Decision control system and method for vehicle, electronic equipment and storage medium

Abstract

The invention relates to a decision control system and method for a vehicle, electronic equipment and a storage medium. The system comprises a data acquisition module used for sending a data request to a vehicle-mounted data center and acquiring vehicle internal data, vehicle external data and cloud data, a multi-source data processing module used for carrying out data fusion processing on the vehicle internal data, the vehicle external data and the cloud data and generating target decision data, and an intelligent decision module used for carrying out intelligent decision processing on the target decision data. The input module is used for inputting the target decision data into the vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data by using preset weight parameters and distance parameters and generates target decision instructions, and the execution control module is used for converting at least one target decision instruction into a control signal and sending the control signal to the vehicle-mounted decision model. And controlling an execution component associated with the control signal to execute the control operation. According to the scheme provided by the invention, all-known and all-controlled decision control can be realized, and the accuracy of vehicle decision is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent driving technology, and in particular to a vehicle decision-making control system, method, electronic equipment and storage medium. Background Art

[0002] The vehicle's electrical and electronic architecture (EEA) refers to the overall structure and organization of all electrical and electronic systems in the vehicle. It includes all electrical and electronic equipment, sensors, control units, and communication interconnection methods in the vehicle. EEA can effectively manage the vehicle's electrical and electronic systems to ensure that they can work in coordination with each other to achieve various functions and performance of the vehicle.

[0003] In the relevant technology, the vehicle's electrical and electronic systems have mainly gone through two stages. In the first stage, decision-making is highly decentralized, and each electrical and electronic system is relatively independent in decision-making, mainly relying on data and algorithms in this field. Although the decision-making in the second stage is concentrated in the Central Control Unit (CCU), each field still retains a certain degree of autonomy and can make decisions independently.

[0004] In general, the current decision-making method has centralized decision-making power to a certain extent. However, due to the lack of autonomy within the system and lack of cross-domain coordination, it is difficult to make cross-domain decisions. Summary of the invention

[0005] The present application provides a vehicle decision control system, method, electronic device and storage medium to solve or partially solve the problem of how to achieve cross-domain decision-making and optimize the decision control performance of the vehicle.

[0006] The first aspect of the present application provides a vehicle decision control system, the decision control system at least includes a data acquisition module, a multi-source data processing module, an intelligent decision module and an execution control module; the intelligent decision module includes an on-board decision model, wherein: The data acquisition module is used to send a data request to the vehicle data center to obtain vehicle internal data, vehicle external data and cloud data; The multi-source data processing module is used to perform data fusion processing on the vehicle internal data, the vehicle external data and the cloud data to generate target decision data; The intelligent decision module is used to input the target decision data into the vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; The execution control module is used to convert at least one target decision instruction into a control signal, and control the execution component associated with the control signal to perform a control operation.

[0007] In one example, the data fusion process includes at least a data preprocessing operation and a feature extraction operation; The multi-source data processing module is used to perform the data preprocessing operation on the vehicle internal data, the vehicle external data and the cloud data to obtain initial decision data; The feature extraction operation is performed on the initial decision data to generate the target decision data.

[0008] In one example, the multi-source data processing module is used to filter noise from the vehicle internal data, the vehicle external data, and the cloud data respectively, and to remove abnormal data from the vehicle internal data, the vehicle external data, and the cloud data.

[0009] In one example, the multi-source data processing module is used to perform spatiotemporal alignment on the vehicle internal data, the vehicle external data, and the cloud data to obtain the initial decision data; The initial decision data is a data set at the same time node and the same space coordinate.

[0010] In one example, the multi-source data processing module is used to extract a variety of decision feature data from the initial decision data according to preset feature categories; The plurality of decision feature data are used to construct a decision feature vector, and the decision feature vector is used as the target decision data.

[0011] In one example, the vehicle-mounted decision model uses the following decision function to process the target decision data: ; ; in, is the weight parameter of the vehicle-mounted decision model, is the distance parameter of the vehicle-mounted decision model.

[0012] In one example, the intelligent decision module is used to sort multiple target decision instructions according to preset priorities to obtain the instruction execution order; The multiple target decision instructions are sent to the execution control module in sequence according to the instruction execution order.

[0013] A second aspect of the present application provides a vehicle decision control method, which is applied to the decision control system, and the method includes: Send data requests to the vehicle data center to obtain vehicle internal data, vehicle external data, and cloud data; Performing data fusion processing on the vehicle internal data, the vehicle external data and the cloud data to generate target decision data; Inputting the target decision data into a preset vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; At least one target decision instruction is converted into a control signal, and an execution component associated with the control signal is controlled to perform a control operation.

[0014] A third aspect of the present application provides an electronic device, including: Processor; and The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0015] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0016] The technical solution provided by this application may have the following beneficial effects: In an embodiment of the present application, the decision control system includes at least a data acquisition module, a multi-source data processing module, an intelligent decision module and an execution control module. The intelligent decision module includes an on-board decision model, wherein the data acquisition module is used to send a data request to the on-board data center to obtain vehicle internal data, vehicle external data and cloud data. The multi-source data processing module is used to perform data fusion processing on vehicle internal data, vehicle external data and cloud data to generate target decision data. The intelligent decision module is used to input the target decision data into the on-board decision model so that the on-board decision model analyzes the target decision data using preset weight parameters and distance parameters to generate target decision instructions. The execution control module is used to convert at least one target decision instruction into a control signal and control the execution component associated with the control signal to perform a control operation.

[0017] The technical solution of the present application, on the one hand, the decision-making control system integrates modules with multiple functions with different functions, and realizes cross-domain information aggregation and data fusion through the collaborative work between various modules, thereby improving the intelligence of the vehicle and the user experience in the actual decision-making process; on the other hand, a multi-source data processing module is designed for data in different fields, and the multi-source data processing module can convert multi-source data into target decision data that is easy to analyze, so that the intelligent decision-making module can use the on-board decision-making model to conduct in-depth analysis of the target decision data, and generate target decision instructions that meet the current driving status of the vehicle, user preferences and other requirements, thereby realizing "full knowledge and full control" decision control, thereby improving the accuracy of vehicle decisions and ensuring that the vehicle makes the best decision in various complex driving environments.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail the exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0020] Figure 1 It is a structural schematic diagram of a vehicle decision control system shown in an embodiment of the present application; Figure 2 is a structural schematic diagram of a vehicle decision control system shown in another embodiment of the present application; Figure 3 is a data interaction diagram of a decision control system shown in an embodiment of the present application; Figure 4 is a flow chart of a vehicle decision control method shown in an embodiment of the present application; Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0022] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0023] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0024] In the traditional decision-making process, the vehicle's decision-making process is highly decentralized, and each electrical and electronic system (such as the power system, brake system, and navigation system, etc.) is relatively independent and mainly relies on data and algorithms in their respective fields. For example, the power system focuses on engine performance parameters, the brake system focuses on its own sensor data, and the navigation system focuses on the vehicle's driving position data.

[0025] Although this decentralized system design can meet the decision-making needs in its own field, it is difficult to cope with complex driving environments and affects the safety of vehicle autonomous driving.

[0026] In response to the above problems, an embodiment of the present application provides a vehicle decision control system that can achieve cross-domain decision-making and optimize the vehicle's decision control performance.

[0027] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0028] Figure 1 is a schematic diagram of a vehicle decision control system according to an embodiment of the present application. Figure 1 The decision control system at least includes a data acquisition module 101, a multi-source data processing module 102, an intelligent decision module 103 and an execution control module 104; the intelligent decision module 103 includes an on-board decision model, wherein: The data acquisition module 101 is used to send a data request to the vehicle data center to obtain vehicle internal data, vehicle external data and cloud data; The multi-source data processing module 102 is used to perform data fusion processing on vehicle internal data, vehicle external data and cloud data to generate target decision data; The intelligent decision module 103 is used to input the target decision data into the vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; The execution control module 104 is used to convert at least one target decision instruction into a control signal, and control the execution component associated with the control signal to perform a control operation.

[0029] In this application, the decision control system refers to a system that integrates multiple data to make corresponding decisions. The decision control system realizes the data collection process through the transmission chain between TBOX (Telematics Box, on-board communication box), cloud server and on-board data center.

[0030] During this process, TBOX is first responsible for receiving data from various sensors of the vehicle, including images and videos obtained by image acquisition sensors, the distance and speed between the vehicle and surrounding objects measured by radar sensors, and acceleration, angular velocity and attitude information provided by the inertial measurement unit, and uploading these data to the cloud server to ensure the real-time and integrity of the data.

[0031] At the same time, TBOX can also download relevant data from the cloud server and store it in the on-board data center inside the vehicle.

[0032] As an integrated system, the on-board data center can store and manage various types of data related to the vehicle's driving process. When a decision is triggered, the decision control system can subscribe to the required data from the on-board data center to support real-time decision-making and control operations, ensuring that the vehicle can respond quickly in complex and changing environments.

[0033] In the present application, the decision control system includes a data acquisition module 101 , a multi-source data processing module 102 , an intelligent decision module 103 and an execution control module 104 .

[0034] In the embodiment of the present application, the data acquisition module 101 refers to a module for acquiring vehicle-related data in real time.

[0035] Since the vehicle is equipped with a variety of sensors, each type of sensor can collect different types of data in real time and upload them to the on-board data center. Therefore, when receiving a decision request, the data acquisition module 101 can directly obtain different types of data from the on-board data center, thereby assisting the multi-source data fusion module 102 and the intelligent decision-making module 103 to comprehensively monitor and analyze the current driving status and current driving environment of the vehicle.

[0036] In one example, the data acquired by the data acquisition module 101 from the vehicle-mounted data center includes: vehicle internal data, vehicle external data, and cloud data.

[0037] Vehicle internal data refers to data related to the vehicle's own performance and status, such as BMS (Battery Management System) data, VCU (Vehicle Control Unit) data, engine data, etc.

[0038] Vehicle external data refers to data related to the vehicle's driving environment, such as GPS (Global Positioning System) data, driving road data, weather data, traffic data, etc.

[0039] Cloud data refers to user-related data recorded in the cloud server history, such as user driving habit data, user driving route data, real-time traffic data, user personalized settings data, etc.

[0040] In the embodiment of the present application, the multi-source data processing module 102 refers to a module that performs fusion processing on data from different sources, and is mainly used to perform data fusion processing on internal vehicle data, external vehicle data, and cloud data to generate target decision data.

[0041] As an example, the data fusion processing process first performs preprocessing such as noise filtering and abnormal data removal on the vehicle's internal data, vehicle's external data, and cloud data, and then aligns the preprocessed multi-source data to the same time and space. Finally, feature extraction is performed on the multi-source data to obtain key features, and the feature set composed of multiple key features is used as the target decision data.

[0042] In the embodiment of the present application, the intelligent decision module 103 refers to a module that analyzes target decision data through a vehicle-mounted decision model and outputs target decision instructions. It mainly uses preset weight parameters and distance parameters to analyze target decision data and generate target decision instructions.

[0043] Among them, the on-board decision-making model refers to a model obtained based on machine learning or deep learning, which can comprehensively consider multi-dimensional information such as the vehicle's own performance, current driving status, driving environment information, and user preferences, and output accurate decision-making instructions.

[0044] The weight parameter is used to indicate the importance of different input features to the decision. The larger the weight parameter, the more important the feature is to the decision.

[0045] The distance parameter is a numerical value used to reflect the relationship between different features. During the decision-making process, the distance parameter can be updated in real time, so that the on-board decision-making model can adapt to complex and changing driving environments.

[0046] In an embodiment of the present application, the execution control module 104 refers to a module that converts a target decision instruction into an actual control signal, which is mainly used to convert at least one target decision instruction into a control signal and control the execution component associated with the control signal to perform a control operation.

[0047] After receiving the control signal, the execution component will parse the control signal. Different types of execution components have different processing mechanisms. Usually, after parsing the control signal, the execution component can obtain the control parameters, and the execution component will perform the control operation according to the control parameters.

[0048] As an example, assuming that the target decision instruction is a body control instruction, the body control instruction can be converted into a steering control signal. After parsing the steering control signal, the steering system can be controlled to rotate to a specific angle, such as twenty degrees to the left.

[0049] Assuming that the target decision instruction is an air conditioning control instruction, the air conditioning control instruction can be converted into a temperature adjustment signal. After parsing the temperature adjustment signal, the compressor can be started or the fan speed can be adjusted to achieve the set temperature.

[0050] In an embodiment of the present application, the decision control system includes at least a data acquisition module 101, a multi-source data processing module 102, an intelligent decision module 103 and an execution control module 104. The intelligent decision module 103 includes an on-board decision model, wherein the data acquisition module 101 is used to send a data request to the on-board data center to obtain vehicle internal data, vehicle external data and cloud data. The multi-source data processing module 102 is used to perform data fusion processing on vehicle internal data, vehicle external data and cloud data to generate target decision data. The intelligent decision module 103 is used to input the target decision data into the on-board decision model so that the on-board decision model analyzes the target decision data using preset weight parameters and distance parameters to generate target decision instructions. The execution control module 104 is used to convert at least one target decision instruction into a control signal and control the execution component associated with the control signal to perform a control operation.

[0051] The technical solution of the present application, on the one hand, the decision-making control system integrates modules with multiple functions with different functions, and realizes cross-domain information aggregation and data fusion through the collaborative work between various modules, thereby improving the intelligence of the vehicle and the user experience in the actual decision-making process. On the other hand, a multi-source data processing module 102 is designed for data in different fields. The multi-source data processing module 102 can convert multi-source data into target decision data that is easy to analyze, so that the intelligent decision-making module 103 can use the on-board decision model to conduct in-depth analysis of the target decision data, generate target decision instructions that meet the current driving status of the vehicle, user preferences and other requirements, and realize "full knowledge and full control" decision control, thereby improving the accuracy of vehicle decisions and ensuring that the vehicle makes the best decision in various complex driving environments.

[0052] Figure 2 It is a structural schematic diagram of a vehicle decision control system shown in another embodiment of the present application. Figure 2 relatively Figure 1 The technical solution of the embodiment of the present application is described in more detail, and the decision control system interacts with various execution components of the vehicle.

[0053] The data acquisition module 201 is respectively connected to the vehicle data center and the multi-source data processing module 202 for communication, and sends the vehicle internal data, vehicle external data and cloud data acquired from the vehicle data center to the multi-source data processing module 202; The multi-source data processing module 202 is in communication with the intelligent decision-making module 203, and after fusing the vehicle internal data, vehicle external data and cloud data, the fused target decision data is sent to the intelligent decision-making system; The intelligent decision module 203 processes the target decision data using a pre-trained vehicle decision model, and introduces pre-set weight parameters and distance parameters during the processing to further analyze the target decision data to obtain a target decision instruction; The execution control module 204 receives the target decision instruction sent from the intelligent decision module 203, converts the target decision instruction into a control signal, and sends the control signal to the corresponding execution component to control the execution component to perform a control operation.

[0054] It is worth noting that the decision control system of the present application can adapt to different driving scenarios and adjust the decision strategy in real time according to the characteristics of different driving scenarios.

[0055] Combination Figure 3 , Figure 3 It is a data interaction diagram of a decision control system shown in an embodiment of the present application. The decision control system of the present application may be an on-board AI (Artificial Intelligence) decision center.

[0056] In order to achieve "full knowledge and full control" decision-making control, this application avoids information islands and data redundancy by acquiring multi-source data (vehicle internal data, vehicle external data, and cloud data).

[0057] Furthermore, by performing data fusion processing on multi-source data, the data in each field can be involved in the decision-making process in other fields. At the same time, the fused target decision data is intelligently analyzed to output decision instructions that comprehensively consider other fields (motor control, battery control, body control, suspension control, air conditioning control, etc.), thereby highly centralizing decision-making power, realizing cross-domain decision-making, and solving decision-making limitations between different fields.

[0058] As an example of an embodiment of the present application, data fusion processing includes at least data preprocessing operations and feature extraction operations. The multi-source data processing module 202 can first perform data preprocessing operations on vehicle internal data, vehicle external data, and cloud data to obtain initial decision data, and then perform feature extraction operations on the initial decision data to generate target decision data.

[0059] Since a large amount of data is obtained, the multi-source data processing module 202 needs to perform data pre-processing operations such as data cleaning and data conversion on the received vehicle internal data, vehicle external data, and cloud data, so as to remove invalid data and reduce data complexity.

[0060] Among them, the data cleaning process at least includes filtering noise and eliminating abnormal data: the multi-source data processing module 202 can filter the noise of vehicle internal data, vehicle external data and cloud data respectively, and eliminate abnormal data of vehicle internal data, vehicle external data and cloud data.

[0061] For example, the noise filtering and abnormal data elimination process for BMS data (vehicle internal data): assuming that the BMS data acquired by the multi-source data processing module 202 includes information such as battery voltage, temperature, and charging status, then the battery voltage that suddenly fluctuates in a short period of time can be marked as noise and filtered, and statistical methods can be used to identify abnormal values ​​and eliminate them.

[0062] It should be noted that methods for filtering noise and eliminating abnormal data include but are not limited to setting reasonable thresholds and using filtering algorithms.

[0063] The data cleaning process also includes time-space alignment: the multi-source data processing module 202 can time-space align the vehicle's internal data, vehicle's external data, and cloud data to obtain initial decision data, where the initial decision data is a data set at the same time node and the same spatial coordinates.

[0064] For example, for the spatiotemporal alignment process of GPS data (vehicle external data) and real-time traffic data (cloud data): Assuming that the GPS data acquired by the multi-source data processing module 202 includes: the current location information of the vehicle and the first timestamp, and the acquired real-time traffic data includes the location information collected by the cloud server, the second timestamp, and the traffic congestion status, then the first timestamp can be compared with the second timestamp. If the time interval between the two is short, they can be regarded as the same moment of recording time. Correspondingly, if the distance between the location information collected by the GPS and the location information collected by the cloud server is short, they can be regarded as being in the same space.

[0065] Furthermore, in order to more accurately align the data collected by different sensors, the corresponding time window and distance threshold can be set according to actual needs, so as to control the accuracy of spatiotemporal alignment and meet the vehicle decision-making and control requirements of different driving scenarios.

[0066] After the multi-source data processing module 202 obtains the initial decision data through the data preprocessing operation, it is necessary to perform a feature extraction operation on the initial decision data to generate a decision feature vector that conforms to the actual driving scenario.

[0067] The feature extraction process includes: extracting a variety of decision feature data from the initial decision data according to preset feature categories, using the multiple decision feature data to construct a decision feature vector, and using the decision feature vector as the target decision data.

[0068] The preset feature categories may be data types set in advance by relevant technical personnel. For example, the preset feature categories may include vehicle status features, vehicle driving environment features, user preference features, and the like.

[0069] The multi-source data processing module 202 extracts a variety of decision feature data from the initial decision data according to preset feature categories, and selects decision feature data of corresponding categories according to decision requirements to form a decision feature vector.

[0070] For example, the vehicle state characteristic data includes a1, a2, and a3, and the vehicle driving environment characteristic data includes b1, b2, and b3. According to decision requirement ①, a1 and b1 can be combined to construct the first decision characteristic vector, and according to decision requirement ②, a2 and b3 can be combined to construct the second decision characteristic vector.

[0071] As an example, assume that the following decision feature data are extracted from the initial decision data according to the preset feature categories: 1) Vehicle status characteristic data includes: the current speed and acceleration of the vehicle; 2) Vehicle driving environment characteristic data includes: obstacle distance, road arrows, and road conditions; 3) User preference characteristic data include: the user's accustomed turning speed and driving speed.

[0072] If the decision requirement is a steering decision, the current driving speed in the vehicle state feature data, the road condition in the vehicle driving environment feature data, and the user's accustomed steering speed in the user preference feature data can be selected, and these decision feature data are used to form a multi-dimensional decision feature vector: [current driving speed, road condition, user's accustomed steering speed], which is used as the target decision data.

[0073] It can be understood that the data fusion of the multi-source data processing module 202 realizes the comprehensive integration of multi-source data such as internal, external and cloud data of the vehicle, and obtains an "omniscient" decision feature vector that comprehensively considers all aspects, so that the decision feature vector accurately reflects the current state of the vehicle, the real-time changes of the external environment and the personalized needs of users.

[0074] As an example of an embodiment of the present application, the intelligent decision module 203 has an on-board decision model, which can process the target decision data using the following decision function, which is actually a weighted decision function for calculating and outputting a comprehensive decision value: ; ; in, is the weight parameter of each node in the vehicle decision model, is the distance parameter of each node in the vehicle decision model, and The data format is 32-bit floating point number.

[0075] For target decision data, is the input feature and n is the number of features.

[0076] It is a comprehensive decision value, which is used to output the target decision instruction.

[0077] When the intelligent decision module 203 receives the target decision data, it uses the target decision data as input data: , input to the vehicle decision model, the vehicle decision model multiplies each input feature by the corresponding weight and through Scaling is performed until all input features are calculated and the target decision instruction is output.

[0078] It can be understood that the intelligent decision-making module 203 comprehensively controls and manages all relevant factors, outputs the optimal target decision instructions, and realizes "full control" decision-making, enabling the system to make the best decision in a complex and changing environment, thereby improving the safety and comfort of vehicle driving.

[0079] In addition, the intelligent decision-making module 203 can also sort multiple target decision instructions according to preset priorities, obtain the instruction execution order, and send the multiple target decision instructions to the execution control module 204 in sequence according to the instruction execution order, thereby improving the accuracy and responsiveness of the decision and better achieving the goal of "full knowledge and full control".

[0080] The preset priority can be a ranking set in advance by relevant technical personnel, usually sorted according to the urgency of the decision. For example, the priority of an emergency brake command is higher than other acceleration commands, deceleration commands or steering commands to ensure the safety of autonomous driving.

[0081] In addition to sorting by urgency, you can also sort by user preference. For example, when the driver first enters the car, he or she is used to turning on the air conditioner before the multimedia platform. In this case, the air conditioner control command can be set to have a higher priority than the multimedia wake-up command.

[0082] In this application, there is no limitation on the actual setting method of the priority.

[0083] After receiving a plurality of target decision instructions, the execution control module 204 may send control signals to corresponding execution components one by one according to the instruction execution sequence, so as to control the execution components to perform control operations.

[0084] It should be noted that the embodiments of the present application include but are not limited to the above examples. It is understandable that under the guidance of the ideas of the embodiments of the present application, technical personnel in this field can make settings according to actual conditions, and the present application does not limit this.

[0085] In an embodiment of the present application, the decision control system includes at least a data acquisition module 201, a multi-source data processing module 202, an intelligent decision module 203 and an execution control module 204. The intelligent decision module 203 includes an on-board decision model, wherein the data acquisition module 201 is used to send a data request to the on-board data center to obtain vehicle internal data, vehicle external data and cloud data. The multi-source data processing module 202 is used to perform data fusion processing on vehicle internal data, vehicle external data and cloud data to generate target decision data. The intelligent decision module 203 is used to input the target decision data into the on-board decision model so that the on-board decision model analyzes the target decision data using preset weight parameters and distance parameters to generate target decision instructions. The execution control module 204 is used to convert at least one target decision instruction into a control signal and control the execution component associated with the control signal to perform a control operation.

[0086] The technical solution of the present application, on the one hand, the decision-making control system integrates modules with multiple functions with different functions, and realizes cross-domain information aggregation and data fusion through the collaborative work between various modules, thereby improving the intelligence of the vehicle and the user experience in the actual decision-making process. On the other hand, a multi-source data processing module 202 is designed for data in different fields. The multi-source data processing module 202 can convert multi-source data into target decision data that is easy to analyze, so that the intelligent decision-making module 203 can use the on-board decision model to conduct in-depth analysis of the target decision data, generate target decision instructions that meet the current driving status of the vehicle, user preferences and other requirements, and realize "full knowledge and full control" decision control, thereby improving the accuracy of vehicle decisions and ensuring that the vehicle makes the best decision in various complex driving environments.

[0087] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a vehicle decision-making control method, electronic device and corresponding embodiments.

[0088] Figure 4 is a flow chart of a vehicle decision control method shown in an embodiment of the present application. Figure 4 , applied to a decision control system, the method comprises at least the following steps: Step 401, sending a data request to the vehicle data center to obtain vehicle internal data, vehicle external data and cloud data; Step 402, performing data fusion processing on the vehicle internal data, vehicle external data and cloud data to generate target decision data; Step 403, inputting the target decision data into a preset vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; Step 404: convert at least one target decision instruction into a control signal, and control an execution component associated with the control signal to perform a control operation.

[0089] As an example of an embodiment of the present application, the data fusion processing includes at least a data preprocessing operation and a feature extraction operation, and performs data fusion processing on the vehicle internal data, the vehicle external data and the cloud data to generate target decision data, including: Perform data preprocessing operations on vehicle internal data, vehicle external data, and cloud data to obtain initial decision data; Perform feature extraction operations on the initial decision data to generate target decision data.

[0090] As an example of an embodiment of the present application, a data preprocessing operation is performed on vehicle internal data, vehicle external data, and cloud data to obtain initial decision data, including: The noise of the vehicle's internal data, vehicle's external data and cloud data is filtered out respectively, and the abnormal data of the vehicle's internal data, vehicle's external data and cloud data are eliminated.

[0091] As an example of an embodiment of the present application, a data preprocessing operation is performed on vehicle internal data, vehicle external data, and cloud data to obtain initial decision data, including: Align the vehicle's internal data, vehicle's external data, and cloud data in time and space to obtain initial decision data; The initial decision data is a data set at the same time node and the same space coordinate.

[0092] As an example of an embodiment of the present application, a feature extraction operation is performed on the initial decision data to generate target decision data, including: Extracting a variety of decision feature data from the initial decision data according to preset feature categories; A variety of decision feature data are used to construct a decision feature vector, and the decision feature vector is used as the target decision data.

[0093] As an example of an embodiment of the present application, the vehicle-mounted decision model uses the following decision function to process the target decision data: ; ; in, is the weight parameter of the vehicle decision model, is the distance parameter of the vehicle-mounted decision model.

[0094] As an example of an embodiment of the present application, the method further includes: Sort multiple target decision instructions according to preset priorities to obtain the instruction execution order; The multiple target decision instructions are sent to the execution control module in sequence according to the instruction execution order.

[0095] Regarding the method in the above embodiment, the specific manner of executing the operation in each step has been described in detail in the embodiment of the module, and will not be elaborated again here.

[0096] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0097] See also Figure 5 , the electronic device 500 includes a memory 510 and a processor 520 .

[0098] The processor 520 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0099] The memory 510 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 520 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at runtime. In addition, the memory 510 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 510 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0100] The memory 510 stores executable codes, and when the executable codes are processed by the processor 520 , the processor 520 can execute part or all of the methods described above.

[0101] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0102] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0103] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A vehicle decision control system, characterized in that: The decision control system at least includes a data acquisition module, a multi-source data processing module, an intelligent decision module and an execution control module; the intelligent decision module includes an on-board decision model, wherein: The data acquisition module is used to send a data request to the vehicle data center to obtain vehicle internal data, vehicle external data and cloud data; The multi-source data processing module is used to perform data fusion processing on the vehicle internal data, the vehicle external data and the cloud data to generate target decision data; The intelligent decision module is used to input the target decision data into the vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; The execution control module is used to convert at least one target decision instruction into a control signal, and control the execution component associated with the control signal to perform a control operation.

2. The system according to claim 1, characterized in that The data fusion processing at least includes a data preprocessing operation and a feature extraction operation; The multi-source data processing module is used to perform the data preprocessing operation on the vehicle internal data, the vehicle external data and the cloud data to obtain initial decision data; The feature extraction operation is performed on the initial decision data to generate the target decision data.

3. The system according to claim 2, characterized in that The multi-source data processing module is used to filter the noise of the vehicle internal data, the vehicle external data and the cloud data respectively, and eliminate abnormal data of the vehicle internal data, the vehicle external data and the cloud data.

4. The system according to claim 2 or 3, characterized in that: The multi-source data processing module is used to perform spatiotemporal alignment on the vehicle internal data, the vehicle external data and the cloud data to obtain the initial decision data; The initial decision data is a data set at the same time node and the same space coordinate.

5. The system according to claim 2, characterized in that The multi-source data processing module is used to extract a variety of decision feature data from the initial decision data according to preset feature categories; The plurality of decision feature data are used to construct a decision feature vector, and the decision feature vector is used as the target decision data.

6. The system according to claim 1, characterized in that The vehicle-mounted decision model uses the following decision function to process the target decision data: ； ； in, is the weight parameter of the vehicle-mounted decision model, is the distance parameter of the vehicle-mounted decision model.

7. The system according to claim 1 or 6, characterized in that: The intelligent decision module is used to sort multiple target decision instructions according to preset priorities to obtain the instruction execution order; The multiple target decision instructions are sent to the execution control module in sequence according to the instruction execution order.

8. A vehicle decision control method, characterized in that: Applied to the decision control system, the method comprises: Send data requests to the vehicle data center to obtain vehicle internal data, vehicle external data, and cloud data; Performing data fusion processing on the vehicle internal data, the vehicle external data and the cloud data to generate target decision data; Inputting the target decision data into a preset vehicle-mounted decision model, so that the vehicle-mounted decision model analyzes the target decision data using preset weight parameters and distance parameters to generate a target decision instruction; At least one target decision instruction is converted into a control signal, and an execution component associated with the control signal is controlled to perform a control operation.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored therein, which, when executed by the processor, causes the processor to execute the method according to claim 8. 10 . A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to claim 8 .

Images