Internet of Things product intelligent management system and method based on Beidou positioning

Abstract

The invention discloses an Internet of Things product intelligent management system and method based on Beidou positioning, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring Beidou positioning data, acquiring vehicle information and cargo information, and forming a Beidou positioning associated data set; analyzing whether the Beidou positioning data has cargo transportation route abnormity or not, and judging whether the cargo transportation state and the vehicle driving state are abnormal or not; when the cargo transportation route or the cargo transportation state is abnormal in the Beidou positioning data, calculating the matching degree of the loading condition of the vehicle and the cargo weight based on the vehicle information and the cargo information; predicting the current position of the cargo by using a linear regression algorithm; if the superposed vehicle driving state is abnormal, dynamically adjusting the linear regression model, and further adjusting cargo position prediction in combination with a vehicle dynamics model; and when only the running state of the vehicle is abnormal, predicting the current position of the cargo by combining the kinematics equation of the vehicle and the cargo dynamics model.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent management system and method for Internet of Things products based on Beidou positioning. Background Art

[0002] With the widespread application of Internet of Things technology in logistics and other fields, accurate monitoring and management of cargo transportation processes have become increasingly important. The Beidou positioning system plays a key role in this with its advantages of high precision, all-weather and all-time. At present, a large number of logistics transportation vehicles and goods are equipped with Beidou positioning terminals, which can obtain a variety of data information including location, speed, etc., and transmit these data to the management system through the network for analysis and processing, so as to optimize transportation routes, improve transportation efficiency and ensure cargo safety.

[0003] The methods for judging the cargo transportation status and vehicle driving status are relatively simple and crude. When judging the abnormal vehicle driving status, they often rely on a single parameter. When judging the cargo transportation status, the characteristics of the cargo itself and its interaction with the vehicle are not fully considered. When the Beidou positioning data is not accurate enough, the existing logistics management system lacks an effective response strategy. When faced with multiple abnormal situations occurring at the same time, such as the abnormal vehicle driving status and the abnormal cargo transportation route or the abnormal cargo transportation status, the existing technology does not comprehensively consider the relationship between these factors. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management system and method for Internet of Things products based on Beidou positioning to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions: A method for intelligent management of Internet of Things products based on Beidou positioning, the method comprising the following steps: S100, collecting Beidou positioning data through a Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the driving speed of the vehicle, the moving direction of the vehicle, the ambient temperature and the positioning accuracy information, obtaining the vehicle information and the cargo information, and associating them with the corresponding Beidou positioning data to form a Beidou positioning associated data set; transmitting the Beidou positioning associated data set through a Beidou satellite communication link and a ground communication network, and encrypting and encapsulating the data before transmission; S200, based on the Beidou positioning associated data set, perform a decryption operation and verify the data using a verification algorithm; analyze the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculate the estimated arrival time of the cargo, and compare it with the standard route of the logistics planning to determine whether it deviates from the preset transportation route; determine whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; S300. When the Beidou positioning data shows an abnormality in the cargo transportation route or the cargo transportation status, the positioning accuracy information is extracted from the Beidou positioning associated data set, and the data features of the time period and location point where the positioning accuracy is insufficient are extracted. The matching degree between the vehicle load and the cargo weight is calculated based on the vehicle information and the cargo information. When the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the historical driving data of the vehicle and the cargo information to predict the current location of the cargo. S400. When the vehicle driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, the vehicle driving speed and the vehicle moving direction in the linear regression model are dynamically adjusted, and the cargo position prediction is further adjusted in combination with the vehicle dynamics model; when only the vehicle driving state is abnormal, the current position of the cargo is predicted based on the type and degree of the abnormal vehicle driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

[0006] According to step S100, the Beidou positioning terminal is initialized, and the real-time three-dimensional coordinate position of the cargo is calculated by presetting a coordinate system in the carriage, taking a corner of the bottom of the carriage as the origin, the vehicle driving direction as the x-axis, the y-axis perpendicular to the driving direction, and the z-axis perpendicular to the bottom of the carriage upwards, in combination with the relative position relationship between the cargo and the vehicle; the distance difference is calculated by comparing the position coordinates of the vehicle at two adjacent positioning moments, and the driving speed of the vehicle is obtained by dividing it by the time interval between the two positionings; the moving direction of the vehicle is determined by using the azimuth information provided by the Beidou positioning system; the ambient temperature is collected by the temperature sensor inside the vehicle; and the positioning accuracy information is obtained by the Beidou positioning terminal; The vehicle information includes: vehicle model, vehicle identification code, vehicle size, vehicle load capacity, vehicle component status and vehicle energy status; the cargo information includes: cargo name, type, number, weight, volume and transportation condition requirements; A timestamp is added to each set of Beidou positioning data collected, and the corresponding time is recorded when the vehicle information and cargo information are entered or updated; the association between data is established through the timestamp to ensure that the positioning data, vehicle information and cargo information collected at the same time correspond to each other; the data associated by the timestamp is organized to form a Beidou positioning associated data set.

[0007] The AES algorithm is used to encrypt the Beidou positioning associated data set. The original plaintext data is converted into ciphertext data by processing the data according to the 128-bit group size. Based on the encrypted Beidou positioning associated data set, the header information is filled in, the relevant identifier and length are filled in the corresponding field, the encrypted Beidou positioning associated data set is placed in the data segment position, the checksum is calculated and filled in the corresponding field, the data encapsulation process is completed, and a data packet is formed.

[0008] According to step S200, the encrypted Beidou positioning associated data set is decrypted using the acquired symmetric key to restore the original plaintext data, extract the checksum, recalculate the checksum, compare the recalculated checksum with the extracted checksum, and perform data verification; For the decrypted Beidou positioning associated data set, the real-time three-dimensional coordinate position of the goods, the driving speed of the vehicle and the moving direction of the vehicle are extracted, and the transportation trajectory of the goods is constructed in chronological order; the destination coordinate information of the goods is obtained from the logistics planning information, and the remaining distance is calculated in combination with the current location and transportation status of the goods; the driving speed of the vehicle in the remaining distance is predicted based on the statistical analysis of the current driving speed of the vehicle and the historical speed data. If there is an acceleration or deceleration trend, the speed change trend is predicted by linear regression; the estimated arrival time of the goods is calculated using the relationship between the distance and speed, and the relationship between the distance and speed is estimated arrival time = remaining distance / expected speed; the standard route of this transportation task is obtained from the logistics planning system, and the standard route is a path composed of several waypoints; the constructed cargo transportation trajectory is compared with the standard route, and the distance between the actual location of the goods and the nearest point on the standard route is calculated within the time interval set by the user. If the distance exceeds the preset threshold, it is considered to deviate from the preset transportation route.

[0009] According to step S200, for the vehicle information, it is determined whether the vehicle component status and the vehicle energy status are abnormal; for the cargo information, it is determined whether the cargo weight, volume and transportation condition requirements are abnormal; The method for judging whether the status of vehicle components is abnormal is as follows: for tire components, pressure check, wear assessment and temperature monitoring are performed; for brake components, brake pad thickness detection and brake fluid level inspection are performed; for engine components, fault code reading, temperature detection and oil pressure detection are performed; for suspension components, vibration monitoring, noise monitoring and vehicle posture monitoring are performed; for steering components, steering flexibility test and steering component inspection are performed; the method for judging whether the vehicle energy status is abnormal is as follows: for fuel vehicles, fuel quantity monitoring and fuel consumption rate analysis are performed; for electric vehicles, battery power inspection and battery health status assessment are performed; For pressure check: Get tire pressure data from vehicle component status information. If the tire pressure is lower than this range, such as lower than 2.0 bar, there is an abnormal situation of insufficient tire pressure. For wear assessment: Check the tire wear mark or obtain wear data through the tire wear sensor. When the tire tread depth is close to or lower than the legal minimum tread depth (such as 1.6mm), it means that the tire is severely worn, which will affect the vehicle's grip and driving stability, and it is judged to be an abnormal tire component. For temperature monitoring: Use the temperature sensor installed on the tire to monitor the tire temperature.

[0010] For brake pad thickness detection: obtain brake pad thickness data. When the brake pad thickness is less than a certain safety threshold (generally the remaining thickness is less than 2-3mm), the braking performance will be seriously affected, and it is determined that there is an abnormality in the brake system. For brake fluid level inspection: check whether the brake fluid level is within the normal range. If the brake fluid level is too low, air will enter the brake line, thereby affecting the braking effect and causing a potential risk of brake failure, which is an abnormal situation.

[0011] For fault code reading: read the engine fault code through the vehicle's on-board diagnostic system (OBD). If a fault code appears, it indicates that there may be a problem with the engine, such as a spark plug failure, sensor failure, or abnormal fuel injection system. For temperature and oil pressure monitoring: check the engine temperature and oil pressure. The normal operating temperature of the engine is generally between 90-110℃, and the oil pressure also has a corresponding normal range. If the engine temperature is too high (over 110℃) or the oil pressure is too low, there is a fault in the cooling system or lubrication system, resulting in abnormal engine components.

[0012] For vibration and noise monitoring: Use the acceleration sensor and sound sensor (if any) on the vehicle to monitor the vibration of the vehicle during driving and the abnormal noise emitted by the suspension system. If the vibration frequency is too high or there is an abnormal "creaking" or "banging" sound, it may be that the suspension spring, shock absorber or ball head and other components are damaged, and it is judged that the suspension system is abnormal. For vehicle posture observation: Combine the vehicle tilt angle information in the Beidou positioning data. If the vehicle tilts excessively during driving (such as the body tilt angle is too large when turning), the suspension system cannot support the body normally, which is also a suspension system abnormality.

[0013] For steering flexibility test: judge whether the steering system is flexible according to the steering angle change and actual driving trajectory during vehicle driving. If the steering is heavy or the steering angle does not match the response of the vehicle's driving direction, it may be a steering system failure or steering mechanism wear, resulting in steering system abnormality. For steering component inspection: check whether the steering rod, ball head and steering gear and other components are loose or worn. If these components are found to have obvious gaps or damage, it is also judged that the steering system is abnormal.

[0014] For fuel vehicles, for fuel quantity monitoring: obtain the remaining fuel in the tank from the vehicle's energy status information. Combined with the vehicle's fuel consumption model and the distance from the current location to the nearest gas station, calculate whether the remaining fuel can support the vehicle to reach the gas station. If the remaining fuel is too low and cannot meet the needs of normal driving to the gas station, it is determined that the energy status is abnormal. For fuel consumption rate analysis: compare the vehicle's actual fuel consumption rate with the normal consumption rate. If the fuel consumption rate is too high, it may be caused by vehicle engine failure, insufficient tire pressure, or excessive vehicle load, which is also considered an abnormal energy status.

[0015] For electric vehicles, for battery power check: check the remaining battery power. Determine whether the battery power is sufficient based on the vehicle's estimated range and remaining driving distance. If the battery power is too low and cannot meet the vehicle's needs to reach the destination or charging station, it is determined to be an abnormal energy state. For battery health status assessment: obtain the battery health status through the battery management system, such as battery internal resistance, charge and discharge efficiency and other indicators. If the battery internal resistance increases and the charge and discharge efficiency decreases, it means that the battery performance has declined, which may cause insufficient power or shortened range during vehicle driving, which is an abnormal energy state.

[0016] The method for judging whether the weight and volume of the cargo are abnormal is as follows: obtain the weight of the cargo from the cargo information, and compare it with the vehicle's load capacity. If the cargo weight exceeds the vehicle's load capacity, it is an abnormal cargo weight situation; compare the volume of the cargo with the effective loading space of the vehicle. If the cargo volume exceeds the space limited by the length, width and height of the vehicle compartment, it is judged that the cargo volume is abnormal; the method for judging whether the cargo transportation conditions are abnormal is as follows: judge based on temperature, humidity, ventilation and shockproof requirements.

[0017] According to step S300, the Beidou positioning system provides a horizontal dilution of precision HDOP and a vertical dilution of precision VDOP, which are used to characterize the positioning accuracy information. The smaller the values ​​of HDOP and VDOP are, the higher the positioning accuracy is. A threshold K is set to determine whether the positioning accuracy is insufficient. Assume that the time series data of the Beidou positioning related data set is ,in, arrive Indicates the HDOP value from the first moment to the nth moment. , VDOP value is , when extracting the time period with insufficient positioning accuracy, the following logical judgment is made: for any continuous time interval , when satisfied When is the time period when the positioning accuracy is insufficient, among which, and ; Assume each moment The corresponding three-dimensional coordinate position of the vehicle is , combined with the HDOP and VDOP values, if at a certain moment satisfy , then the position point corresponding to this moment The position points marked as insufficient positioning accuracy; For the position points with insufficient positioning accuracy, further extract relevant data features: Assume that the vehicle is at time The speed is , calculate the average speed at the position where the positioning accuracy is insufficient : ; Where I is the time index set corresponding to the position points with insufficient positioning accuracy, and |I| represents the number of elements in the set I; Calculate the standard deviation of speed : ; Describe the central tendency and dispersion of speed through the mean speed and standard deviation; Assume that the vehicle is at time The moving direction angle is , with the north direction as 0°, rotate clockwise and calculate the average direction angle and the standard deviation of the direction angles , reflects the change of the vehicle's driving direction at the point where the positioning accuracy is insufficient; Let the vehicle load capacity be C, which is obtained from the vehicle information and represents the maximum cargo weight that the vehicle can safely carry. Let the actual cargo weight be W, whose unit is consistent with the vehicle load capacity, and the actual cargo weight value is obtained from the cargo information, and the matching degree M between the vehicle load and the cargo weight is calculated: When M is equal to 100%, it means the vehicle is fully loaded. When M exceeds 100%, it means the cargo is overweight and the vehicle is in an overloaded state.

[0018] When the positioning accuracy is found to be insufficient and the vehicle driving status is confirmed to be normal, the historical driving data of the vehicle is selected from the Beidou positioning related data set and arranged in chronological order; a linear regression model is constructed with the real-time three-dimensional coordinate position of the cargo as the target variable, and the vehicle's driving speed, vehicle's moving direction, cargo weight, cargo volume and time as independent variables; the linear relationship coefficient between the independent variable and the target variable is learned through historical data; The linear regression model is trained using the organized historical driving data and cargo information samples. During the training process, the model attempts to find the optimal linear relationship coefficient so that the cargo location can be predicted based on the input independent variables. Through historical data training, the model continuously adjusts the coefficient to minimize the error between the predicted location and the actual historical location. When it is necessary to predict the current location of the cargo, the vehicle's driving speed, vehicle movement direction, cargo weight and cargo volume are obtained at the current moment, and the number of time steps from the start of transportation to the current moment is calculated for data input. Based on the learned linear relationship, the model calculates and outputs the current predicted location of the cargo, expressed as a three-dimensional coordinate.

[0019] According to step S400, when an abnormal driving state of the vehicle occurs, the specific type of the abnormality is determined, and the abnormality is analyzed in combination with the information of the abnormal cargo transportation route or the abnormal cargo transportation state; according to the abnormality type, the influence on the driving speed of the vehicle and the moving direction of the vehicle in the linear regression model is clarified; in the case of sudden braking of the vehicle, the speed parameter in the linear regression model is adjusted according to the severity of the braking, wherein the severity of the braking is determined by the vehicle deceleration information; the speed adjustment range is estimated according to the performance parameters of the vehicle's brake components and the inertia characteristics of the cargo in the vehicle compartment; for sudden acceleration, the speed parameter value in the linear regression model is increased according to the acceleration capacity of the vehicle and the inertia of the cargo; When the vehicle makes a sharp turn, the moving direction parameters in the linear regression model are changed; if the vehicle's driving direction deviates from the planned route, the trend of the deviation direction and angle is analyzed, and the moving direction parameters in the linear regression model are gradually adjusted so that the cargo location prediction can reflect the direction change; The vehicle dynamics model describes the motion state of the vehicle under the action of various forces. The vehicle dynamics model is used to calculate the impact of sudden braking and sharp turns on the cargo position. The cargo position change information calculated by the vehicle dynamics model is combined with the linear regression model after speed and direction adjustment to obtain a new cargo position prediction result.

[0020] According to step S400, when only the driving state of the vehicle is abnormal, when the vehicle brakes suddenly, the displacement of the vehicle during the braking process is calculated based on the speed-displacement relationship in the vehicle kinematic equation, taking into account the initial speed of the vehicle, the braking deceleration and the braking duration; for the cargo, the additional displacement of the cargo relative to the carriage is calculated based on its initial position in the carriage, the friction coefficient between the carriage and the cargo, and the weight of the cargo; the current position of the cargo is predicted based on the displacement of the vehicle and the cargo; When the vehicle accelerates suddenly, the vehicle displacement is calculated according to the vehicle kinematic equation, the vehicle acceleration and acceleration time. The relative displacement of the cargo in the car is determined in combination with the cargo weight, the friction coefficient with the car body and the acceleration, thereby obtaining a prediction of the current position of the cargo. When the vehicle makes a sharp turn, the trajectory of the vehicle during the turn is calculated according to the circular motion principle in the vehicle kinematic equation, taking into account the vehicle speed, turning radius and weight. For the cargo, the lateral displacement of the cargo is estimated based on the cargo weight, its position in the car body and the constraints between the car body and the cargo, thereby predicting the position of the cargo during the turn. The prediction results are optimized in combination with the cargo dynamics model.

[0021] An intelligent management system for Internet of Things products based on Beidou positioning, including: Data collection and transmission module: including: data collection unit, data association unit and data encryption and transmission unit; wherein, the data collection unit collects Beidou positioning data through the Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the vehicle's driving speed, the vehicle's moving direction, the ambient temperature and the positioning accuracy information, and obtains the vehicle information and cargo information; the data association unit associates the vehicle information and cargo information with the corresponding Beidou positioning data to form a Beidou positioning associated data set; the data encryption and transmission unit transmits the Beidou positioning associated data set through the Beidou satellite communication link and the ground communication network, and encrypts and encapsulates the data before transmission; Data processing and analysis module: including: decryption and verification unit, transportation route analysis unit and transportation status abnormality judgment unit; wherein the decryption and verification unit performs decryption operation based on the Beidou positioning associated data set and verifies the data using a verification algorithm; the transportation route analysis unit analyzes the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculates the estimated arrival time of the cargo, and determines whether it deviates from the preset transportation route by comparing it with the standard route of the logistics planning; the transportation status abnormality judgment unit determines whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; Abnormal processing and prediction module: including: data extraction and load calculation unit and linear regression prediction unit; wherein, when the Beidou positioning data has abnormal cargo transportation route or abnormal cargo transportation status, the data extraction and load calculation unit extracts the positioning accuracy information from the Beidou positioning associated data set, extracts the data features of the time period and location point where the positioning accuracy is insufficient, and calculates the matching degree between the vehicle load and the cargo weight based on the vehicle information and cargo information; the linear regression prediction unit uses a linear regression algorithm, when the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the vehicle's historical driving data and cargo information to predict the current location of the cargo; Cargo location prediction module under abnormal conditions: including: complex abnormality adjustment prediction unit and single abnormality prediction unit; among them, the complex abnormality adjustment prediction unit dynamically adjusts the vehicle's driving speed and the vehicle's moving direction in the linear regression model when the vehicle's driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, and further adjusts the cargo location prediction in combination with the vehicle dynamics model; the single abnormality prediction unit predicts the current location of the cargo according to the type and degree of the abnormality of the vehicle's driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

[0022] Compared with the prior art, the present invention has the following beneficial effects: 1. When judging the cargo transportation status and vehicle driving status, the present invention more accurately judges whether the vehicle is actually in an abnormal driving state by comparing the reasonable speed range under different road conditions, combining the historical maintenance records and fault information of the vehicle, and considering the impact of the vehicle load on the driving performance; and obtains detailed data through a variety of sensors installed on the vehicle and cargo, and combines it with the characteristic parameters of the cargo to timely and accurately judge whether the cargo transportation status is abnormal.

[0023] 2. When the positioning accuracy is insufficient, the present invention extracts the positioning accuracy information from the Beidou positioning associated data set, analyzes the data characteristics of the time period and location points with insufficient positioning accuracy; combines the vehicle information and cargo information to calculate the degree of matching between the vehicle load and the cargo weight, and uses this information to establish a model through a linear regression algorithm to predict the current location of the cargo when the vehicle is in normal driving condition.

[0024] 3. When faced with complex abnormal situations, such as abnormal vehicle driving status and abnormal cargo transportation route or abnormal cargo transportation status, the present invention can comprehensively consider the relationship between these factors; by dynamically adjusting the vehicle's driving speed and moving direction in the linear regression model, and further adjusting the cargo location prediction in combination with the vehicle dynamics model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1It is a schematic diagram of the steps of an intelligent management method for Internet of Things products based on Beidou positioning of the present invention; Figure 2 It is a system structure diagram of an Internet of Things product intelligent management system based on Beidou positioning in the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution. According to one embodiment of the present invention, Figure 1 A method for intelligent management of Internet of Things products based on Beidou positioning is shown in a schematic diagram of steps. A method for intelligent management of Internet of Things products based on Beidou positioning comprises the following steps: S100, collecting Beidou positioning data through a Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the driving speed of the vehicle, the moving direction of the vehicle, the ambient temperature and the positioning accuracy information, obtaining the vehicle information and the cargo information, and associating them with the corresponding Beidou positioning data to form a Beidou positioning associated data set; transmitting the Beidou positioning associated data set through a Beidou satellite communication link and a ground communication network, and encrypting and encapsulating the data before transmission; S200, based on the Beidou positioning associated data set, perform a decryption operation and verify the data using a verification algorithm; analyze the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculate the estimated arrival time of the cargo, and compare it with the standard route of the logistics planning to determine whether it deviates from the preset transportation route; determine whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; S300. When the Beidou positioning data shows an abnormality in the cargo transportation route or the cargo transportation status, the positioning accuracy information is extracted from the Beidou positioning associated data set, and the data features of the time period and location point where the positioning accuracy is insufficient are extracted. The matching degree between the vehicle load and the cargo weight is calculated based on the vehicle information and the cargo information. When the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the historical driving data of the vehicle and the cargo information to predict the current location of the cargo. S400. When the vehicle driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, the vehicle driving speed and the vehicle moving direction in the linear regression model are dynamically adjusted, and the cargo position prediction is further adjusted in combination with the vehicle dynamics model; when only the vehicle driving state is abnormal, the current position of the cargo is predicted based on the type and degree of the abnormal vehicle driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

[0028] According to step S100, the Beidou positioning terminal is initialized, and the real-time three-dimensional coordinate position of the cargo is calculated by presetting a coordinate system in the carriage, taking a corner of the bottom of the carriage as the origin, the vehicle driving direction as the x-axis, the y-axis perpendicular to the driving direction, and the z-axis perpendicular to the bottom of the carriage upwards, in combination with the relative position relationship between the cargo and the vehicle; the distance difference is calculated by comparing the position coordinates of the vehicle at two adjacent positioning moments, and the driving speed of the vehicle is obtained by dividing it by the time interval between the two positionings; the moving direction of the vehicle is determined by using the azimuth information provided by the Beidou positioning system; the ambient temperature is collected by the temperature sensor inside the vehicle; and the positioning accuracy information is obtained by the Beidou positioning terminal; The vehicle information includes: vehicle model, vehicle identification code, vehicle size, vehicle load capacity, vehicle component status and vehicle energy status; the cargo information includes: cargo name, type, number, weight, volume and transportation condition requirements; A timestamp is added to each set of Beidou positioning data collected, and the corresponding time is recorded when the vehicle information and cargo information are entered or updated; the association between data is established through the timestamp to ensure that the positioning data, vehicle information and cargo information collected at the same time correspond to each other; the data associated by the timestamp is organized to form a Beidou positioning associated data set.

[0029] The AES algorithm is used to encrypt the Beidou positioning associated data set. The original plaintext data is converted into ciphertext data by processing the data according to the 128-bit group size. Based on the encrypted Beidou positioning associated data set, the header information is filled in, the relevant identifier and length are filled in the corresponding field, the encrypted Beidou positioning associated data set is placed in the data segment position, the checksum is calculated and filled in the corresponding field, the data encapsulation process is completed, and a data packet is formed.

[0030] According to step S200, the encrypted Beidou positioning associated data set is decrypted using the acquired symmetric key to restore the original plaintext data, extract the checksum, recalculate the checksum, compare the recalculated checksum with the extracted checksum, and perform data verification; For the decrypted Beidou positioning associated data set, the real-time three-dimensional coordinate position of the goods, the driving speed of the vehicle and the moving direction of the vehicle are extracted, and the transportation trajectory of the goods is constructed in chronological order; the destination coordinate information of the goods is obtained from the logistics planning information, and the remaining distance is calculated in combination with the current location and transportation status of the goods; the driving speed of the vehicle in the remaining distance is predicted based on the statistical analysis of the current driving speed of the vehicle and the historical speed data. If there is an acceleration or deceleration trend, the speed change trend is predicted by linear regression; the estimated arrival time of the goods is calculated using the relationship between the distance and speed, and the relationship between the distance and speed is estimated arrival time = remaining distance / expected speed; the standard route of this transportation task is obtained from the logistics planning system, and the standard route is a path composed of several waypoints; the constructed cargo transportation trajectory is compared with the standard route, and the distance between the actual location of the goods and the nearest point on the standard route is calculated within the time interval set by the user. If the distance exceeds the preset threshold, it is considered to deviate from the preset transportation route.

[0031] In this embodiment, there is a vehicle transporting fresh goods, the transportation time is 10 hours, and Beidou positioning associated data is collected every 1 minute. The vehicle starts from the starting point (coordinates: (0, 0, 0)), and the destination coordinates are (500 km, 300 km, 0) (here simplified as coordinates on a two-dimensional plane, the z coordinate is 0). The vehicle speed data is as follows: in the first 3 hours, the speed fluctuates between 60 and 80 km / h; in the middle 4 hours, due to good road conditions, the speed is stable at 90 km / h; in the last 3 hours, approaching the destination, the road conditions are complicated, and the speed fluctuates between 40 and 60 km / h. The vehicle movement direction data is as follows: the overall direction is towards the destination, but there are some small steering adjustments during driving, and the angle changes between -10° and 10°. Logistics planning standard route: Set 5 waypoints with coordinates of ((50,30), (150, 90), (300, 180), (400, 250), (500, 300)), and connect the waypoints with straight lines.

[0032] The time interval is set to 15 minutes for comparing the cargo transportation trajectory with the standard route. The preset deviation threshold is 2 kilometers, that is, if the distance between the actual location of the cargo and the nearest point on the standard route exceeds 2 kilometers, it is considered to deviate from the preset transportation route.

[0033] The real-time three-dimensional coordinate position of the cargo, the vehicle speed, and the vehicle movement direction in the decrypted Beidou positioning associated data are extracted in chronological order. For example, at the first minute, the cargo position is (0.1 km, 0.05 km, 0), the speed is 62 km / h, and the movement direction is 2° east of the destination. As time goes by, these data points are continuously recorded to gradually construct the transportation trajectory of the cargo.

[0034] At a certain moment in the transportation process, such as the 5th hour, the current cargo position is (220 km, 130 km, 0). By calculating the distance to the destination coordinates (500 km, 300 km, 0), the remaining distance is obtained. Analyze the current speed (90 km / h at this time) and the statistical analysis of historical speed data. Through linear regression analysis of the speed data of the first 5 hours, it is found that the speed has a slight downward trend, and the subsequent speed is expected to gradually decrease, and the estimated speed is 80 km / h.

[0035] According to the formula ETA = Remaining distance / Estimated speed, the estimated arrival time = 327.3 / 80 ≈ 4.09 hours, or about 4 hours and 6 minutes. At the 5th hour (corresponding to 300 minutes), check at 15-minute intervals. Calculate the distance between the actual location of the goods (220 km, 130 km, 0) and the nearest point on the standard route (using the shortest distance algorithm from point to line segment). The calculated distance is 1.5 km, which is less than the preset threshold of 2 km. At this time, it is considered that the goods are on the normal transportation route.

[0036] According to step S200, for the vehicle information, it is determined whether the vehicle component status and the vehicle energy status are abnormal; for the cargo information, it is determined whether the cargo weight, volume and transportation condition requirements are abnormal; The method for judging whether the status of vehicle components is abnormal is as follows: for tire components, pressure check, wear assessment and temperature monitoring are performed; for brake components, brake pad thickness detection and brake fluid level inspection are performed; for engine components, fault code reading, temperature detection and oil pressure detection are performed; for suspension components, vibration monitoring, noise monitoring and vehicle posture monitoring are performed; for steering components, steering flexibility test and steering component inspection are performed; the method for judging whether the vehicle energy status is abnormal is as follows: for fuel vehicles, fuel quantity monitoring and fuel consumption rate analysis are performed; for electric vehicles, battery power inspection and battery health status assessment are performed; The method for judging whether the weight and volume of the cargo are abnormal is as follows: obtain the weight of the cargo from the cargo information, and compare it with the vehicle's load capacity. If the cargo weight exceeds the vehicle's load capacity, it is an abnormal cargo weight situation; compare the volume of the cargo with the effective loading space of the vehicle. If the cargo volume exceeds the space limited by the length, width and height of the vehicle compartment, it is judged that the cargo volume is abnormal; the method for judging whether the cargo transportation conditions are abnormal is as follows: judge based on temperature, humidity, ventilation and shockproof requirements.

[0037] According to step S300, the Beidou positioning system provides a horizontal dilution of precision HDOP and a vertical dilution of precision VDOP, which are used to characterize the positioning accuracy information. The smaller the values ​​of HDOP and VDOP are, the higher the positioning accuracy is. A threshold K is set to determine whether the positioning accuracy is insufficient. Assume that the time series data of the Beidou positioning related data set is ,in, arrive Indicates the HDOP value from the first moment to the nth moment. , VDOP value is , when extracting the time period with insufficient positioning accuracy, the following logical judgment is made: for any continuous time interval , when satisfied When is the time period when the positioning accuracy is insufficient, among which, and ; Assume each moment The corresponding three-dimensional coordinate position of the vehicle is , combined with the HDOP and VDOP values, if at a certain moment satisfy , then the position point corresponding to this moment The position points marked as insufficient positioning accuracy; For the position points with insufficient positioning accuracy, further extract relevant data features: Assume that the vehicle is at time The speed is , calculate the average speed at the position where the positioning accuracy is insufficient : ; Where I is the time index set corresponding to the position points with insufficient positioning accuracy, and |I| represents the number of elements in the set I; Calculate the standard deviation of speed : ; Describe the central tendency and dispersion of speed through the mean speed and standard deviation; Assume that the vehicle is at time The moving direction angle is , with the north direction as 0°, rotate clockwise and calculate the average direction angle and the standard deviation of the direction angles , reflects the change of the vehicle's driving direction at the point where the positioning accuracy is insufficient; Let the vehicle load capacity be C, which is obtained from the vehicle information and represents the maximum cargo weight that the vehicle can safely carry. Let the actual cargo weight be W, whose unit is consistent with the vehicle load capacity, and the actual cargo weight value is obtained from the cargo information, and the matching degree M between the vehicle load and the cargo weight is calculated: When M is equal to 100%, it means the vehicle is fully loaded. When M exceeds 100%, it means the cargo is overweight and the vehicle is in an overloaded state.

[0038] In this embodiment, we have a set of time series data of Beidou positioning association data set, with a time range from t_1 to t_100 (here n=100) and a time interval of 1 minute. The HDOP and VDOP values ​​are as follows: the HDOP value fluctuates randomly between 2 and 4 from t_1 to t_20, rises to between 6 and 8 from t_21 to t_30, falls back to between 3 and 5 from t_31 to t_70, rises again to between 7 and 9 from t_71 to t_80, and fluctuates between 4 and 6 from t_81 to t_100. The VDOP value fluctuates randomly between 3 and 5 from t_1 to t_40, rises to between 7 and 9 from t_41 to t_50, falls back to between 4 and 6 from t_51 to t_90, and fluctuates between 5 and 7 from t_91 to t_100. Set the threshold K=5.

[0039] According to logical judgment, when HDOP>5 or VDOP>5, it is determined as a time period with insufficient positioning accuracy. It can be obtained that the time period with insufficient positioning accuracy is: [t_21, t_30] and [t_71, t_80]. The position points with insufficient positioning accuracy are extracted. For the time index set I corresponding to the position points with insufficient positioning accuracy, in this embodiment, I includes the time indexes from t_21 to t_30 and from t_71 to t_80.

[0040] Calculate average speed : The speed data (unit: km / h) at these moments are 32, 35, 38, 33, 36, 31, 34, 37, 30, 32, 22, 25, 28, 23, 26, 21, 24, 27, 20, 23, then: is approximately equal to 29.25 km / h. By calculation, we can get Approximately equal to 5.12 km / h.

[0041] The moving direction angle data (unit: °) at the position point where the positioning accuracy is insufficient are 85, 88, 92, 90, 87, 83, 86, 89, 91, 93, 72, 75, 78, 73, 76, 71, 74, 77, 79, and 81. Calculate the average direction angle Approximately equal to 83.2°, calculate the standard deviation of the direction angle Approximately equal to 5.83°.

[0042] From t_1 to t_50, the cargo weight W = 8 tons, and the vehicle load capacity C = 10 tons, so the matching degree is 80%. From t_51 to t_100, the cargo weight W = 12 tons, so the matching degree is 120%, indicating that the cargo is overweight.

[0043] The time periods with insufficient positioning accuracy are successfully extracted as [t_21, t_30] and [t_71, t_80], as well as the corresponding positions with insufficient positioning accuracy. The average speed at the position points with insufficient positioning accuracy is about 29.25 km / h, the standard deviation is about 5.12 km / h, the average direction angle is about 83.2°, and the standard deviation is about 5.83°. These features describe the changes in the speed and direction of the vehicle when the positioning accuracy is insufficient. For example, a large standard deviation indicates that the changes in speed and direction are relatively discrete, which may have a certain impact on cargo transportation.

[0044] When the positioning accuracy is found to be insufficient and the vehicle driving status is confirmed to be normal, the historical driving data of the vehicle is selected from the Beidou positioning related data set and arranged in chronological order; a linear regression model is constructed with the real-time three-dimensional coordinate position of the cargo as the target variable, and the vehicle's driving speed, vehicle's moving direction, cargo weight, cargo volume and time as independent variables; the linear relationship coefficient between the independent variable and the target variable is learned through historical data; The linear regression model is trained using the organized historical driving data and cargo information samples. During the training process, the model attempts to find the optimal linear relationship coefficient so that the cargo location can be predicted based on the input independent variables. Through historical data training, the model continuously adjusts the coefficient to minimize the error between the predicted location and the actual historical location. When it is necessary to predict the current location of the cargo, the vehicle's driving speed, vehicle movement direction, cargo weight and cargo volume are obtained at the current moment, and the number of time steps from the start of transportation to the current moment is calculated for data input. Based on the learned linear relationship, the model calculates and outputs the current predicted location of the cargo, expressed as a three-dimensional coordinate.

[0045] According to step S400, when an abnormal driving state of the vehicle occurs, the specific type of the abnormality is determined, and the abnormality is analyzed in combination with the information of the abnormal cargo transportation route or the abnormal cargo transportation state; according to the abnormality type, the influence on the driving speed of the vehicle and the moving direction of the vehicle in the linear regression model is clarified; in the case of sudden braking of the vehicle, the speed parameter in the linear regression model is adjusted according to the severity of the braking, wherein the severity of the braking is determined by the vehicle deceleration information; the speed adjustment range is estimated according to the performance parameters of the vehicle's brake components and the inertia characteristics of the cargo in the vehicle compartment; for sudden acceleration, the speed parameter value in the linear regression model is increased according to the acceleration capacity of the vehicle and the inertia of the cargo; When the vehicle makes a sharp turn, the moving direction parameters in the linear regression model are changed; if the vehicle's driving direction deviates from the planned route, the trend of the deviation direction and angle is analyzed, and the moving direction parameters in the linear regression model are gradually adjusted so that the cargo location prediction can reflect the direction change; The vehicle dynamics model describes the motion state of the vehicle under the action of various forces. The vehicle dynamics model is used to calculate the impact of sudden braking and sharp turns on the cargo position. The cargo position change information calculated by the vehicle dynamics model is combined with the linear regression model after speed and direction adjustment to obtain a new cargo position prediction result.

[0046] According to step S400, when only the driving state of the vehicle is abnormal, when the vehicle brakes suddenly, the displacement of the vehicle during the braking process is calculated based on the speed-displacement relationship in the vehicle kinematic equation, taking into account the initial speed of the vehicle, the braking deceleration and the braking duration; for the cargo, the additional displacement of the cargo relative to the carriage is calculated based on its initial position in the carriage, the friction coefficient between the carriage and the cargo, and the weight of the cargo; the current position of the cargo is predicted based on the displacement of the vehicle and the cargo; When the vehicle accelerates suddenly, the vehicle displacement is calculated according to the vehicle kinematic equation, the vehicle acceleration and acceleration time. The relative displacement of the cargo in the car is determined in combination with the cargo weight, the friction coefficient with the car body and the acceleration, thereby obtaining a prediction of the current position of the cargo. When the vehicle makes a sharp turn, the trajectory of the vehicle during the turn is calculated according to the circular motion principle in the vehicle kinematic equation, taking into account the vehicle speed, turning radius and weight. For the cargo, the lateral displacement of the cargo is estimated based on the cargo weight, its position in the car body and the constraints between the car body and the cargo, thereby predicting the position of the cargo during the turn. The prediction results are optimized in combination with the cargo dynamics model.

[0047] According to another embodiment of the present invention, Figure 2As shown in the system structure diagram of an IoT product intelligent management system based on Beidou positioning, an IoT product intelligent management system based on Beidou positioning includes: Data collection and transmission module: including: data collection unit, data association unit and data encryption and transmission unit; wherein, the data collection unit collects Beidou positioning data through the Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the vehicle's driving speed, the vehicle's moving direction, the ambient temperature and the positioning accuracy information, and obtains the vehicle information and cargo information; the data association unit associates the vehicle information and cargo information with the corresponding Beidou positioning data to form a Beidou positioning associated data set; the data encryption and transmission unit transmits the Beidou positioning associated data set through the Beidou satellite communication link and the ground communication network, and encrypts and encapsulates the data before transmission; Data processing and analysis module: including: decryption and verification unit, transportation route analysis unit and transportation status abnormality judgment unit; wherein the decryption and verification unit performs decryption operation based on the Beidou positioning associated data set and verifies the data using a verification algorithm; the transportation route analysis unit analyzes the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculates the estimated arrival time of the cargo, and determines whether it deviates from the preset transportation route by comparing it with the standard route of the logistics planning; the transportation status abnormality judgment unit determines whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; Abnormal processing and prediction module: including: data extraction and load calculation unit and linear regression prediction unit; wherein, when the Beidou positioning data has abnormal cargo transportation route or abnormal cargo transportation status, the data extraction and load calculation unit extracts the positioning accuracy information from the Beidou positioning associated data set, extracts the data features of the time period and location point where the positioning accuracy is insufficient, and calculates the matching degree between the vehicle load and the cargo weight based on the vehicle information and cargo information; the linear regression prediction unit uses a linear regression algorithm, when the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the vehicle's historical driving data and cargo information to predict the current location of the cargo; Cargo location prediction module under abnormal conditions: including: complex abnormality adjustment prediction unit and single abnormality prediction unit; among them, the complex abnormality adjustment prediction unit dynamically adjusts the vehicle's driving speed and the vehicle's moving direction in the linear regression model when the vehicle's driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, and further adjusts the cargo location prediction in combination with the vehicle dynamics model; the single abnormality prediction unit predicts the current location of the cargo according to the type and degree of the abnormality of the vehicle's driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

[0048] In this embodiment, three simulated transport states are selected, including normal transport state, only abnormal vehicle driving state, and complex abnormality (vehicle driving state is abnormal and the transport route deviates). The data acquisition module records the actual driving data and environmental information of the experimental vehicle, including vehicle position, speed, direction, temperature, load and other data, and collects them every 30 seconds. The experimental setting path and its standard route can be compared, and the abnormal situation is that the vehicle deviates from the standard route and the driving speed is abnormal.

[0049] The following is a summary of the results of the three sets of experimental data: 1. Normal transportation status: average positioning error: 5 meters, cargo estimated arrival time error: ±2 minutes, prediction accuracy: 98%.

[0050] 2. Only the vehicle driving state is abnormal: Abnormal setting: The vehicle speed fluctuates greatly, and the driving direction deviates within 10 degrees. Average positioning error: 12 meters. Error in the estimated arrival time of the goods: ±5 minutes. Prediction accuracy: 92%. Analysis: In this state, the single abnormal prediction unit can better predict the current location of the goods based on the vehicle kinematic equation and linear regression model, but the error is slightly increased.

[0051] 3. Complex anomalies (vehicle driving state abnormalities and route deviations): Abnormal settings: vehicle speed fluctuations increase, driving direction deviates by 15 degrees, and deviates from the standard route by more than 20 meters. Average positioning error: 20 meters. Estimated arrival time error of goods: ±10 minutes. Prediction accuracy: 85%. Analysis: In this case, the complex anomaly adjustment prediction unit dynamically adjusts the vehicle driving speed and direction, and corrects the current location prediction of the goods in combination with the vehicle dynamics model, so that the final location prediction error is controlled, but due to multiple anomalies, the error is still large.

[0052] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for intelligent management of Internet of Things products based on Beidou positioning, characterized in that: The method comprises the following steps: S100, collecting Beidou positioning data through a Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the driving speed of the vehicle, the moving direction of the vehicle, the ambient temperature and the positioning accuracy information, obtaining the vehicle information and the cargo information, and associating them with the corresponding Beidou positioning data to form a Beidou positioning associated data set; transmitting the Beidou positioning associated data set through a Beidou satellite communication link and a ground communication network, and encrypting and encapsulating the data before transmission; S200, based on the Beidou positioning associated data set, perform a decryption operation and verify the data using a verification algorithm; analyze the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculate the estimated arrival time of the cargo, and compare it with the standard route of the logistics planning to determine whether it deviates from the preset transportation route; determine whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; S300. When the Beidou positioning data shows an abnormality in the cargo transportation route or the cargo transportation status, the positioning accuracy information is extracted from the Beidou positioning associated data set, and the data features of the time period and location point where the positioning accuracy is insufficient are extracted. The matching degree between the vehicle load and the cargo weight is calculated based on the vehicle information and the cargo information. When the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the historical driving data of the vehicle and the cargo information to predict the current location of the cargo. S400. When the vehicle driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, the vehicle driving speed and the vehicle moving direction in the linear regression model are dynamically adjusted, and the cargo position prediction is further adjusted in combination with the vehicle dynamics model; when only the vehicle driving state is abnormal, the current position of the cargo is predicted based on the type and degree of the abnormal vehicle driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

2. According to claim 1, a method for intelligent management of Internet of Things products based on Beidou positioning is characterized in that: According to step S100, the Beidou positioning terminal is initialized, and the real-time three-dimensional coordinate position of the cargo is calculated by presetting a coordinate system in the carriage, taking a corner of the bottom of the carriage as the origin, the vehicle driving direction as the x-axis, the y-axis perpendicular to the driving direction, and the z-axis perpendicular to the bottom of the carriage upwards, in combination with the relative position relationship between the cargo and the vehicle; the distance difference is calculated by comparing the position coordinates of the vehicle at two adjacent positioning moments, and the driving speed of the vehicle is obtained by dividing it by the time interval between the two positionings; the moving direction of the vehicle is determined by using the azimuth information provided by the Beidou positioning system; and the ambient temperature is collected by the temperature sensor inside the vehicle; Obtain positioning accuracy information through Beidou positioning terminal; The vehicle information includes: vehicle model, vehicle identification code, vehicle size, vehicle load capacity, vehicle component status and vehicle energy status; the cargo information includes: cargo name, type, number, weight, volume and transportation condition requirements; A timestamp is added to each set of Beidou positioning data collected, and the corresponding time is recorded when the vehicle information and cargo information are entered or updated; the association between data is established through the timestamp to ensure that the positioning data, vehicle information and cargo information collected at the same time correspond to each other; the data associated by the timestamp is organized to form a Beidou positioning associated data set.

3. According to claim 2, a method for intelligent management of Internet of Things products based on Beidou positioning is characterized in that: The AES algorithm is used to encrypt the Beidou positioning associated data set. The original plaintext data is converted into ciphertext data by processing the data according to the 128-bit group size. Based on the encrypted Beidou positioning associated data set, the header information is filled in, the relevant identifier and length are filled in the corresponding field, the encrypted Beidou positioning associated data set is placed in the data segment position, the checksum is calculated and filled in the corresponding field, the data encapsulation process is completed, and a data packet is formed.

4. The method for intelligent management of IoT products based on Beidou positioning according to claim 1, characterized in that: According to step S200, the encrypted Beidou positioning associated data set is decrypted using the acquired symmetric key to restore the original plaintext data, extract the checksum, recalculate the checksum, compare the recalculated checksum with the extracted checksum, and perform data verification; For the decrypted Beidou positioning associated data set, the real-time three-dimensional coordinate position of the goods, the driving speed of the vehicle and the moving direction of the vehicle are extracted, and the transportation trajectory of the goods is constructed in chronological order; the destination coordinate information of the goods is obtained from the logistics planning information, and the remaining distance is calculated in combination with the current location and transportation status of the goods; the driving speed of the vehicle in the remaining distance is predicted based on the statistical analysis of the current driving speed of the vehicle and the historical speed data. If there is an acceleration or deceleration trend, the speed change trend is predicted by linear regression; the estimated arrival time of the goods is calculated using the relationship between the distance and speed, and the relationship between the distance and speed is estimated arrival time = remaining distance / expected speed; the standard route of this transportation task is obtained from the logistics planning system, and the standard route is a path composed of several waypoints; the constructed cargo transportation trajectory is compared with the standard route, and the distance between the actual location of the goods and the nearest point on the standard route is calculated within the time interval set by the user. If the distance exceeds the preset threshold, it is considered to deviate from the preset transportation route.

5. The method for intelligent management of IoT products based on Beidou positioning according to claim 4 is characterized in that: According to step S200, for the vehicle information, it is determined whether the vehicle component status and the vehicle energy status are abnormal; for the cargo information, it is determined whether the cargo weight, volume and transportation condition requirements are abnormal; The method for judging whether the status of vehicle components is abnormal is as follows: for tire components, pressure check, wear assessment and temperature monitoring are performed; for brake components, brake pad thickness detection and brake fluid level inspection are performed; for engine components, fault code reading, temperature detection and oil pressure detection are performed; for suspension components, vibration monitoring, noise monitoring and vehicle posture monitoring are performed; for steering components, steering flexibility test and steering component inspection are performed; the method for judging whether the vehicle energy status is abnormal is as follows: for fuel vehicles, fuel quantity monitoring and fuel consumption rate analysis are performed; for electric vehicles, battery power inspection and battery health status assessment are performed; The method for judging whether the weight and volume of the cargo are abnormal is as follows: obtain the weight of the cargo from the cargo information, and compare it with the vehicle's load capacity. If the cargo weight exceeds the vehicle's load capacity, it is an abnormal cargo weight situation; compare the volume of the cargo with the effective loading space of the vehicle. If the cargo volume exceeds the space limited by the length, width and height of the vehicle compartment, it is judged that the cargo volume is abnormal; the method for judging whether the cargo transportation conditions are abnormal is as follows: judge based on temperature, humidity, ventilation and shockproof requirements.

6. The method for intelligent management of IoT products based on Beidou positioning according to claim 1, characterized in that: According to step S300, the Beidou positioning system provides a horizontal dilution of precision HDOP and a vertical dilution of precision VDOP, which are used to characterize the positioning accuracy information. The smaller the values ​​of HDOP and VDOP are, the higher the positioning accuracy is. A threshold K is set to determine whether the positioning accuracy is insufficient. Assume that the time series data of the Beidou positioning related data set is ,in, arrive Indicates the HDOP value from the first moment to the nth moment. , VDOP value is , when extracting the time period with insufficient positioning accuracy, the following logical judgment is made: for any continuous time interval , when satisfied When is the time period when the positioning accuracy is insufficient, among which, and ; Assume each moment The corresponding three-dimensional coordinate position of the vehicle is , combined with the HDOP and VDOP values, if at a certain moment satisfy , then the position point corresponding to this moment The position points marked as insufficient positioning accuracy; For the position points with insufficient positioning accuracy, further extract relevant data features: Assume that the vehicle is at time The speed is , calculate the average speed at the position where the positioning accuracy is insufficient : ； Where I is the time index set corresponding to the position points with insufficient positioning accuracy, and |I| represents the number of elements in the set I; Calculate the standard deviation of speed : ； Describe the central tendency and dispersion of speed through the mean speed and standard deviation; Assume that the vehicle is at time The moving direction angle is , with the north direction as 0°, rotate clockwise and calculate the average direction angle and the standard deviation of the direction angles , reflects the change of the vehicle's driving direction at the point where the positioning accuracy is insufficient; Let the vehicle load capacity be C, which is obtained from the vehicle information and represents the maximum cargo weight that the vehicle can safely carry. Let the actual cargo weight be W, whose unit is consistent with the vehicle load capacity, and the actual cargo weight value is obtained from the cargo information, and the matching degree M between the vehicle load and the cargo weight is calculated: When M is equal to 100%, it means the vehicle is fully loaded. When M exceeds 100%, it means the cargo is overweight and the vehicle is in an overloaded state.

7. The method for intelligent management of IoT products based on Beidou positioning according to claim 6 is characterized in that: When the positioning accuracy is found to be insufficient and the vehicle driving status is confirmed to be normal, the historical driving data of the vehicle is selected from the Beidou positioning related data set and arranged in chronological order; a linear regression model is constructed with the real-time three-dimensional coordinate position of the cargo as the target variable, and the vehicle's driving speed, vehicle's moving direction, cargo weight, cargo volume and time as independent variables; the linear relationship coefficient between the independent variable and the target variable is learned through historical data; The linear regression model is trained using the organized historical driving data and cargo information samples. During the training process, the model attempts to find the best linear relationship coefficient so that the cargo location can be predicted based on the input independent variables. Through historical data training, the model continuously adjusts the coefficient to minimize the error between the predicted location and the actual historical location. When the current location of the cargo needs to be predicted, the vehicle's driving speed, vehicle's moving direction, cargo weight and cargo volume are obtained at the current moment, and the number of time steps from the start of transportation to the current moment is calculated for data input. Based on the learned linear relationship, the model calculates and outputs the current predicted location of the goods, expressed as three-dimensional coordinates.

8. The method for intelligent management of IoT products based on Beidou positioning according to claim 1, characterized in that: According to step S400, when an abnormal driving state of the vehicle occurs, the specific type of the abnormality is determined, and the abnormality is analyzed in combination with the information of the abnormal cargo transportation route or the abnormal cargo transportation state; according to the abnormality type, the influence on the driving speed of the vehicle and the moving direction of the vehicle in the linear regression model is clarified; in the case of sudden braking of the vehicle, the speed parameter in the linear regression model is adjusted according to the severity of the braking, wherein the severity of the braking is determined by the vehicle deceleration information; the speed adjustment range is estimated according to the performance parameters of the vehicle's brake components and the inertia characteristics of the cargo in the vehicle compartment; for sudden acceleration, the speed parameter value in the linear regression model is increased according to the acceleration capacity of the vehicle and the inertia of the cargo; When the vehicle makes a sharp turn, the moving direction parameters in the linear regression model are changed; if the vehicle's driving direction deviates from the planned route, the trend of the deviation direction and angle is analyzed, and the moving direction parameters in the linear regression model are gradually adjusted so that the cargo location prediction can reflect the direction change; The vehicle dynamics model describes the motion state of the vehicle under the action of various forces. The vehicle dynamics model is used to calculate the impact of sudden braking and sharp turns on the cargo position. The cargo position change information calculated by the vehicle dynamics model is combined with the linear regression model after speed and direction adjustment to obtain a new cargo position prediction result.

9. The method for intelligent management of IoT products based on Beidou positioning according to claim 8, characterized in that: According to step S400, when only the driving state of the vehicle is abnormal, when the vehicle brakes suddenly, the displacement of the vehicle during the braking process is calculated based on the speed-displacement relationship in the vehicle kinematic equation, taking into account the initial speed of the vehicle, the braking deceleration and the braking duration; for the cargo, the additional displacement of the cargo relative to the carriage is calculated based on its initial position in the carriage, the friction coefficient between the carriage and the cargo, and the weight of the cargo; the current position of the cargo is predicted based on the displacement of the vehicle and the cargo; When the vehicle accelerates suddenly, the vehicle displacement is calculated according to the vehicle kinematic equation, the vehicle acceleration and acceleration time. The relative displacement of the cargo in the car is determined in combination with the cargo weight, the friction coefficient with the car body and the acceleration, thereby obtaining a prediction of the current position of the cargo. When the vehicle makes a sharp turn, the trajectory of the vehicle during the turn is calculated according to the circular motion principle in the vehicle kinematic equation, taking into account the vehicle speed, turning radius and weight. For the cargo, the lateral displacement of the cargo is estimated based on the cargo weight, its position in the car body and the constraints between the car body and the cargo, thereby predicting the position of the cargo during the turn. The prediction results are optimized in combination with the cargo dynamics model.

10. An intelligent management system for Internet of Things products based on Beidou positioning, using an intelligent management method for Internet of Things products based on Beidou positioning according to any one of claims 1 to 9, characterized in that: include: Data collection and transmission module: including: data collection unit, data association unit and data encryption and transmission unit; wherein, the data collection unit collects Beidou positioning data through the Beidou positioning terminal, including the real-time three-dimensional coordinate position of the cargo, the vehicle's driving speed, the vehicle's moving direction, the ambient temperature and the positioning accuracy information, and obtains the vehicle information and cargo information; the data association unit associates the vehicle information and cargo information with the corresponding Beidou positioning data to form a Beidou positioning associated data set; the data encryption and transmission unit transmits the Beidou positioning associated data set through the Beidou satellite communication link and the ground communication network, and encrypts and encapsulates the data before transmission; Data processing and analysis module: including: decryption and verification unit, transportation route analysis unit and transportation status abnormality judgment unit; wherein the decryption and verification unit performs decryption operation based on the Beidou positioning associated data set and verifies the data using a verification algorithm; the transportation route analysis unit analyzes the Beidou positioning data to see if there is any abnormality in the cargo transportation route, calculates the estimated arrival time of the cargo, and determines whether it deviates from the preset transportation route by comparing it with the standard route of the logistics planning; the transportation status abnormality judgment unit determines whether there is any abnormality in the cargo transportation status and the vehicle driving status based on the vehicle information and cargo information; Abnormal processing and prediction module: including: data extraction and load calculation unit and linear regression prediction unit; wherein, when the Beidou positioning data has abnormal cargo transportation route or abnormal cargo transportation status, the data extraction and load calculation unit extracts the positioning accuracy information from the Beidou positioning associated data set, extracts the data features of the time period and location point where the positioning accuracy is insufficient, and calculates the matching degree between the vehicle load and the cargo weight based on the vehicle information and cargo information; the linear regression prediction unit uses a linear regression algorithm, when the positioning accuracy is insufficient, if the vehicle driving status is normal, a linear regression model is established through the vehicle's historical driving data and cargo information to predict the current location of the cargo; Cargo location prediction module under abnormal conditions: including: complex abnormality adjustment prediction unit and single abnormality prediction unit; among them, the complex abnormality adjustment prediction unit dynamically adjusts the vehicle's driving speed and the vehicle's moving direction in the linear regression model when the vehicle's driving state is abnormal, if the cargo transportation route is abnormal or the cargo transportation state is abnormal, and further adjusts the cargo location prediction in combination with the vehicle dynamics model; the single abnormality prediction unit predicts the current location of the cargo according to the type and degree of the abnormality of the vehicle's driving state, combined with the vehicle's kinematic equation and the cargo dynamics model.

Images