Communication monitoring reminding method, system and equipment based on traffic moving cone

Abstract

The invention discloses a communication monitoring reminding method, system and equipment based on a traffic moving cone, and relates to the technical field of road monitoring. Acquiring vehicle data sent by other traffic moving cones in real time, and determining a coordinate step length and a vehicle speed of the target vehicle in a preset time period according to the vehicle data; inputting the coordinate step length and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path; performing collision judgment on the target vehicle according to the prediction path, and if the target vehicle has a collision risk, performing danger early warning; vehicle data sent by other traffic moving cones are received and processed in real time, the coordinate step length and the vehicle speed of the target vehicle in a preset time period are determined, the path of the target vehicle is predicted through the vehicle path prediction model, and collision judgment is performed on the predicted path to determine the collision speed of the target vehicle. The system can give out danger early warning in time when the target vehicle has the collision risk, collision accidents are reduced, and the overall operation efficiency and safety of the traffic system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of road monitoring, and specifically relates to a communication monitoring and reminder method, system and device based on traffic moving cones. Background Art

[0002] Traffic moving cones are mainly used in scenarios such as road construction, accident scenes, traffic diversion, and separation of pedestrian and vehicle groups, playing a role in warning, guiding, and protecting. With the development of transportation and the improvement of safety requirements, traffic moving cones have been continuously improved in terms of material, reflectivity, portability, etc., and have become an important and indispensable facility for road traffic safety.

[0003] During the process of highway road construction, traffic moving cones are arranged to enclose a specific road area, effectively guiding vehicles to decelerate and merge lanes, ensuring the smooth adjustment of traffic flow, and avoiding traffic chaos and accidents caused by construction. Traffic moving cones can attract the attention of drivers due to their distinct colors and shapes, making drivers consciously decelerate, providing time and space for smooth lane merging and avoiding traffic accidents that may be caused by emergency lane changes. However, there are still the following defects in arranging traffic moving cones as described above, for example: the alarm of traffic moving cones is not eye-catching enough, the early warning is not timely enough, and it threatens the safety of operating personnel. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems that the alarm of traffic moving cones is not eye-catching enough, the early warning is not timely enough, and it threatens the safety of operating personnel, and to propose a communication monitoring and reminder method, system and device based on traffic moving cones.

[0005] In the first aspect of the implementation of the present invention, a communication monitoring and reminder method based on traffic moving cones is first proposed. The method includes:

[0006] Real-time acquisition of vehicle data sent by other traffic moving cones, and determination of the coordinate step length and vehicle speed of the target vehicle within a preset time period according to the vehicle data;

[0007] Inputting the coordinate step length and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path;

[0008] Performing a collision judgment on the target vehicle according to the predicted path, and performing a danger warning if the target vehicle has a collision risk.

[0009] Optionally, before inputting the coordinate step length and the vehicle speed into the vehicle path prediction model, it includes:

[0010] Step 1, acquiring historical coordinate step length data and historical vehicle speed data, and using the historical coordinate step length data set and the historical vehicle speed data set as a training data set;

[0011] Step 2: Divide the training data set in the training data collection at a preset interval in the time series to obtain training data; the training data includes historical coordinate steps and historical vehicle speeds, and there is a one-to-one correspondence between the historical coordinate steps and the historical vehicle speeds; the historical vehicle speed includes a basic speed and an acceleration;

[0012] Step 3: Use the first training data in the training data set as the input in the long short-term memory network model to obtain the first prediction data, use the first prediction data and the second training data as the input of the long short-term memory network model to obtain the second prediction data, and use the prediction data of the current period and the training data of the next period of the current period as the model training mode for training;

[0013] Step 4: Execute Step 2 and Step 3 on the training data in the training data collection, and use the output of the long short-term memory network model as model parameters, so that the long short-term memory network model updates the model according to the model parameters to obtain a vehicle path prediction model.

[0014] Optionally, the collision judgment on the target vehicle according to the predicted path includes:

[0015] Input the vehicle data obtained by other traffic moving cones into the vehicle path prediction model to obtain multiple predicted paths;

[0016] Determine the fitting weight according to the distance between the receiver and the traffic moving cone, and fit the multiple predicted paths according to the fitting weight to obtain a target prediction curve;

[0017] Calculate the distance between the target prediction curve and the detection array. If the distance is less than the danger threshold, it is determined that there is a collision risk for the target vehicle.

[0018] Optionally, if there is a collision risk for the target vehicle, the danger warning includes:

[0019] If there is a collision risk for the target vehicle, send a flashing instruction to other traffic moving cones to make the traffic moving cones perform a light alarm, and send an alarm instruction to the receiver.

[0020] In the second aspect of the implementation of the present invention, a communication monitoring reminder system based on traffic moving cones is proposed, including: a vehicle data acquisition module, a vehicle path prediction module, and a vehicle collision alarm module:

[0021] The vehicle data acquisition module is used to acquire the vehicle data sent by other traffic moving cones in real time, and determine the coordinate steps and vehicle speeds of the target vehicle within a preset time period according to the vehicle data;

[0022] The vehicle path prediction module is used to input the coordinate step length and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path;

[0023] The vehicle collision warning module is used to perform a collision judgment on the target vehicle according to the predicted path, and issue a danger warning if there is a collision risk for the target vehicle.

[0024] Optionally, the system further includes: a training data acquisition module, a data partitioning module, an iterative update module, and a model update module:

[0025] The training data acquisition module is used to acquire historical coordinate step length data and historical vehicle speed data, and use the historical coordinate step length data set and the historical vehicle speed data set as a training data set;

[0026] The data partitioning module is used to partition the training data set in the training data set at a preset interval in the time series to obtain training data; the training data includes historical coordinate step length and historical vehicle speed, and there is a one-to-one correspondence between the historical coordinate step length and the historical vehicle speed; the historical vehicle speed includes a basic speed and an acceleration;

[0027] The iterative update module is used to use the first training data in the training data set as an input in a long short-term memory network model to obtain first predicted data, use the first predicted data and the second training data as inputs of the long short-term memory network model to obtain second predicted data, and use the predicted data of the current cycle and the training data of the next cycle of the current cycle as a model training mode for training;

[0028] The model update module is used to execute the data partitioning module and the iterative update module on the training data in the training data set, and use the output of the long short-term memory network model as model parameters, so that the long short-term memory network model performs model update according to the model parameters to obtain a vehicle path prediction model.

[0029] Optionally, the vehicle collision warning module includes: a vehicle data analysis module, a predicted route fitting module, and a collision risk judgment module

[0030] The vehicle data analysis module is used to input vehicle data obtained by other traffic moving cones into a vehicle path prediction model to obtain multiple predicted paths;

[0031] The predicted route fitting module is used to determine a fitting weight according to the distance between the receiver and the traffic moving cone, and fit multiple predicted paths according to the fitting weight to obtain a target predicted curve;

[0032] The collision risk judgment module is used to calculate the distance between the target prediction curve and the detection array. If the distance is less than the danger threshold, it is determined that there is a collision risk for the target vehicle.

[0033] Optionally, the collision risk judgment module is further used to, if there is a collision risk for the target vehicle, send a flashing instruction to other traffic cones so that the traffic cones perform a lighting alarm, and send an alarm instruction to the receiver.

[0034] In the third aspect of the implementation of the present invention, an electronic device is proposed, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus;

[0035] The memory is used to store a computer program;

[0036] The processor is used to, when executing the program stored on the memory, implement the steps of any one of the above-mentioned transportation vehicle dynamic planning methods.

[0037] Advantages of the present invention:

[0038] The present invention proposes a communication monitoring and reminder method based on traffic cones. By obtaining vehicle data sent by other traffic cones in real time, the coordinate step and vehicle speed of the target vehicle within a preset time period are determined according to the vehicle data; the coordinate step and vehicle speed are input into the vehicle path prediction model to obtain the predicted vehicle path; a collision judgment is made on the target vehicle according to the predicted path. If there is a collision risk for the target vehicle, a danger warning is given; the vehicle data sent by other traffic cones is received and processed in real time, the coordinate step and vehicle speed of the target vehicle within a preset time period are determined, the path of the target vehicle is predicted through the vehicle path prediction model, and a collision judgment is made on the predicted path. The system can give a danger warning in time when there is a collision risk for the target vehicle, reduce the occurrence of collision accidents, and improve the overall operation efficiency and safety of the traffic system. Description of the Drawings

[0039] The following further describes the present invention with reference to the drawings.

[0040] Figure 1 It is a flowchart of the communication monitoring and reminder method based on traffic cones provided by an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the communication monitoring and reminder method based on traffic cones provided by an embodiment of the present invention;

[0042] Figure 3 It is a flowchart of the communication monitoring and reminder system based on traffic cones provided by an embodiment of the present invention;

[0043] Figure 4 An embodiment of the present invention provides a structural diagram of an electronic device. Specific embodiments

[0044] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The term "and / or" in this article is only a description of the associated relationship of the associated objects, indicating that there can be three relationships. For example, A and B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations. In addition, the descriptions such as "first" and "second" in the present invention are only for the purpose of description, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of the technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0045] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0046] An embodiment of the present invention provides a communication monitoring and reminder method based on a traffic mobile cone. See Figure 1 , Figure 1 which is a flowchart of the communication monitoring and reminder method based on a traffic mobile cone provided by an embodiment of the present invention. The method includes the following steps:

[0047] S101, obtaining vehicle data sent by other traffic mobile cones in real time, and determining the coordinate step and vehicle speed of the target vehicle within a preset time period according to the vehicle data;

[0048] S102, inputting the coordinate step and vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path;

[0049] S103, performing a collision judgment on the target vehicle according to the predicted path, and giving a danger warning if the target vehicle has a collision risk;

[0050] Based on the communication monitoring and reminder method based on traffic mobile cones provided by the embodiments of the present invention, by receiving and processing vehicle data sent by other traffic mobile cones in real time, the coordinate step length and vehicle speed of the target vehicle within a preset time period are determined. By predicting the path of the target vehicle through a vehicle path prediction model and performing collision judgment on the predicted path, the system can issue a danger warning in a timely manner when there is a collision risk for the target vehicle, reduce the occurrence of collision accidents, and improve the overall operation efficiency and safety of the traffic system.

[0051] In one implementation, refer to Figure 2 , Figure 2 is a schematic diagram of the communication monitoring and reminder method based on traffic mobile cones provided by the embodiments of the present invention, where solid dots represent the target traffic mobile cones, hollow dots represent other traffic mobile cones, the trapezoidal area in S1 is the working area, the receiver is within the S1 area, the solid arrow is the driving direction of the vehicle flow, and the dashed line is the lane demarcation line; a detection array is formed by arranging multiple traffic mobile cones around the working area, the receiver is located within the working area, and the target traffic mobile cone is any one of the multiple traffic mobile cones; the working area is the place where the person holding the receiver constructs, for example: when constructing on a highway, the traffic mobile cones are arranged obliquely so that the vehicles converge towards the target lane; and the traffic mobile cones arranged obliquely form a detection array, where the traffic mobile cones deployed and placed at the edge of the road on the highway are data processing units, which receive the data sent by other traffic mobile cones at the edge of the road, can reduce the probability of direct collision, and the data collection efficiency will decrease due to the existence of data collection blind spots when collecting data at the edge of the road. Therefore, the traffic mobile cones at the edge of the road are used as data processing units; the target traffic mobile cone will also continue to preprocess the data sent by other traffic mobile cones.

[0052] In one implementation, the coordinate step length refers to the driving trajectory of the vehicle, which is formed by the coordinates measured each time and the step length between the coordinates; predicting the future movement trajectory of the target vehicle, using the coordinate step length and vehicle speed as input parameters, the model can comprehensively analyze the changes in vehicle speed and coordinate step length (trajectory), and generate the possible driving path of the target vehicle. The above-mentioned correlation analysis of the data improves the accuracy of the prediction, enabling the system to identify potential collision risks in advance.

[0053] In one implementation, performing collision judgment on the predicted path and issuing a danger warning in a timely manner when there is a collision risk for the target vehicle can provide a timely warning before the danger occurs, enabling the driver or relevant management personnel to have enough time to take avoidance measures, and ensuring the overall operation efficiency and safety of the traffic system by reducing the occurrence of collision accidents.

[0054] In one embodiment, before step S102, it includes:

[0055] Step 1: Obtain historical coordinate step data and historical vehicle speed data, and use the historical coordinate step data set and the historical vehicle speed data set as the training data set.

[0056] Step 2: Divide the training data set in the training data collection at a preset interval in the time series to obtain training data; the training data includes historical coordinate steps and historical vehicle speeds, and there is a one-to-one correspondence between the historical coordinate steps and the historical vehicle speeds; the historical vehicle speed includes a basic speed and an acceleration.

[0057] Step 3: Use the first training data in the training data set as the input in the long short-term memory network model to obtain the first prediction data, use the first prediction data and the second training data as the input of the long short-term memory network model to obtain the second prediction data, and use the prediction data of the current period and the training data of the next period of the current period as the model training mode for training.

[0058] Step 4: Execute Step 2 and Step 3 on the training data in the training data collection, and use the output of the long short-term memory network model as the model parameter, so that the long short-term memory network model updates the model according to the model parameter to obtain a vehicle path prediction model.

[0059] In one implementation, by dividing the training data set in the time series, the model can learn the temporal correlation and continuity between the data, and the correspondence between the historical coordinate steps and the historical vehicle speeds, so that the model can more accurately capture the dynamic characteristics (changes in the basic speed and acceleration) of the vehicle's driving. Dividing the data also helps the model maintain efficiency and stability when processing long sequence data.

[0060] In one implementation, the training data collection contains multiple training data sets. By training on the entire training data collection, that is, using all the training data sets in the training data collection as the model input for training and updating the model parameters, the model can learn global rules and characteristics. In the time series, the second training data follows the first training data. The first prediction data is the predicted value of the second training data, and the second training data is the actual value. By inputting the predicted value (the first prediction data) and the actual value (the second training data) into the model for training together, the model can learn the difference between the predicted value and the actual value and adjust its internal parameters accordingly. This training method helps the model more accurately capture the rules and characteristics in the data, thereby improving its prediction ability. The model can gradually optimize its prediction strategy by comparing the predicted value and the actual value, making the prediction more accurate.

[0061] In one implementation, the iterative training method enables the model to gradually learn the patterns and features in the data. By using the predicted data of the current cycle and the training data of the next cycle as the model training mode, the model can continuously adjust its parameters to more accurately predict future trajectories. Feeding the predicted values and the actual values into the model for training is actually a process of iterative optimization. In each iteration, the model adjusts its parameters based on the difference between the predicted values and the actual values to gradually approach the true trajectory. Through this iterative optimization process, the model's prediction accuracy can be continuously improved, and the iterative optimization process can also help the model better learn the continuity and correlation of time series data, thereby further enhancing the model's prediction performance.

[0062] In one embodiment, step S103 includes:

[0063] Input the vehicle data obtained by other traffic cones into the vehicle path prediction model to obtain multiple predicted paths;

[0064] Determine the fitting weights according to the distance between the receiver and the traffic cones, and fit the multiple predicted paths according to the fitting weights to obtain the target prediction curve;

[0065] Calculate the distance between the target prediction curve and the detection array. If the distance is less than the danger threshold, it is determined that there is a collision risk for the target vehicle.

[0066] In one implementation, other traffic cones can obtain vehicle data of the vehicles on the road. Each of the other traffic cones can obtain the vehicle data of the target vehicle, so multiple predicted paths can be obtained; the receiver is worn by the staff to determine the position of the staff within the working area and receive information. The closer the receiver is to the traffic cone, the greater the fitting weight. For example: there are currently five traffic cones, and the distances from the receiver are d1, d2, d3, d4, and d5 respectively. The fitting weights are as follows: When the distances are 1 meter, 2 meters, 2 meters, and 3 meters respectively, each fitting weight is: and The target traffic cone fits the predicted paths to obtain the target predicted path. If the distance between the target prediction curve and the detection array is less than the danger threshold, it is determined that there is a collision risk, that is, the target vehicle does not have enough time to change lanes to the target lane; the risk threshold is, for example, 5 meters or 10 meters.

[0067] In one embodiment, step S103 further includes:

[0068] If there is a collision risk for the target vehicle, send a flashing instruction to other traffic cones to make the traffic cones give a light alarm, and send an alarm instruction to the receiver.

[0069] In one implementation, if there is a collision risk for the target vehicle, a flashing instruction is sent to the traffic cone, and other traffic cones receive the flashing instruction and perform a light warning and a voice alarm; the alarm instruction is sent to the receiver, and the staff member holding the receiver leaves the work area after receiving the instruction; the light signal has the characteristics of high brightness and fast flashing, which can not only remind the driver of the target vehicle, but also wake up the operators in the work area. The voice alarm can also prevent the operators from being reminded of dangerous situations that have not been observed, improving the safety of the construction site.

[0070] Based on the same inventive concept, the embodiment of the present invention also provides a communication monitoring and reminder system based on traffic cones. See Figure 3 , Figure 3 FIG. is a schematic structural diagram of a communication monitoring and reminder system based on traffic cones provided by an embodiment of the present invention, including: a vehicle data acquisition module, a vehicle path prediction module, and a vehicle collision alarm module:

[0071] The vehicle data acquisition module is used to acquire vehicle data sent by other traffic cones, and determine the coordinate step length and vehicle speed of the target vehicle within a preset time period according to the vehicle data;

[0072] The vehicle path prediction module is used to input the coordinate step length and vehicle speed into the vehicle path prediction model to obtain a predicted vehicle path;

[0073] The vehicle collision alarm module is used to perform a collision judgment on the target vehicle according to the predicted path. If there is a collision risk for the target vehicle, a danger warning is given.

[0074] Based on the communication monitoring and reminder system based on traffic cones provided by the embodiment of the present invention, by receiving and processing vehicle data sent by other traffic cones in real time, determining the coordinate step length and vehicle speed of the target vehicle within a preset time period, predicting the path of the target vehicle through the vehicle path prediction model, and performing a collision judgment on the predicted path, the system can timely issue a danger warning when there is a collision risk for the target vehicle, reduce the occurrence of collision accidents, and improve the overall operation efficiency and safety of the traffic system.

[0075] In one embodiment, the system further includes: a training data acquisition module, a data division module, an iterative update module, and a model update module:

[0076] The training data acquisition module is used to acquire historical coordinate step length data and historical vehicle speed data, and use the historical coordinate step length data set and the historical vehicle speed data set as the training data set;

[0077] A data division module, configured to divide the training data set in the training data collection at a preset interval in the time series to obtain training data; the training data includes historical coordinate steps and historical vehicle speeds, and there is a one-to-one correspondence between the historical coordinate steps and the historical vehicle speeds; the historical vehicle speeds include a basic speed and an acceleration;

[0078] An iterative update module, configured to use the first training data in the training data set as an input in a long short-term memory network model to obtain first prediction data, use the first prediction data and the second training data as inputs of the long short-term memory network model to obtain second prediction data, and use the prediction data of the current period and the training data of the next period of the current period as a model training mode for training;

[0079] A model update module, configured to execute the data division module and the iterative update module on the training data in the training data collection, and use the output of the long short-term memory network model as model parameters, so that the long short-term memory network model updates the model according to the model parameters to obtain a vehicle path prediction model.

[0080] In one embodiment, the vehicle collision alarm module includes: a vehicle data analysis module, a predicted route fitting module, and a collision risk judgment module

[0081] The vehicle data analysis module is configured to input the vehicle data obtained by other traffic moving cones into the vehicle path prediction model to obtain multiple predicted paths;

[0082] The predicted route fitting module is configured to determine a fitting weight according to the distance between the receiver and the traffic moving cone, and fit the multiple predicted paths according to the fitting weight to obtain a target predicted curve;

[0083] The collision risk judgment module is configured to calculate the distance between the target predicted curve and the detection array, and if the distance is less than a danger threshold, determine that there is a collision risk for the target vehicle.

[0084] In one embodiment, the collision risk judgment module is further configured to, if there is a collision risk for the target vehicle, send a flashing instruction to other traffic moving cones to enable the traffic moving cones to perform a light alarm, and send an alarm instruction to the receiver.

[0085] An embodiment of the present invention further provides an electronic device, as Figure 4 shown, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404. The memory 403 is used to store a computer program; the processor 401 is configured to, when executing the program stored in the memory 403, implement the following steps:

[0086] Obtain vehicle data sent by other traffic moving cones in real time, and determine the coordinate step and vehicle speed of the target vehicle within a preset time period according to the vehicle data;

[0087] Input the coordinate step and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path;

[0088] Perform a collision judgment on the target vehicle according to the predicted path. If there is a collision risk for the target vehicle, a danger warning is issued.

[0089] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0090] The communication interface is used for communication between the above terminal and other devices.

[0091] The memory may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0092] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0093] The above has described an embodiment of the present invention in detail, but the content is only a preferred embodiment of the present invention and cannot be considered as used to limit the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A communication monitoring and reminder method based on traffic moving cones, characterized in that: A plurality of traffic moving cones are arranged outside the working area to obtain a detection array, and a receiver is located in the working area. The method is applied to a target traffic moving cone, and the target traffic moving cone is any one of the plurality of traffic moving cones. The method includes: Acquire vehicle data sent by other traffic cones in real time, and determine the coordinate step and vehicle speed of the target vehicle within a preset time period according to the vehicle data; Inputting the coordinate step size and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path; A collision judgment is made on the target vehicle according to the predicted path, and a danger warning is issued if there is a collision risk for the target vehicle.

2. The communication monitoring and reminder method based on traffic moving cones according to claim 1 is characterized in that: Before inputting the coordinate step length and the vehicle speed into the vehicle path prediction model, the method includes: Step 1: Obtain historical coordinate step data and historical vehicle speed data, and use the historical coordinate step data set and the historical vehicle speed data set as a training data set; Step 2: Divide the training data set in the training data set into a time series according to a preset interval to obtain training data; the training data includes a historical coordinate step length and a historical vehicle speed, and there is a one-to-one correspondence between the historical coordinate step length and the historical vehicle speed; the historical vehicle speed includes a basic speed and an acceleration; Step 3: using the first training data in the training data set as input to the long short-term memory network model to obtain the first prediction data, using the first prediction data and the second training data as input to the long short-term memory network model to obtain the second prediction data, and using the prediction data of the current cycle and the training data of the next cycle of the current cycle as a model training mode for training; Step 4: Execute steps 2 and 3 on the training data in the training data set, and use the output of the long short-term memory network model as a model parameter, so that the long short-term memory network model is updated according to the model parameters to obtain a vehicle path prediction model.

3. The communication monitoring and reminder method based on traffic moving cones according to claim 1 is characterized in that: Performing collision judgment on the target vehicle according to the predicted path includes: Inputting vehicle data obtained by other traffic moving cones into the vehicle path prediction model to obtain multiple predicted paths; Determining a fitting weight according to the distance between the receiver and the traffic moving cone, and fitting multiple predicted paths according to the fitting weight to obtain a target prediction curve; The distance between the target prediction curve and the detection array is calculated, and if the distance is less than a danger threshold, it is determined that there is a collision risk with the target vehicle.

4. The communication monitoring and reminder method based on traffic moving cones according to claim 3 is characterized in that: If the target vehicle has a collision risk, a danger warning is issued including: If the target vehicle has a collision risk, a flashing instruction is sent to other traffic cones to make the traffic cones give a light warning, and an alarm instruction is sent to the receiver.

5. The communication monitoring and reminder system based on traffic moving cones is characterized by: The system includes: a vehicle data acquisition module, a vehicle path prediction module and a vehicle collision alarm module: The vehicle data acquisition module is used to acquire the vehicle data sent by other traffic moving cones in real time, and determine the coordinate step length and vehicle speed of the target vehicle within a preset time period according to the vehicle data; The vehicle path prediction module is used to input the coordinate step size and the vehicle speed into a vehicle path prediction model to obtain a predicted vehicle path; The vehicle collision alarm module is used to make a collision judgment on the target vehicle according to the predicted path, and issue a danger warning if there is a collision risk with the target vehicle.

6. The communication monitoring and reminder system based on traffic moving cones according to claim 5 is characterized in that: The system also includes: a training data acquisition module, a data partitioning module, an iterative update module and a model update module: The training data acquisition module is used to acquire historical coordinate step data and historical vehicle speed data, and use the historical coordinate step data set and the historical vehicle speed data set as a training data set; The data partitioning module is used to partition the training data set in the training data set according to a preset interval in a time series to obtain training data; the training data includes a historical coordinate step length and a historical vehicle speed, and there is a one-to-one correspondence between the historical coordinate step length and the historical vehicle speed; the historical vehicle speed includes a basic speed and an acceleration; The iterative update module is used to use the first training data in the training data set as the input of the long short-term memory network model to obtain the first prediction data, use the first prediction data and the second training data as the input of the long short-term memory network model to obtain the second prediction data, and use the prediction data of the current cycle and the training data of the next cycle of the current cycle as the model training mode for training; The model updating module is used to execute the data partitioning module and the iterative updating module on the training data in the training data set, and use the output of the long short-term memory network model as a model parameter, so that the long short-term memory network model is updated according to the model parameters to obtain a vehicle path prediction model.

7. The communication monitoring and reminder system based on traffic moving cones according to claim 5 is characterized in that: The vehicle collision alarm module includes: a vehicle data analysis module, a predicted route fitting module and a collision risk judgment module The vehicle data analysis module is used to input the vehicle data obtained by other traffic moving cones into the vehicle path prediction model to obtain multiple predicted paths; The predicted route fitting module is used to determine a fitting weight according to the distance between the receiver and the traffic moving cone, and to fit multiple predicted paths according to the fitting weight to obtain a target prediction curve; The collision risk judgment module is used to calculate the distance between the target prediction curve and the detection array. If the distance is less than a danger threshold, it is judged that there is a collision risk with the target vehicle.

8. The communication monitoring and reminder system based on traffic moving cones according to claim 7 is characterized in that: The collision risk judgment module is also used to send a flashing instruction to other traffic moving cones to make the traffic moving cones give a light alarm if there is a collision risk with the target vehicle, and send an alarm instruction to the receiver.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 4 when executing a program stored in a memory.

Images