A vehicle charging status monitoring system and method based on Internet of Things technology

Abstract

The present invention discloses a vehicle charging status monitoring system and method based on Internet of Things technology, belonging to the field of Internet of Things technology. The system includes a new energy vehicle charging platform, a charging area judgment module, a real-time monitoring and prediction module, a charging initial recommendation module, and an adjustment module; the output end of the new energy vehicle charging platform is connected to the input end of the charging area judgment module; the output end of the charging area judgment module is connected to the input end of the real-time monitoring and prediction module; the output end of the real-time monitoring and prediction module is connected to the input end of the charging initial recommendation module; the output end of the charging initial recommendation module is connected to the input end of the adjustment module; the output end of the adjustment module is connected to the input end of the new energy vehicle charging platform. The present invention can monitor the charging status of new energy vehicles in real time and provide accurate charging points for users.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and particularly to a vehicle charging status monitoring system and method based on Internet of Things technology. Background Art

[0002] New energy vehicles generally refer to vehicles powered by unconventional vehicle fuels, mainly electric vehicles. In current life, from the perspective of environmental protection, new energy vehicles have multiple advantages such as zero emissions (pure electric vehicles use electric energy and emit no exhaust gas during driving, without polluting the environment), high energy utilization rate, simple structure, low noise, and wide raw material sources. It is a direction strongly supported and developed by the country. However, new energy vehicles also have a fatal flaw. Since they are mainly electric vehicles, a short driving range is an inevitable flaw. For a pure electric vehicle equipped with a lead-acid battery of the same mass as gasoline, its driving range is only 1 / 70 of that of a fuel vehicle. At the same time, the long charging time also troubles many electric vehicle owners. Especially when driving on long-distance routes, it takes 6 - 10 hours to complete one charge (even fast charging takes about 30 minutes to be able to drive again). The small and non-universal distribution of charging points also often leads to the occurrence of new energy vehicle owners queuing for charging. Currently, there is no system that can recommend charging points to new energy vehicle owners. Summary of the Invention

[0003] The purpose of the present invention is to provide a vehicle charging status monitoring system and method based on Internet of Things technology to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solutions:

[0005] A vehicle charging status monitoring method based on Internet of Things technology, the method comprising the following steps:

[0006] S1. A user inputs a destination on a new energy vehicle charging platform which is built-in with map software. The new energy vehicle charging platform generates a charging area based on the user's destination and the current power of the new energy vehicle, and marks the charging points within the charging area;

[0007] S2. Real-time monitor the charging status of new energy vehicles at each charging point within the charging area, and predict the charging duration of new energy vehicles at each charging point;

[0008] S3. Construct a charging recommendation model, generate an initial optimal recommended point, and real-time obtain the new energy vehicles within the charging area, and determine whether they need the charging points within the charging area;

[0009] S4. If there are new energy vehicles within the charging area that need the charging points within the charging area, construct an adjustment model to recommend the best charging points to the user.

[0010] According to the above technical solution, the charging points within the marked charging area include:

[0011] Obtain the destination input by the user on the new energy vehicle charging platform;

[0012] Obtain the average speed of the user's new energy vehicle for a single trip. The user's new energy vehicle for a single trip means that the user inputs the destination and arrives, which is recorded as a single trip;

[0013] A total of T groups of average speeds of the user's new energy vehicle for a single trip are obtained. T represents a constant value, and the maximum value v 2 and the minimum value v 1 are used to construct a speed interval, denoted as [v 1 , v 2 ;

[0014] Generate a charging area:

[0015]

[0016] where U 1 represents the power warning threshold of the new energy vehicle; represents the power consumption per unit time of the new energy vehicle when driving at an average speed of v 1 ; represents the power consumption per unit time of the new energy vehicle when driving at an average speed of v 2 ;

[0017] The charging area refers to the area between the maximum driving distance and the minimum driving distance when driving from the starting point until the new energy vehicle's power is warned, and the charging point refers to the position of the charging pile within the charging area.

[0018] According to the above technical solution, the prediction of the charging duration of new energy vehicles at each charging point includes:

[0019] Real-time obtain the charging information data of new energy vehicles at each charging point within the charging area, and construct a trend prediction network;

[0020] Use the new energy vehicle charging platform to obtain the charging data of any new energy vehicle, extract the charging time set, and divide it into a sample set and a test sample set in a ratio of 7:3 to construct an LSTM trend prediction network:

[0021] f a = σ(W f × [x a-1 , y a + b f )

[0022] ia = σ(W i × [x a-1 , y a + b i )

[0023] o a = σ(W o × [x a-1 , y a + b o )

[0024] F = o a × tanh(C a )

[0025] where f a represents the output of the forget gate; W f is the weight matrix of the forget gate; [x a-1 , y a means concatenating the two vectors x a-1 , y a into a longer vector; b f is the bias term of the forget gate; σ represents the sigmoid function; i a represents the output of the input gate; y a represents the input at the current time; W i represents the weight matrix of the input gate; b i represents the bias term of the input gate; o a represents the output of the output gate; W o represents the weight matrix of the output gate; b o represents the bias term of the output gate; F represents the current state output value; C a represents the cell state at the current time; x a-1 represents the cell state at the previous time; tanh represents the activation function;

[0026] According to the trend prediction network, obtain the current state output value as the predicted charging duration of new energy vehicles at each charging point within the charging area. Based on the predicted charging duration, obtain the predicted idle time of each charging point.

[0027] According to the above technical solution, the charging recommendation model includes:

[0028] Set the charging area of any user as P;

[0029] Obtain the charging points in the charging area P, sort them by distance and record them in the set {m 1 , m 2 , …, m n}, and the set of times for the new energy vehicle driven by the user to reach each charging point at the current vehicle speed is {m 11, m 22 , …, m nn};

[0030] According to the trend prediction network, obtain the set of predicted idle times {F 11 , F 22 , …, F nn} of the corresponding charging points in the charging area P;

[0031] Calculate the waiting duration:

[0032] T w = F ww - m ww

[0033] where w represents the charging point serial number; T w represents the waiting duration of the w-th charging point; F ww represents the predicted idle time of the w-th charging point; m ww represents the time for the new energy vehicle driven to reach the w-th charging point at the current vehicle speed;

[0034] Obtain the waiting times of all charging points, sort them in ascending order. If there is any T w less than 0, discard all positive values, sort in ascending order of w in the remaining T w , and select the charging point corresponding to the smallest w in the remaining T w as the initial optimal recommended charging point; if there is any T w not less than 0, select the charging point corresponding to the smallest T w as the initial optimal recommended charging point;

[0035] Obtain the time when the user arrives at the initial optimal recommended charging point, denoted as t 00 ;

[0036] Obtain the new energy vehicles in the charging area P in real time, and judge whether there is an overlapping area between the charging areas of the new energy vehicles in the charging area P and the charging area P according to the charging area provided by the new energy vehicle charging platform;

[0037] If there is, judge whether the time to reach the initial optimal recommended charging point is less than t 00 according to the current vehicle speed of the new energy vehicles in the charging area P; if it is less, construct an adjustment model:

[0038]

[0039] where E 0 represents the probability that the new energy vehicles in the charging area P reach the initial optimal recommended charging point for charging; θ 1Represents the probability value for the user to reach the initial optimal recommended charging point, which can be set by the system; g 1 Represents the probability decay coefficient value; w 00 Represents the recommended sorting serial number of the initial optimal recommended charging point among the charging points in the charging area of new energy vehicles within the charging area P; n 00 Represents the number of charging points in the charging area of new energy vehicles within the charging area P;

[0040] Set the threshold E M体X , if there exists E 0 greater than E M体X , then sequentially select the next point of the initial optimal recommended point as the initial optimal recommended point until E 0 is not greater than E M体X ; if all E 0 are greater than E M体X , then recommend the charging point closest in distance as the best charging point to the user;

[0041] If there exists E 0 greater than E M体X , it means that new energy vehicles in the charging area P are likely to arrive at the initial optimal recommended point for charging in advance, so this point is not recommended to the user; and if all E 0 are greater than E M体X , it means that the current charging points are relatively tense, so recommend the charging point closest in distance as the best charging point to the user;

[0042] If there is no intersection area or the time to reach the initial optimal recommended point is not less than t 00 , then output the initial optimal recommended point as the best charging point and recommend it to the user.

[0043] A vehicle charging status monitoring system based on Internet of Things technology, which includes a new energy vehicle charging platform, a charging area judgment module, a real-time monitoring and prediction module, a charging initial recommendation module, and an adjustment module;

[0044] The new energy vehicle charging platform is built-in with map software. When a user inputs a destination on the new energy vehicle charging platform, the new energy vehicle charging platform generates vehicle power consumption data based on the user's destination and the current power of the new energy vehicle. The charging area judgment module is used to generate a charging area according to the average speed of the new energy vehicle and mark the charging points within the charging area. The real-time monitoring and prediction module is used to monitor the charging status of new energy vehicles at each charging point within the charging area in real time and predict the charging duration of new energy vehicles at each charging point. The initial charging recommendation module is used to build a charging recommendation model, generate an initial optimal recommended point, and obtain new energy vehicles within the charging area in real time to determine whether they need the charging points within the charging area. The adjustment module is used to build an adjustment model to recommend the best charging point for the user.

[0045] The output end of the new energy vehicle charging platform is connected to the input end of the charging area judgment module; the output end of the charging area judgment module is connected to the input end of the real-time monitoring and prediction module; the output end of the real-time monitoring and prediction module is connected to the input end of the initial charging recommendation module; the output end of the initial charging recommendation module is connected to the input end of the adjustment module; the output end of the adjustment module is connected to the input end of the new energy vehicle charging platform.

[0046] According to the above technical solution, the new energy vehicle charging platform includes a driving assistance unit and a recommendation output unit;

[0047] The driving assistance unit is used to generate power consumption data of the new energy vehicle according to the built-in map software and the destination input by the user on the new energy vehicle charging platform; the recommendation output unit is used to receive the final output result of the adjustment module and push it to the user port to remind the user to check.

[0048] The output end of the driving assistance unit is connected to the input end of the charging area judgment module; the output end of the recommendation output unit is connected to the user port.

[0049] According to the above technical solution, the charging area judgment module includes a charging area judgment unit and a charging point collection unit;

[0050] The charging area judgment unit is used to collect the vehicle driving data of the new energy vehicle, obtain the average speed range, and generate a charging area; the charging point collection unit is used to collect the charging points within the charging area and record them.

[0051] The output end of the charging area judgment unit is connected to the input end of the charging point collection unit; the output end of the charging point collection unit is connected to the output end of the real-time monitoring and prediction module.

[0052] According to the above technical solution, the real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit;

[0053] The real-time monitoring unit is used to monitor the charging status of new energy vehicles at each charging point in the charging area in real time and obtain the information data of new energy vehicles that are charging; the prediction unit is used to predict the charging duration of new energy vehicles at each charging point according to the information data of new energy vehicles that are charging;

[0054] The output end of the real-time monitoring unit is connected to the input end of the prediction unit; the output end of the prediction unit is connected to the input end of the initial charging recommendation module.

[0055] According to the above technical solution, the initial charging recommendation module includes a first model construction unit and a judgment unit;

[0056] The first model construction unit is used to construct a charging recommendation model and generate an initial optimal recommended location; the judgment unit is used to obtain new energy vehicles in the charging area in real time and judge whether they need a charging point in the charging area;

[0057] The output end of the first model construction unit is connected to the input end of the judgment unit; the output end of the judgment unit is connected to the input end of the adjustment module.

[0058] According to the above technical solution, the adjustment module includes a second model construction unit and an output unit;

[0059] The second model construction unit is used to construct an adjustment model when new energy vehicles in the charging area need a charging point in the charging area; the output unit is used to recommend the best charging point to the user after the adjustment by the adjustment model.

[0060] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0061] The present invention uses the map software built into the new energy vehicle charging platform for route guidance. The user inputs the destination on the new energy vehicle charging platform, and the new energy vehicle charging platform generates vehicle power consumption data based on the user's destination and the current battery level of the new energy vehicle. The charging area judgment module generates a charging area according to the average speed of the new energy vehicle and marks the charging points within the charging area. The real-time monitoring and prediction module monitors the charging status of new energy vehicles at each charging point in the charging area in real time and predicts the charging duration of new energy vehicles at each charging point. The initial charging recommendation module constructs a charging recommendation model to generate an initial optimal recommended charging point and obtains the new energy vehicles in the charging area in real time to determine whether they need the charging points in the charging area. The adjustment module is used to construct an adjustment model to recommend the best charging point for the user. The present invention can provide route guidance when people travel by new energy vehicles, and at the same time, according to the vehicle's battery status and the route, provide the best charging points, making the journey safer and at the same time accurately reducing the charging waiting time. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0063] Figure 1 is a schematic flowchart of a vehicle charging status monitoring system and method based on the Internet of Things technology of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] Please refer to Figure 1 , in the first embodiment:

[0066] A vehicle charging status monitoring method based on the Internet of Things technology, characterized in that the method includes the following steps:

[0067] S1. The user inputs the destination on the new energy vehicle charging platform. The new energy vehicle charging platform is built with map software. The new energy vehicle charging platform generates a charging area according to the user's destination and the current battery level of the new energy vehicle, and marks the charging points within the charging area;

[0068] S2. Monitor the charging status of new energy vehicles at each charging point in the charging area in real time and predict the charging duration of new energy vehicles at each charging point.

[0069] S3. Build a charging recommendation model to generate an initial optimal recommended location, and obtain new energy vehicles in the charging area in real time to determine whether they need the charging locations in the charging area;

[0070] S4. If there are new energy vehicles in the charging area that need the charging locations in the charging area, build an adjustment model to recommend the best charging location for the user.

[0071] Obtain the destination entered by the user on the new energy vehicle charging platform;

[0072] Set the distance between the user's destination and the starting point to 500 km;

[0073] Obtain the average speed of the user's new energy vehicle for a single trip. The user's new energy vehicle for a single trip means that the user enters the destination and arrives, which is recorded as a single trip;

[0074] A total of T groups of average speeds of the user's new energy vehicle for a single trip are obtained. T represents a constant value, and T takes 10;

[0075] Take the maximum value v 2 and the minimum value v 1 Build a speed interval, denoted as [v 1 , v 2 ;

[0076] where v 1 = 60; v 2 = 110; Because in new energy vehicles, the faster the speed, the higher the power consumption. Therefore, at different speeds, the time to reach the power threshold is different. Based on different times, a charging area is generated:

[0077]

[0078] where U 1 represents the power warning threshold of the new energy vehicle; represents the power consumption per unit time of the new energy vehicle when traveling at an average speed of v 1 ; represents the power consumption per unit time of the new energy vehicle when traveling at an average speed of v 2 ;

[0079] The charging area refers to the area between the maximum driving distance and the minimum driving distance when driving from the starting point to the power warning of the new energy vehicle. The charging location refers to the location of the charging pile in the charging area.

[0080] Obtain the new energy vehicle charging information data of each charging location in the charging area in real time, and build a trend prediction network;

[0081] Use the new energy vehicle charging platform to obtain the charging data of any new energy vehicle, extract the charging time set, divide it into a sample set and a test sample set at a ratio of 7:3, and construct an LSTM trend prediction network:

[0082] f a = σ(W f × [x a-1 , y a + b f )

[0083] i a = σ(W i × [x a-1 , y a + b i )

[0084] o a = σ(W o × [x a-1 , y a + b o )

[0085] F = o a × tanh(C a )

[0086] Among them, f a represents the output of the forget gate; W f is the weight matrix of the forget gate; [x a-1 , y a means concatenating the two vectors x a-1 , y a into a longer vector; b f is the bias term of the forget gate; σ represents the sigmoid function; i a represents the output of the input gate; y a represents the input at the current moment; W i represents the weight matrix of the input gate; b i represents the bias term of the input gate; o a represents the output of the output gate; W o represents the weight matrix of the output gate; b o represents the bias term of the output gate; F represents the current state output value; C a represents the cell state at the current moment; x a-1 represents the cell state at the previous moment; tanh represents the activation function;

[0087] According to the trend prediction network, obtain the current state output value, which is used as the predicted charging duration of new energy vehicles at each charging point within the charging area. Based on the predicted charging duration, obtain the predicted idle time of each charging point.

[0088] Set the charging area of any user as P;

[0089] Obtain the charging points in the charging area P, sort them by distance and record them in the set {m 1 、m 2 、…、m n}, and the set of times for the new energy vehicle driven by this user to reach each charging point at the current vehicle speed is {m 11 、m 22 、…、m nn};

[0090] Obtain that there are 3 charging points in the charging area. Set the time for the new energy vehicle to enter the charging area as 3:00; the times to reach the three charging points are 3:20; 3:50; 4:20 respectively.

[0091] According to the trend prediction network, obtain the set of predicted idle times {F 11 、F 22 、…、F nn} for the corresponding charging points in the charging area P;

[0092] The predicted idle times of the charging points are 3:30; 3:35; 3:20

[0093] Calculate the waiting duration:

[0094] T w = F ww - m ww

[0095] where w represents the charging point serial number; T w represents the waiting duration of the w-th charging point; F ww represents the predicted idle time of the w-th charging point; m ww represents the time for the new energy vehicle driven to reach the w-th charging point at the current vehicle speed;

[0096] The waiting durations are 10, -15, -60 respectively; the unit is minutes;

[0097] Obtain the waiting times of all charging points, sort them in ascending order. If there is any T w less than 0, discard all positive values, sort them in ascending order of w in the remaining T w , and select the charging point corresponding to the smallest w in the remaining T w as the initial optimal recommended charging point; if there is any T w not less than 0, select the charging point corresponding to the smallest T w as the initial optimal recommended charging point;

[0098] Because there is a T w less than 0, so the first charging point is discarded, and the second charging point is selected as the initial optimal recommended point;

[0099] Obtain the time when the user arrives at the initial optimal recommended point, denoted as t 00 ;

[0100] t 00 = 3:50

[0101] Obtain the new energy vehicles in the charging area P in real time, and judge whether there is an overlapping area between the charging area of the new energy vehicles in the charging area P and the charging area P according to the charging area provided by the new energy vehicle charging platform;

[0102] There is a new energy vehicle (denoted as P1) in the charging area P whose charging area overlaps with the charging area P, and the time it arrives at the initial optimal recommended point is less than t 00 , construct an adjustment model:

[0103]

[0104] Among them, E 0 represents the probability that the new energy vehicle in the charging area P arrives at the initial optimal recommended point for charging; θ 1 represents the probability value that the user arrives at the initial optimal recommended point for charging, which can be set by the system; g 1 represents the probability decay coefficient value; w 00 represents the recommended sorting number of the initial optimal recommended point among the charging points in the charging area of the new energy vehicle in the charging area P; n 00 represents the number of charging points in the charging area of the new energy vehicle in the charging area P;

[0105] Among them, θ 1 = 90%, g 1 = 5%, there are 7 charging points in the charging area of the new energy vehicle (P1) in the charging area P, and the charging point that is the initial optimal recommended point for the user is ranked 4th among the charging points of the new energy vehicle (P1);

[0106] Therefore, calculate:

[0107]

[0108] Set the threshold E M体X = 50%, because there is no 10% greater than E M体X , then output the initial optimal recommended point (i.e., the second charging point) as the best charging point recommendation to the user.

[0109] In the second embodiment, a vehicle charging status monitoring system based on Internet of Things technology is provided. The system includes a new energy vehicle charging platform, a charging area judgment module, a real-time monitoring and prediction module, a charging initial recommendation module, and an adjustment module;

[0110] The new energy vehicle charging platform is built-in with map software. When a user inputs a destination on the new energy vehicle charging platform, the new energy vehicle charging platform generates vehicle power consumption data based on the user's destination and the current power of the new energy vehicle. The charging area judgment module is used to generate a charging area according to the average speed of the new energy vehicle and mark the charging points within the charging area. The real-time monitoring and prediction module is used to monitor the charging status of new energy vehicles at each charging point within the charging area in real time and predict the charging duration of new energy vehicles at each charging point. The charging initial recommendation module is used to build a charging recommendation model, generate an initial optimal recommended point, and obtain new energy vehicles within the charging area in real time to judge whether they need the charging points within the charging area. The adjustment module is used to build an adjustment model to recommend the best charging point for the user;

[0111] The output end of the new energy vehicle charging platform is connected to the input end of the charging area judgment module; the output end of the charging area judgment module is connected to the input end of the real-time monitoring and prediction module; the output end of the real-time monitoring and prediction module is connected to the input end of the charging initial recommendation module; the output end of the charging initial recommendation module is connected to the input end of the adjustment module; the output end of the adjustment module is connected to the input end of the new energy vehicle charging platform.

[0112] The new energy vehicle charging platform includes a driving assistance unit and a recommendation output unit;

[0113] The driving assistance unit is used to generate power consumption data of the new energy vehicle according to the built-in map software and the destination input by the user on the new energy vehicle charging platform. The recommendation output unit is used to receive the final output result of the adjustment module and push it to the user port to remind the user to check.

[0114] The output end of the driving assistance unit is connected to the input end of the charging area judgment module; the output end of the recommendation output unit is connected to the user port.

[0115] The charging area judgment module includes a charging area judgment unit and a charging point collection unit;

[0116] The charging area judgment unit is used to collect the vehicle driving data of the new energy vehicle, obtain the average speed range, and generate a charging area. The charging point collection unit is used to collect the charging points within the charging area and record them;

[0117] The output end of the charging area determination unit is connected to the input end of the charging point acquisition unit; the output end of the charging point acquisition unit is connected to the output end of the real-time monitoring and prediction module.

[0118] The real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit;

[0119] The real-time monitoring unit is used to monitor the charging status of new energy vehicles at each charging point in the charging area in real time and obtain the information data of new energy vehicles being charged; the prediction unit is used to predict the charging duration of new energy vehicles at each charging point according to the information data of new energy vehicles being charged.

[0120] The output end of the real-time monitoring unit is connected to the input end of the prediction unit; the output end of the prediction unit is connected to the input end of the initial charging recommendation module.

[0121] The initial charging recommendation module includes a first model construction unit and a judgment unit;

[0122] The first model construction unit is used to construct a charging recommendation model and generate an initial optimal recommended point; the judgment unit is used to obtain new energy vehicles in the charging area in real time and judge whether they need a charging point in the charging area.

[0123] The output end of the first model construction unit is connected to the input end of the judgment unit; the output end of the judgment unit is connected to the input end of the adjustment module.

[0124] The adjustment module includes a second model construction unit and an output unit;

[0125] The second model construction unit is used to construct an adjustment model when new energy vehicles in the charging area need a charging point in the charging area; the output unit is used to recommend the best charging point for the user after the adjustment of the adjustment model.

[0126] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0127] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A vehicle charging status monitoring method based on Internet of Things technology, characterized in that: The method comprises the following steps: S1. A user inputs a destination on a new energy vehicle charging platform. The new energy vehicle charging platform is built with map software. The new energy vehicle charging platform generates a charging area according to the user's destination and the current battery level of the new energy vehicle, and marks the charging points within the charging area; S2. Real-time monitor the charging status of new energy vehicles at each charging point within the charging area, and predict the charging duration of new energy vehicles at each charging point; S3. Build a charging recommendation model, generate an initial optimal recommended point, and real-time obtain the new energy vehicles within the charging area to determine whether they need the charging points within the charging area; S4. If there are new energy vehicles within the charging area that need the charging points within the charging area, build an adjustment model to recommend the best charging points to the user; if there are no new energy vehicles within the charging area that need the charging points within the charging area, then output the initial optimal recommended point as the best charging point and recommend it to the user; The charging recommendation model includes: Set the charging area of any user as P; Obtain the charging points in the charging area P, sort them by distance and record them in a set , and the set of times for the new energy vehicle driven by the corresponding user to reach each charging point at the current vehicle speed is ; According to the trend prediction network, obtain the set of predicted idle times for each corresponding charging point in the charging area P ; Calculate the waiting duration: ； Among them, represents the charging point serial number; represents the waiting duration of the th charging point; represents the predicted idle time of the th charging point; represents the time when the new energy vehicle driven arrives at the th charging point at the current vehicle speed. Obtain the waiting times of all charging points, sort them in ascending order. If any is less than 0, discard all positive values, and sort the remaining ones in ascending order. Select the smallest one among the remaining ones as the initial optimal recommended charging point; if any is not less than 0, select the charging point corresponding to the smallest one as the initial optimal recommended charging point; Obtain the time when the user arrives at the initial optimal recommended point, denoted as ; Real-time obtain the new energy vehicles within the charging area P, and according to the charging area provided by the new energy vehicle charging platform, determine whether there is an overlapping area between the charging areas of the new energy vehicles within the charging area P and the charging area P; If it exists, based on the current vehicle speed of the new energy vehicle in the charging area P, determine whether the time to reach the initial optimal recommended point is less than ; if it is less, construct an adjustment model: ； Among them, represents the probability that a new energy vehicle in the charging area P reaches the initial optimal recommended charging point; represents the probability value that a user reaches the initial optimal recommended charging point, which can be set by the system; represents the probability decay coefficient value; represents the recommended sorting serial number of the initial optimal recommended charging point among the charging points in the charging area of new energy vehicles in the charging area P; represents the number of charging points in the charging area of new energy vehicles in the charging area P; Set a threshold , if there exists greater than , then sequentially select the next point of the initial optimal recommended point as the initial optimal recommended point until is not greater than ; if all exist are all greater than , then recommend the charging point with the shortest distance to the user as the best charging point; if there exists not greater than , then output the initial optimal recommended point as the best charging point and recommend it to the user; If there is no intersection area or the time to reach the initial optimal recommended point is not less than , then the initial optimal recommended point is output as the best charging point and recommended to the user.

2. A vehicle charging status monitoring method based on Internet of Things technology according to claim 1, characterized in that: The marking of the charging points within the charging area includes: Obtain the destination input by the user on the new energy vehicle charging platform; Obtain the average speed of the user for completing one driving with the new energy vehicle. The user's completion of one driving with the new energy vehicle means that the user inputs the destination and arrives, which is recorded as completing one driving; A total of T sets of average speeds of users using new energy vehicles to complete a single trip are obtained. T represents a constant value, and the maximum value among them is taken. and the minimum value Construct a speed interval, denoted as ; Generate a charging area: ； Among them, represents the power warning threshold of new energy vehicles; represents the power consumption per unit time when the new energy vehicle travels at an average speed of ; represents the power consumption per unit time when the new energy vehicle travels at an average speed of ; The charging area refers to the area between the maximum driving distance and the minimum driving distance from the starting point to when the battery level of the new energy vehicle alarms. The charging point refers to the position of the charging pile within the charging area.

3. A vehicle charging status monitoring method based on Internet of Things technology according to claim 2, characterized in that: The prediction of the charging duration of new energy vehicles at each charging point includes: Real-time obtain the charging information data of new energy vehicles at each charging point within the charging area, and build a trend prediction network; Use the new energy vehicle charging platform to obtain the charging data of any new energy vehicle, extract the charging time set, and divide it into a sample set and a test sample set at a ratio of 7:3 to build an LSTM trend prediction network: ； ； ； ； Among them, represents the output of the forget gate; is the weight matrix of the forget gate; denotes concatenating two vectors into a longer vector; is the bias term of the forget gate; represents the sigmoid function; represents the output of the input gate; represents the input at the current time; is the weight matrix of the input gate; is the bias term of the input gate; represents the output of the output gate; is the weight matrix of the output gate; is the bias term of the output gate; represents the current state output value; represents the cell state at the current time; represents the cell state at the previous time; represents the activation function; According to the trend prediction network, obtain the current state output value as the predicted charging duration of new energy vehicles at each charging point within the charging area, and based on the predicted charging duration, obtain the predicted idle time of each charging point.

4. A vehicle charging status monitoring system based on Internet of Things technology, using a vehicle charging status monitoring method based on Internet of Things technology according to claim 1, characterized in that: The system includes a new energy vehicle charging platform, a charging area judgment module, a real-time monitoring and prediction module, a charging initial recommendation module, and an adjustment module; The new energy vehicle charging platform is built-in with map software. When a user enters a destination on the new energy vehicle charging platform, the new energy vehicle charging platform generates vehicle power consumption data based on the user's destination and the current power of the new energy vehicle. The charging area judgment module is used to generate a charging area according to the average speed of the new energy vehicle and mark the charging points within the charging area. The real-time monitoring and prediction module is used to monitor the charging status of new energy vehicles at each charging point within the charging area in real time and predict the charging duration of new energy vehicles at each charging point. The initial charging recommendation module is used to construct a charging recommendation model, generate an initial optimal recommended point, and obtain new energy vehicles within the charging area in real time to determine whether they need the charging points within the charging area. The adjustment module is used to construct an adjustment model to recommend the best charging point for the user. The output end of the new energy vehicle charging platform is connected to the input end of the charging area judgment module. The output end of the charging area judgment module is connected to the input end of the real-time monitoring and prediction module. The output end of the real-time monitoring and prediction module is connected to the input end of the initial charging recommendation module. The output end of the initial charging recommendation module is connected to the input end of the adjustment module. The output end of the adjustment module is connected to the input end of the new energy vehicle charging platform.

5. A vehicle charging status monitoring system based on Internet of Things technology according to claim 4, characterized in that: The new energy vehicle charging platform includes a driving assistance unit and a recommendation output unit; The driving assistance unit is used to generate power consumption data of the new energy vehicle according to the built-in map software and the destination entered by the user on the new energy vehicle charging platform. The recommendation output unit is used to receive the final output result of the adjustment module and push it to the user port to remind the user to check. The output end of the driving assistance unit is connected to the input end of the charging area judgment module. The output end of the recommendation output unit is connected to the user port.

6. A vehicle charging status monitoring system based on Internet of Things technology according to claim 4, characterized in that: The charging area judgment module includes a charging area judgment unit and a charging point collection unit; The charging area judgment unit is used to collect vehicle driving data of the new energy vehicle, obtain the average speed range, and generate a charging area; The charging point collection unit is used to collect the charging points within the charging area and record them; The output end of the charging area judgment unit is connected to the input end of the charging point collection unit; The output end of the charging point collection unit is connected to the output end of the real-time monitoring and prediction module.

7. A vehicle charging status monitoring system based on Internet of Things technology according to claim 4, characterized in that: The real-time monitoring and prediction module includes a real-time monitoring unit and a prediction unit; The real-time monitoring unit is used to monitor the charging status of new energy vehicles at each charging point in the charging area in real time and obtain the information data of the new energy vehicles being charged; the prediction unit is used to predict the charging duration of new energy vehicles at each charging point according to the information data of the new energy vehicles being charged. The output end of the real-time monitoring unit is connected to the input end of the prediction unit; the output end of the prediction unit is connected to the input end of the initial charging recommendation module.

8. A vehicle charging status monitoring system based on Internet of Things technology according to claim 4, characterized in that: The initial charging recommendation module includes a first model construction unit and a judgment unit; The first model construction unit is used to construct a charging recommendation model and generate an initial optimal recommended point; the judgment unit is used to obtain new energy vehicles in the charging area in real time and judge whether they need a charging point in the charging area. The output end of the first model construction unit is connected to the input end of the judgment unit; the output end of the judgment unit is connected to the input end of the adjustment module.

9. A vehicle charging status monitoring system based on Internet of Things technology according to claim 4, characterized in that: The adjustment module includes a second model construction unit and an output unit; The second model construction unit is used to construct an adjustment model when new energy vehicles in the charging area need a charging point in the charging area; the output unit is used to recommend the best charging point to the user after the adjustment of the adjustment model.

Images