type-a historical operation data to indicate that type-a historical operation data needs to be input into simulation model x and simulation model y respectively.

[0062] In this embodiment, after the simulation model determination module completes the determination and labeling of the simulation models to which various types of historical operation data belong, the simulation processing module determines the simulation models corresponding to each type of historical operation data that should be input based on the labels assigned to the various types of historical operation data, and inputs them into the corresponding simulation models for simulation processing to obtain simulation data of various data types. The simulation model simulates the normal operation state and data generation process of the vehicle. The simulation process of the simulation model is based on the physical characteristics of the vehicle and the historical operation data of the vehicle, and can accurately reflect the dynamic changes of the vehicle under different working conditions and generate simulation data.

[0063] Combined with the above embodiments, in one implementation, the embodiment of this application also provides a data optimization system for intelligent connected vehicles. In this data optimization system for intelligent connected vehicles, the data comparison module includes: a comparison strategy determination module, which is used to determine the target anomaly judgment strategy corresponding to the data type according to the data type of the simulation data; an abnormal data determination module, which is used to obtain the original operation data of the same data type as the simulation data, and based on the simulation data and the obtained original operation data, determine whether the original operation data is abnormal through the target anomaly judgment strategy.

[0064] In this embodiment, the present application sets corresponding anomaly judgment strategies for different types of operation data to improve the accuracy of anomaly judgment. Specifically: In a data optimization system for an intelligent connected vehicle provided by the present application, the data comparison module includes a comparison strategy determination module and an abnormal data determination module. The comparison strategy determination module determines an anomaly judgment strategy corresponding to the data type of the simulation data based on the data type of the simulation data, and this anomaly judgment strategy is the target anomaly judgment strategy corresponding to this data type. The abnormal data determination module then calls the target anomaly judgment strategy corresponding to the data type of the simulation data determined by the comparison strategy determination module, and through the called target anomaly judgment strategy, determines anomalies in the simulation data and the original operation data of the same data type as the simulation data received from the data distribution module. For example, for the vehicle positioning data type, an anomaly judgment strategy of comparing the current original operation data of the positioning data type with the current simulation data is used to determine whether there are anomalies in the current original operation data of the positioning data type; for the vehicle speed data type, an anomaly judgment strategy of first comparing the current original operation data of the speed data type with the current simulation data, ending if there are anomalies, and if there are no anomalies, further comparing the speed change rate corresponding to the current original operation data with the speed change rate corresponding to the current simulation data to determine whether there are anomalies in the current original operation data of the speed data type is adopted.

[0065] Combined with the above embodiments, in one implementation, the embodiments of the present application further provide a data optimization system for an intelligent connected vehicle. In this data optimization system for an intelligent connected vehicle, when the data type of the simulation data is numerical, the simulation model corresponding to the numerical simulation data in the simulation processing module includes: a fractional digit data determination module for determining the first fractional digit value and the second fractional digit value of the first operation data input to the simulation model, where the first fractional digit value is less than the second fractional digit value, and the first operation data is data of the same data type as the simulation data input to the simulation model; a constraint correction module for performing constraint correction on the first fractional digit value and the second fractional digit value through the input second operation data to obtain simulation data, where the second operation data is data of a different data type from the simulation data input to the simulation model.

[0066] In this embodiment, when the data type of the simulation data is numerical, an optional implementation manner of the simulation model corresponding to the numerical simulation data in the simulation processing module is that the simulation model includes two modules, namely a fractional digit data determination module and a constraint correction module. The fractional digit determination module determines a first fractional digit value and a second fractional digit value for the input first operation data that is of the same data type as the data type simulated by the simulation model to which the fractional digit determination module belongs. The first fractional digit value is less than the second fractional digit value. The first fractional digit value is the lower limit value of the range value, and the second fractional digit value is the upper limit value of the range value. The first fractional digit value is preferably the value of the 5% fractional digit in the sequential sequence data of the first operation data. That is, after multiple data in the first operation data are sorted according to the value size, when only 5% of the data in the sequential sequence data is less than a certain value, the value is determined as the first fractional digit value; the second fractional digit value is preferably the value of the 95% fractional digit in the sequential sequence data of the first operation data. That is, after multiple data in the first operation data are sorted according to the value size, when only 5% of the data in the sequential sequence data is greater than a certain value, the value is determined as the second fractional digit value. It should be understood that the first fractional digit value being preferably the value of the 5% fractional digit in the sequential sequence data of the first operation data, and the second fractional digit value being preferably the value of the 95% fractional digit in the sequential sequence data of the first operation data are only a preferred implementation manner, and both can also take the values of other fractional digits.

[0067] In this embodiment, after obtaining, by the fractional digit data determination module, a value range with the first fractional digit value and the second fractional digit value as the upper and lower limits, the constraint correction module corrects the constraint on this value range with the second operation data that is different from the data type simulated by the simulation model to which the fractional digit determination module belongs, that is, corrects the first fractional digit value and the second fractional digit value. The value range composed of the corrected first fractional digit value and the second fractional digit value is the corresponding simulation data. For example, when the simulation model simulates the speed of a vehicle, first obtain the historical operation data of the speed in a continuous period of time in the past starting from the current moment from the historical data storage unit, and then based on the obtained historical operation data of the speed, determine the first fractional digit value and the second fractional digit value in this historical operation data of the speed. Since the simulation of the speed also requires the use of acceleration, the historical operation data of the acceleration in a continuous period of time in the past starting from the current moment will also be obtained from the historical data storage unit, and this historical operation data of the acceleration is used as a physical constraint to correct the first fractional digit value and the second fractional digit value, obtaining a value range composed of the corrected first fractional digit value and the second fractional digit value. This value range is the simulation data of the final speed at the current moment. It should be understood that this is an optional implementation manner of the simulation model. The simulation model can also be other implementation manners. For example, a simple deep learning model is used to determine the simulation data by inputting various historical operation data of the model. For example, when the type of the simulation data is positioning data, the historical operation data of the speed, the historical operation data of the acceleration, and the historical operation data of the positioning that will affect the position of the vehicle at each moment are input into the corresponding simulation model for processing to obtain the simulation data representing the current position of the vehicle. Among them, all kinds of historical operation data mentioned in this application are data stored in the historical data storage unit.

[0068] Combined with the above embodiments, in one implementation manner, the embodiment of the present application also provides a data optimization system for an intelligent connected vehicle. In this data optimization system for an intelligent connected vehicle, the fractional digit data determination module includes: a first fractional digit data determination module for determining the short-term first fractional digit value, the short-term second fractional digit value, the long-term first fractional digit value, and the long-term second fractional digit value of the first operation data input into the simulation model; a second fractional digit data determination module for performing weighted fusion on the short-term first fractional digit value and the long-term first fractional digit value, and performing weighted fusion on the short-term second fractional digit value and the long-term second fractional digit value to obtain the fused first fractional digit value and second fractional digit value.

[0069] In this embodiment, to ensure that the first fractional digit value and the second fractional digit value determined based on historical operation data are more in line with the current reasonable operation state of the vehicle, when determining the final first fractional digit value and the second fractional digit value in this application, not only the long-term fractional digit values but also the short-term fractional digit values are considered.

[0070] Specifically, in this embodiment, the fractional digit data determination module includes a first fractional digit data determination module and a second fractional digit data determination module. The first fractional digit data determination module divides the input first operation data of the same data type as the data type simulated by the simulation model to which the first fractional digit determination module belongs into two ordered sequence data according to long-term time intervals and short-term time intervals. For example, if the first operation data is the speed historical operation data with a duration of 30 minutes, the long-term time interval is 1 minute, and the short-term time interval is 5 seconds. After sorting the first operation data according to the value size, one speed historical operation data is taken every 1 minute to form the ordered sequence data of the long-term time interval; after sorting the first operation data according to the value size, one speed historical operation data is taken every 5 seconds to form the ordered sequence data of the short-term time interval. Then, based on the ordered sequence data of the long-term time interval, the long-term first fractional digit value and the long-term second fractional digit value are determined; based on the ordered sequence data of the short-term time interval, the short-term first fractional digit value and the short-term second fractional digit value are determined. Among them, the long-term first fractional digit value is preferably the value of the 5% fractional digit in the ordered sequence data of the long-term time interval of the first operation data, that is, when only 5% of the data in the ordered sequence data of the long-term time interval is less than a certain value, this value is determined as the long-term first fractional digit value, and the short-term first fractional digit value can also be preferably the value of the 5% fractional digit in the ordered sequence data of the short-term time interval of the first operation data; the long-term second fractional digit value is preferably the value of the 95% fractional digit in the ordered sequence data of the long-term time interval of the first operation data, that is, when only 5% of the data in the ordered sequence data of the long-term time interval is greater than a certain value, this value is determined as the long-term second fractional digit value, and the short-term second fractional digit value can also be preferably the value of the 95% fractional digit in the ordered sequence data of the short-term time interval of the first operation data.

[0071] In this embodiment, the present application has preset the respective fusion weights of the long-term fractional digit values and the short-term fractional digit values. After determining the current short-term first fractional digit value, short-term second fractional digit value, long-term first fractional digit value, and long-term second fractional digit value of a certain data type of the vehicle through the first fractional digit data determination module, the second fractional digit data determination module performs weighted fusion on the short-term first fractional digit value and the long-term first fractional digit value, and also performs weighted fusion on the short-term second fractional digit value and the long-term second fractional digit value to obtain the fused first fractional digit value and second fractional digit value. For example, the present application has preset the fusion weight of the long-term fractional digit value as α1 and the fusion weight of the short-term fractional digit value as α2. If the determined short-term first fractional digit value is f1, short-term second fractional digit value is f2, long-term first fractional digit value is g1, and long-term second fractional digit value is g2, then the fused first fractional digit value is α2×f1 + α1×g1, and the fused second fractional digit value is α2×f2 + α1×g2.

[0072] In this embodiment, the data optimization system of an intelligent connected vehicle provided by the present application will be updated and maintained regularly, which includes updating the simulation model in the simulation model module, optimizing the algorithms and thresholds in the data comparison module, adding new data sources, etc. In addition, regular performance tests and fault troubleshooting will be carried out on the system to ensure the stability and reliability of the system.

[0073] Exemplarily, the data acquisition module collects the original operation data of the vehicle in real time. In this example, it is assumed that the original operation data includes GPS data, acceleration, and steering data, and uploads the collected original operation data to the data distribution module in the cloud. The data distribution module distributes the collected original operation data to the data comparison module and the original operation data storage unit. The original operation data storage unit stores these real-time collected original operation data for subsequent data traceability. The data distribution module also sends instructions to synchronously trigger the simulation model module to start the process of generating simulation data.

[0074] The simulation model module obtains historical operation data from the historical data storage unit, and based on physical characteristics through the simulation model in the simulation model module, generates reasonable current positioning data of the vehicle (i.e., simulation data of positioning). The data comparison module compares the reasonable current positioning data with the positioning data in the currently collected original operation data in real time to determine whether the positioning data in the currently collected original operation data in real time is abnormal. Specifically: Obtain relevant historical operation data from the historical data storage unit, including historical longitude sequence data, historical latitude sequence data, historical speed sequence data, historical acceleration sequence data; utilize the physical characteristics of the vehicle, such as mass, air resistance coefficient, rolling resistance coefficient, to establish the kinematic equation of the vehicle; utilize the kinematic equation and the obtained historical operation data to generate the theoretically possible position range of the vehicle at the current moment, and realize calculating the theoretically possible position range of the vehicle at the current moment based on the position, speed, and direction in a period of time before the current moment; the data comparison module compares the positioning data in the currently collected original operation data in real time with the theoretically possible position range of the vehicle at the current moment (i.e., simulation data of positioning) to determine whether the positioning data in the currently collected original operation data in real time is within the theoretically possible position range; in the case of being within, determine that the positioning data in the currently collected original operation data in real time is normal; in the case of not being within, determine that the positioning data in the currently collected original operation data in real time is abnormal.

[0075] In the case of determining that the positioning data in the currently collected original operation data in real time is abnormal, the data optimization module calculates the motion trajectory of the vehicle based on data such as speed and acceleration in the historical operation data in the historical data storage unit, adjusts the real-time GPS data based on the calculated actual displacement, and generates the calibrated positioning data of the vehicle. Send the calibrated positioning data to the vehicle terminal to update the position information of the vehicle. Record the abnormal GPS data and the calibrated positioning data of the vehicle in the abnormal data recording and analysis module for subsequent analysis and optimization.

[0076] Based on the same inventive concept, an embodiment of the present application provides a data optimization method for an intelligent connected vehicle, as Figure 4 shown, the method includes:

[0077] Step S401: Perform simulation processing on historical operation data through a simulation model to obtain simulation data, where the simulation data is range data of the reasonable operation state of the current vehicle, and the historical operation data consists of normal original operation data stored in the historical data storage unit and abnormal target operation data after optimization and correction;

[0078] Step S402: Compare the originally collected operation data in real time with the simulation data to determine whether the originally collected operation data is abnormal;

[0079] Step S403: In the case of abnormal original operation data, optimize and correct the abnormal original operation data according to historical operation data to obtain target operation data after optimization and correction.

[0080] Optionally, the method further includes:

[0081] Real-time collect the original operation data of the vehicle;

[0082] Store the original operation data in the original operation data storage unit, and at the same time control the simulation model to perform simulation processing on the historical operation data to obtain simulation data.

[0083] Optionally, the method further includes:

[0084] Record the attribute information of the abnormal original operation data, and the attribute information at least includes a timestamp and an abnormal type;

[0085] Determine and execute corresponding countermeasures according to the attribute information of the recorded abnormal original operation data;

[0086] Record the abnormal original operation data, the attribute information of the abnormal original operation data, and the execution information of the countermeasures.

[0087] Optionally, performing simulation processing on the historical operation data through a simulation model to obtain simulation data includes:

[0088] According to the target mapping relationship, determine the simulation models corresponding to the operation data of various data types in the historical operation data, where the target mapping relationship is a mapping relationship established in advance between the data type and the simulation model;

[0089] Input the operation data of various data types in the historical operation data into their respective corresponding simulation models for simulation processing to obtain simulation data of various data types.

[0090] Optionally, comparing the real-time collected original operation data with the simulation data to determine whether the original operation data is abnormal includes:

[0091] According to the data type of the simulation data, determine the target abnormal judgment strategy corresponding to the data type;

[0092] Obtain the original operation data with the same data type as the simulation data, and based on the simulation data and the obtained original operation data, determine whether the original operation data is abnormal through the target abnormal judgment strategy.

[0093] Optionally, in the case where the data type of the simulation data is numerical, performing simulation processing on the historical operation data through a simulation model to obtain simulation data includes:

[0094] Determine the first fractional digit value and the second fractional digit value of the first operating data of the input simulation model, where the first fractional digit value is less than the second fractional digit value, and the first operating data is data of the same data type as the simulation data input to the simulation model;

[0095] Perform constraint correction on the first fractional digit value and the second fractional digit value through the input second operating data to obtain simulation data, where the second operating data is data of a different data type from the simulation data input to the simulation model.

[0096] Optionally, determining the first fractional digit value and the second fractional digit value of the first operating data of the input simulation model includes:

[0097] Determine the short-term first fractional digit value, short-term second fractional digit value, long-term first fractional digit value, and long-term second fractional digit value of the first operating data of the input simulation model;

[0098] Perform weighted fusion on the short-term first fractional digit value and the long-term first fractional digit value, and perform weighted fusion on the short-term second fractional digit value and the long-term second fractional digit value to obtain the fused first fractional digit value and second fractional digit value.

[0099] Based on the same inventive concept, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and running on the processor, where when the computer program is executed by the processor, it implements the steps in the data optimization method of an intelligent networked vehicle as described in the second aspect of the present application.

[0100] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps in the data optimization method of an intelligent networked vehicle as described in the second aspect of the present application.

[0101] For the method embodiment, since it is basically similar to the system embodiment, the description is relatively simple. For related parts, refer to the partial description of the method embodiment.

[0102] It should be noted that for the method embodiment, for the sake of simple description, it is all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present application are not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present application.

[0103] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0104] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can take the form of all-hardware embodiments, all-software embodiments, or embodiments combining software and hardware aspects. Moreover, the embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate means for implementing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0108] Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0109] Finally, it should also be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0110] The above has introduced in detail a data optimization system, method and product for an intelligent networked vehicle provided by the present application. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An intelligent networked vehicle data optimization system, characterized in that, The system includes: A simulation model module, which is used to perform simulation processing on the historical operation data in the historical data storage unit through a simulation model to obtain simulation data, and the simulation data is the range data of the reasonable operation state of the current vehicle; A data comparison module, which is used to compare the originally collected operation data collected in real time with the simulation data to determine whether the originally collected operation data is abnormal; A data optimization module, which is used to optimize and correct the abnormal originally collected operation data according to the historical operation data in the historical data storage unit in the case where the originally collected operation data is abnormal, so as to obtain the target operation data after optimization and correction; A historical data storage unit, which is used to store the normal originally collected operation data and the abnormal target operation data after optimization and correction.

2. The data optimization system of an intelligent networked vehicle according to claim 1, characterized in that, The system further includes: A data collection module, which is used to collect the originally collected operation data of the vehicle in real time; A data distribution module, which is used to distribute the collected originally collected operation data to the data comparison module and the originally collected operation data storage unit, and synchronously send an instruction to instruct the simulation model module to work; An originally collected operation data storage unit, which is used to store the originally collected operation data collected in real time.

3. The data optimization system for an intelligent networked vehicle according to claim 1, characterized in that, The data comparison module includes an abnormal attribute recording module, which is used to record the attribute information of the abnormal originally collected operation data, and the attribute information at least includes a timestamp and an abnormal type; The data optimization module includes a measure triggering module, which is used to determine and execute corresponding countermeasures according to the attribute information of the recorded abnormal originally collected operation data; An abnormal data recording and analysis module, which is used to record the abnormal originally collected operation data, the attribute information of the abnormal originally collected operation data, and the information on the execution of countermeasures.

4. An intelligent networked vehicle data optimization system according to claim 1, characterized in that The simulation model module includes: A simulation model determination module, which is used to determine the simulation models corresponding to the operation data of various data types in the historical operation data according to a target mapping relationship, and the target mapping relationship is a mapping relationship between data types and simulation models established in advance; A simulation processing module, which is used to input the operation data of various data types in the historical operation data into their respective corresponding simulation models for simulation processing to obtain simulation data of various data types.

5. The data optimization system of an intelligent networked vehicle according to claim 1, characterized in that, The data comparison module includes: A comparison strategy determination module, which is used to determine a target abnormal judgment strategy corresponding to the data type according to the data type of the simulation data; An abnormal data determination module, which is used to obtain the originally collected operation data with the same data type as the simulation data, and determine whether the originally collected operation data is abnormal through the target abnormal judgment strategy based on the simulation data and the obtained originally collected operation data.

6. The data optimization system for an intelligent networked vehicle according to claim 1, wherein, In the case where the data type of the simulation data is numerical, the simulation model corresponding to the numerical simulation data in the simulation processing module includes: A fractional digit data determination module, which is used to determine the first fractional digit value and the second fractional digit value of the first operation data input into the simulation model, the first fractional digit value is less than the second fractional digit value, and the first operation data is the data of the same data type as the simulation data input into the simulation model; A constraint correction module, configured to perform constraint correction on the first fractional bit value and the second fractional bit value through the input second operation data to obtain simulation data, where the second operation data is data of a different data type from the simulation data input to the simulation model.

7. The data optimization system for an intelligent networked vehicle according to claim 6, characterized in that, The fractional bit data determination module includes: A first fractional bit data determination module, configured to determine the short-term first fractional bit value, the short-term second fractional bit value, the long-term first fractional bit value, and the long-term second fractional bit value of the first operation data input to the simulation model; A second fractional bit data determination module, configured to perform weighted fusion on the short-term first fractional bit value and the long-term first fractional bit value, and perform weighted fusion on the short-term second fractional bit value and the long-term second fractional bit value, to obtain the fused first fractional bit value and second fractional bit value.

8. A data optimization method for an intelligent connected vehicle, characterized in that, The method includes: Performing simulation processing on historical operation data through a simulation model to obtain simulation data, where the simulation data is range data of a reasonable operation state of a current vehicle, and the historical operation data is composed of normal original operation data stored in a historical data storage unit and abnormal target operation data after optimization and correction; Comparing the originally collected operation data with the simulation data to determine whether the originally collected operation data is abnormal; In the case where the originally collected operation data is abnormal, optimizing and correcting the abnormal originally collected operation data according to the historical operation data to obtain the optimized and corrected target operation data.

9. An electronic device, characterized in that, Includes: A processor, a memory, and a computer program stored on the memory and running on the processor, where when the computer program is executed by the processor, the steps in a data optimization method for an intelligent connected vehicle as claimed in claim 8 are implemented.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in a data optimization method for an intelligent connected vehicle as claimed in claim 8 are implemented.

Images