Control method and system of anti-theft starting battery
By building a vehicle behavior data model and feature map, identifying abnormal behaviors and generating intelligent control strategies, the problem of low anti-theft performance of traditional vehicle-mounted anti-theft system is solved, and the safety of the vehicle and battery management efficiency are improved.
Patent Information
- Application Number
- CN202411353561.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2024-11-29
AI Technical Summary
The anti-theft performance of traditional car-mounted anti-theft system is low and cannot be dynamically optimized and adjusted according to the owner's usage habits and behavioral characteristics, resulting in low level of anti-theft safety.
By obtaining real-time and historical vehicle behavior data, a vehicle action probability distribution map, behavior timing evolution trajectory and feature map are constructed, abnormal behavior evaluation is carried out, and the optimal anti-theft control strategy and battery sleep control strategy are generated to realize intelligent battery control.
It improves the vehicle's anti-theft safety and battery utilization, extends battery life, enhances the system's response speed and accuracy, and ensures the vehicle's quick switching response between abnormal and normal state.
Smart Images

Figure CN119037334A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of battery control, and in particular to a control method and system for an anti-theft starting battery. Background Art
[0002] With the continuous advancement of automotive electronic technology, vehicle anti-theft systems have become an important part of modern car safety. Traditional vehicle anti-theft systems usually rely on mechanical locks or simple remote control devices, and have problems such as low anti-theft performance and easy to be cracked. In order to further improve the anti-theft security of vehicles, anti-theft through vehicle anti-theft starting batteries has gradually become a feasible technology. As the core power source of the vehicle, the battery plays a key role in the vehicle anti-theft system. At present, the control of vehicle anti-theft starting batteries mainly relies on fixed control strategies, and cannot be dynamically optimized and adjusted according to the owner's usage habits and behavioral characteristics. Traditional vehicle starting batteries often have a single starting mode and cannot adapt to the owner's user behavior. The first-level anti-theft security is low, so an intelligent anti-theft battery starting method is needed. Summary of the invention
[0003] In order to solve the above technical problems, the present invention proposes a control method and system for an anti-theft starting battery to solve at least one of the above technical problems.
[0004] To achieve the above object, the present invention provides a control method for an anti-theft starting battery, comprising the following steps: Step S1: acquiring real-time vehicle behavior data and historical vehicle behavior monitoring data; generating a historical vehicle behavior monitoring sequence based on the historical vehicle behavior monitoring data; performing a probability calculation on the historical vehicle behavior monitoring sequence to construct a vehicle action probability distribution diagram; Step S2: Evolving the time trajectory based on the vehicle action probability distribution graph to obtain the behavior time series evolution trajectory; mining user preferences on the behavior time series evolution trajectory to construct a behavior feature map; Step S3: performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior feature map to generate a behavior abnormality evaluation result, wherein the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state; Step S4: When the abnormal behavior evaluation result is an abnormal vehicle state, an optimal anti-theft control iterative decision is made for the anti-theft starting battery to generate an optimal battery anti-theft control strategy; Step S5: When the abnormal behavior assessment result is a normal vehicle state, a low current monitoring decision is made for the anti-theft starting battery, and a battery dormancy control strategy is constructed; Step S6: Optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy to build a battery intelligent control model.
[0005] The present invention generates a historical vehicle behavior monitoring sequence through historical vehicle behavior monitoring data, and the system understands the evolution law and trend of vehicle behavior, provides basic data support for subsequent analysis, and constructs a vehicle action probability distribution map to help the system comprehensively consider the probability distribution of vehicle behavior, and provide a basis for the generation of subsequent behavior time series evolution trajectory. Through the time trajectory evolution and behavior time series evolution trajectory, the system helps understand the development process and trend of vehicle behavior, and provides time series support for subsequent user preference mining. The behavior feature map system is constructed to mine user preferences for vehicle behavior, and provide a basis for subsequent comprehensive evaluation of abnormal behavior. The comprehensive evaluation of abnormal behavior helps the system to monitor vehicle behavior data in real time, identify abnormal behavior, ensure vehicle safety and stable operation, and generate abnormal behavior evaluation results. The system responds in time Abnormal situations, improve the efficiency and safety of vehicle management, the optimal anti-theft control strategy helps the system take quick measures when abnormal vehicle status is detected to protect the vehicle from theft and damage, iterative decision-making can continuously optimize the anti-theft control strategy, improve response speed and accuracy, the low current monitoring decision system identifies energy-saving measures under normal vehicle conditions, extends battery life, and improves vehicle energy efficiency. Building a battery dormancy control strategy helps the system effectively manage battery energy under normal conditions and improve battery utilization. Fast switching response optimization can help the system quickly switch between abnormal and normal states, ensuring timely and effective response and control. Building a battery intelligent control model comprehensively considers the optimal control strategy under different situations, realizes intelligent management and optimization of the battery, and improves the efficiency and reliability of the overall system.
[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire real-time vehicle behavior data and historical vehicle behavior monitoring data; Step S12: Timestamp the historical vehicle behavior monitoring data and perform sequential fitting to generate a historical vehicle behavior monitoring sequence; Step S13: performing vehicle action recognition on the historical vehicle behavior monitoring data to obtain multiple vehicle action types; Step S14: performing probability calculation on the historical vehicle behavior monitoring sequence based on multiple vehicle action types to obtain multiple vehicle action probabilities; Step S15: Perform probability distribution fitting on multiple vehicle action probabilities to construct a vehicle action probability distribution graph.
[0007] The present invention obtains real-time vehicle behavior data and historical vehicle behavior monitoring data in order to fully understand the real-time status and historical evolution of vehicle behavior, and provide data support for subsequent analysis. Timestamp marking and sequence fitting integrate historical vehicle behavior monitoring data into an ordered historical vehicle behavior monitoring sequence, and provide a clear time series data basis for subsequent analysis. Vehicle action recognition helps the system to accurately identify different action types in historical vehicle behavior monitoring data, and provide a more refined behavior classification basis for subsequent analysis. Through behavior probability calculation, the occurrence probability of different vehicle action types is quantified, which helps to identify and focus on frequently occurring vehicle behaviors. Through probability distribution fitting, the probability of each vehicle action type is integrated into a probability distribution diagram, which intuitively displays the probability of vehicle behavior and provides an intuitive reference for battery control optimization.
[0008] Preferably, step S2 specifically comprises the following steps: Step S21: performing time series change analysis on the historical vehicle behavior monitoring sequence to generate vehicle behavior time series change data; Step S22: performing time trajectory evolution on the vehicle behavior time series change data based on the vehicle action probability distribution diagram, thereby obtaining a behavior time series evolution trajectory; Step S23: mining user preferences on the behavior temporal evolution trajectory to obtain user behavior preference feature data; Step S24: reconstructing a personalized feature map of the user's behavior preference feature data to construct a behavior feature map. The present invention analyzes the time series changes of historical vehicle behavior monitoring sequences, and the system discovers the change pattern of vehicle behavior over time. This analysis reveals information such as the frequency change and trend evolution of specific actions or behaviors in different time periods. By mapping the vehicle behavior time series change data onto the time trajectory, the system can more clearly observe the evolution of vehicle behavior. This time trajectory evolution helps to discover the correlation, continuity, and periodic laws between behaviors. By mining user preferences on the behavior time series evolution trajectory, the system identifies the user's preference for specific behavior types or patterns. This personalized mining system better understands user needs and provides a more accurate reference for subsequent decision-making. By reconstructing the personalized feature map of user behavior preference feature data, the system presents the user behavior features in the form of a map. This graphical display system better visualizes and understands the relationship between user behavior features, providing support for the formulation of personalized strategies.
[0009] Preferably, step S3 specifically comprises the following steps: Step S31: performing state difference analysis on the real-time vehicle behavior data based on the behavior feature map to obtain a plurality of behavior difference points; Step S32: Calculating the overall deviation degree of multiple behavior difference points, thereby obtaining a behavior deviation degree value; Step S33: Performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior deviation degree value to generate a behavior abnormality evaluation result; the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state.
[0010] The present invention uses behavior state difference analysis to systematically identify the differences between different behavior states in real-time vehicle behavior data, discover changes in behavior patterns and abnormalities, and quantify the degree of deviation of multiple behavior difference points through overall deviation degree calculation. The system further analyzes the abnormalities of vehicle behavior data to provide an objective reference for subsequent decision-making. The real-time vehicle behavior data is comprehensively evaluated through the behavior deviation degree value. The system effectively identifies normal vehicle states and abnormal vehicle states, promptly discovers potential problems and abnormalities, and provides a real-time abnormality detection and evaluation mechanism for battery control optimization.
[0011] Preferably, the specific steps of step S32 are: Marking multiple behavior difference points with occurrence timestamps to obtain behavior occurrence timestamps; Calculate the difference trend before and after the timestamp for multiple behavior difference points according to the behavior occurrence timestamp, so as to generate difference trend data for multiple behavior difference points; Conduct differential transmission impact analysis on multiple behavioral difference points to obtain the transmission impact between difference points; Perform feature association mining based on the transfer influence between difference points to obtain feature association data of difference points; Based on the feature association data of the difference points, the difference weights of multiple behavior difference points are defined, so as to obtain the weight of each difference point; The deviation superposition calculation is performed on the difference trend data of multiple behavior difference points according to the weight of each difference point, so as to obtain the behavior deviation degree value.
[0012] The present invention marks the timestamp of the occurrence of behavior, and the system accurately records the occurrence time of multiple behavior difference points, determines the time distribution and occurrence frequency of the behavior difference points, and by calculating the difference trend before and after the timestamp, the system analyzes the change trend of the behavior difference points over time, which helps to understand the evolution process and change law of the behavior difference points. Through the difference transmission impact analysis, the system reveals the mutual influence relationship between multiple behavior difference points, and helps to identify the transmission path and influence mechanism between the difference points. Through feature association mining, the system identifies the feature correlation between the difference points, and helps to understand the correlation and intrinsic connection between the difference points. By defining the difference weight, the system quantifies the importance of different difference points. The system prioritizes and focuses on the behavior difference points according to the actual situation. Through the weight superposition calculation, the system comprehensively considers the importance of each difference point, obtains the behavior deviation degree value, and provides comprehensive behavior abnormality evaluation and decision support for the system.
[0013] Preferably, the specific steps of step S4 are: Step S41: When the abnormal behavior evaluation result is an abnormal vehicle state, the anti-theft starter battery enters the anti-theft mode, and performs abnormal behavior type identification on the real-time vehicle behavior data to obtain the abnormal vehicle behavior type; Step S42: quantify the risk of abnormal vehicle behavior types and generate abnormal behavior risk levels; Step S43: performing optimal anti-theft control iterative decision on the anti-theft starting battery based on the abnormal behavior risk level, and generating an optimal battery anti-theft control strategy.
[0014] The present invention places the anti-theft starting battery in the anti-theft mode, and the system responds and controls the abnormal vehicle status in a timely manner to ensure the safety of the vehicle and the battery. Through abnormal behavior type identification, the system accurately identifies the specific type of abnormal behavior, further analyzes and handles the abnormal situation, and through behavior risk quantification, the system converts the abnormal behavior type into a specific risk level to help evaluate the impact of the abnormal behavior on the system security and generate an abnormal behavior risk level. The system prioritizes and processes the abnormal situation to improve the efficiency and accuracy of responding to the abnormal situation. Through the optimal control decision based on the abnormal behavior risk level, the system formulates corresponding anti-theft control strategies according to different risk levels, improves the pertinence and effectiveness of the anti-theft control, and generates the optimal battery anti-theft control strategy. The system quickly responds to abnormal situations, ensures the safe operation of the battery, and minimizes potential risks.
[0015] Preferably, the specific steps of step S5 are: Step S51: When the abnormal behavior evaluation result is a normal vehicle state, the frequency of the real-time vehicle behavior data is calculated to obtain the vehicle behavior frequency; Step S52: performing vehicle mode analysis based on the vehicle behavior frequency, thereby obtaining normal vehicle startup mode data and vehicle sleep mode data; Step S53: Perform low current monitoring decision on the anti-theft starting battery based on the vehicle sleep mode data, and construct a battery sleep control strategy. The present invention calculates the behavior frequency through behavior frequency calculation. The system quantifies the behavior frequency of normal vehicles, helps to understand the typical behavior patterns and behavior habits of vehicles, obtains the vehicle behavior frequency to establish a vehicle behavior model, and provides a basis for subsequent data analysis and decision-making. Through vehicle mode analysis, the system identifies the start-up mode and sleep mode of normal vehicles according to the vehicle behavior frequency, understands the behavior characteristics of the vehicle in different states, and obtains the normal vehicle start-up mode and vehicle sleep mode data. The system classifies and analyzes normal vehicle behavior to provide a basis for subsequent battery control strategies. Through low-current monitoring decisions, the system monitors the battery status in real time according to the vehicle sleep mode data, promptly discovers the battery sleep state, and constructs a battery sleep control strategy system to effectively manage battery energy consumption in the vehicle sleep state, extend battery life and improve battery performance.
[0016] Preferably, the specific steps of step S6 are: Step S61: performing battery start response analysis on the optimal battery anti-theft control strategy, normal vehicle start mode data and battery dormancy control strategy, thereby obtaining anti-theft start battery response data; Step S62: Calculate the response delay of the anti-theft start battery response data to generate battery response delay data; Step S63: optimizing the rapid switching response of the anti-theft starting battery according to the battery response delay data, and generating a response optimization control strategy; Step S64: Conduct data mining on the response optimization control strategy to construct a battery intelligent control model.
[0017] The present invention analyzes the battery start-up response, and the system comprehensively considers the optimal anti-theft control strategy, the normal start-up mode and the battery sleep control strategy, thereby generating battery start-up response data for different situations, and obtaining the anti-theft start-up battery response data system to understand the response characteristics of the battery under various situations, and provide a basis for subsequent response optimization; through response delay calculation, the system evaluates the time delay of the battery start-up response, helps to understand the speed and efficiency of the battery response, generates battery response delay data, and optimizes the response time, improves the battery response speed and performance; through fast switching response optimization, the system optimizes the battery switching response strategy according to the response delay data, improves the battery response speed and efficiency, generates a response optimization control strategy system to achieve fast response, and improves the real-time and flexibility of battery control; through data mining construction, the system uses the data of the response optimization control strategy to build an intelligent control model, realizes intelligent management of battery control, and builds a battery intelligent control model system to optimize the battery control strategy, and improves the operating efficiency and stability of the battery.
[0018] In this specification, a control system of an anti-theft starting battery is provided, which is used to execute the control method of the anti-theft starting battery as described above, including: The behavior probability module is used to obtain real-time vehicle behavior data and historical vehicle behavior monitoring data; generate historical vehicle behavior monitoring sequences based on historical vehicle behavior monitoring data; perform behavior probability calculations on historical vehicle behavior monitoring sequences and construct vehicle action probability distribution diagrams; The behavior feature module is used to perform time trajectory evolution based on the vehicle action probability distribution map to obtain the behavior time series evolution trajectory; perform user preference mining on the behavior time series evolution trajectory to construct a behavior feature map; An abnormal behavior assessment module is used to perform a comprehensive abnormal behavior assessment on real-time vehicle behavior data based on a behavior feature map to generate a behavior abnormality assessment result, wherein the behavior abnormality assessment result includes a normal vehicle state and an abnormal vehicle state; The anti-theft control module is used to make optimal anti-theft control iterative decisions on the anti-theft starting battery and generate the optimal battery anti-theft control strategy when the behavior abnormality assessment result is an abnormal vehicle state; The sleep control module is used to make low current monitoring decisions on the anti-theft starting battery and build a battery sleep control strategy when the abnormal behavior assessment result is a normal vehicle state; The intelligent control module is used to optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy, and to build a battery intelligent control model.
[0019] The present invention constructs a vehicle action probability distribution map through behavior probability calculation, systematically analyzes the frequency and trend of vehicle behavior, helps understand the vehicle's regular operation mode, obtains real-time vehicle behavior data and historical monitoring data, and systematically establishes a comprehensive behavior probability model to improve the accuracy and reliability of vehicle behavior. Through time trajectory evolution and behavior time series evolution trajectory analysis, the system reveals the evolution trend and law of vehicle behavior, helps understand the dynamic change process of vehicle behavior, and mines user preferences and constructs behavior feature maps. The system identifies user behavior preferences and behavior characteristics, provides reference for personalized services and decision-making, and conducts abnormal evaluation of real-time vehicle behavior data through behavior feature maps. The system quickly and accurately identifies normal and abnormal vehicle states, improves the detection and response capabilities of vehicle behavior anomalies, and generates behavior anomaly evaluation results. The system takes targeted measures in a timely manner to ensure the safety of vehicles and drivers. When the behavior anomaly evaluation results are abnormal, When the vehicle is in normal state, the optimal battery anti-theft control strategy is generated through the optimal anti-theft control iterative decision. The system effectively responds to abnormal situations such as vehicle theft and improves vehicle safety. The optimal anti-theft control strategy generation system optimizes the handling of abnormal situations, reduces losses and improves emergency response efficiency. When the behavior abnormality assessment result is a normal vehicle state, a low current monitoring decision is made to construct a battery dormancy control strategy. The system effectively manages battery energy consumption, extends battery life and improves performance. The battery dormancy control strategy establishment system reasonably utilizes battery energy under normal circumstances to improve the vehicle's energy-saving efficiency. The optimal anti-theft control strategy and the battery dormancy control strategy are quickly switched and responded to and optimized. A battery intelligent control model is constructed. The system realizes intelligent management and optimization of the battery control strategy. The battery intelligent control model system improves the monitoring and control capabilities of the battery state and optimizes the battery's usage efficiency and performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 A schematic flow chart of the steps of a method for controlling an anti-theft starting battery according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION
[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0022] The present application example provides a control method and system for an anti-theft starting battery. The execution subject of the control method and system for the anti-theft starting battery includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as a general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.
[0023] See also Figures 1 to 4 The present invention provides a control method for an anti-theft starting battery, the control method for an anti-theft starting battery comprising the following steps: Step S1: acquiring real-time vehicle behavior data and historical vehicle behavior monitoring data; generating a historical vehicle behavior monitoring sequence based on the historical vehicle behavior monitoring data; performing a probability calculation on the historical vehicle behavior monitoring sequence to construct a vehicle action probability distribution diagram; Step S2: Evolving the time trajectory based on the vehicle action probability distribution graph to obtain the behavior time series evolution trajectory; mining user preferences on the behavior time series evolution trajectory to construct a behavior feature map; Step S3: performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior feature map to generate a behavior abnormality evaluation result, wherein the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state; Step S4: When the abnormal behavior evaluation result is an abnormal vehicle state, an optimal anti-theft control iterative decision is made for the anti-theft starting battery to generate an optimal battery anti-theft control strategy; Step S5: When the abnormal behavior assessment result is a normal vehicle state, a low current monitoring decision is made for the anti-theft starting battery, and a battery dormancy control strategy is constructed; Step S6: Optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy to build a battery intelligent control model.
[0024] The present invention generates a historical vehicle behavior monitoring sequence through historical vehicle behavior monitoring data, and the system understands the evolution law and trend of vehicle behavior, provides basic data support for subsequent analysis, and constructs a vehicle action probability distribution map to help the system comprehensively consider the probability distribution of vehicle behavior, and provide a basis for the generation of subsequent behavior time series evolution trajectory. Through the time trajectory evolution and behavior time series evolution trajectory, the system helps understand the development process and trend of vehicle behavior, and provides time series support for subsequent user preference mining. The behavior feature map system is constructed to mine user preferences for vehicle behavior, and provide a basis for subsequent comprehensive evaluation of abnormal behavior. The comprehensive evaluation of abnormal behavior helps the system to monitor vehicle behavior data in real time, identify abnormal behavior, ensure vehicle safety and stable operation, and generate abnormal behavior evaluation results. The system responds in time Abnormal situations, improve the efficiency and safety of vehicle management, the optimal anti-theft control strategy helps the system take quick measures when abnormal vehicle status is detected to protect the vehicle from theft and damage, iterative decision-making can continuously optimize the anti-theft control strategy, improve response speed and accuracy, the low current monitoring decision system identifies energy-saving measures under normal vehicle conditions, extends battery life, and improves vehicle energy efficiency. Building a battery dormancy control strategy helps the system effectively manage battery energy under normal conditions and improve battery utilization. Fast switching response optimization can help the system quickly switch between abnormal and normal states, ensuring timely and effective response and control. Building a battery intelligent control model comprehensively considers the optimal control strategy under different situations, realizes intelligent management and optimization of the battery, and improves the efficiency and reliability of the overall system.
[0025] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of a method for controlling an anti-theft starting battery of the present invention. In this example, the steps of the method for controlling an anti-theft starting battery include: Step S1: acquiring real-time vehicle behavior data and historical vehicle behavior monitoring data; generating a historical vehicle behavior monitoring sequence based on the historical vehicle behavior monitoring data; performing a probability calculation on the historical vehicle behavior monitoring sequence to construct a vehicle action probability distribution diagram; In this embodiment, based on the built-in sensor of the anti-theft starting battery in the vehicle, the startup behavior monitoring data of the user in the vehicle is collected in real time, the vehicle-mounted user behavior monitoring data collected in the past period of time (such as 1 week or 1 month) is read from the database, and these historical data are cleaned and preprocessed, such as removing outliers, filling missing data, etc., to ensure data quality, and the processed historical vehicle-mounted user behavior monitoring data is stored in the database for subsequent monitoring sequence generation and use, the cleaned historical vehicle-mounted user behavior monitoring data is read from the database, and the data is sorted in chronological order according to the timestamp to generate a historical vehicle-mounted user behavior monitoring sequence, and the generated historical vehicle-mounted user behavior monitoring sequence is stored in the database to provide input for subsequent behavior probability calculation, the aforementioned generated historical vehicle-mounted user behavior monitoring sequence is read, and different types of user driving actions (such as steering, acceleration, deceleration, etc.) in the monitoring sequence are statistically analyzed to calculate the probability of each action appearing in the entire sequence, and the calculated user behavior action probability data is used to construct a user behavior action probability distribution diagram in the form of a chart or other form to intuitively display the occurrence probability of different actions, and the user behavior action probability distribution diagram is stored in the database for subsequent user behavior prediction and decision support.
[0026] Step S2: Evolving the time trajectory based on the vehicle action probability distribution graph to obtain the behavior time series evolution trajectory; mining user preferences on the behavior time series evolution trajectory to construct a behavior feature map; In this embodiment, according to the vehicle action probability distribution diagram, the probability of different actions taken by the vehicle at the next moment is calculated, and according to the probability of each action, the state of the vehicle at the next moment is randomly generated. By analogy, the future time trajectory evolution process of the vehicle is recursively predicted. For each trajectory, the action sequence contained in it is analyzed to identify the common behavior patterns and preferences of users. For example, statistics show that a certain user tends to take more actions such as turning left or right within a certain period of time, or tends to maintain a higher / lower speed on certain sections of the road. The mined user behavior features are constructed into a user behavior feature map to intuitively display the behavior preferences of different users.
[0027] Step S3: performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior feature map to generate a behavior abnormality evaluation result, wherein the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state; In this embodiment, the user behavior characteristic map constructed above is read, which includes common behavior patterns and preferences of different users. The vehicle behavior data collected in real time is compared and analyzed with the patterns in the user behavior characteristic map, and the degree of difference between the real-time vehicle behavior data and the user behavior characteristics is calculated as the basis for abnormal behavior evaluation. Different levels of vehicle status are divided according to the degree of difference between the real-time vehicle behavior data and the user behavior characteristics: normal vehicle status: the real-time behavior data is highly consistent with the user characteristics, and the vehicle is in a normal driving state; abnormal vehicle status: there is a large deviation between the real-time behavior data and the user characteristics, and the vehicle exhibits abnormal driving behavior. The abnormal status can be further subdivided into levels such as slight abnormality and severe abnormality. The generated vehicle status evaluation results (including normal status and abnormal status) are stored in the database for subsequent decision support and alarm system use.
[0028] Step S4: When the abnormal behavior evaluation result is an abnormal vehicle state, an optimal anti-theft control iterative decision is made for the anti-theft starting battery to generate an optimal battery anti-theft control strategy; In this embodiment, the abnormal state vehicle data collected above is used to construct a machine learning model to optimize the vehicle's anti-theft control strategy. Reinforcement learning and other methods are used to find the optimal anti-theft control strategy through continuous trial and error and feedback optimization. The optimization goals include: minimizing the risk of vehicle theft, shortening the accident response time, reducing interference with normal users, etc. When the vehicle is found to be in an abnormal state, the trained anti-theft control decision model is called in real time. According to the output of the model, the battery power supply of the vehicle anti-theft system is finely controlled: consider reducing the battery power supply voltage to reduce the probability of vehicle startup or disconnecting the battery power supply within a specific time period to temporarily prohibit the vehicle from starting; at the same time, a safety alarm is issued to notify the owner to handle it, and the executed anti-theft control decision record is stored in the database for subsequent analysis and improvement.
[0029] Step S5: When the abnormal behavior assessment result is a normal vehicle state, a low current monitoring decision is made for the anti-theft starting battery, and a battery dormancy control strategy is constructed; In this embodiment, the collected battery current data is analyzed to identify the characteristic mode of the battery current under normal conditions, such as the average current value, the current fluctuation range, etc., and these battery current characteristic indicators are stored in a database as a basis for judging the abnormal state of the battery. Based on the above battery current characteristic analysis, a reasonable battery dormancy control strategy is formulated: when the battery current is within the normal range, the battery supply voltage is appropriately reduced to make it enter a dormant state to save power. When the battery current fluctuates abnormally, an alarm is issued in time to prompt the user to check the battery status. For batteries that have been in a dormant state for a long time, short power supply wake-up is performed regularly to prevent over-discharge. The constructed battery dormancy control strategy is stored in a database for real-time execution by the vehicle-mounted system. The vehicle-mounted system reads the battery dormancy control strategy in the database in real time and executes corresponding control measures according to the battery current state monitored in real time: when the battery current is within the normal range, the battery supply voltage is reduced to enter a dormant state. When the battery current fluctuates abnormally, an alarm is issued and the battery supply voltage is appropriately increased. For batteries that have been in a dormant state for a long time, short power supply wake-up is performed regularly. The executed battery dormancy control situation is recorded in the database for subsequent analysis and optimization.
[0030] Step S6: Optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy to build a battery intelligent control model.
[0031] In this embodiment, an intelligent decision-making algorithm is designed in combination with the real-time data of the battery status monitoring model, which can automatically select the optimal anti-theft control strategy or battery dormancy control strategy according to the vehicle status. When designing the algorithm, multiple factors such as battery status, vehicle usage behavior pattern, location environment, etc. need to be considered, and continuous learning and optimization are carried out to improve the accuracy and timeliness of decision-making. The intelligent switching model is deployed to the vehicle system to run and execute the optimal control strategy in real time. In view of the requirement of quickly switching the anti-theft control strategy in emergency situations, the response speed of the intelligent switching model is optimized. Parallel processing, cache preloading and other technical means can be used to improve the execution efficiency of the switching strategy. At the same time, smooth switching of the battery dormancy control strategy is ensured in non-emergency situations to achieve the goal of power saving. The battery status data and the execution of the anti-theft / sleeping control strategy are continuously monitored, and the effect and performance are analyzed. According to the analysis results, the battery status monitoring model and the intelligent switching algorithm are continuously optimized to improve the accuracy and efficiency of decision-making. The anti-theft control strategy library is regularly updated, new countermeasures are added, and the comprehensive defense capability of the anti-theft system is improved. In combination with user feedback, the strategy switching logic is adjusted and optimized to improve user experience and satisfaction.
[0032] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Acquire real-time vehicle behavior data and historical vehicle behavior monitoring data; Step S12: Timestamp the historical vehicle behavior monitoring data and perform sequential fitting to generate a historical vehicle behavior monitoring sequence; Step S13: performing vehicle action recognition on the historical vehicle behavior monitoring data to obtain multiple vehicle action types; Step S14: performing probability calculation on the historical vehicle behavior monitoring sequence based on multiple vehicle action types to obtain multiple vehicle action probabilities; Step S15: Perform probability distribution fitting on multiple vehicle action probabilities to construct a vehicle action probability distribution graph.
[0033] In this embodiment, after obtaining user authorization, based on the built-in sensor of the anti-theft starting battery in the vehicle, the startup behavior monitoring data of the user in the vehicle is collected in real time, and the vehicle-mounted user behavior monitoring data collected in the past period of time (such as 1 week or 1 month) is read from the database. These historical data are cleaned and preprocessed, such as removing outliers, filling missing data, etc., to ensure data quality, and the processed historical vehicle-mounted user behavior monitoring data is stored in the database. The accuracy and continuity of the acquired historical vehicle behavior monitoring data are checked one by one. In the case of disordered timestamps or missing data, interpolation, fitting and other methods are used to correct and supplement them to ensure the time series of the data. The corrected data are arranged in chronological order to form a complete historical vehicle behavior monitoring sequence, which will provide orderly data input for subsequent behavior recognition and probability distribution analysis. Machine learning algorithms, such as support vector machines and neural networks, are used to train and identify the historical vehicle behavior monitoring data to obtain To various types of vehicle actions, the action recognition results include not only the action type, but also key information such as the time of occurrence and duration, so as to provide basic data for subsequent probability analysis. The historical vehicle behavior monitoring sequence is traversed, and the frequency of occurrence of various types of vehicle actions in the sequence is counted. According to the frequency of occurrence of each action, the corresponding probability value is calculated to form multiple vehicle action probabilities. These probability values reflect the probability distribution of occurrence of different vehicle actions in historical data, so as to provide basic data for subsequent probability distribution fitting. A suitable probability distribution model is selected, such as normal distribution, Poisson distribution, etc., to fit the vehicle action probabilities calculated in step S14. Through fitting analysis, it is determined which probability distribution each vehicle action probability conforms to, and the corresponding distribution parameters are obtained. The probability distribution of each vehicle action is presented in a graphical way to form a vehicle action probability distribution diagram, which intuitively shows the probability characteristics of different actions. The probability distribution diagram provides a statistical basis for subsequent vehicle behavior prediction and identifies vehicle behavior patterns.
[0034] In this embodiment, refer to Figure 3, is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing time series change analysis on the historical vehicle behavior monitoring sequence to generate vehicle behavior time series change data; Step S22: performing time trajectory evolution on the vehicle behavior time series change data based on the vehicle action probability distribution diagram, thereby obtaining a behavior time series evolution trajectory; Step S23: mining user preferences on the behavior temporal evolution trajectory to obtain user behavior preference feature data; Step S24: reconstructing a personalized feature map of the user's behavior preference feature data to construct a behavior feature map. In this embodiment, the change trend of each behavior indicator (such as position, speed, acceleration, etc.) is analyzed in chronological order, and the time series analysis method, such as sliding window method, Fourier transform, etc., is used to extract the change characteristics of each behavior indicator in time, and these time series change characteristics are organized into structured data to form vehicle behavior time series change data, which provides a basis for subsequent behavior trajectory evolution analysis. With the vehicle action probability distribution diagram as a reference, the change trajectory of each indicator in the vehicle behavior time series change data is analyzed, and the probability distribution of different vehicle actions is superimposed and evolved on the time axis, so as to deduce the overall vehicle behavior time series evolution trajectory. The evolution trajectory reflects the behavior change process of the vehicle in the time series, which provides key input for subsequent user preference analysis. Combined with the actual driving behavior data monitored by the vehicle-mounted sensor, the driver's behavior preference characteristics in different situations are explored, and the user's preference characteristics in vehicle control, driving style, safety awareness, etc. are extracted to form structured user behavior preference feature data. The data provides a basis for subsequent personalized services and deeply understands the user's behavior habits and needs.
[0035] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: performing state difference analysis on the real-time vehicle behavior data based on the behavior feature map to obtain a plurality of behavior difference points; Step S32: Calculating the overall deviation degree of multiple behavior difference points, thereby obtaining a behavior deviation degree value; Step S33: Performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior deviation degree value to generate a behavior abnormality evaluation result; the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state.
[0036] In this embodiment, various indicators in the real-time vehicle behavior data are compared and analyzed with the corresponding user behavior preferences in the behavior feature map, and the key points where the real-time vehicle behavior differs from the user preference are identified, and these difference points are recorded to form multiple behavior difference points. The behavior difference points reflect the degree of deviation between the real-time vehicle behavior and the expected behavior, and provide basic data for the subsequent overall deviation degree calculation. According to the multiple behavior difference points, the deviation degree and influence weight of each difference point are comprehensively considered, and the weighted average method is adopted to calculate the overall deviation degree value of the real-time vehicle behavior relative to the user preference. The deviation degree value reflects the overall difference between the real-time vehicle behavior and the expected behavior, and provides a basis for abnormal behavior evaluation. Based on the behavior deviation degree value, a reasonable abnormal threshold is set, and the real-time vehicle behavior data is compared with the abnormal threshold to determine whether the current vehicle behavior is in an abnormal state, and a comprehensive evaluation result including a normal vehicle state and an abnormal vehicle state is generated. The abnormal evaluation result can quickly identify abnormal conditions in the real-time vehicle behavior, and provide a basis for subsequent safety warnings and intelligent control.
[0037] In this embodiment, the specific steps of step S32 are: Marking multiple behavior difference points with occurrence timestamps to obtain behavior occurrence timestamps; Calculate the difference trend before and after the timestamp for multiple behavior difference points according to the behavior occurrence timestamp, so as to generate difference trend data for multiple behavior difference points; Conduct differential transmission impact analysis on multiple behavioral difference points to obtain the transmission impact between difference points; Perform feature association mining based on the transfer influence between difference points to obtain feature association data of difference points; Based on the feature association data of the difference points, the difference weights of multiple behavior difference points are defined, so as to obtain the weight of each difference point; The deviation superposition calculation is performed on the difference trend data of multiple behavior difference points according to the weight of each difference point, so as to obtain the behavior deviation degree value.
[0038] In this embodiment, according to each identified behavior difference point, the precise timestamps of their occurrence are recorded. These timestamp information reflects the order in which each difference point appears, providing basic data for subsequent trend analysis. The timestamps of each difference point recorded are sorted to form a time series, and adjacent difference points are compared before and after to calculate the difference trend between them, such as whether it is an increase or a decrease. These difference trend information are recorded to form difference trend data of multiple behavior difference points. These trend data reflect the change relationship between each difference point, providing a basis for subsequent difference transmission analysis, analyzing the transmission relationship between each difference point, identifying the main transmission impact path between the difference points, and quantifying their impact. The transmission impact information between these difference points can be used to understand the entire behavior. In order to understand the formation mechanism of the difference and the influence of the difference points, the corresponding vehicle behavior characteristics are analyzed, the key behavior characteristics that lead to each difference point are identified, and the correlation between them is recorded. These difference point feature association data can deeply understand the potential causes of the behavior differences. Combined with the obtained feature association data, the importance of each difference point to the overall behavior deviation is evaluated, and a corresponding weight coefficient is assigned to each difference point to reflect its influence in the overall behavior deviation. These difference point weight information provides a basis for subsequent deviation degree calculation. The difference trend data is weighted and superimposed using the difference point weights to obtain the overall behavior deviation degree value that comprehensively considers the importance of each difference point. The deviation degree value reflects the overall difference between real-time vehicle behavior and expected behavior.
[0039] In this embodiment, the specific steps of step S4 are: Step S41: When the abnormal behavior evaluation result is an abnormal vehicle state, the anti-theft starter battery enters the anti-theft mode, and performs abnormal behavior type identification on the real-time vehicle behavior data to obtain the abnormal vehicle behavior type; Step S42: quantify the risk of abnormal vehicle behavior types and generate abnormal behavior risk levels; Step S43: performing optimal anti-theft control iterative decision on the anti-theft starting battery based on the abnormal behavior risk level, and generating an optimal battery anti-theft control strategy.
[0040] In this embodiment, if it is assessed that the real-time vehicle behavior is in an abnormal state, the anti-theft starting battery is immediately triggered to enter the anti-theft mode. At the same time, the vehicle behavior data currently collected in real time is deeply analyzed and identified to determine the specific abnormal behavior type. The abnormal behavior types include: forced start, illegal movement, suspected theft, etc., which need to be identified based on specific behavioral characteristics. These abnormal behavior type information provides a basis for subsequent risk quantification and anti-theft control decisions. According to the identified abnormal behavior type, combined with the real-time status and environmental information of the vehicle, its potential risk level is quantitatively evaluated, considering factors such as: abnormal behavior duration, vehicle location, surrounding environment Etc., comprehensively judge the risk level faced by abnormal behavior. The risk level can be divided into low, medium and high levels, reflecting the potential threat degree of abnormal behavior to vehicle safety. These risk level information are used to guide subsequent optimal anti-theft control decisions. Based on the obtained abnormal behavior risk level, combined with the current state of the anti-theft battery and the executable anti-theft control measures, the optimal decision is made. Dynamic programming or reinforcement learning methods are used to iteratively calculate the optimal anti-theft control strategy of the anti-theft battery under the current environment and abnormal behavior risk. The optimal control strategy includes: power cut-off, fault simulation, alarm and other anti-theft measures of different degrees to deal with abnormal behaviors of different risk levels.
[0041] These anti-theft control strategies are dynamically adjusted to minimize the potential damage to vehicle safety caused by abnormal behavior.
[0042] In this embodiment, the specific steps of step S5 are: Step S51: When the abnormal behavior evaluation result is a normal vehicle state, the frequency of the real-time vehicle behavior data is calculated to obtain the vehicle behavior frequency; Step S52: performing vehicle mode analysis based on the vehicle behavior frequency, thereby obtaining normal vehicle startup mode data and vehicle sleep mode data; Step S53: Perform low current monitoring decision on the anti-theft starting battery based on the vehicle sleep mode data, and construct a battery sleep control strategy. In this embodiment, if it is evaluated that the real-time vehicle behavior is in a normal state, the vehicle behavior data is analyzed in depth. Specifically, the frequency of various behaviors (such as starting, moving, stopping, etc.) of the vehicle within a certain period of time is counted and analyzed. These behavior frequency data reflect the normal working mode and usage habits of the vehicle. According to the statistical vehicle behavior frequency data, the normal working mode of the vehicle is analyzed, and the typical starting mode of the vehicle is identified, such as the daily starting time, mileage and other characteristics. At the same time, the sleep mode of the vehicle is also analyzed, such as the daily parking time, parking location and other characteristics. These normal vehicle start mode and sleep mode data provide a basis for subsequent battery management. Based on the vehicle sleep mode data, the sleep time of the vehicle under normal circumstances is predicted. When the vehicle enters the sleep state, the anti-theft starting battery is monitored at a low current to maintain the normal power supply of the battery and monitor the battery power. When the power is lower than a certain threshold, an appropriate battery charging or management strategy is adopted to prevent the battery from being over-discharged. This ensures that during the normal sleep period of the vehicle, the anti-theft starting battery can maintain a normal working state and provide reliable power support for subsequent vehicle starts.
[0043] In this embodiment, the specific steps of step S6 are: Step S61: performing battery start response analysis on the optimal battery anti-theft control strategy, normal vehicle start mode data and battery dormancy control strategy, thereby obtaining anti-theft start battery response data; Step S62: Calculate the response delay of the anti-theft start battery response data to generate battery response delay data; Step S63: optimizing the rapid switching response of the anti-theft starting battery according to the battery response delay data, and generating a response optimization control strategy; Step S64: Conduct data mining on the response optimization control strategy to construct a battery intelligent control model.
[0044] In this embodiment, these strategies and data are simulated or measured to analyze the response characteristics of the anti-theft starting battery in various situations. Specifically, the normal vehicle start-up, anti-theft start-up and other scenarios are simulated to measure the battery's response time, voltage fluctuation, current change and other indicators as battery response data. These response data provide a basis for subsequent optimization. According to the battery response data, the response delay time of the battery in different situations is calculated. The response delay time refers to the time interval from receiving the control command to the actual response of the battery. Different starting scenarios, battery states, etc. are analyzed and calculated to generate comprehensive battery response delay data. These delay data reflect the response performance of the battery, providing an important basis for subsequent optimization. Combined with the obtained battery response delay data, the battery is targeted. The response control of the battery is optimized, and adaptive control, preview control and other methods are used to improve the switching response speed of the battery from sleep to start. The optimization goal is to shorten the battery response time as much as possible to ensure rapid start-up in an emergency and improve anti-theft performance. Through optimization, a set of targeted rapid response optimization control strategies are obtained. The response optimization control strategy is combined with a large amount of vehicle and battery data accumulated in the early stage, and in-depth data mining and analysis are carried out. Using machine learning, neural network and other technologies, a battery intelligent control model capable of adaptive learning and optimization is constructed. This model can automatically adjust the battery control strategy according to the real-time vehicle status and usage habits, improve the reliability and response speed of anti-theft starting, and finally form a control system for intelligent management of anti-theft starting batteries.
[0045] In this embodiment, a control system of an anti-theft starting battery is provided, which is used to execute the control method of the anti-theft starting battery as described above, including: The behavior probability module is used to obtain real-time vehicle behavior data and historical vehicle behavior monitoring data; generate historical vehicle behavior monitoring sequences based on historical vehicle behavior monitoring data; perform behavior probability calculations on historical vehicle behavior monitoring sequences and construct vehicle action probability distribution diagrams; The behavior feature module is used to perform time trajectory evolution based on the vehicle action probability distribution map to obtain the behavior time series evolution trajectory; perform user preference mining on the behavior time series evolution trajectory to construct a behavior feature map; An abnormal behavior assessment module is used to perform a comprehensive abnormal behavior assessment on real-time vehicle behavior data based on a behavior feature map to generate a behavior abnormality assessment result, wherein the behavior abnormality assessment result includes a normal vehicle state and an abnormal vehicle state; The anti-theft control module is used to make optimal anti-theft control iterative decisions on the anti-theft starting battery and generate the optimal battery anti-theft control strategy when the behavior abnormality assessment result is an abnormal vehicle state; The sleep control module is used to make low current monitoring decisions on the anti-theft starting battery and build a battery sleep control strategy when the abnormal behavior assessment result is a normal vehicle state; The intelligent control module is used to optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy, and to build a battery intelligent control model.
[0046] The present invention constructs a vehicle action probability distribution map through behavior probability calculation, systematically analyzes the frequency and trend of vehicle behavior, helps understand the vehicle's regular operation mode, obtains real-time vehicle behavior data and historical monitoring data, and systematically establishes a comprehensive behavior probability model to improve the accuracy and reliability of vehicle behavior. Through time trajectory evolution and behavior time series evolution trajectory analysis, the system reveals the evolution trend and law of vehicle behavior, helps understand the dynamic change process of vehicle behavior, and mines user preferences and constructs behavior feature maps. The system identifies user behavior preferences and behavior characteristics, provides reference for personalized services and decision-making, and conducts abnormal evaluation of real-time vehicle behavior data through behavior feature maps. The system quickly and accurately identifies normal and abnormal vehicle states, improves the detection and response capabilities of vehicle behavior anomalies, and generates behavior anomaly evaluation results. The system takes targeted measures in a timely manner to ensure the safety of vehicles and drivers. When the behavior anomaly evaluation results are abnormal, When the vehicle is in normal state, the optimal battery anti-theft control strategy is generated through the optimal anti-theft control iterative decision. The system effectively responds to abnormal situations such as vehicle theft and improves vehicle safety. The optimal anti-theft control strategy generation system optimizes the handling of abnormal situations, reduces losses and improves emergency response efficiency. When the behavior abnormality assessment result is a normal vehicle state, a low current monitoring decision is made to construct a battery dormancy control strategy. The system effectively manages battery energy consumption, extends battery life and improves performance. The battery dormancy control strategy establishment system reasonably utilizes battery energy under normal circumstances to improve the vehicle's energy-saving efficiency. The optimal anti-theft control strategy and the battery dormancy control strategy are quickly switched and responded to and optimized. A battery intelligent control model is constructed. The system realizes intelligent management and optimization of the battery control strategy. The battery intelligent control model system improves the monitoring and control capabilities of the battery state and optimizes the battery's usage efficiency and performance.
[0047] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0048] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A method for controlling an anti-theft starting battery, characterized in that: The following steps are involved: Step S1: acquiring real-time vehicle behavior data and historical vehicle behavior monitoring data; generating a historical vehicle behavior monitoring sequence based on the historical vehicle behavior monitoring data; performing a probability calculation on the historical vehicle behavior monitoring sequence to construct a vehicle action probability distribution diagram; Step S2: Evolving the time trajectory based on the vehicle action probability distribution graph to obtain the behavior time series evolution trajectory; mining user preferences on the behavior time series evolution trajectory to construct a behavior feature map; Step S3: performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior feature map to generate a behavior abnormality evaluation result, wherein the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state; Step S4: When the abnormal behavior evaluation result is an abnormal vehicle state, an optimal anti-theft control iterative decision is made for the anti-theft starting battery to generate an optimal battery anti-theft control strategy; Step S5: When the abnormal behavior assessment result is a normal vehicle state, a low current monitoring decision is made for the anti-theft starting battery, and a battery dormancy control strategy is constructed; Step S6: Optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy to build a battery intelligent control model.
2. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire real-time vehicle behavior data and historical vehicle behavior monitoring data; Step S12: Timestamp the historical vehicle behavior monitoring data and perform sequential fitting to generate a historical vehicle behavior monitoring sequence; Step S13: performing vehicle action recognition on the historical vehicle behavior monitoring data to obtain multiple vehicle action types; Step S14: performing probability calculation on the historical vehicle behavior monitoring sequence based on multiple vehicle action types to obtain multiple vehicle action probabilities; Step S15: Perform probability distribution fitting on multiple vehicle action probabilities to construct a vehicle action probability distribution graph.
3. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing time series change analysis on the historical vehicle behavior monitoring sequence to generate vehicle behavior time series change data; Step S22: performing time trajectory evolution on the vehicle behavior time series change data based on the vehicle action probability distribution diagram, thereby obtaining a behavior time series evolution trajectory; Step S23: mining user preferences on the behavior temporal evolution trajectory to obtain user behavior preference feature data; Step S24: reconstructing a personalized feature map of the user's behavior preference feature data to construct a behavior feature map.
4. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing state difference analysis on the real-time vehicle behavior data based on the behavior feature map to obtain a plurality of behavior difference points; Step S32: Calculating the overall deviation degree of multiple behavior difference points, thereby obtaining a behavior deviation degree value; Step S33: Performing a comprehensive abnormal behavior evaluation on the real-time vehicle behavior data based on the behavior deviation degree value to generate a behavior abnormality evaluation result; the behavior abnormality evaluation result includes a normal vehicle state and an abnormal vehicle state.
5. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S32 are: Marking multiple behavior difference points with occurrence timestamps to obtain behavior occurrence timestamps; Calculate the difference trend before and after the timestamp for multiple behavior difference points according to the behavior occurrence timestamp, so as to generate difference trend data for multiple behavior difference points; Conduct differential transmission impact analysis on multiple behavioral difference points to obtain the transmission impact between difference points; Perform feature association mining based on the transfer influence between difference points to obtain feature association data of difference points; Based on the feature association data of the difference points, the difference weights of multiple behavior difference points are defined, so as to obtain the weight of each difference point; The deviation superposition calculation is performed on the difference trend data of multiple behavior difference points according to the weight of each difference point, so as to obtain the behavior deviation degree value.
6. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: When the abnormal behavior evaluation result is an abnormal vehicle state, the anti-theft starter battery enters the anti-theft mode, and performs abnormal behavior type identification on the real-time vehicle behavior data to obtain the abnormal vehicle behavior type; Step S42: quantify the risk of abnormal vehicle behavior types and generate abnormal behavior risk levels; Step S43: performing optimal anti-theft control iterative decision on the anti-theft starting battery based on the abnormal behavior risk level, and generating an optimal battery anti-theft control strategy.
7. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: When the abnormal behavior evaluation result is a normal vehicle state, the frequency of the real-time vehicle behavior data is calculated to obtain the vehicle behavior frequency; Step S52: performing vehicle mode analysis based on the vehicle behavior frequency, thereby obtaining normal vehicle startup mode data and vehicle sleep mode data; Step S53: Perform low current monitoring decision on the anti-theft starting battery based on the vehicle sleep mode data, and construct a battery sleep control strategy.
8. The control method of the anti-theft starting battery according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing battery start response analysis on the optimal battery anti-theft control strategy, normal vehicle start mode data and battery dormancy control strategy, thereby obtaining anti-theft start battery response data; Step S62: Calculating the response delay of the anti-theft start battery response data to generate battery response delay data; Step S63: optimizing the rapid switching response of the anti-theft starting battery according to the battery response delay data, and generating a response optimization control strategy; Step S64: Conduct data mining on the response optimization control strategy to construct a battery intelligent control model.
9. A control system for an anti-theft starting battery, characterized in that: A method for controlling an anti-theft starting battery as claimed in claim 1, comprising: The behavior probability module is used to obtain real-time vehicle behavior data and historical vehicle behavior monitoring data; generate historical vehicle behavior monitoring sequences based on historical vehicle behavior monitoring data; perform behavior probability calculations on historical vehicle behavior monitoring sequences and construct vehicle action probability distribution diagrams; The behavior feature module is used to perform time trajectory evolution based on the vehicle action probability distribution map to obtain the behavior time series evolution trajectory; perform user preference mining on the behavior time series evolution trajectory to construct a behavior feature map; An abnormal behavior assessment module is used to perform a comprehensive abnormal behavior assessment on real-time vehicle behavior data based on a behavior feature map, and generate a behavior abnormality assessment result, wherein the behavior abnormality assessment result includes a normal vehicle state and an abnormal vehicle state; The anti-theft control module is used to make optimal anti-theft control iterative decisions on the anti-theft starting battery and generate the optimal battery anti-theft control strategy when the behavior abnormality assessment result is an abnormal vehicle state; The sleep control module is used to make low current monitoring decisions on the anti-theft starting battery and build a battery sleep control strategy when the abnormal behavior assessment result is a normal vehicle state; The intelligent control module is used to optimize the fast switching response of the optimal battery anti-theft control strategy and the battery sleep control strategy, and to build a battery intelligent control model.
Citation Information
Cited By
Automobile data analysis method and system based on intelligent diagnostic instrument
CN119541080A
