High-speed rail seat cover intelligent management method and system based on multi-terminal interconnection

Abstract

The present invention provides a method and system for intelligent management of high-speed rail seat covers based on multi-terminal interconnection, wherein the method includes: in response to the operating state being the passenger transport state, calling the passive detection strategy to configure the strategy for the high-speed rail end, and passively acquiring the management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy; in response to the operating state being the out-of-service state, calling the active detection strategy to configure the strategy for the high-speed rail end, and controlling the drone to collect data for each high-speed rail seat cover respectively based on the active detection strategy, and actively acquiring the management attributes of each high-speed rail seat cover based on the collection result; in response to the management attribute of any high-speed rail seat cover being the replacement attribute, calling the digital twin data corresponding to the high-speed rail end, and marking the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space constructed based on the digital twin data. The present invention at least improves the management efficiency.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a high-speed railway seat cover intelligent management method and system based on multi-terminal interconnection. Background Art

[0002] In the high-speed railway service industry, the cleanliness and damage degree of high-speed rail seat covers are important indicators for measuring passenger comfort and train maintenance management. Traditional high-speed rail seat cover inspection relies on manual visual inspection, which is not only inefficient and easily affected by subjective factors, but also difficult to cope with the inspection needs brought about by large-scale train formations and high-frequency operations.

[0003] With the rapid development of automation and intelligent technology, how to realize automatic detection of the cleanliness and damage degree of high-speed rail seat covers has become a technical problem that needs to be solved urgently in order to improve the service quality of high-speed rail and reduce operating costs. Summary of the invention

[0004] Based on the above problems, the present invention is proposed to provide a high-speed railway seat cover intelligent management method and system based on multi-terminal interconnection to overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present invention, a high-speed railway seat cover intelligent management method based on multi-terminal interconnection is provided, comprising the following steps:

[0006] The management method comprises:

[0007] Acquire the operation status corresponding to the high-speed rail terminal, wherein the operation status includes passenger transport status and suspension status;

[0008] In response to the running state being a passenger transport state, calling a passive detection strategy to configure the strategy for the high-speed rail end, and passively acquiring management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy;

[0009] In response to the running state being the outage state, calling the active detection strategy to configure the strategy for the high-speed rail end, and controlling the drone to collect data for each high-speed rail seat cover based on the active detection strategy, and actively acquiring the management attributes of each high-speed rail seat cover based on the collection results;

[0010] In response to the management attribute of any high-speed rail seat cover being a replacement attribute, the digital twin data corresponding to the high-speed rail end is retrieved, and the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover is model marked in the high-speed rail twin space constructed based on the digital twin data.

[0011] Optionally, in the method according to the present invention, passively acquiring management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy includes:

[0012] Acquire each gravity detection value output by each gravity detection unit pre-set at each high-speed rail seat corresponding to the high-speed rail end, and compare each gravity detection value with the retrieved gravity threshold;

[0013] In response to any gravity detection value being greater than the gravity threshold, aggregating the high-speed rail seats corresponding to the gravity detection value into a seat detection group;

[0014] Establishing a data transmission channel between each touch interaction unit that has a communication connection relationship with each high-speed rail seat located in the seat detection group, and in response to obtaining a seat cover replacement signal output by any touch indication unit based on the data transmission channel, obtaining a signal duration corresponding to the seat cover replacement signal;

[0015] The signal duration is compared with a retrieved time threshold, and in response to the signal duration being greater than or equal to the time threshold, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat corresponding to the touch indication unit is determined as a replacement attribute.

[0016] Optionally, in the method according to the present invention, based on the active detection strategy, the drone is controlled to collect images of each high-speed rail seat cover respectively, and the management attributes of each high-speed rail seat cover are actively acquired based on the collection results, including:

[0017] A preset main route is established based on the extension direction of any high-speed rail carriage at the corresponding high-speed rail end, the drone is controlled to fly along the preset main route, and a first tag detection unit and a second tag detection unit pre-installed on both sides of the drone are triggered to perform tag detection on the first carriage space and the second carriage space located on both sides of the preset main route respectively;

[0018] In response to any positioning unit detecting a seat tag located in a corresponding compartment space, obtaining each seat number included in the seat tag and the number of seats corresponding to each seat number;

[0019] Control the drone to move toward the seat tag to a preset detection position, trigger an image acquisition unit pre-installed at the bottom of the drone to acquire an image, and perform image segmentation corresponding to the number of seats on the acquired seat acquisition image to obtain seat sub-images corresponding to different high-speed rail seats;

[0020] Based on each seat sub-image, each high-speed rail seat is evaluated for the corresponding stain dimension, and each stain evaluation value corresponding to each high-speed rail seat is obtained;

[0021] Retrieving the seat usage data corresponding to each high-speed rail seat based on each seat number, and performing seat evaluation of the corresponding frequency dimension on each high-speed rail seat based on each seat usage data, to obtain each frequency evaluation value corresponding to each high-speed rail seat;

[0022] The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are respectively multiplied by the retrieved first update weight and the second update weight to obtain an updated stain evaluation value and a frequency evaluation value;

[0023] The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are summed and calculated, and in response to the obtained cleaning evaluation value being greater than or equal to the retrieved benchmark evaluation value, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat is determined as a replacement attribute.

[0024] Optionally, in the method according to the present invention, the method further comprises:

[0025] Obtaining an actual evaluation value uploaded by the cleaning end based on the high-speed rail seat cover, and comparing the cleaning evaluation value corresponding to the high-speed rail seat cover with the actual evaluation value;

[0026] When the actual evaluation value is greater than the clean evaluation value, increasing training is performed on the first update weight and the second update weight respectively;

[0027] When the actual evaluation value is less than the clean evaluation value, the first update weight and the second update weight are respectively trained to be reduced;

[0028] The first updated weight and the second updated weight after training are obtained by the following formula:

[0029] ;

[0030] in, Update weights for the first Increase the number of training sessions. Update weights for the first The training constant value of Update weights for the first Reduce the number of training sessions. is the first updated weight after training, Update weights for the second Increase the number of training sessions. Update weights for the second The training constant value of Update weights for the second Reduce the number of training sessions. Update weights for the second time after training.

[0031] Optionally, in the method according to the present invention, the drone is controlled to move toward the seat tag to a preset detection position, an image acquisition unit pre-installed at the bottom of the drone is triggered to perform image acquisition, and the obtained seat acquisition image is subjected to image segmentation corresponding to the number of seats to obtain seat sub-images corresponding to different high-speed rail seats, including:

[0032] Controlling the drone to move toward the seat tag and continuously acquiring the captured content in a capture window corresponding to an image capture unit pre-installed at the bottom of the drone;

[0033] When the collected content includes at least one seat pixel point corresponding to a high-speed rail seat, and any seat pixel point is not located in the window outline of the collection window, the drone is controlled to hover at the current detection position, and seat collection frames having the same number as the number of seats arranged in a straight line are generated in the collection window;

[0034] Comparing all the seat pixel points included in the collected content with the frame outline corresponding to each seat collection frame based on relative positions;

[0035] In response to any seat pixel point being located at the frame outline of any seat acquisition frame, controlling the drone to adjust the position based on the current detection position, and determining the drone after the position adjustment to move to a preset detection position;

[0036] The image acquisition unit is triggered to perform image acquisition, and image segmentation is performed based on each seat acquisition frame located in the acquisition window to obtain each seat sub-image corresponding to each different high-speed rail seat.

[0037] Optionally, in the method according to the present invention, each high-speed rail seat is evaluated for a corresponding stain dimension based on each seat sub-image to obtain each stain evaluation value corresponding to each high-speed rail seat, including:

[0038] Binarizing each seat sub-image to obtain binarized images corresponding to each seat sub-image, wherein any of the binarized images includes seat pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value;

[0039] Performing pixel connection based on adjacent position relationship on each seat pixel point located in the same binary image to obtain a seat area located in the binary image;

[0040] Performing pixel connection based on adjacent position relationship on each noise pixel point located in the same binary image to obtain each noise region located in the binary image;

[0041] Perform coordinate processing on each binary image respectively, and obtain the seat area located in the same binary image, the seat coordinate interval corresponding to each noise area, and each noise coordinate interval;

[0042] Comparing the coordinates of each noise coordinate area with the seat coordinate interval one by one, and in response to any noise coordinate interval being surrounded by the seat coordinate interval, aggregating the corresponding noise area into a stain area group;

[0043] A seat evaluation of the corresponding stain dimension is performed on each high-speed rail seat based on all noise areas in the same stain area group, and each stain evaluation value corresponding to each high-speed rail seat is obtained.

[0044] Optionally, in the method according to the present invention, seat evaluation of corresponding stain dimensions is performed on each high-speed rail seat based on all noise areas in the same stain area group, to obtain stain evaluation values ​​corresponding to each high-speed rail seat, including:

[0045] Acquire the region number of each noise region in the same stain region group, and obtain the quantity coefficient by multiplying the region number by the retrieved quantity normalization value;

[0046] Determine the proportion of each noise area and the seat area in the same stain area group, and calculate the proportion coefficient based on the product of the obtained stain proportion and the retrieved normalized value of the proportion;

[0047] In each seat sub-image corresponding to each stain area group, image areas corresponding to each noise area are obtained respectively, and pixels are extracted from each image area to obtain image pixel points constituting each image area;

[0048] Calculate the mean of each image pixel value corresponding to each image pixel point, and calculate the difference between the obtained pixel mean and the first pixel value to obtain a pixel difference;

[0049] The pixel difference value is multiplied by the retrieved pixel normalization value to obtain a color difference coefficient;

[0050] The quantity coefficient, proportion coefficient and color difference coefficient corresponding to the same high-speed rail seat are integrated and calculated to obtain the stain evaluation values ​​corresponding to each high-speed rail seat.

[0051] Optionally, in the method according to the present invention, seat usage data corresponding to each high-speed rail seat is retrieved based on each seat number, and seat evaluation of each high-speed rail seat in a corresponding frequency dimension is performed based on each seat usage data to obtain frequency evaluation values ​​corresponding to each high-speed rail seat, including:

[0052] Retrieving a historical database, and acquiring seat usage data corresponding to each seat number based on the historical database, wherein the seat usage data includes a carrying quantity and a carrying duration;

[0053] Retrieving a quantity comparison table and a duration comparison table, wherein the quantity comparison table includes different quantity intervals and different first frequency values ​​corresponding to the different quantity intervals, and the duration comparison table includes different duration intervals and different second frequency values ​​corresponding to the different duration intervals;

[0054] The quantity comparison table and the duration comparison table are traversed respectively, and based on the quantity interval and the duration interval respectively including the bearer quantity and the bearer duration, a first frequency value corresponding to the bearer quantity and a second frequency value corresponding to the bearer quantity are obtained;

[0055] The first frequency value and the second frequency value corresponding to the same seat number are summed up to obtain the frequency evaluation values ​​corresponding to each high-speed rail seat.

[0056] Optionally, in the method according to the present invention, in response to the management attribute of any high-speed rail seat cover being a replacement attribute, retrieving digital twin data corresponding to the high-speed rail end, and marking a high-speed rail model corresponding to a high-speed rail seat covered by the high-speed rail seat cover in a high-speed rail twin space constructed based on the digital twin data, including:

[0057] In response to the management attribute of any high-speed rail seat cover being a replacement attribute, controlling the drone to send a marking signal carrying a seat number corresponding to the high-speed rail seat cover;

[0058] Acquire the digital twin data corresponding to the high-speed rail end uploaded by the management end based on the marking signal, and construct the high-speed rail twin space based on the digital twin data;

[0059] Determine a seat model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space based on the seat number, and disassemble the seat number to obtain a compartment sub-number, a row sub-number, and a seat sub-number;

[0060] Retrieving the first number color, the second number color and the third number color corresponding to the compartment sub-number, the row sub-number and the position sub-number respectively, and determining the first number color, the second number color and the third number color as a preset color group;

[0061] The seat model is flashed with a first numbered color, a second numbered color, and a third numbered color in a preset color group.

[0062] According to another aspect of the present invention, a high-speed rail seat cover intelligent management system based on multi-terminal interconnection is provided, comprising:

[0063] A status acquisition module is configured to acquire an operation status corresponding to the high-speed rail terminal, wherein the operation status includes a passenger transport status and a suspension status;

[0064] A passive detection module is configured to call a passive detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being a passenger transport state, and passively acquire management attributes of each high-speed rail seat cover corresponding to the high-speed rail terminal based on the passive detection strategy;

[0065] The active detection module is configured to call the active detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being the out-of-service state, and control the drone to collect data from each high-speed rail seat cover based on the active detection strategy, and actively obtain the management attributes of each high-speed rail seat cover based on the collection results;

[0066] The model marking module is configured to, in response to the management attribute of any high-speed rail seat cover being a replacement attribute, retrieve the digital twin data corresponding to the high-speed rail end, and model mark the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space constructed based on the digital twin data.

[0067] According to the scheme of the present invention, the present invention realizes accurate response to the management of high-speed rail seat covers under different states by acquiring the operating status of the high-speed rail end in real time. In the passenger transport state, a passive detection strategy is adopted to effectively reduce unnecessary resource consumption, while ensuring the timely acquisition of seat cover management information and improving management efficiency. When the high-speed rail is in a state of suspension, it switches to an active detection strategy and uses drones for efficient data collection. This innovative measure not only greatly improves the accuracy and comprehensiveness of data collection, but also significantly shortens the cycle of seat cover inspection and maintenance, and enhances the sanitary quality and passenger experience of high-speed rail services; more importantly, the method introduces digital twin technology. When a seat cover that needs to be replaced is detected, the digital twin data of the corresponding high-speed rail end can be quickly retrieved and the model is marked in the high-speed rail twin space. This step not only facilitates the management personnel to intuitively and quickly locate the problem seat, but also provides precise guidance for subsequent maintenance or replacement work, effectively reducing the cost and time of manual investigation, and improving the overall operation efficiency; the present invention comprehensively optimizes the management process of high-speed rail seat covers through intelligent and precise management means, and sets a new benchmark for the modern management of high-speed rail operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A flowchart of a high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to an embodiment of the present invention is shown;

[0069] Figure 2 A schematic diagram of a scene in which a drone in this embodiment collects images of a high-speed rail seat is shown;

[0070] Figure 3 A schematic diagram of a collection window corresponding to a drone in this embodiment is shown;

[0071] Figure 4 A structural block diagram of a high-speed rail seat cover intelligent management system based on multi-terminal interconnection according to another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0072] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0073] In order to solve the problems existing in the above-mentioned prior art, the inventor proposes the solution of the present invention. One embodiment of the present invention provides a high-speed rail seat cover intelligent management method based on multi-terminal interconnection, which can be executed in a computing device, wherein the computing device can be understood as a terminal with data processing function, such as a mobile phone or a computer.

[0074] Figure 1 A flow chart of a high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to an embodiment of the present invention is shown, and the method is suitable for execution in a computing device.

[0075] like Figure 1 As shown, the high-speed rail seat cover intelligent management method based on multi-terminal interconnection proposed in this embodiment starts with step S101, wherein S101 includes the following contents:

[0076] Obtain the operating status corresponding to the high-speed rail end, wherein the operating status includes passenger status and suspension status.

[0077] For example, in this embodiment, the management of high-speed rail seat covers can be carried out based on two different application scenarios, namely, the passenger status and the out-of-service status. The passenger status corresponds to the high-speed rail being in passenger operation, and there are passengers on the high-speed rail train; and the out-of-service status corresponds to the high-speed rail train being stopped, and there are no corresponding passengers on the high-speed rail train. Here, the acquisition of the operating status of the high-speed rail end can be determined based on the real-time motion status of the high-speed rail end.

[0078] It should be noted that the above-mentioned high-speed rail terminal can be understood as a terminal device with data processing function that is pre-installed on the high-speed rail train.

[0079] In step S102, the following contents are included:

[0080] In response to the operating state being the passenger transport state, a passive detection strategy is called to configure the strategy for the high-speed rail end, and based on the passive detection strategy, management attributes of each high-speed rail seat cover corresponding to the high-speed rail end are passively acquired.

[0081] For example, in this embodiment, when it is detected that the operating status of the high-speed rail train is the passenger state, the server triggers and executes the following steps: first, the preset passive detection strategy is called up, and this strategy set is specially designed to configure the strategy for the high-speed rail end in the passenger state; then, based on the selected passive detection strategy, the server will perform a passive acquisition operation on the management attributes of each high-speed rail seat cover directly associated with the high-speed rail train where the high-speed rail end is located. Here, "passive acquisition" means that the server does not need to actively trigger or intervene, but automatically collects status information about the high-speed rail seat covers through monitoring, sensing or other non-direct request methods.

[0082] It should be noted that, since the high-speed train is in passenger transport, that is, the high-speed train is carrying corresponding passengers, active detection cannot be performed on the high-speed train seat covers, and the corresponding management attributes need to be passively acquired.

[0083] Furthermore, in this embodiment, the above-mentioned “passively acquiring the management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy” may also include the following steps:

[0084] Acquire each gravity detection value output by each gravity detection unit pre-set at each high-speed rail seat corresponding to the high-speed rail end, and compare each gravity detection value with the retrieved gravity threshold;

[0085] In response to any gravity detection value being greater than the gravity threshold, aggregating the high-speed rail seats corresponding to the gravity detection value into a seat detection group;

[0086] Establishing a data transmission channel between each touch interaction unit that has a communication connection relationship with each high-speed rail seat located in the seat detection group, and in response to obtaining a seat cover replacement signal output by any touch indication unit based on the data transmission channel, obtaining a signal duration corresponding to the seat cover replacement signal;

[0087] The signal duration is compared with a retrieved time threshold, and in response to the signal duration being greater than or equal to the time threshold, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat corresponding to the touch indication unit is determined as a replacement attribute.

[0088] For example, in this embodiment, after the corresponding passive detection strategy is retrieved and the strategy is configured on the high-speed rail end, the corresponding management attributes of all high-speed rail seat covers in the high-speed rail train can be passively acquired based on the following method steps:

[0089] First, the server obtains the gravity detection value output by the gravity detection unit pre-installed on each high-speed rail seat (these seats are located in the high-speed rail train corresponding to the high-speed rail end). These gravity detection units are used to measure the gravity on the high-speed rail seat in real time to determine whether the high-speed rail seat is occupied;

[0090] Next, the server may compare each gravity detection value with a preset gravity threshold, which is used to distinguish whether the high-speed rail seat is occupied by a passenger (i.e., when the gravity detection value exceeds this threshold, it is considered that there is a passenger on the high-speed rail seat); when any gravity detection value is detected to be greater than the gravity threshold, the server may classify the high-speed rail seat corresponding to the gravity detection value into a "seat detection group", which includes all high-speed rail seats currently determined to be occupied by passengers;

[0091] Subsequently, the server establishes a data transmission channel between the touch interaction units that are in communication connection with each high-speed rail seat in the seat detection group, wherein these touch interaction units allow passengers or staff to issue instructions through touch operations, such as requesting to replace the high-speed rail seat cover of the corresponding high-speed rail seat; once the server receives a seat cover replacement signal output by any touch indication unit through the data transmission channel, the system starts to record the duration of the signal, which can be mainly used to verify the validity of the replacement request and avoid misoperation;

[0092] Finally, the server can compare the recorded signal duration with the retrieved time threshold. If the signal duration reaches or exceeds the time threshold, the system considers that this is a valid seat cover replacement request. The server can mark the management attribute of the high-speed rail seat cover attached to the high-speed rail seat that sends the seat cover replacement signal as "replacement attribute" based on this valid seat cover replacement request, which indicates that the high-speed rail seat cover needs to be replaced, thereby triggering the subsequent replacement process.

[0093] It should be noted that, in this embodiment, the above-mentioned touch interaction unit can correspond to a touch button, and each high-speed rail seat can be independently configured with a touch button to perform the corresponding signal sending task; in addition, the above-mentioned gravity threshold and time threshold can be set in advance and stored in the server, and the specific values ​​are not limited in this embodiment.

[0094] In step S103, the following contents are included:

[0095] In response to the operating status being the outage status, the active detection strategy is called to configure the strategy for the high-speed rail end, and based on the active detection strategy, the drone is controlled to collect data for each high-speed rail seat cover respectively, and the management attributes of each high-speed rail seat cover are actively acquired based on the collection results.

[0096] For example, in this embodiment, when the server detects that the operating status of the high-speed rail train is a suspended state, that is, the high-speed rail is not in a normal operating period or has completed all operating tasks for the day and is in a non-service state, the server will automatically trigger and execute the configuration process of the active detection strategy, and based on the configured active detection strategy, instruct and control the drone equipment to start and execute data collection tasks. It should be noted that these drones are programmed or configured to be able to autonomously navigate to each high-speed rail carriage included in the high-speed rail train, and are equipped with appropriate sensors or imaging devices to perform corresponding data collection on the high-speed rail seat covers on each high-speed rail seat included in each high-speed rail carriage, so as to realize the active acquisition of the management attributes of each high-speed rail seat cover.

[0097] It should be noted that since the high-speed train is out of service, that is, the high-speed train has no corresponding passengers on board, in order to improve the efficiency and accuracy of high-speed rail seat cover management and reduce the cost and time consumption of manual inspection, active drone-based inspection can be performed on the high-speed rail seat cover to obtain the corresponding management attributes.

[0098] Furthermore, in this embodiment, the above-mentioned “controlling the drone to collect images of each high-speed rail seat cover based on the active detection strategy, and actively acquiring the management attributes of each high-speed rail seat cover based on the collection results” may also include the following steps:

[0099] A preset main route is established based on the extension direction of any high-speed rail carriage at the corresponding high-speed rail end, the drone is controlled to fly along the preset main route, and a first tag detection unit and a second tag detection unit pre-installed on both sides of the drone are triggered to perform tag detection on the first carriage space and the second carriage space located on both sides of the preset main route respectively;

[0100] In response to any positioning unit detecting a seat tag located in a corresponding compartment space, obtaining each seat number included in the seat tag and the number of seats corresponding to each seat number;

[0101] Control the drone to move toward the seat tag to a preset detection position, trigger an image acquisition unit pre-installed at the bottom of the drone to acquire an image, and perform image segmentation corresponding to the number of seats on the acquired seat acquisition image to obtain seat sub-images corresponding to different high-speed rail seats;

[0102] Based on each seat sub-image, each high-speed rail seat is evaluated for the corresponding stain dimension, and each stain evaluation value corresponding to each high-speed rail seat is obtained;

[0103] Retrieving the seat usage data corresponding to each high-speed rail seat based on each seat number, and performing seat evaluation of the corresponding frequency dimension on each high-speed rail seat based on each seat usage data, to obtain each frequency evaluation value corresponding to each high-speed rail seat;

[0104] The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are respectively multiplied by the retrieved first update weight and the second update weight to obtain an updated stain evaluation value and a frequency evaluation value;

[0105] The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are summed and calculated, and in response to the obtained cleaning evaluation value being greater than or equal to the retrieved benchmark evaluation value, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat is determined as a replacement attribute.

[0106] For example, in this embodiment, the above-mentioned active acquisition of the management attributes of the high-speed rail seat cover by the drone may specifically include the following method steps:

[0107] First, for any high-speed rail carriage of the high-speed rail train corresponding to the high-speed rail end, a preset main route can be set according to the extension direction of the high-speed rail carriage. Then, the drone is controlled to fly along the preset main route, and the first label detection unit and the second label detection unit installed on the left and right sides of the drone are activated and triggered to scan and identify the seat labels in the first carriage space and the second carriage space on the left and right sides of the preset main route respectively; when any label detection unit successfully detects the seat label in the carriage space, the server will automatically capture and parse the seat number contained in the seat label and the number of seats corresponding to each number, wherein it can be explained that the seat number included in the seat label corresponding to each carriage space and the number of seats corresponding to each number refer to the seat information corresponding to the carriage space, for example, when the seat number of the seat label corresponding to any carriage space is 12A, 12B, 12C, and the corresponding number of seats is 3, it indicates that the carriage space includes 3 high-speed rail seats, and the seat numbers of the 3 high-speed rail seats are 12A, 12B, 12C, respectively, wherein 12 can be understood as the carriage order corresponding to the high-speed rail seat;

[0108] Next, the server controls the drone to move to a preset detection position toward the identified seat tag, and activates the image acquisition unit installed at the bottom of the drone to acquire images of the high-speed rail seats, and performs segmentation processing on the acquired seat acquisition images to cut them into multiple seat sub-images according to the number of seats, wherein each seat sub-image corresponds to a high-speed rail seat, wherein, for example Figure 2 As shown, Figure 2 The drone in the system flies to the corresponding preset detection position and collects images of the corresponding high-speed rail seats. Figure 2 The corresponding high-speed rail seats include two;

[0109] Next, it should be noted that the replacement conditions for the high-speed rail seat cover that needs to be replaced mainly include two points: 1. The corresponding stain area is generated, such as spilling tea or other liquids; 2. The high-speed rail seat cover is used frequently, which causes more bacteria to be generated on the high-speed rail seat cover. Therefore, the server can perform seat evaluation in the stain dimension based on each seat sub-image, and generate a stain evaluation value corresponding to each high-speed rail seat; at the same time, the seat usage data of each high-speed rail seat is retrieved from the server according to the seat number, and the high-speed rail seat is evaluated in the frequency dimension based on the seat usage data, and then the frequency evaluation value corresponding to each high-speed rail seat is obtained, so as to complete the evaluation operation for two different dimensions;

[0110] Furthermore, the server may retrieve the first update weight and the second update weight to perform weighted processing on the stain evaluation value and the frequency evaluation value, respectively, so as to obtain the updated stain evaluation value and the frequency evaluation value. It should be noted that the first update weight and the second update weight may be preset and adjusted according to specific needs or operation strategies;

[0111] Finally, by adding the updated stain evaluation value and frequency evaluation value of the same high-speed rail seat, the cleanliness evaluation value corresponding to the high-speed rail seat can be obtained. If the cleanliness evaluation value is greater than or equal to the retrieved benchmark evaluation value, the server can mark the management attribute of the high-speed rail seat cover on which the high-speed rail seat is mounted as a replacement attribute, prompting the operator or the system to automatically replace the high-speed rail seat cover.

[0112] Through the above method steps, this embodiment not only realizes the rapid and accurate evaluation of the status of high-speed rail seats, but also greatly improves the efficiency and accuracy of seat management by introducing drone inspection technology, providing passengers with a cleaner and more comfortable riding environment.

[0113] Here, from the above content, it can be seen that the cleanliness evaluation value is obtained by summing the stain evaluation value and the frequency evaluation value, and the updated stain evaluation value and the frequency evaluation value are obtained by multiplying the stain evaluation value and the frequency evaluation value before the update with the retrieved first update weight and the second update weight respectively. Based on this, since the cleanliness evaluation value determined by numerical calculation may deviate from the actual situation to a certain extent, in order to improve the corresponding determination accuracy, the corresponding weight values ​​can be updated and trained in real time to realize the process of updating and iterating each weight value, thereby continuously improving the corresponding determination accuracy.

[0114] Here, the update iteration of each weight can be achieved through the following steps:

[0115] Obtaining an actual evaluation value uploaded by the cleaning end based on the high-speed rail seat cover, and comparing the cleaning evaluation value corresponding to the high-speed rail seat cover with the actual evaluation value;

[0116] When the actual evaluation value is greater than the clean evaluation value, increasing training is performed on the first update weight and the second update weight respectively;

[0117] When the actual evaluation value is less than the clean evaluation value, the first update weight and the second update weight are respectively trained to be reduced;

[0118] The first updated weight and the second updated weight after training are obtained by the following formula:

[0119] ;

[0120] in, Update weights for the first Increase the number of training sessions. Update weights for the first The training constant value of Update weights for the first Reduce the number of training sessions. is the first updated weight after training, Update weights for the second Increase the number of training sessions. Update weights for the second The training constant value of Update weights for the second Reduce the number of training sessions. Update weights for the second time after training.

[0121] It should be noted that the above-mentioned cleaning end can be understood as the terminal used by the cleaning staff who replace the high-speed rail seat covers on the high-speed rail train. When replacing the high-speed rail seat covers, the cleaning staff can simultaneously perform manual evaluation based on the actual situation of the high-speed rail seat covers, and upload the determined actual evaluation value to the server to iteratively update the corresponding first update weight and the second update weight to improve the corresponding determination accuracy.

[0122] Furthermore, in this embodiment, the above-mentioned "controlling the drone to move toward the seat tag to a preset detection position, triggering the image acquisition unit pre-installed at the bottom of the drone to perform image acquisition, and performing image segmentation corresponding to the number of seats on the acquired seat acquisition image to obtain each seat sub-image corresponding to each different high-speed rail seat" may also include the following steps:

[0123] Controlling the drone to move toward the seat tag and continuously acquiring the captured content in a capture window corresponding to an image capture unit pre-installed at the bottom of the drone;

[0124] When the collected content includes at least one seat pixel point corresponding to a high-speed rail seat, and any seat pixel point is not located in the window outline of the collection window, the drone is controlled to hover at the current detection position, and seat collection frames having the same number as the number of seats arranged in a straight line are generated in the collection window;

[0125] Comparing all the seat pixel points included in the collected content with the frame outline corresponding to each seat collection frame based on relative positions;

[0126] In response to any seat pixel point being located at the frame outline of any seat acquisition frame, controlling the drone to adjust the position based on the current detection position, and determining the drone after the position adjustment to move to a preset detection position;

[0127] The image acquisition unit is triggered to perform image acquisition, and image segmentation is performed based on each seat acquisition frame located in the acquisition window to obtain each seat sub-image corresponding to each different high-speed rail seat.

[0128] For example, in this embodiment, controlling the drone to collect images of high-speed rail seat covers may specifically include the following method steps:

[0129] First, the server can control the drone to move toward the identified seat tag, and obtain the image content in its acquisition window in real time through the image acquisition unit pre-installed at the bottom of the drone. This acquisition window serves as the main area for image capture, continuously monitoring and recording all dynamic changes in its field of view; when the acquisition content of the image acquisition unit contains at least one seat pixel point corresponding to a high-speed rail seat, and any of these seat pixel points does not touch the edge of the window contour of the acquisition window, it indicates that the corresponding high-speed rail seat is completely in the acquisition window, and the server can control the drone to hover at the current position; and the server will automatically generate a seat acquisition frame corresponding to the same number of seats in the acquisition window according to the number of seats identified above, and these acquisition frames are arranged in a straight line to facilitate the subsequent independent image capture of a single high-speed rail seat. For example, when the number of seats is 3, the corresponding seat acquisition frame is also 3, and when the number of seats is 2, the corresponding seat acquisition frame is also 2. It can be explained that in common high-speed rail trains, the two compartments in the same compartment row include 3 and 2 high-speed rail seats respectively;

[0130] Next, the server will compare all the seat pixels contained in the acquisition window with the frame outline of each seat acquisition frame. This comparison is based on the relative position information of the pixels. This step is to ensure that each seat pixel corresponding to each independent high-speed rail seat can accurately correspond to a specific seat acquisition frame, providing an accurate positioning basis for subsequent image cutting; once the server detects that any seat pixel is located on the frame outline of any seat acquisition frame, it means that the high-speed rail seat corresponding to the seat pixel does not correspond to a specific seat acquisition frame. At this time, the system will control the drone to make fine adjustments based on the current detection position to ensure that each high-speed rail seat can be included in the specific seat acquisition frame. After the corresponding position adjustment, the drone is confirmed to have moved from the current detection position to the preset detection position;

[0131] Finally, after the drone stabilizes at the preset detection position, the server can trigger the image acquisition unit to acquire images. Subsequently, the image of each seat acquisition frame located in the acquisition window is cut to obtain a seat sub-image corresponding to each different high-speed rail seat.

[0132] Through the above method, this embodiment not only realizes the automatic collection of high-speed rail seats by drones, but also ensures the high definition and independence of each seat sub-image through intelligent recognition and positioning technology, providing a solid foundation for the subsequent analysis and evaluation of the management attributes of high-speed rail seat covers.

[0133] For example, Figure 3 As shown, Figure 3The corresponding drone collection window is included. It can be seen that the collection window is based on the number of seats on the high-speed rail ( Figure 3 includes two high-speed rail seats) generates seat collection frames corresponding to the number of seats, and each seat collection frame includes a high-speed rail seat; it should be noted that since the high-speed rail seat may include a seat body and corresponding seat handles, in this embodiment, the image collection of the high-speed rail seat is mainly based on the seat body. Therefore, the corresponding seat collection frame only needs to include the entire seat body in its entirety.

[0134] Furthermore, in this embodiment, the above-mentioned "performing seat evaluations of the corresponding stain dimensions for each high-speed rail seat based on each seat sub-image to obtain stain evaluation values ​​corresponding to each high-speed rail seat" may also include the following steps:

[0135] Binarizing each seat sub-image to obtain binarized images corresponding to each seat sub-image, wherein any of the binarized images includes seat pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value;

[0136] Performing pixel connection based on adjacent position relationship on each seat pixel point located in the same binary image to obtain a seat area located in the binary image;

[0137] Performing pixel connection based on adjacent position relationship on each noise pixel point located in the same binary image to obtain each noise region located in the binary image;

[0138] Perform coordinate processing on each binary image respectively, and obtain the seat area located in the same binary image, the seat coordinate interval corresponding to each noise area, and each noise coordinate interval;

[0139] Comparing the coordinates of each noise coordinate area with the seat coordinate interval one by one, and in response to any noise coordinate interval being surrounded by the seat coordinate interval, aggregating the corresponding noise area into a stain area group;

[0140] A seat evaluation of the corresponding stain dimension is performed on each high-speed rail seat based on all noise areas in the same stain area group, and each stain evaluation value corresponding to each high-speed rail seat is obtained.

[0141] For example, in this embodiment, the seat evaluation of the high-speed rail seat corresponding to the stain dimension can be implemented based on the following method steps:

[0142] First, the server can perform binarization processing on each seat sub-image collected to generate binarized images corresponding to each seat sub-image. In these binarized images, seat pixels are assigned a first pixel value (such as white, with a pixel value of 255), while noise pixels (including abnormal pixels caused by stains, light changes, etc.) are assigned a second pixel value (such as black, with a pixel value of 0);

[0143] Next, based on the adjacent position relationship, the seat pixels in the same binary image can be connected pixel by pixel to form seat regions; similarly, the noise pixels can be connected pixel by pixel to form noise regions;

[0144] Next, coordinate processing is performed on each binary image to obtain the specific positions of the seat area and each noise area in the image, that is, the seat coordinate interval and each noise coordinate interval;

[0145] Then, the coordinates of each noise coordinate area are compared with the seat coordinate interval one by one. If a noise coordinate interval is completely within the seat coordinate interval, that is, surrounded by the seat coordinate interval, the noise area can be regarded as a stain area and summarized into the stain area group;

[0146] Finally, based on all the noise areas (i.e., stain areas) in the same stain area group, a quantitative evaluation of the stain dimension of each high-speed rail seat was performed. By calculating the number, proportion, color difference and other parameters of the stain areas, a stain evaluation value was assigned to each high-speed rail seat to objectively reflect the cleanliness condition of the high-speed rail seat.

[0147] It should be noted that when the high-speed rail seat cover sleeved on any high-speed rail seat has a corresponding stain area, the corresponding stain area should be located on the high-speed rail seat cover, and generally speaking, the high-speed rail seat cover corresponds to the same color, and the seat sub-image can be binarized to quickly identify the seat area of ​​the corresponding high-speed rail seat and the noise area of ​​the corresponding non-high-speed rail seat in the seat sub-image, and further compare the noise area with the seat area. When any noise area is located in the seat area, it can be indicated that the noise area is a stain area on the high-speed rail seat cover, and when any noise area is not in the seat area, it can be indicated that the noise area may be an area corresponding to other debris; in this embodiment, through the steps of image binarization, area extraction, coordinate comparison and stain evaluation, the automatic detection and quantitative evaluation of high-speed rail seat stains are realized, and the detection efficiency and the objectivity of the evaluation are improved. At the same time, the method is easy to implement and is suitable for online monitoring and management of the cleanliness of large-scale high-speed rail seats.

[0148] Furthermore, after the corresponding stain area group is obtained, the above-mentioned "performing seat evaluation of the corresponding stain dimension for each high-speed rail seat based on all noise areas in the same stain area group to obtain each stain evaluation value corresponding to each high-speed rail seat" may also include the following steps:

[0149] Acquire the region number of each noise region in the same stain region group, and obtain the quantity coefficient by multiplying the region number by the retrieved quantity normalization value;

[0150] Determine the proportion of each noise area and the seat area in the same stain area group, and calculate the proportion coefficient based on the product of the obtained stain proportion and the retrieved normalized value of the proportion;

[0151] In each seat sub-image corresponding to each stain area group, image areas corresponding to each noise area are obtained respectively, and pixels are extracted from each image area to obtain image pixel points constituting each image area;

[0152] Calculating the mean of each image pixel value corresponding to each image pixel point, and performing difference calculation between the obtained pixel mean and the first pixel value to obtain a pixel difference;

[0153] The pixel difference value is multiplied by the retrieved pixel normalization value to obtain a color difference coefficient;

[0154] The quantity coefficient, proportion coefficient and color difference coefficient corresponding to the same high-speed rail seat are integrated and calculated to obtain the stain evaluation values ​​corresponding to each high-speed rail seat.

[0155] For example, in this embodiment, it should be noted that in order to improve the objectivity of the evaluation based on the stain dimension, this embodiment can evaluate the high-speed rail seat based on the stain dimension based on three different aspects: the number of stains, the proportion of stains, and the color difference of stains. Specifically, it can be achieved through the following method steps:

[0156] First, the server may obtain the number of regions of each noise region in the same stain region group, and perform normalization processing on the number of regions according to a preset number normalization value to obtain a number coefficient, wherein the number coefficient reflects the number characteristics of the stain region;

[0157] Next, the server calculates the area ratio of each noise area and the seat area in the same stain area group to obtain the stain ratio. The stain ratio is normalized according to the preset ratio normalization value to obtain the ratio coefficient, where the ratio coefficient reflects the distribution characteristics of the stain in the seat area;

[0158] Next, in each seat sub-image corresponding to each stain area group, the server can extract the image area corresponding to each noise area, and perform pixel extraction on these image areas to obtain the image pixel points that constitute each image area; by calculating the pixel mean of each image pixel point, and performing a difference calculation between the pixel mean and the first pixel value representing the normal color of the high-speed rail seat, a pixel difference is obtained. According to a preset pixel normalization value, the pixel difference is multiplied by the pixel normalization value to obtain a color difference coefficient, wherein the color difference coefficient reflects the difference characteristics between the stain area and the normal color of the seat;

[0159] Finally, by integrating the quantity coefficient, proportion coefficient and color difference coefficient corresponding to the same high-speed rail seat, weighted summation or weighted average can be performed according to the weight of each coefficient to obtain the stain evaluation value corresponding to the high-speed rail seat, wherein the stain evaluation value is a quantitative indicator that comprehensively reflects the stain condition of the seat. It should be noted that, in this embodiment, the larger the corresponding quantity coefficient, the larger the proportion coefficient, and the larger the color difference coefficient, the larger the corresponding stain evaluation value should be, which indicates that the higher the demand for replacing the high-speed rail seat cover on the high-speed rail seat.

[0160] This embodiment achieves accurate quantitative evaluation of stains on high-speed rail seats by comprehensively considering factors such as the number, proportion, and color difference of the stain areas, thereby improving the accuracy and objectivity of the evaluation.

[0161] In addition, in this embodiment, the above-mentioned "retrieving the seat usage data corresponding to each high-speed rail seat based on each seat number, and performing seat evaluation of each high-speed rail seat in the corresponding frequency dimension based on each seat usage data, to obtain each frequency evaluation value corresponding to each high-speed rail seat", can also include the following steps:

[0162] Retrieving a historical database, and acquiring seat usage data corresponding to each seat number based on the historical database, wherein the seat usage data includes a carrying quantity and a carrying duration;

[0163] Retrieving a quantity comparison table and a duration comparison table, wherein the quantity comparison table includes different quantity intervals and different first frequency values ​​corresponding to the different quantity intervals, and the duration comparison table includes different duration intervals and different second frequency values ​​corresponding to the different duration intervals;

[0164] The quantity comparison table and the duration comparison table are traversed respectively, and based on the quantity interval and the duration interval respectively including the bearer quantity and the bearer duration, a first frequency value corresponding to the bearer quantity and a second frequency value corresponding to the bearer quantity are obtained;

[0165] The first frequency value and the second frequency value corresponding to the same seat number are summed up to obtain the frequency evaluation values ​​corresponding to each high-speed rail seat.

[0166] For example, in this embodiment, it should be noted that in order to improve the objectivity of the evaluation based on the frequency dimension, this embodiment can evaluate the high-speed rail seats based on the frequency dimension based on the two different aspects of the carrying quantity and the carrying duration. Specifically, it can be achieved through the following method steps:

[0167] First, the server can retrieve data from a pre-stored historical database, which stores the seat usage data of each high-speed rail seat. For each seat number, the server can extract the corresponding seat usage data based on the historical database. These data mainly include the number of passengers carried by the corresponding seats (carrying number) and the time the passengers stay on the seats (carrying time).

[0168] Next, the server can further retrieve two key comparison tables: a quantity comparison table and a duration comparison table, wherein the quantity comparison table lists in detail different quantity intervals, and the different first frequency values ​​indicated by each quantity interval, and these first frequency values ​​indicate the evaluation values ​​corresponding to the high-speed rail seats under different load durations; the duration comparison table lists different load duration intervals, and the different second frequency values ​​corresponding to each load duration interval, and these second frequency values ​​indicate the evaluation values ​​corresponding to the high-speed rail seats under different load durations;

[0169] Then, the server can traverse the quantity comparison table and the duration comparison table, and find the quantity interval and duration interval to which they belong respectively according to the bearer quantity and bearer duration extracted from the historical database; on this basis, the server can obtain the first frequency value corresponding to the bearer quantity from the quantity comparison table, and can also obtain the second frequency value corresponding to the bearer duration from the duration comparison table;

[0170] Finally, for each seat number, the server sums the corresponding first frequency value and second frequency value to obtain a comprehensive frequency evaluation value, which provides a quantitative basis for the evaluation of the usage of high-speed rail seats.

[0171] It should be noted that, in the above process, the carrying capacity can be understood as the number of passengers carried by the high-speed rail seat during the travel of the high-speed rail train, which can be learned based on the ticket sales situation. For example, when the high-speed rail train runs from Beijing to Nanjing, it stops in Shijiazhuang, and the tickets at the two end sections of Beijing-Shijiazhuang and Shijiazhuang-Nanjing are purchased by two passengers respectively, then the carrying capacity of the corresponding high-speed rail seat is 2; the carrying time can be understood as the time that the high-speed rail seat carries the passengers during the travel of the high-speed rail train, which can also be learned based on the ticket sales situation. For example, when the high-speed rail train runs from Beijing to Nanjing, and a passenger purchases a full-journey ticket, then the carrying time corresponding to the high-speed rail seat can be the total travel time of the high-speed rail train from Beijing to Nanjing.

[0172] In step S104, the following contents are included:

[0173] In response to the management attribute of any high-speed rail seat cover being a replacement attribute, the digital twin data corresponding to the high-speed rail end is retrieved, and the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover is model marked in the high-speed rail twin space constructed based on the digital twin data.

[0174] For example, in this embodiment, when the management attribute of any high-speed rail seat cover is determined to be a replacement attribute based on the aforementioned passive acquisition and active acquisition, at this time, in order to be able to quickly locate and mark the high-speed rail seat cover so that the cleaning end can perform corresponding replacement operations, the digital twin data corresponding to the high-speed rail end can be retrieved, and further in the high-speed rail twin space constructed based on the digital twin data, the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover can be marked accordingly.

[0175] Further, in this embodiment, the above-mentioned "in response to the management attribute of any high-speed rail seat cover being a replacement attribute, retrieving the digital twin data corresponding to the high-speed rail end, and marking the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space constructed based on the digital twin data" may also include the following steps:

[0176] In response to the management attribute of any high-speed rail seat cover being a replacement attribute, controlling the drone to send a marking signal carrying a seat number corresponding to the high-speed rail seat cover;

[0177] Acquire the digital twin data corresponding to the high-speed rail end uploaded by the management end based on the marking signal, and construct the high-speed rail twin space based on the digital twin data;

[0178] Determine a seat model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space based on the seat number, and disassemble the seat number to obtain a compartment sub-number, a row sub-number, and a seat sub-number;

[0179] Retrieving the first number color, the second number color and the third number color corresponding to the compartment sub-number, the row sub-number and the position sub-number respectively, and determining the first number color, the second number color and the third number color as a preset color group;

[0180] The seat model is flashed with a first numbered color, a second numbered color, and a third numbered color in a preset color group.

[0181] For example, in this embodiment, marking any high-speed rail seat cover with an update attribute as a management attribute can be implemented based on the following method steps:

[0182] First, when the server determines that the management status of any high-speed rail seat cover is set to the replacement attribute, the server automatically triggers a control command to instruct the drone to send a marking signal carrying the seat number corresponding to the high-speed rail seat cover;

[0183] Then, after receiving the corresponding marking signal, the management end can upload the digital twin data corresponding to the high-speed rail end, so that the server can obtain it and build the corresponding high-speed rail twin space based on the digital twin data; here, the high-speed rail twin space accurately maps the physical layout of the high-speed rail train, that is, includes the high-speed rail model of the corresponding high-speed rail train;

[0184] Then, in the constructed high-speed rail twin space, the server can accurately locate the seat model corresponding to the high-speed rail seat according to the seat number, and further parse the seat number into three components: compartment sub-number, row sub-number and position sub-number. These numbers represent the high-speed rail compartment, compartment row and seat position of the high-speed rail seat.

[0185] Then, according to the compartment sub-number, row sub-number and position sub-number obtained by disassembly, the first number color, the second number color and the third number color pre-associated therewith are respectively retrieved, and these three colors are combined into a specific preset color group for subsequent visual identification;

[0186] Finally, in the high-speed rail twin space, the located seat model is flashed and marked based on the preset color group. Specifically, the seat model flashes in the order of the first numbered color, the second numbered color, and the third numbered color in the preset color group or simultaneously, so as to intuitively indicate the specific location where the high-speed rail seat cover needs to be replaced, so that the cleaning staff can quickly identify and perform the replacement operation.

[0187] It should be noted that the above-mentioned first number color, second number color and third number color can be different colors, wherein different high-speed rail cars have corresponding different first number colors, different car rows have corresponding different second number colors, and different car seats also have corresponding different third number colors, so that the seat model corresponding to each high-speed rail seat has an independent and different preset color group, thereby improving the corresponding model identification.

[0188] In summary, this embodiment achieves accurate response to the management of high-speed rail seat covers under different states by acquiring the operating status of the high-speed rail end in real time. In the passenger transport state, the passive detection strategy is adopted to effectively reduce unnecessary resource consumption, while ensuring the timely acquisition of seat cover management information and improving management efficiency. When the high-speed rail is out of service, it switches to the active detection strategy and uses drones for efficient data collection. This innovative measure not only greatly improves the accuracy and comprehensiveness of data collection, but also significantly shortens the cycle of seat cover inspection and maintenance, and enhances the sanitary quality and passenger experience of high-speed rail services; more importantly, this method introduces digital twin technology. When the seat cover that needs to be replaced is detected, the digital twin data of the corresponding high-speed rail end can be quickly retrieved and the model is marked in the high-speed rail twin space. This step not only facilitates the management personnel to intuitively and quickly locate the problem seat, but also provides precise guidance for subsequent maintenance or replacement work, effectively reducing the cost and time of manual investigation, and improving the overall operation efficiency; this embodiment comprehensively optimizes the management process of high-speed rail seat covers through intelligent and precise management means, and sets a new benchmark for the modern management of high-speed rail operations.

[0189] Figure 4 FIG. 1 is a block diagram showing a high-speed rail seat cover intelligent management system based on multi-terminal interconnection proposed in another embodiment of the present invention. Figure 4 As shown, the system includes:

[0190] A status acquisition module is configured to acquire an operation status corresponding to the high-speed rail terminal, wherein the operation status includes a passenger transport status and a suspension status;

[0191] A passive detection module is configured to call a passive detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being a passenger transport state, and passively acquire management attributes of each high-speed rail seat cover corresponding to the high-speed rail terminal based on the passive detection strategy;

[0192] The active detection module is configured to call the active detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being the out-of-service state, and control the drone to collect data from each high-speed rail seat cover based on the active detection strategy, and actively obtain the management attributes of each high-speed rail seat cover based on the collection results;

[0193] The model marking module is configured to, in response to the management attribute of any high-speed rail seat cover being a replacement attribute, retrieve the digital twin data corresponding to the high-speed rail end, and model mark the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space constructed based on the digital twin data.

[0194] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the preferred embodiment of the present invention.

[0195] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0196] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0197] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0198] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of submodules or subunits or subcomponents.

[0199] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0200] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0201] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0202] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is primarily selected for readability and instructional purposes, rather than for explaining or limiting the subject matter of the present invention.

Claims

1. A high-speed rail seat cover intelligent management method based on multi-terminal interconnection, characterized in that: The management method comprises: Acquire the operation status corresponding to the high-speed rail terminal, wherein the operation status includes passenger transport status and suspension status; In response to the running state being a passenger transport state, calling a passive detection strategy to configure the strategy for the high-speed rail end, and passively acquiring management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy; In response to the running state being the outage state, calling the active detection strategy to configure the strategy for the high-speed rail end, and controlling the drone to collect data for each high-speed rail seat cover based on the active detection strategy, and actively acquiring the management attributes of each high-speed rail seat cover based on the collection results; In response to the management attribute of any high-speed rail seat cover being a replacement attribute, the digital twin data corresponding to the high-speed rail end is retrieved, and the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover is model marked in the high-speed rail twin space constructed based on the digital twin data.

2. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 1 is characterized in that: Passively acquiring management attributes of each high-speed rail seat cover corresponding to the high-speed rail end based on the passive detection strategy includes: Acquire each gravity detection value output by each gravity detection unit pre-set at each high-speed rail seat corresponding to the high-speed rail end, and compare each gravity detection value with the retrieved gravity threshold; In response to any gravity detection value being greater than the gravity threshold, aggregating the high-speed rail seats corresponding to the gravity detection value into a seat detection group; Establishing a data transmission channel between each touch interaction unit that has a communication connection relationship with each high-speed rail seat located in the seat detection group, and in response to obtaining a seat cover replacement signal output by any touch indication unit based on the data transmission channel, obtaining a signal duration corresponding to the seat cover replacement signal; The signal duration is compared with a retrieved time threshold, and in response to the signal duration being greater than or equal to the time threshold, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat corresponding to the touch indication unit is determined as a replacement attribute.

3. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 1 is characterized in that: Based on the active detection strategy, the drone is controlled to collect images of each high-speed rail seat cover respectively, and the management attributes of each high-speed rail seat cover are actively acquired based on the collection results, including: A preset main route is established based on the extension direction of any high-speed rail carriage at the corresponding high-speed rail end, the drone is controlled to fly along the preset main route, and a first tag detection unit and a second tag detection unit pre-installed on both sides of the drone are triggered to perform tag detection on the first carriage space and the second carriage space located on both sides of the preset main route respectively; In response to any positioning unit detecting a seat tag located in a corresponding compartment space, obtaining each seat number included in the seat tag and the number of seats corresponding to each seat number; Control the drone to move toward the seat tag to a preset detection position, trigger an image acquisition unit pre-installed at the bottom of the drone to acquire an image, and perform image segmentation corresponding to the number of seats on the acquired seat acquisition image to obtain seat sub-images corresponding to different high-speed rail seats; Based on each seat sub-image, each high-speed rail seat is evaluated for the corresponding stain dimension, and each stain evaluation value corresponding to each high-speed rail seat is obtained; Retrieving the seat usage data corresponding to each high-speed rail seat based on each seat number, and performing seat evaluation of the corresponding frequency dimension on each high-speed rail seat based on each seat usage data, to obtain each frequency evaluation value corresponding to each high-speed rail seat; The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are respectively multiplied by the retrieved first update weight and the second update weight to obtain an updated stain evaluation value and a frequency evaluation value; The stain evaluation value and the frequency evaluation value corresponding to the same high-speed rail seat are summed and calculated, and in response to the obtained cleaning evaluation value being greater than or equal to the retrieved benchmark evaluation value, the management attribute of the high-speed rail seat cover mounted on the high-speed rail seat is determined as a replacement attribute.

4. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 3 is characterized in that: The method further comprises: Obtaining an actual evaluation value uploaded by the cleaning end based on the high-speed rail seat cover, and comparing the cleaning evaluation value corresponding to the high-speed rail seat cover with the actual evaluation value; When the actual evaluation value is greater than the clean evaluation value, increasing training is performed on the first update weight and the second update weight respectively; When the actual evaluation value is less than the clean evaluation value, the first update weight and the second update weight are respectively trained to be reduced; The first updated weight and the second updated weight after training are obtained by the following formula: ； in, Update weights for the first Increase the number of training sessions. Update weights for the first The training constant value of Update weights for the first Reduce the number of training sessions. is the first updated weight after training, Update weights for the second Increase the number of training sessions. Update weights for the second The training constant value of Update weights for the second Reduce the number of training sessions. Update weights for the second time after training.

5. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 3 is characterized in that: The drone is controlled to move toward the seat tag to a preset detection position, an image acquisition unit pre-installed at the bottom of the drone is triggered to acquire an image, and the acquired seat acquisition image is cut into images corresponding to the number of seats to obtain seat sub-images corresponding to different high-speed rail seats, including: Controlling the drone to move toward the seat tag and continuously acquiring the captured content in a capture window corresponding to an image capture unit pre-installed at the bottom of the drone; When the collected content includes at least one seat pixel point corresponding to a high-speed rail seat, and any seat pixel point is not located in the window outline of the collection window, the drone is controlled to hover at the current detection position, and seat collection frames having the same number as the number of seats arranged in a straight line are generated in the collection window; Comparing all the seat pixel points included in the collected content with the frame outline corresponding to each seat collection frame based on relative positions; In response to any seat pixel point being located at a frame outline of any seat acquisition frame, controlling the drone to adjust its position based on a current detection position, and determining the drone after the position adjustment to move to a preset detection position; The image acquisition unit is triggered to perform image acquisition, and image segmentation is performed based on each seat acquisition frame located in the acquisition window to obtain each seat sub-image corresponding to each different high-speed rail seat.

6. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 3 is characterized in that: Based on each seat sub-image, each high-speed rail seat is evaluated for the corresponding stain dimension, and each stain evaluation value corresponding to each high-speed rail seat is obtained, including: Binarization is performed on each seat sub-image to obtain binarized images corresponding to each seat sub-image, wherein any of the binarized images includes seat pixel points corresponding to the first pixel value and noise pixel points corresponding to the second pixel value; Performing pixel connection based on adjacent position relationship on each seat pixel point located in the same binary image to obtain a seat area located in the binary image; Performing pixel connection based on adjacent position relationship on each noise pixel point located in the same binary image to obtain each noise region located in the binary image; Perform coordinate processing on each binary image respectively, and obtain the seat area located in the same binary image, the seat coordinate interval corresponding to each noise area, and each noise coordinate interval; Comparing the coordinates of each noise coordinate area with the seat coordinate interval one by one, and in response to any noise coordinate interval being surrounded by the seat coordinate interval, aggregating the corresponding noise area into a stain area group; A seat evaluation of the corresponding stain dimension is performed on each high-speed rail seat based on all noise areas in the same stain area group, and each stain evaluation value corresponding to each high-speed rail seat is obtained.

7. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 6 is characterized in that: The seat evaluation of the corresponding stain dimension is performed on each high-speed rail seat based on all noise areas in the same stain area group, and the stain evaluation values ​​corresponding to each high-speed rail seat are obtained, including: Acquire the region number of each noise region in the same stain region group, and obtain the quantity coefficient by multiplying the region number by the retrieved quantity normalization value; Determine the proportion of each noise area and the seat area in the same stain area group, and calculate the proportion coefficient based on the product of the obtained stain proportion and the retrieved proportion normalization value; In each seat sub-image corresponding to each stain area group, image areas corresponding to each noise area are obtained respectively, and pixels are extracted from each image area to obtain image pixel points constituting each image area; Calculating the mean of each image pixel value corresponding to each image pixel point, and performing difference calculation between the obtained pixel mean and the first pixel value to obtain a pixel difference; The pixel difference value is multiplied by the retrieved pixel normalization value to obtain a color difference coefficient; The quantity coefficient, proportion coefficient and color difference coefficient corresponding to the same high-speed rail seat are integrated and calculated to obtain the stain evaluation values ​​corresponding to each high-speed rail seat.

8. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 3 is characterized in that: Based on each seat number, the seat usage data corresponding to each high-speed rail seat is retrieved, and based on each seat usage data, the seat evaluation of each high-speed rail seat in the corresponding frequency dimension is performed to obtain each frequency evaluation value corresponding to each high-speed rail seat, including: Retrieving a historical database, and acquiring seat usage data corresponding to each seat number based on the historical database, wherein the seat usage data includes a carrying quantity and a carrying duration; Retrieving a quantity comparison table and a duration comparison table, wherein the quantity comparison table includes different quantity intervals and different first frequency values ​​corresponding to the different quantity intervals, and the duration comparison table includes different duration intervals and different second frequency values ​​corresponding to the different duration intervals; The quantity comparison table and the duration comparison table are traversed respectively, and based on the quantity interval and the duration interval respectively including the bearer quantity and the bearer duration, a first frequency value corresponding to the bearer quantity and a second frequency value corresponding to the bearer quantity are obtained; The first frequency value and the second frequency value corresponding to the same seat number are summed up to obtain the frequency evaluation values ​​corresponding to each high-speed rail seat.

9. The high-speed rail seat cover intelligent management method based on multi-terminal interconnection according to claim 3 is characterized in that: In response to the management attribute of any high-speed rail seat cover being a replacement attribute, the digital twin data corresponding to the high-speed rail end is retrieved, and a high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover is model marked in a high-speed rail twin space constructed based on the digital twin data, including: In response to the management attribute of any high-speed rail seat cover being a replacement attribute, controlling the drone to send a marking signal carrying a seat number corresponding to the high-speed rail seat cover; Acquire the digital twin data corresponding to the high-speed rail end uploaded by the management end based on the marking signal, and construct the high-speed rail twin space based on the digital twin data; Determine a seat model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space based on the seat number, and disassemble the seat number to obtain a compartment sub-number, a row sub-number, and a seat sub-number; Retrieving the first number color, the second number color and the third number color corresponding to the compartment sub-number, the row sub-number and the position sub-number respectively, and determining the first number color, the second number color and the third number color as a preset color group; The seat model is flashed with a first numbered color, a second numbered color, and a third numbered color in a preset color group.

10. A high-speed rail seat cover intelligent management system based on multi-terminal interconnection, characterized in that: include: A status acquisition module is configured to acquire an operation status corresponding to the high-speed rail terminal, wherein the operation status includes a passenger transport status and a suspension status; A passive detection module is configured to call a passive detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being a passenger transport state, and passively acquire management attributes of each high-speed rail seat cover corresponding to the high-speed rail terminal based on the passive detection strategy; The active detection module is configured to call the active detection strategy to configure the strategy for the high-speed rail terminal in response to the operating state being the out-of-service state, and control the drone to collect data from each high-speed rail seat cover based on the active detection strategy, and actively obtain the management attributes of each high-speed rail seat cover based on the collection results; The model marking module is configured to, in response to the management attribute of any high-speed rail seat cover being a replacement attribute, retrieve the digital twin data corresponding to the high-speed rail end, and model mark the high-speed rail model corresponding to the high-speed rail seat covered by the high-speed rail seat cover in the high-speed rail twin space constructed based on the digital twin data.

Images