An intelligent working condition monitoring feedback method, system and storage medium thereof

Abstract

The present invention discloses an intelligent working condition supervision and feedback method, system and storage medium thereof, which relate to the field of shared electric vehicle management, and include the following steps: first, an energy consumption evaluation model of the shared electric vehicle is established based on historical itinerary data, and the slope of the terrain road condition is introduced to accurately quantify the impact of the terrain on battery energy consumption, and the travel energy consumption of the shared electric vehicle is monitored at all times. Subsequent user fault feedback is combined with whether the energy consumption is abnormal to assist staff in handling the fault. The present invention identifies the abnormal energy consumption of the shared electric vehicle, discovers hidden battery aging or damage in advance, and maintains the battery in time to avoid continuous damage that leads to final scrapping, thereby greatly reducing losses. At the same time, the average slope in the itinerary can be used to prioritize the dispatch of high-power shared electric vehicles to parking spots with high uphill demand, and dispatch low-power vehicles to parking spots with high downhill demand, which can greatly increase the number of orders served by the vehicle on a single charge.

Description

Technical Field

[0001] The present invention relates to the technical field of shared electric vehicles, and specifically to an intelligent working condition monitoring feedback method, system and storage medium thereof. Background Art

[0002] With the continuous development of our technology, shared electric vehicles have become popular, and people's appearance has been greatly improved. At this time, the corresponding shared electric vehicle operating companies are also facing some problems. As the number of shared electric vehicles put into the market is increasing, due to long-term outdoor operation, it is inevitable that failures will occur. At this time, timely maintenance is needed to ensure operation;

[0003] We found that the current maintenance of shared electric vehicles mostly relies on user feedback, and user feedback can basically only reflect some external damaged equipment. It is difficult to know the core battery problems of shared electric vehicles, and some faults are actually caused by battery problems. By the time the battery problem is discovered, the battery has been severely damaged, and the loss is very large. The current regular inspection of shared electric vehicles not only has low maintenance efficiency, but also affects the use of the vehicle. The most important thing is that static inspections cannot simulate the impact of external environment and road conditions on shared electric vehicles, so the inspection results are not very accurate. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent working condition monitoring feedback method, system and storage medium thereof, which monitors the energy consumption of the battery by introducing the slope road condition with the greatest impact and combines user fault feedback and random inspections to perform comprehensive maintenance on shared electric vehicles, so as to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent working condition monitoring and feedback method, comprising the following steps:

[0006] S1: Establish an evaluation model. Collect historical driving data of shared electric vehicles in each operating area according to the division of shared electric vehicles. This can minimize the impact of road conditions on driving data. Calculate the average slope corresponding to each trip based on the driving data of shared electric vehicles in each trip. Introduce the influence coefficient of average slope on energy consumption to establish an energy consumption evaluation model for each trip of shared electric vehicles.

[0007] S2: Driving data evaluation. After each shared electric vehicle trip, the corresponding driving data is transmitted to the energy consumption evaluation model and the corresponding evaluated energy consumption data is output. A dynamic energy consumption baseline is established to classify the actual energy consumption data. At the same time, fault feedback from users in each trip is collected. The terminal system generates a working condition instruction with a safety level based on the fault feedback and the energy consumption level of the corresponding trip. At the same time, the driving data of several consecutive trips of each shared electric vehicle is regularly extracted, the driving data is analyzed, and the corresponding dispatch instructions are generated;

[0008] S3: Dispatching execution layer. The terminal system sends the working condition instructions and scheduling instructions to the nearest staff according to the location of the corresponding shared electric vehicle. After receiving the instructions, the staff will perform corresponding processing on the shared electric vehicle and upload the processing results at the same time.

[0009] Preferably, the method for establishing an energy consumption evaluation model for a shared electric vehicle during each driving operation specifically comprises the following steps:

[0010] S101: Extracting motion data corresponding to each trip from the historical driving data, the motion data including travel distance, average speed, load, and acceleration, calculating the average slope for the corresponding travel distance using acceleration, and calculating the corresponding energy consumption value based on the battery data corresponding to each trip;

[0011] S102: Import a linear regression model, set X = [travel distance, average speed, load, average slope] as the input feature matrix of the model, and Y = [energy consumption value] as the target variable, train and build the relationship between the input features and the energy consumption value, and predict the energy consumption of each shared electric vehicle trip.

[0012] Preferably, the method for establishing a dynamic energy consumption baseline to classify the actual energy consumption data includes comparing the actual energy consumption data corresponding to each trip sheet with the output estimated energy consumption data, and dividing the interval levels according to the proportion of the actual energy consumption exceeding the estimated energy consumption and marking them simultaneously. The divided intervals include:

[0013] The proportion in the range of (0,10%] is set as the first-level interval and marked in green;

[0014] The proportion in the range of (10%, 20%] is set as the secondary range and marked in yellow;

[0015] The proportion greater than 20% is set as the third-level interval and marked in red.

[0016] Preferably, the method for generating the operating condition instruction comprises the following steps:

[0017] S201: After each itinerary is completed, a fault feedback window pops up on the user's mobile terminal interface, and the user enters the corresponding fault problem and uploads it to the terminal system;

[0018] S202: The backend customer service staff assigns a corresponding safety level based on the feedback fault description. The terminal system generates a working condition instruction with an attached safety level based on the feedback fault description. At the same time, combined with the energy consumption level of the corresponding trip, it determines whether the feedback fault is a battery problem and assigns an energy loss label to the working condition instruction that is a battery problem.

[0019] Preferably, the scheduling instruction includes a maintenance scheduling instruction and an operation scheduling instruction, and the method for generating the maintenance scheduling instruction includes:

[0020] Extract at least three of the last itineraries. If three or more consecutive trips show that the actual energy consumption exceeds the assessed energy consumption by a percentage within the third level, a maintenance dispatch instruction is directly generated.

[0021] Extract the completion time of the last itinerary. If no new itinerary appears after the set time node and the location of the shared electric vehicle has not moved, a maintenance scheduling instruction is directly generated.

[0022] Preferably, the method for generating the operation scheduling instruction specifically includes the following steps:

[0023] Set an average slope threshold P, extract itineraries with an average slope greater than P and mark them as uphill itineraries, and extract itineraries with an average slope less than -P and mark them as downhill itineraries;

[0024] Analyze and compare the travel routes of uphill and downhill itineraries. First, eliminate itineraries with similar travel routes. Then, classify the uphill and downhill itineraries based on their departure points and extract the departure points with the most trips.

[0025] When there is a shortage of shared electric vehicles at the extracted starting point and they need to be dispatched, the shared electric vehicle with the most power is prioritized and dispatched to the starting point corresponding to the extracted uphill itinerary, and the shared electric vehicle with the least power is dispatched to the starting point corresponding to the extracted downhill itinerary. At the same time, the numbers and positions of the corresponding electric vehicles are obtained to generate corresponding operational dispatch instructions.

[0026] Preferably, after receiving the working condition instruction, the staff performs a method for processing the shared electric vehicle, which includes the following steps:

[0027] Based on the safety level of the working condition instructions, high-level working condition instructions are processed first. First, the corresponding fault point is found according to the fault description, and the accuracy of the fault description reported by the user is fed back and photos are taken. For the working condition instructions assigned with power loss labels, the battery is directly replaced. The fault point is re-inspected and repaired, and photos are taken. Finally, the photos are uploaded and it is confirmed that the working condition processing is completed.

[0028] Preferably, the processing of the maintenance scheduling instruction includes transferring the shared electric vehicle assigned the maintenance scheduling instruction to a maintenance point by the staff for full inspection and maintenance of the shared electric vehicle, and the priority of the maintenance scheduling instruction is higher than the working condition instruction.

[0029] To solve the above technical problems, the present invention further provides an intelligent working condition monitoring and feedback system, comprising:

[0030] memory for storing computer programs;

[0031] A processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of an intelligent working condition supervision and feedback method as described in any one of the above items are implemented.

[0032] In order to solve the above technical problems, the present invention further provides a readable storage medium having a computer program stored thereon.

[0033] When the computer program is executed by a processor, the steps of an intelligent working condition supervision and feedback method as described in any one of the above items are implemented.

[0034] In summary, the beneficial effects of the present invention are:

[0035] The present invention collects historical data according to the operating areas of shared electric vehicles, which can effectively avoid the influence of road conditions on historical data of shared electric vehicles in other areas. It uses historical data to build a model to predict energy consumption. At the same time, it introduces the slope of the terrain and road conditions to accurately quantify the impact of terrain on battery energy consumption. It constantly monitors the energy consumption of shared electric vehicles during their travel, identifies abnormal energy consumption, and discovers hidden battery aging or damage, such as increased internal resistance and capacity decay, in advance. It can then promptly maintain the battery to avoid continuous damage that leads to eventual scrapping, greatly reducing losses.

[0036] When a shared electric vehicle breaks down, the system can first identify the faults discovered by users during use and, based on the feedback, determine whether the fault is caused by a battery problem based on whether the shared electric vehicle's energy consumption is abnormal. This helps staff to carry out an efficient repair of the fault. It can also identify vehicles that have not been used for a long time and promptly recall them for repair.

[0037] At the same time, the average slope in the itinerary can be used to extract the shared electric vehicles that are most used uphill or downhill. When dispatching vehicles, shared electric vehicles with high battery power will be dispatched to parking spots with high uphill demand, and low battery power will be dispatched to parking spots with high downhill demand. Through reasonable allocation, the number of orders served by the vehicle on a single charge can be greatly increased, and the battery life can be effectively extended.

[0038] The present invention also provides an intelligent working condition monitoring feedback system and a storage medium thereof, which have the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a schematic diagram of the overall framework process structure of an intelligent working condition monitoring and feedback method of the present invention;

[0041] Figure 2 This is a main interface diagram of a trip sheet for fault feedback in an intelligent working condition monitoring and feedback method of the present invention;

[0042] Figure 3 A schematic diagram of a trip sheet for fault feedback in an intelligent working condition monitoring and feedback method of the present invention;

[0043] Figure 4 A schematic diagram of a trip sheet for fault feedback in an intelligent working condition monitoring and feedback method of the present invention;

[0044] Figure 5 A schematic diagram of a trip sheet for fault feedback in an intelligent working condition monitoring and feedback method of the present invention;

[0045] Figure 6 This is a statistical chart of instructions for issuing a travel order in an intelligent working condition monitoring and feedback method of the present invention;

[0046] Figure 7 This is a diagram of the staff position statistics interface in an intelligent working condition supervision and feedback method of the present invention. DETAILED DESCRIPTION

[0047] The present invention will now be further described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of the present invention. These drawings are all simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic way, and therefore only show the structures related to the present invention.

[0048] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0049] All features disclosed in this specification, or all steps in the disclosed methods or processes, except mutually exclusive features and / or steps, can be combined in any manner.

[0050] Any feature disclosed in this specification (including any appended claims, abstract, and drawings), unless otherwise stated, may be replaced by other equivalent or similar features. In other words, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

[0051] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connected," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; they can refer to mechanical connection, direct connection, or indirect connection through an intermediate medium; they can refer to internal communication between at least two elements or interaction between at least two elements, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0052] The following combination Figure 1-Figure 7The present invention is described in detail. An embodiment of the present invention is: an intelligent working condition monitoring and feedback method for the management of shared electric vehicles. During the use of shared electric vehicles currently on the market, due to long-term operation outdoors, it is inevitable that faults will occur. At this time, it is necessary to promptly discover the corresponding faults so as to dispatch staff for maintenance to ensure the safe use of shared electric vehicles. Although we can often repair some external damaged equipment of shared electric vehicles in a timely manner, it is often difficult to discover problems with battery energy consumption and energy conduction in a timely manner. By the time the problems are discovered, the battery is almost completely damaged, and the loss is relatively serious. Therefore, an intelligent working condition monitoring and feedback method is used in each operating area to monitor the status of shared electric vehicles, which specifically includes the following steps:

[0053] Step 1: Build an evaluation model

[0054] According to the operating areas of shared electric vehicles, historical trip records of shared electric vehicles in each area are collected. Each trip record corresponds to driving data. Driving data includes battery data and motion data. Battery data includes voltage, current and SOC, while motion data includes driving path, driving distance, average speed, load, acceleration and average slope during driving. The driving path can be used to obtain the starting point and return point of the shared electric vehicle;

[0055] Under the battery data of each trip, an energy consumption value of each trip can be calculated based on the difference ΔSOC between the SOC at the beginning and the SOC at the end of the trip. Energy consumption value = (ΔSOC × total battery capacity);

[0056] During the driving process of shared electric vehicles, different road conditions have different effects on energy consumption. The influence of slope has a significant impact on the energy consumption of shared electric vehicles, which is mainly reflected in:

[0057] Additional work when climbing: When climbing a slope, the vehicle must overcome gravity to do work, which significantly increases the load on the motor. The steeper the slope, the exponential increase in energy consumption. When going downhill, gravity can be used for acceleration, consuming less energy.

[0058] Reduced driving range: A 5% slope can increase energy consumption by more than 30%, and frequent uphill and downhill routes (such as mountainous cities) may reduce driving range by 40-50%;

[0059] Battery and motor burden: Continuous climbing can cause the motor to overheat and accelerate battery aging.

[0060] Therefore, the slope during driving has a relatively large impact on shared electric vehicles, especially on the internal battery. Therefore, the acceleration of the shared electric vehicle in each itinerary is used to calculate an average slope under the corresponding path. Using acceleration to calculate the slope is a mature technology and will not be introduced in detail here. The slope is attached to the driving data and imported into the linear regression model. Let X=[driving distance, average speed, load, average slope] be used as the input feature matrix of the model, and Y=[energy consumption value] be used as the target variable. The corresponding data in the historical itinerary is input as sample data, and the relationship between the input features and the energy consumption value is trained and constructed. The established model can be used to evaluate the energy consumption value of subsequent itineraries, thereby achieving more accurate energy consumption management of shared electric vehicles. At the same time, the battery performance can be monitored based on the difference between the evaluated energy consumption and the actual energy consumption.

[0061] For example, the format of the collected historical driving data is shown in the following table:

[0062]

[0063] The corresponding input feature matrix X and target variable Y are:

[0064] # Input feature matrix X and target variable Y (historical data)

[0065] X = np.array([

[0066] [3.0, 20, 60, 2.0],

[0067] [5.0, 18, 70, 1.5],

[0068] [4.0, 22, 80, 3.0],

[0069] [2.5, 15, 50, 4.0],

[0070] [6.0, 25, 75, 2.5]

[0071] …

[0072] [Sn, Vn, Mn, Pn] ])

[0074] Y = np.array([1.20, 1.50, 1.80, 1.00, 2.00,……,Qn ])

[0076] # Train linear regression model

[0077] model = LinearRegression()

[0078] model.fit(X, Y)

[0079] Finally, the model coefficients are output. As the subsequent data is continuously input, the model coefficients will be updated and iterated.

[0080] Step 2: Driving Data Evaluation

[0081] After the user has used the shared electric vehicle and returns the vehicle to the designated parking spot and executes the return instruction, a fault feedback window will pop up on the user's mobile phone interface. The user can report the fault problems of the shared electric vehicle during the ride, and finally generate a trip sheet. The driving data in the trip sheet is input into the evaluation model to output the corresponding evaluation energy consumption data. At the same time, the set energy consumption baseline is used to classify the actual energy consumption data. The energy consumption of the trip sheet is classified by the difference between the actual energy consumption data and the evaluation energy consumption data. The established energy consumption baseline can be adjusted because the outdoor temperature will have a certain impact on the battery, especially in winter, the energy consumption of shared electric vehicles will increase, so the energy consumption baseline needs to be adjusted in different seasons to ensure the accuracy of the classification of the actual energy consumption data.

[0082] One of the classification methods is as follows: let the actual energy consumption be Q, and the assessed energy consumption be Q 、 , then the difference △Q is QQ 、 , using the difference △Q and the evaluation energy consumption Q 、 The ratio of is used to divide the levels:

[0083] If the percentage is in the range of (0,10%), it is set to the first level, indicating that the energy consumption is within a normal range and is marked green.

[0084] If the percentage is between 10% and 20%, it is set as the second level, indicating that there is a certain abnormal loss in energy consumption and requires extra attention, and is marked in yellow.

[0085] The proportion greater than 20% is set to the third level interval. At this time, there is a relatively large loss of energy consumption, which is marked in red. If there are more or continuous reds for the same shared electric vehicle, there is a high possibility that there is a problem with the power supply part of the shared electric vehicle. At this time, maintenance personnel can be dispatched in time for inspection and maintenance of the battery in time to avoid continuous damage that may lead to scrapping.

[0086] Step 3: Instruction Generation

[0087] After the energy consumption level classification is completed for the corresponding itinerary, the user's fault feedback is collected at the same time. The back-end customer service staff will refer to the fault description of the feedback. Figure 2-Figure 5, assign the corresponding security level to the itinerary with reference to the set security level classification standards;

[0088] One of the security level classification methods is:

[0089] High risk (L3): Directly threatens user life safety and may cause serious accidents or casualties. Immediate shutdown and repair are required, and the processing time must be completed within 12 hours;

[0090] Medium risk (L2): May cause user injury or property loss and must be handled as soon as possible to avoid escalation of risk. The processing time must be completed within 24 hours;

[0091] Low risk (L1): affects the user experience but does not directly endanger safety. Regular maintenance or user-friendly solutions are required and must be handled within seven days.

[0092] For example, high-risk fault descriptions include "brake failure", "steering failure, unable to steer", "loose wheel connection", etc.

[0093] The descriptions of medium-risk faults include "tire blowout or air leakage", "sudden automatic power failure", "frame damage", etc.

[0094] Descriptions of low-risk faults include "handlebars don't move", "headlight failure", "abnormal instrument panel display", "chain falls off", etc.

[0095] The terminal system generates a working condition instruction with a safety level based on the feedback fault description and the safety level classification. It should be noted that some faults may be caused by battery problems. After all, it is difficult for users to find faults caused by battery problems. For example, "the handlebar does not move" and "sudden power failure" are faults. These problems are very likely caused by battery problems. Therefore, the generated working condition instruction with a safety level is combined with the energy consumption level of the current itinerary of the shared electric vehicle and the itinerary of the previous trip to assist in judging whether the feedback fault is a battery problem. The working condition instruction that is a battery problem is given a power loss label, for example:

[0096] refer to Figure 5The itinerary's work order number is CB2025042303564, and the fault is "failure to proceed halfway." The customer service staff for this itinerary rated it at a medium risk (L2). Failures that "failure to proceed halfway" are most likely caused by a battery problem. Therefore, the energy consumption levels of the current and previous itineraries are extracted. If the energy consumption levels are in the third-level range, a power loss tag is directly added, indicating that the fault is most likely caused by a battery problem. With the power loss tag, the staff can effectively reduce the time it takes to find the cause of the fault when they receive instructions for repairs. It also makes repairs very convenient for the staff with a clear direction. After all, the description of this "failure to proceed halfway" covers a wide range of fault causes. In traditional repair processes, without the assistance of power loss tags, staff may need to investigate the causes of the "failure to proceed halfway" fault one by one, including battery problems, external transmission problems, etc. With the power loss tag, staff can directly investigate the cause of the battery problem, effectively narrowing the scope of fault investigation and greatly improving work efficiency.

[0097] The generation of working condition instructions is based on the fault feedback of users on shared electric vehicles with problems. Since shared electric vehicles are outdoors for a long time, it is inevitable that some shared electric vehicles are damaged but no users have reported them. It may be that the shared electric vehicles are even unusable, resulting in the inability of users to provide fault feedback. Such shared electric vehicles need to be handled in a timely manner. Since the cause of the fault is unclear, it is best for such shared electric vehicles to be concentrated in a maintenance point for full inspection and maintenance. Such shared electric vehicles should be fully inspected and repaired;

[0098] There is also a situation where the shared electric vehicle itself does not have any faults, but due to long-term use, the internal power supply has aged or been damaged, resulting in abnormal energy consumption. Each time it is fully charged, it cannot travel a suitable distance. In this case, the user is unable to provide feedback. The user believes that the electric vehicle is working normally, but in fact there is a problem with the internal battery. Therefore, this type of shared electric vehicle also needs to be fully inspected and repaired;

[0099] Therefore, maintenance scheduling instructions are generated for shared electric vehicles that undergo comprehensive inspection and maintenance. First, a sampling inspection time period is set in the terminal system, which can be one week, one month or three months. According to the set sampling inspection time period, at least the last three trip sheets of each shared electric vehicle are regularly extracted, and generally five are extracted. If three or more energy consumption levels are in the third level range in a row, it means that the energy consumption of the shared electric vehicle is abnormal, indicating that there is a major problem with the battery. For such shared electric vehicles, the battery needs to be replaced and repaired in time. Otherwise, the degree of damage to the battery will be seriously aggravated if it is operated for a long time, and it will be completely scrapped, resulting in a large loss. Therefore, comprehensive inspection and maintenance are required to generate maintenance scheduling instructions.

[0100] At the same time, the time of the last travel completed by the shared electric vehicle is extracted from the itinerary regularly extracted during the sampling period. If it is found that the span between the last travel time of the shared electric vehicle and the time of the current draw is large, the time of this span can be set, generally set to 15 days, indicating that the shared electric vehicle has not been used for a long time and the location has not changed. In this case, the shared electric vehicle has a problem of being unusable, so it needs to be fully inspected and repaired, thereby generating a maintenance scheduling instruction.

[0101] It should be noted that the operating condition instruction and the maintenance scheduling instruction may exist on the same shared electric vehicle. In this case, the maintenance scheduling instruction has a higher priority than the operating condition instruction, and the maintenance scheduling instruction is executed first.

[0102] Step 4: Instruction dispatch

[0103] After the shared electric vehicle with a problem generates the corresponding instruction, the terminal system sends the instruction to the nearest staff member according to the location of the corresponding shared electric vehicle. Different staff members have different positions, including inspection positions, battery replacement positions, and dispatching positions. There are also situations where one person has multiple positions. Figure 7 Among them, the inspection post mainly receives working condition instructions and repairs shared electric vehicles, while the dispatching post mainly receives dispatching instructions and dispatches and transfers shared electric vehicles; the battery replacement post is mainly responsible for replacing the charged batteries of shared electric vehicles with insufficient power.

[0104] After receiving the instruction, the corresponding staff will process the shared electric vehicle according to the instruction. For the working condition instruction, the staff need to prioritize the working condition instruction with a higher level according to the safety level of the working condition instruction, find the corresponding fault point according to the fault description, and confirm whether the fault is the same as the user's feedback. If it is, take a photo and upload it to confirm the fault point. If not, the feedback is incorrect. At the same time, find out whether there are other problems with the shared electric vehicle and repair them. If the staff finds problems with a risk level of L2 or above and repairs them, they will be rewarded;

[0105] For the operating condition instructions assigned with the power loss label, since the battery has already consumed too much energy, the battery of the shared electric vehicle is directly replaced with a new one to see if the corresponding fault still exists. If not, the repair is completed. If the fault still exists, the corresponding fault is inspected and repaired and photos are taken. Finally, the photos are uploaded and it is confirmed that the operating condition processing is completed.

[0106] In addition, in one embodiment, shared electric vehicles have corresponding parking spots. When there are too few shared electric vehicles at one parking spot and too many shared electric vehicles at another parking spot, we need to dispatch and distribute them evenly. Since road conditions have a greater impact on the operation of shared electric vehicles, there may be some road conditions with larger slopes between some shared electric vehicle parking spots. Shared electric vehicles require more power when going uphill, and thus require more electricity for support. When going downhill, due to the support of gravity acceleration, they do not require large power and have lower electricity requirements. If some shared electric vehicles with insufficient power are dispatched to parking spots that need to go uphill during the dispatch process, they will easily have difficulty going uphill or even stop halfway, which is a very bad experience for users. Therefore, for parking spots that need to go uphill, shared electric vehicles with high power are required for dispatch. At this time, statistical analysis can be performed based on the slope in the itinerary of the shared electric vehicle. The lack of shared electric vehicles at the corresponding location can be used to realize the dispatch between shared electric vehicles with different power levels, and the shared electric vehicles with corresponding power levels can be dispatched to the appropriate location.

[0107] First, we set an average slope threshold P, extract the trips with an average slope greater than P and mark them as uphill trips, and extract the trips with an average slope less than -P and mark them as downhill trips.

[0108] Analyze and compare the driving paths in the uphill itinerary and the downhill itinerary, and eliminate the itineraries with similar driving paths. Similar itineraries indicate round trips between two parking points. In the remaining itineraries, classify the uphill and downhill itineraries according to the location of the starting point, and extract the starting point with the largest number of orders in the corresponding uphill and downhill itineraries. If there are a large number of uphill shared electric vehicles departing from parking point A as the starting point, it means that parking point A needs enough high-power shared electric vehicles. If there are a large number of downhill shared electric vehicles departing from parking point B as the starting point, it means that parking point B does not need many high-power shared electric vehicles. Once there is a shortage of shared electric vehicles at parking point A and they need to be dispatched and supplemented, priority will be given to dispatching the nearby shared electric vehicles with the most power to parking point A. When parking point B needs to be dispatched and supplemented, the shared electric vehicles with less power can be dispatched to parking point B. Generate corresponding operation dispatch instructions for the shared electric vehicles that need to be dispatched, and the staff at the dispatch post dispatches the shared electric vehicles after receiving the instructions.

[0109] To this end, vehicles with high battery power are dispatched to parking spots with high uphill demand first, ensuring that users have sufficient power when riding and avoiding vehicles being stranded halfway up the slope due to insufficient battery power. Vehicles with low battery power are dispatched to parking spots with high downhill demand, using gravity to assist in reducing the motor load when going downhill, which can effectively reduce the battery discharge depth, thereby greatly improving the battery cycle life. By matching power and terrain requirements, the vehicle can serve more orders on a single charge, which not only extends the battery life but also improves utilization rate.

[0110] In summary, the present invention collects historical data according to the operating areas divided by shared electric vehicles, which can effectively avoid the influence of road conditions on historical data of shared electric vehicles in other areas. It uses historical data to build a model to predict energy consumption. At the same time, it introduces the slope of the terrain and road conditions to accurately quantify the impact of the terrain on battery energy consumption. It monitors the energy consumption of shared electric vehicles at all times, identifies abnormal energy consumption, and discovers hidden battery aging or damage in advance, such as increased internal resistance and capacity decay. It can then promptly maintain the battery to avoid continuous damage that leads to eventual scrapping, greatly reducing losses.

[0111] When a shared electric vehicle breaks down, the system can first identify the faults discovered by users during use and, based on the feedback, determine whether the fault is caused by a battery problem based on whether the shared electric vehicle's energy consumption is abnormal. This helps staff to carry out an efficient repair of the fault. It can also identify vehicles that have not been used for a long time and promptly recall them for repair.

[0112] At the same time, the average slope in the itinerary can be used to extract the shared electric vehicles that are most used uphill or downhill. When dispatching vehicles, shared electric vehicles with high battery power will be dispatched to parking spots with high uphill demand, and low battery power will be dispatched to parking spots with high downhill demand. Through reasonable allocation, the number of orders served by the vehicle on a single charge can be greatly increased, and the battery life can be effectively extended.

[0113] The above describes in detail an embodiment corresponding to an intelligent working condition monitoring and feedback method. On this basis, the present invention also discloses an intelligent working condition monitoring and feedback system and a storage medium corresponding to the above method.

[0114] An intelligent working condition monitoring and feedback system, comprising:

[0115] memory for storing computer programs;

[0116] A processor is used to execute the computer program, and when the computer program is executed by the processor, it can implement the relevant steps of an intelligent working condition supervision and feedback method disclosed in any of the aforementioned embodiments.

[0117] The processor may include one or more processing cores, such as a core processor, a core processor, etc. The processor may be implemented in at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor may also include a main processor and a coprocessor. The main processor is used to process data in the awake state, also known as the central processing unit (CPU); the coprocessor is a low-power processor used to process data in the standby state.

[0118] In some embodiments, the processor may include an integrated graphics processing unit (GPU) that is responsible for rendering and drawing the content displayed on the display screen. In some embodiments, the processor may also include an artificial intelligence (AI) processor that is responsible for processing machine learning-related computing operations.

[0119] The memory may include one or more readable storage media, which may be non-transitory. The memory may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory is used to store at least the following computer program, wherein, after the computer program is loaded and executed by the processor, it can implement the relevant steps in an intelligent working condition supervision feedback method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory may also include an operating system and data, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system may be Windows. The data may include but is not limited to the data involved in the above method.

[0120] In addition, the functional modules in the various embodiments of the present invention can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in the various embodiments of the present invention.

[0121] To this end, an embodiment of the present invention further provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of an intelligent working condition monitoring feedback method are implemented.

[0122] The readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media that can store program codes.

[0123] The computer program contained in the readable storage medium provided in this embodiment can implement the steps of the intelligent working condition supervision and feedback method described above when executed by the processor, and the effect is the same as above.

[0124] The above is a detailed introduction to an intelligent working condition monitoring feedback method, system and storage medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the devices, equipment and readable storage media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, the present invention can also be improved and modified in several ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0125] The above description is merely a specific embodiment of the invention, but the scope of protection of the invention is not limited thereto. Any changes or substitutions that are not conceived through creative effort should be included within the scope of protection of the invention. Therefore, the scope of protection of the invention should be based on the scope of protection defined in the claims.

Claims

1. An intelligent working condition monitoring and feedback method, characterized by: The following steps are involved: S1: Establish an evaluation model. Collect historical driving data of shared electric vehicles in each area according to the operating areas of shared electric vehicles. Calculate the average slope corresponding to each trip based on the driving data of shared electric vehicles in each trip. Introduce the influence coefficient of average slope on energy consumption to establish an energy consumption evaluation model for each trip of shared electric vehicles. S2: Driving data evaluation. After each trip of the shared electric vehicle, the driving data of the corresponding trip is transmitted to the energy consumption evaluation model and the corresponding evaluated energy consumption data is output. A dynamic energy consumption baseline is established to grade the actual energy consumption data. At the same time, the fault feedback of the user in each trip is collected. The terminal system generates a working condition instruction with a safety level based on the fault feedback and the energy consumption level of the corresponding trip. The method for generating the working condition instruction includes popping up a fault feedback window on the user's mobile terminal interface after each trip, and the user inputs the corresponding fault problem and uploads it to the terminal system. The backend customer service staff assigns the corresponding safety level according to the fault description of the feedback. The terminal system generates a working condition instruction with a safety level based on the fault description of the feedback, and at the same time combines the energy consumption level of the corresponding trip to judge Whether the fault reported by the shared electric vehicle is a battery problem, the operating condition instructions belonging to the battery problem are given an electric loss label, and at the same time, the driving data of several consecutive trips of each shared electric vehicle are regularly extracted, the driving data are analyzed and corresponding dispatch instructions are generated. The dispatch instructions include maintenance dispatch instructions and operation dispatch instructions. The method for generating the maintenance dispatch instructions includes extracting at least three last trip orders. If three or more consecutive actual energy consumptions exceed the assessed energy consumption by more than 20%, a maintenance dispatch instruction is directly generated. The method for generating the operation dispatch instruction specifically includes the following steps: setting an average slope threshold P, extracting trip orders with an average slope greater than P and marking them as uphill trip orders, and extracting trip orders with an average slope less than -P and marking them as downhill trip orders; Analyze and compare the travel routes of uphill and downhill itineraries. First, eliminate itineraries with similar travel routes. Then, classify the uphill and downhill itineraries based on their departure points and extract the departure points with the most trips. When there is a shortage of shared electric vehicles at the extracted starting point and they need to be dispatched, the shared electric vehicle with the most power is preferentially dispatched to the starting point corresponding to the extracted uphill itinerary, and the shared electric vehicle with the least power is dispatched to the starting point corresponding to the extracted downhill itinerary. At the same time, the corresponding electric vehicle number and position are obtained to generate the corresponding operation dispatch instruction; S3: Dispatching execution layer. The terminal system sends the working condition instructions and scheduling instructions to the nearest staff according to the location of the corresponding shared electric vehicle. After receiving the instructions, the staff will perform corresponding processing on the shared electric vehicle and upload the processing results at the same time.

2. The intelligent working condition monitoring and feedback method according to claim 1, characterized in that: The method for establishing an energy consumption evaluation model for a shared electric vehicle during each driving operation specifically includes the following steps: S101: Extracting motion data corresponding to each trip from the historical driving data, the motion data including travel distance, average speed, load, and acceleration, calculating the average slope for the corresponding travel distance using acceleration, and calculating the corresponding energy consumption value based on the battery data corresponding to each trip; S102: Import a linear regression model, set X = [travel distance, average speed, load, average slope] as the input feature matrix of the model, and Y = [energy consumption value] as the target variable, train and build the relationship between the input features and the energy consumption value, and predict the energy consumption of each shared electric vehicle trip.

3. The intelligent working condition monitoring and feedback method according to claim 2, characterized in that: The method for establishing a dynamic energy consumption baseline to categorize actual energy consumption data specifically includes comparing the actual energy consumption data corresponding to each trip with the output estimated energy consumption data, and categorizing and marking the intervals based on the percentage of actual energy consumption exceeding the estimated energy consumption. The categorized intervals include: The proportion in the range of (0,10%] is set as the first-level interval; The proportion in the range of (10%, 20%] is set as the secondary range; The proportion greater than 20% is set as the third-level interval.

4. The intelligent working condition monitoring and feedback method according to claim 3 is characterized in that: The method for generating the maintenance scheduling instruction also includes extracting the completion time of the last itinerary. If no new itinerary appears after the set time node and the position of the shared electric vehicle has not moved, a maintenance scheduling instruction is directly generated.

5. The intelligent working condition monitoring and feedback method according to claim 4 is characterized in that: After receiving the working condition instruction, the staff will handle the shared electric vehicle in the following steps: Based on the safety level of the working condition instructions, high-level working condition instructions are processed first. First, the corresponding fault point is found according to the fault description, and the accuracy of the fault description reported by the user is fed back and photos are taken. For the working condition instructions assigned with power loss labels, the battery is directly replaced. The fault point is re-inspected and repaired, and photos are taken. Finally, the photos are uploaded and it is confirmed that the working condition processing is completed.

6. The intelligent working condition monitoring and feedback method according to claim 5, characterized in that: The processing of the maintenance scheduling instruction includes transferring the shared electric vehicle assigned the maintenance scheduling instruction to a maintenance point by the staff for full inspection and maintenance of the shared electric vehicle. The priority of the maintenance scheduling instruction is higher than the working condition instruction.

7. An intelligent working condition monitoring and feedback system, characterized by: include memory for storing computer programs; A processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the intelligent working condition supervision feedback method as described in any one of claims 1 to 6 are implemented.

8. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of an intelligent working condition monitoring feedback method as described in any one of claims 1 to 6 are implemented.

Images