A digital-based intelligent monitoring system and method for electric vehicles

Abstract

The present invention discloses a digital-based intelligent monitoring system and method for electric vehicles, belonging to the field of electric vehicle monitoring. The electric vehicle monitoring system includes a data acquisition module, a database, a data analysis module, and an intelligent reminder module. The data acquisition module is used to collect basic data information and monitor the driving information of the electric vehicle in real time. The database is used to store the collected data information and the analysis results and perform data encryption. The data analysis module is used to analyze and process the collected real-time data of the electric vehicle. The intelligent reminder module is used to remind the user based on the analysis results. The present invention collects basic data information, and through the location information of the electric vehicle and the location information of nearby vehicles, predicts and analyzes the trajectory of the electric vehicle based on the collected data information, thereby analyzing the collision situation of the electric vehicle with other vehicles, providing intelligent reminders to the user, and intelligently monitoring the electric vehicle, thereby ensuring the driving safety of the user.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicle monitoring, and in particular to a digital-based intelligent monitoring system and method for electric vehicles. Background Art

[0002] With the advancement of technology, people have increasingly more options for transportation, including cars, high-speed trains, and airplanes. These diverse modes of transportation have made travel more convenient. Electric vehicles, thanks to their speed, environmental friendliness, convenience, and affordability, have become a frequently used mode of transportation in daily life. An electric bicycle consists of a body, electric motor, controller, position sensor, battery, charger, and instrumentation system. Not only do they align with energy-saving and environmentally friendly trends, greatly facilitating short-distance travel, but they also play a vital role in the national economy by conserving and protecting energy and the environment.

[0003] However, although electric vehicles have made our lives more convenient, they still pose some safety risks. In daily use, when people drive electric vehicles through intersections, because crossing the street twice is time-consuming, people often choose to turn left with the motor vehicle. In fact, this is a very dangerous situation. During the turn, the electric vehicle is outside the motor vehicle and is very likely to be in the blind spot of other vehicles, causing the electric vehicle to collide with other vehicles, which is very detrimental to people's driving safety when using electric vehicles.

[0004] Therefore, it is very necessary to intelligently monitor electric vehicles, predict their driving trajectories in advance, and analyze the collision risks between electric vehicles and other vehicles. Therefore, a digital-based intelligent monitoring system and method for electric vehicles is needed. Summary of the Invention

[0005] The purpose of the present invention is to provide a digital-based intelligent monitoring system and method for electric vehicles, which collects basic data information, collects the location information of the electric vehicle through GPS, and calls surrounding camera equipment to collect the location information of vehicles near the electric vehicle. Based on the collected data information, the trajectory of the electric vehicle is predicted and analyzed, thereby analyzing the collision situation of the electric vehicle with other vehicles, providing intelligent reminders to users, and encrypting data throughout the entire process to solve the problems raised in the above-mentioned background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a digital-based intelligent monitoring system for electric vehicles, the electric vehicle monitoring system comprising: a data acquisition module, a database, a data analysis module and an intelligent reminder module;

[0007] The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the intelligent reminder module; the data acquisition module is used to collect basic data information and monitor the electric vehicle driving information in real time, the database is used to store the collected data information and analysis results, and perform data encryption, the data analysis module is used to analyze and process the collected real-time data of the electric vehicle, and the intelligent reminder module is used to remind the user based on the analysis results.

[0008] Furthermore, the data acquisition module includes a basic data information entry unit and a vehicle data acquisition unit. The basic information entry unit is used to enter basic information and road traffic information of electric vehicles, such as the license plate number of the electric vehicle, the name of the electric vehicle owner, the change cycle of traffic lights and the electronic map of the city. The vehicle data acquisition unit is used to collect the position information of the electric vehicle in real time through a GPS locator. By installing a GPS locator on the electric vehicle, it is convenient to predict the movement trajectory of the electric vehicle, the analysis speed is fast, and the efficiency of the system's data analysis is improved. At the same time, according to the real-time collected target electric vehicle position information, the camera equipment around the target electric vehicle, such as traffic cameras, is retrieved, and the vehicle in the image is extracted using OpenCV technology. The relative position relationship between the surrounding vehicles and the target electric vehicle is obtained through image ranging technology, thereby collecting vehicle position information near the electric vehicle, such as position information of electric bicycles, motorcycles or cars.

[0009] Furthermore, the database includes a data storage unit, a data encryption unit and a data sharing unit. The data storage unit stores the collected data and analysis results through a data warehouse. The data warehouse is a structured data environment for decision support systems and online analytical application data sources. The data warehouse studies and solves the problem of obtaining information from the database. The data warehouse is characterized by being subject-oriented, integrated, stable and time-varying. Under the general environment of information technology and data intelligence, the data warehouse provides many economical and efficient computing resources in the fields of software and hardware, Internet and enterprise intranet solutions, and databases. It can store a large amount of data for analysis and allows the use of multiple data access technologies. The data encryption unit encrypts data for the entire system through the SM3 encryption algorithm. The SM3 encryption algorithm is a cryptographic hash algorithm suitable for digital signatures and verification, message authentication code generation and verification, and random number generation. It can meet the security requirements of various cryptographic applications. It is an improved algorithm implemented based on SHA-256 and uses Merkle-Da The Mgard structure has a message packet length of 512 bits and an output digest value length of 256 bits. This algorithm generates a 256-bit hash value for bit messages with an input length less than 2 to the power of 64 through padding and iterative compression. It uses XOR, modulo, modular addition, shift, AND, OR, and NOT operations, and is composed of padding, iteration, message expansion, and compression functions. The data sharing unit uses a public blockchain to share resources after user authorization. For example, when a user's electric vehicle starts, the user is authorized to upload location information in a pseudo-anonymous manner. Simultaneously, based on the GPS location information, the user retrieves the camera equipment near the electric vehicle and collects the location information of other vehicles near the electric vehicle for upload. When the electric vehicle stops, the location information upload stops. Pseudo-anonymity can refer to a state of having a false identity, which can effectively protect the privacy of users' information. A public blockchain refers to a blockchain in which anyone can read and send transactions, obtain valid confirmation of transactions, and participate in the consensus process. The public blockchain is tamper-proof, ensuring the authenticity of the data.

[0010] Furthermore, the data analysis module includes a trajectory prediction unit and a risk prediction unit. The trajectory prediction unit performs predictive analysis on the estimation of the user's use of the electric vehicle by establishing a trajectory prediction model. The risk prediction analysis unit is used to analyze and predict the risk of collision between the electric vehicle and other vehicles, so as to facilitate the early analysis of whether the user will encounter a collision, thereby ensuring the driving safety of the user when driving the electric vehicle.

[0011] Furthermore, the intelligent reminder module includes a sound reminder unit and a visual reminder unit. The sound reminder unit is used to provide sound reminders, such as voice or alarm sound effects, when a collision risk is predicted based on the analysis results. The visual reminder unit is used to remind the user through visual reminder tools, such as vehicle lights or electric vehicle electronic display screens, so that the user can obtain reminder information in a variety of situations. For example, in a noisy environment, even if it is difficult to hear the reminder sound, the user can be reminded through visual reminder tools to ensure the user's driving safety.

[0012] A digital-based intelligent monitoring method for electric vehicles, characterized by:

[0013] S1. Collect basic data information, collect the location information of the electric vehicle through GPS, and call the surrounding camera equipment to collect the location information of vehicles near the electric vehicle, store the collected information in the database, and encrypt the data;

[0014] S2. Predict and analyze the trajectory of the electric vehicle based on the collected basic data information and the location information of the electric vehicle;

[0015] S3. Analyze the collision between the electric vehicle and other vehicles based on the predicted trajectory of the electric vehicle;

[0016] S4. Based on the analysis results, intelligent reminders are given to users through sound and visual reminder tools.

[0017] Furthermore, in step S2, based on the collected basic data information, the electric vehicle location information uploaded to the public blockchain, and the collected nearby vehicle location information, a trajectory prediction model is established to predict and analyze the trajectory of the user's electric vehicle;

[0018] The collected electric vehicle location information is placed in a coordinate system. The coordinate system can be established according to the actual situation, such as establishing a coordinate system based on longitude and latitude or establishing a suitable coordinate system based on the geographical location of the city. At time t, the location coordinates of the user's electric vehicle are (x i ,y i ), the vehicle positions form a set P = {(x1, y1), (x2, y2), ..., (x n ,y n )}, where n is the number of vehicles, and the predicted state Z of the target electric vehicle is calculated using the following formula:

[0019] Z=∑ j∈Q L[x j -x i ,y j -y i ]Z j ;

[0020] Where Q represents the coordinate set formed by the positions of vehicles near the user's electric vehicle. For example, with the user's electric vehicle as the center and the radius set to r, the set of vehicle position information within the circle is formed, (x j ,y j ) represents the position coordinate of the jth vehicle, L represents the indicator function of the predicted state, Z j Represented as the state information of the j-th vehicle at time t-1, such as speed, acceleration, etc.;

[0021] The predicted state of the electric vehicle at time t is used to predict the trajectory position distribution (x i ,y i ) t+1 , let the bivariate Gaussian distribution be parameterized with mean μ t+1 =(μ x , μ y ) t+1 , where μ x Expressed as the mean value on the horizontal axis, μ y Expressed as the mean value on the vertical axis and the standard deviation σ t+1 =(σ x , σ y ) t+1 , where σ x Expressed as the standard deviation on the horizontal axis, σ y Expressed as the standard deviation on the ordinate, the correlation coefficient is ρ t+1 , then the predicted coordinates (x i ,y i ) t+1 Perform the calculation:

[0022] (x i ,y i ) t+1 ~N(μ t+1 , σ t+1 ,ρ t+1 );

[0023] Through the trajectory prediction model, the position of the electric vehicle is predicted in real time, and the predicted position coordinates are connected to form a continuous electric vehicle prediction trajectory.

[0024] Furthermore, in step S3, the collision risk of the user while driving the electric vehicle is analyzed and processed based on the predicted trajectory of the electric vehicle;

[0025] Based on the real-time collected electric vehicle position information, the speed of the electric vehicle is obtained as v, and the acceleration is a. The braking distance S of the electric vehicle is calculated using the following formula:

[0026]

[0027] Among them, t α is the user reaction time, t β is the braking coordination time, t α +t β is the braking hysteresis time;

[0028] When a collision occurs within the braking delay time, the collision time T1 is calculated using the following formula:

[0029]

[0030] Where v′ represents the speed of the possible collision vehicle, a′ represents the acceleration of the possible collision vehicle, l represents the overall length of the possible collision vehicle, l s Represented as the distance between the front wheel of the electric vehicle and the front wheel of the vehicle that may collide; a threshold is set for the collision time when When , it means the risk of collision is not high and no reminder is given; when When it is on, it indicates that the risk of collision is high and the user is reminded;

[0031] When a collision occurs during the braking phase, the collision time is calculated using the following formula:

[0032]

[0033] Where T = t α +t β , S γ =vl s -l;

[0034] Collision time setting threshold when When , it means the risk of collision is not high and no reminder is given; when When , it indicates that the risk of collision is high and the user is reminded.

[0035] Furthermore, in step S3, a hidden Markov model is established to predict the user's driving behavior of the electric vehicle. It is assumed that the unobservable changes in the user's hidden psychological state follow a Markov process, and each hidden state corresponds to an observable vehicle state, such as the vehicle's speed and acceleration, so as to predict the user's potential risk perception. The hidden Markov model is a statistical model that is used to describe a Markov process with hidden unknown parameters.

[0036] The hidden Markov model E is established by the following formula:

[0037] E=(F,G,H,I,τ);

[0038] F = {f1, f2};

[0039]

[0040]

[0041]

[0042] τ = {τ1, τ2};

[0043] Among them, F represents the finite set of user's hidden psychological state changing over time, f1 and f2 represent the user's psychological decision results of passing and failing, G represents the finite set of vehicle observable state data, v i represents the speed of the electric vehicle, a j represents the acceleration of the electric vehicle, H represents the state transition probability matrix, h ij It is expressed as the probability that the user's psychological state at time t-1 changes to the psychological state at time t, I is expressed as the probability distribution matrix of the observed value, and I jk It is expressed as every moment, when the user's observable state is (v i , a j ), the probability that his psychological state is pass or fail, τ represents the probability that the user's psychological state is pass or fail when the green light is on under a given initial observation state;

[0044] The user's hidden psychological decision-making state is calculated using the following formula:

[0045] μ t (i)=[max 2≤t≤T μ t-1 (i)h ij ]p(ω t );

[0046]

[0047]

[0048] Among them, μ t (i) is expressed as a dimensional bit variable at time t, that is, the probability of the path to the predicted location, p(ω t ) is expressed as the trajectory ω at time t t The maximum probability, μ t-1 (i) represents the bit variable at time t-1, T represents the total time, Represented as a memory variable, recording the previous state before the current state on the path with the maximum probability, f t It is expressed as the hidden psychological decision result of the user at time t, thereby obtaining the predicted hidden psychological decision sequence F of the user * ={f1,…,f j};

[0049] The hidden Markov model is used to predict the user's decision-making psychological state. That is, when the traffic light at the intersection is on, the user chooses to go through or not. The corresponding dangerous driving behavior prediction and recognition rules are entered into the system. When dangerous driving behavior is predicted, the user is reminded.

[0050] Furthermore, in step S4, based on the analysis results, when it is predicted that the user is at high risk of collision while driving an electric vehicle, a reminder is given to the user through sound, such as voice or alarm sound effects, and at the same time, a reminder is given to the user through visual reminder tools, such as vehicle lights or electric vehicle electronic display screens, so that the user can obtain reminder information in a timely manner. Even in a noisy environment where it is difficult to hear the reminder sound, the user can be reminded through visual reminder tools to ensure the user's driving safety.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention collects basic data information, collects the position information of the electric vehicle through GPS, and calls the surrounding camera equipment to collect the position information of vehicles near the electric vehicle. After the user authorizes, the information is uploaded to the public blockchain in a pseudo-anonymous manner to realize data sharing, thereby ensuring the privacy and security of the user. According to the collected data information, the trajectory of the electric vehicle is predicted and analyzed, thereby analyzing the collision situation of the electric vehicle with other vehicles, and using the hidden Markov model to predict the user's driving behavior, so as to facilitate the prediction in advance of whether a collision will occur, thereby ensuring the driving safety of the user when using the electric vehicle; the user is intelligently reminded by sound and visual reminder tools to ensure that the user can obtain reminder information in time even in noisy or dim environments; at the same time, data is encrypted throughout the entire process to ensure the user's data security, avoid user information leakage, improve the robustness and security of the system, and improve the user's usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0054] Figure 1 This is a schematic diagram of the module composition of a digital electric vehicle intelligent monitoring system of the present invention;

[0055] Figure 2 This is a schematic diagram of the steps of a digital-based intelligent monitoring method for electric vehicles of the present invention; DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] See also Figure 1-Figure 2 , the present invention provides a technical solution: a digital-based intelligent monitoring system for electric vehicles, the electric vehicle monitoring system includes: a data acquisition module, a database, a data analysis module and an intelligent reminder module;

[0058] The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the intelligent reminder module;

[0059] The data acquisition module is used to collect basic data information and monitor the driving information of electric vehicles in real time. The data acquisition module includes a basic data information entry unit and a vehicle data acquisition unit. The basic information entry unit is used to enter the basic information and road traffic information of the electric vehicle, such as the electric vehicle license plate number, the name of the electric vehicle owner, the change cycle of the traffic light and the electronic map of the city. The vehicle data acquisition unit is used to collect the position information of the electric vehicle in real time through the GPS locator. By installing a GPS locator on the electric vehicle, it is convenient to predict the movement trajectory of the electric vehicle, the analysis speed is fast, and the efficiency of the system's data analysis is improved. At the same time, according to the real-time collected target electric vehicle position information, the camera equipment around the target electric vehicle, such as traffic cameras, is retrieved, and the vehicle in the image is extracted using OpenCV technology. The relative position relationship between the surrounding vehicles and the target electric vehicle is obtained through image ranging technology, thereby collecting vehicle position information near the electric vehicle, such as battery vehicles, motorcycles or cars.

[0060] The database is used to store collected data information and analysis results, and to encrypt data. The database includes a data storage unit, a data encryption unit and a data sharing unit. The data storage unit stores the collected data and analysis results through a data warehouse. The data warehouse is a structured data environment for decision support systems and online analytical application data sources. The data warehouse studies and solves the problem of obtaining information from the database. The characteristics of the data warehouse are subject-oriented, integrated, stable and time-varying. Under the general environment of information technology and data intelligence, the data warehouse provides many economical and efficient computing resources in the fields of software and hardware, Internet and enterprise intranet solutions, and databases. It can save a large amount of data for analysis and allows the use of multiple data access technologies. The data encryption unit encrypts data for the entire system through the SM3 encryption algorithm. The SM3 encryption algorithm is a cryptographic hash algorithm suitable for digital signatures and verification, message authentication code generation and verification, and random number generation. It can meet the security requirements of various cryptographic applications. It is an improved algorithm implemented based on SHA-256. , using the Merkle-Damgard structure, the message group length is 512 bits, and the output digest value length is 256 bits. This algorithm generates a 256-bit hash value for bit messages with an input length less than 2 to the power of 64 through padding and iterative compression. It uses exclusive OR, modulo, modular addition, shift, AND, OR, and NOT operations. It consists of padding, iterative process, message expansion and compression functions. The data sharing unit shares resources through the public blockchain after user authorization. For example, when the user's electric car starts, the user is authorized to upload location information in a pseudo-anonymous manner. At the same time, based on the GPS location information, the camera equipment near the electric car is retrieved to collect the location information of other vehicles near the electric car for uploading. When the electric car stops, the location information is stopped from being uploaded. Pseudo-anonymity can refer to a state of having a false identity, which can effectively ensure the security of the user's privacy information. A public chain refers to a blockchain in which anyone can read and send transactions, and transactions can be effectively confirmed and can also participate in the consensus process. The public blockchain has the characteristic of being tamper-proof, which ensures the authenticity of the data.

[0061] The data analysis module is used to analyze and process the collected real-time data of electric vehicles. The data analysis module includes a trajectory prediction unit and a risk prediction unit. The trajectory prediction unit predicts and analyzes the estimation of the user's use of the electric vehicle by establishing a trajectory prediction model. The risk prediction analysis unit is used to analyze and predict the risk of collision between the electric vehicle and other vehicles, which is convenient for analyzing in advance whether the user will encounter a collision situation, thereby ensuring the driving safety of the user when driving the electric vehicle.

[0062] The intelligent reminder module is used to remind the user according to the analysis results. The intelligent reminder module includes a sound reminder unit and a visual reminder unit. The sound reminder unit is used to make a sound reminder, such as voice or alarm sound effects, when a collision risk is predicted according to the analysis results. The visual reminder unit is used to remind the user through visual reminder tools, such as vehicle lights or electric vehicle electronic display screens, so that the user can obtain reminder information in various situations. For example, in a noisy environment, even if it is difficult to hear the reminder sound, the user can be reminded through the visual reminder tool to ensure the user's driving safety.

[0063] A digital-based intelligent monitoring method for electric vehicles, characterized by:

[0064] S1. Collect basic data information, collect the location information of the electric vehicle through GPS, and call the surrounding camera equipment to collect the location information of vehicles near the electric vehicle, store the collected information in the database, and encrypt the data;

[0065] S2. Predict and analyze the trajectory of the electric vehicle based on the collected basic data information and the location information of the electric vehicle;

[0066] In step S2, based on the collected basic data information, the electric vehicle location information uploaded to the public blockchain, and the collected nearby vehicle location information, a trajectory prediction model is established to predict and analyze the trajectory of the user's electric vehicle;

[0067] The collected electric vehicle location information is placed in a coordinate system. The coordinate system can be established according to the actual situation, such as establishing a coordinate system based on longitude and latitude or establishing a suitable coordinate system based on the geographical location of the city. At time t, the location coordinates of the user's electric vehicle are (x o ,y i ), the vehicle positions form a set P = {(x1, y1), (x2, y2), ..., (x n ,y n )}, where n is the number of vehicles, and the predicted state Z of electric vehicles is calculated using the following formula:

[0068] Z=∑ j∈Q L[x j -x i ,y j -y i ]Z j ;

[0069] Where Q represents the coordinate set formed by the positions of vehicles near the user's electric vehicle. For example, with the user's electric vehicle as the center and the radius set to r, the set of vehicle position information within the circle is formed, (x j ,y j) represents the position coordinate of the jth vehicle, L represents the indicator function of the predicted state, Z j Represented as the state information of the j-th vehicle at time t-1, such as speed, acceleration, etc.;

[0070] The predicted state of the electric vehicle at time t is used to predict the trajectory position distribution (x i ,y i ) t+1 , let the bivariate Gaussian distribution be parameterized with mean μ t+1 =(μ x , μ y ) t+1 , where μ x Expressed as the mean value on the horizontal axis, μ y Expressed as the mean value on the vertical axis and the standard deviation σ t+1 =(σ x , σ y ) t+1 , where σ x Expressed as the standard deviation on the horizontal axis, σ y Expressed as the standard deviation on the ordinate, the correlation coefficient is ρ t+1 , then the predicted coordinates (x i ,y i ) t+1 Perform the calculation:

[0071] (x i ,y i ) t+1 ~N(μ t+1 , σ t+1 ,ρ t+1 );

[0072] Through the trajectory prediction model, the position of the electric vehicle is predicted in real time, and the predicted position coordinates are connected to form a continuous electric vehicle prediction trajectory.

[0073] S3. Analyze the collision between the electric vehicle and other vehicles based on the predicted trajectory of the electric vehicle;

[0074] In step S3, based on the predicted trajectory of the electric vehicle, the collision risk of the user while driving the electric vehicle is analyzed and processed;

[0075] Based on the real-time collected electric vehicle position information, the speed of the electric vehicle is obtained as v, and the acceleration is a. The braking distance S of the electric vehicle is calculated using the following formula:

[0076]

[0077] Among them, t α is the user reaction time, t β is the braking coordination time, tα +t β is the braking hysteresis time;

[0078] When a collision occurs within the braking delay time, the collision time T1 is calculated using the following formula:

[0079]

[0080] Where v′ represents the speed of the possible collision vehicle, a′ represents the acceleration of the possible collision vehicle, l represents the overall length of the possible collision vehicle, l s Represented as the distance between the front wheel of the electric vehicle and the front wheel of the vehicle that may collide; a threshold is set for the collision time when When , it means the risk of collision is not high and no reminder is given; when When it is on, it indicates that the risk of collision is high and the user is reminded;

[0081] When a collision occurs during the braking phase, the collision time is calculated using the following formula:

[0082]

[0083] Where T = t α +t β , S γ =vl s -l;

[0084] Collision time setting threshold when When , it means the risk of collision is not high and no reminder is given; when When , it indicates that the risk of collision is high and the user is reminded.

[0085] By establishing a hidden Markov model, the user's driving behavior of electric vehicles is predicted. It assumes that the changes in the user's hidden psychological state follow a Markov process, and each hidden state corresponds to an observable vehicle state, such as vehicle speed and acceleration. This allows the user's potential risk perception to be predicted. The hidden Markov model is a statistical model that describes a Markov process with hidden unknown parameters.

[0086] The hidden Markov model E is established by the following formula:

[0087] E=(F,G,H,I,τ);

[0088] F = {f1, f2};

[0089]

[0090]

[0091]

[0092] τ = {τ1, τ2};

[0093] Among them, F represents the finite set of user's hidden psychological state changing over time, f1 and f2 represent the user's psychological decision results of passing and failing, G represents the finite set of vehicle observable state data, v i represents the speed of the electric vehicle, a j represents the acceleration of the electric vehicle, H represents the state transition probability matrix, h ij It is expressed as the probability that the user's psychological state at time t-1 changes to the psychological state at time t, I is expressed as the probability distribution matrix of the observed value, and I jk It is expressed as every moment, when the user's observable state is (v i , a j ), the probability that his psychological state is pass or fail, τ represents the probability that the user's psychological state is pass or fail when the green light is on under a given initial observation state;

[0094] The user's hidden psychological decision-making state is calculated using the following formula:

[0095] μ t (i)=[max 2≤t≤T μ t-1 (i)h ij ]p(ω t );

[0096]

[0097]

[0098] Among them, μ t (i) is expressed as a dimensional bit variable at time t, that is, the probability of the path to the predicted location, p(ω t ) is expressed as the trajectory ω at time t t The maximum probability, μ t-1 (i) represents the bit variable at time t-1, T represents the total time, Represented as a memory variable, recording the previous state before the current state on the path with the maximum probability, f t It is expressed as the hidden psychological decision result of the user at time t, thereby obtaining the predicted hidden psychological decision sequence F of the user * ={f1,…,f j};

[0099] The hidden Markov model is used to predict the user's decision-making psychological state. That is, when the traffic light at the intersection is on, the user chooses to go through or not. The corresponding dangerous driving behavior prediction and recognition rules are entered into the system. When dangerous driving behavior is predicted, the user is reminded.

[0100] S4. Based on the analysis results, intelligent reminders are given to users through sound and visual reminder tools.

[0101] In step S4, according to the analysis results, when it is predicted that the user is at high risk of collision while driving an electric vehicle, a reminder is given to the user through sound, such as voice or alarm sound effects, and at the same time, a reminder is given to the user through visual reminder tools, such as vehicle lights or electric vehicle electronic display screens, so that the user can obtain reminder information in a timely manner. Even in a noisy environment where it is difficult to hear the reminder sound, the user can be reminded through visual reminder tools to ensure the user's driving safety.

[0102] Example 1:

[0103] At a certain moment, the position coordinates of the user's electric car are (5, 10), and the vehicle positions form a set P = {(4, 12), (5, 10), (6, 18), (9, 10)}, Z = ∑ j∈Q L[x j -x i ,y j -y i ]Z j ; If the mean μ t+1 =(μ x , μ y ) t+1 =(4,7), standard deviation σ t+1 =(σ x , σ y ) t+1 =(1.2,2.3), the correlation coefficient is ρ t+1 =0.8, then (x i ,y i ) t+1 ~N(μ t+1 , σ t+1 ,ρ t+1 ), obtain the predicted coordinates, and connect the predicted position coordinates to form a continuous electric vehicle prediction trajectory.

[0104] When the user reaction time is 0.5s and the brake coordination time is 0.7s, the brake hysteresis time is 1.2s, the speed is 4m / s, and the acceleration is 2m / s. 2 , the braking distance is:

[0105]

[0106] The speed of the possible collision vehicle is 6m / s and the acceleration is 3.5m / s 2 The overall vehicle length is 4m, and the distance between the front wheel of the electric vehicle and the front wheel of the possible collision vehicle is 8m. When a collision occurs within the braking hysteresis time, the collision time T1 = [(v′-v)± If a threshold is set for the collision time at this time Indicates that the risk of collision is low. If a threshold is set for the collision time at this time When the collision occurs during the braking phase, the collision time If a threshold is set for the collision time at this time When the collision risk is small, no reminder will be given; if a threshold is set for the collision time at this time When , it indicates that the risk of collision is high and the user is reminded.

[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0108] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A digital-based intelligent monitoring method for electric vehicles, characterized by: S1. Collect basic data information, collect the location information of the electric vehicle through GPS, and call the surrounding camera equipment to collect the location information of vehicles near the electric vehicle, store the collected information in the database, and encrypt the data; S2. Predict and analyze the trajectory of the electric vehicle based on the collected basic data information and the location information of the electric vehicle; S3. Analyze the collision between the electric vehicle and other vehicles based on the predicted trajectory of the electric vehicle; S4. Based on the analysis results, intelligent reminders are given to users through sound and visual reminder tools; In step S3, a hidden Markov model is established to predict the user's driving behavior of the electric vehicle; the hidden Markov model is established by the following formula : ； ； ； ； ； ； Among them, F represents the finite set of users’ hidden mental states that change over time. 、 represents the user's psychological decision of passing or failing, G represents a finite set of observable state data of the vehicle, Indicates the speed of the electric vehicle, represents the acceleration of the electric vehicle, H represents the state transition probability matrix, It is expressed as the probability that the user's psychological state at time t-1 changes to the psychological state at time t, and I is expressed as the probability distribution matrix of the observed value. Represented as every moment, when the user's observable state is When , his mental state is the probability of passing or failing, It is expressed as the probability that the user's psychological state is pass or fail when the green light is on under a given initial observation state; The user's hidden psychological decision-making state is calculated using the following formula: ； ； ； in, Expressed as the dimension bit variable at time t, Expressed as the trajectory at time t The maximum probability, It is represented as the dimension bit variable at time t-1, T is the total time, Represented as a memory variable, recording the previous state before the current state on the path with maximum probability, It is expressed as the hidden psychological decision result of the user at time t, thereby obtaining the predicted hidden psychological decision sequence of the user ; The hidden Markov model is used to predict the user's decision-making psychological state, and the corresponding dangerous driving behavior prediction and recognition rules are entered into the system. When dangerous driving behavior is predicted, the user is reminded.

2. The method for intelligently monitoring electric vehicles based on digitalization according to claim 1, characterized in that: In step S2, based on the collected basic data information, the electric vehicle location information uploaded to the public blockchain, and the collected nearby vehicle location information, a trajectory prediction model is established to predict and analyze the trajectory of the user's electric vehicle; The collected electric vehicle location information is placed in the coordinate system. At time t, the location coordinates of the user's electric vehicle are , the vehicle positions form a set , where n is the number of vehicles. The predicted state Z of the target electric vehicle is calculated using the following formula: ； Among them, Q represents the coordinate set formed by the positions of vehicles near the user's electric vehicle, It is represented as the position coordinate of the jth vehicle, L is represented as the indicator function of the predicted state, It is represented by the jth car in Status information at all times; The predicted state of the electric vehicle at time t is used to predict the next moment The trajectory position distribution , let the bivariate Gaussian distribution be parameterized as mean ,in, Expressed as the mean value on the horizontal axis, Expressed as the vertical axis mean, standard deviation ,in, Expressed as the standard deviation on the horizontal axis, Expressed as the standard deviation on the ordinate, the correlation coefficient is , then Predicted coordinates at time Perform the calculation: ； Through the trajectory prediction model, the position of the target electric vehicle is predicted in real time, and the predicted position coordinates are connected to form a continuous target electric vehicle prediction trajectory.

3. The method for intelligently monitoring electric vehicles based on digitalization according to claim 2, characterized in that: In step S3, based on the predicted trajectory of the target electric vehicle, the collision risk of the user while driving the electric vehicle is analyzed and processed; According to the real-time collected electric vehicle position information, the speed of the electric vehicle is obtained as v, and the acceleration is a. The braking distance S of the electric vehicle is calculated using the following formula: ； in, For user response time, is the braking coordination time, is the braking hysteresis time; When a collision occurs within the braking delay time, the collision time is calculated using the following formula: Perform the calculation: ； in, is the speed of the vehicle that may collide, It is represented by the acceleration of the possible collision vehicle, l is represented by the overall length of the possible collision vehicle, Represented as the distance between the front wheel of the electric vehicle and the front wheel of the vehicle that may collide; a threshold is set for the collision time ,when When , it means the risk of collision is not high and no reminder is given; when When it is on, it indicates that the risk of collision is high and the user is reminded; When a collision occurs during the braking phase, the collision time is calculated using the following formula: ； in, , ; Collision time setting threshold ,when When , it means the risk of collision is not high and no reminder is given; when When , it indicates that the risk of collision is high and the user is reminded.

4. The method for intelligently monitoring electric vehicles based on digitalization according to claim 3, characterized in that: In step S4, based on the analysis results, when it is predicted that the user is at high risk of collision while driving the electric vehicle and dangerous driving behavior is predicted, a reminder is issued to the user through sound and a visual reminder tool is used to remind the user at the same time.

5. A digital electric vehicle intelligent monitoring system, applied to a digital electric vehicle intelligent monitoring method according to any one of claims 1 to 4, characterized in that: The electric vehicle monitoring system includes: a data acquisition module, a database, a data analysis module and an intelligent reminder module; The data acquisition module is connected to the database, the database is connected to the data analysis module, and the data analysis module is connected to the intelligent reminder module; the data acquisition module is used to collect basic data information and monitor the electric vehicle driving information in real time, the database is used to store the collected data information and analysis results, and perform data encryption, the data analysis module is used to analyze and process the collected real-time data of the electric vehicle, and the intelligent reminder module is used to remind the user based on the analysis results.

6. The digital electric vehicle intelligent monitoring system according to claim 5, characterized in that: The data acquisition module includes a basic data information entry unit and a vehicle data acquisition unit. The basic data information entry unit is used to enter the basic information and road traffic information of the electric vehicle. The vehicle data acquisition unit is used to collect the location information of the target electric vehicle in real time through the GPS locator. At the same time, according to the collected target electric vehicle location information, the camera equipment around the target electric vehicle is retrieved, the vehicle in the image is extracted using OpenCV technology, and the relative position relationship between the surrounding vehicles and the target electric vehicle is obtained through image ranging technology, thereby collecting the vehicle location information near the electric vehicle.

7. The digital electric vehicle intelligent monitoring system according to claim 6, characterized in that: The database includes a data storage unit, a data encryption unit and a data sharing unit. The data storage unit stores the collected data and analysis results through a data warehouse. The data encryption unit encrypts data for the entire system through an SM3 encryption algorithm. The data sharing unit shares resources through a public blockchain after user authorization.

8. The digital electric vehicle intelligent monitoring system according to claim 7, characterized in that: The data analysis module includes a trajectory prediction unit and a risk prediction analysis unit. The trajectory prediction unit predicts and analyzes the user's estimate of the use of the electric vehicle by establishing a trajectory prediction model. The risk prediction analysis unit is used to analyze and predict the risk of collision between the electric vehicle and other vehicles.

9. The digital electric vehicle intelligent monitoring system according to claim 8, characterized in that: The intelligent reminder module includes a sound reminder unit and a visual reminder unit. The sound reminder unit is used to make a sound reminder when a collision risk is predicted based on the analysis results, and the visual reminder unit is used to remind the user through a visual reminder tool.

Images