A smart bus shelter data processing method and system based on digital analysis

Abstract

The application discloses a kind of wisdom bus shelter data processing method and system based on digital analysis, including the seat use information in the collection target vehicle and air conditioner use state, the temperature distribution information and crowdedness information of different seats are sent to all bus shelters to carry out data sharing;Receive the request instruction of target passenger, identify the historical ride record and current ride demand information of target passenger, predict ride preference behavior and demand seat to the expected distance of drop-off port;According to temperature distribution information and crowdedness information, ride preference behavior and expected distance, build seat recommendation model, generate target seat for recommendation, when target passenger determines to use target seat, update data and synchronize to all bus shelters, continue seat recommendation for next passenger.The application considers the individualized demand of different passengers, can scientifically and reasonably recommend seat for passenger, avoid the problem that passenger frequently changes after blind seat selection, improve the ride experience of passenger.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart bus, and particularly to a smart bus shelter data processing method and system based on digital analysis. BACKGROUND

[0002] With the acceleration of urbanization, public transportation system plays an increasingly important role in people's daily life. Traditional bus shelters usually only provide basic waiting and information display functions, such as estimated arrival time, interval between trips, etc. Since passengers cannot obtain more detailed state information inside the vehicle and lack effective seat recommendation mechanism, when the vehicle arrives at the station, passengers can only randomly choose seats by feeling, which may result in that the selected seats cannot meet the real needs of passengers, for example, a passenger actually needs a ventilated position, but chooses a seat with a closed window due to fast seating, or a passenger randomly chooses a seat with a lower temperature, but the passenger is actually not in good health, so the passenger needs to change seats. At this time, the passenger cannot predict whether the next seat is suitable, and when other seats are occupied, the changing operation may not be smooth, and being forced to sit in the original seat greatly reduces the passenger experience. In addition, this blind seat selection by passengers may also lead to overcrowding in some areas and vacancy in other places, reducing space utilization. SUMMARY

[0003] To solve at least one of the above technical problems, the present application provides a smart bus shelter data processing method and system based on digital analysis.

[0004] In a first aspect, the present application provides a smart bus shelter data processing method based on digital analysis, which comprises:

[0005] Taking a bus departing from a previous bus shelter as a target vehicle, collecting seat usage information and air conditioner usage state in the target vehicle;

[0006] According to the seat usage information and the air conditioner usage state, calculating temperature distribution information of different seats; according to the seat usage information, calculating congestion degree information around different seats; sending the temperature distribution information and the congestion degree information to the current smart bus shelter, and sharing data with other bus shelters;

[0007] Based on the queuing order of passengers at the current smart bus shelter, taking the passenger at the first place as a target passenger; receiving a request instruction of the target passenger, identifying historical vehicle riding records and current vehicle riding demand information of the target passenger; predicting vehicle riding preference behavior of the target passenger according to the historical vehicle riding records, and evaluating expected distance from the demand seat of the target passenger to the alighting port according to the current vehicle riding demand information;

[0008] According to the temperature distribution information and the crowdedness information, the riding preference behavior of the target passenger and the expected distance, a seat recommendation model is constructed, and a target seat recommended for the target passenger is outputted;

[0009] In response to the confirmation result of the target passenger, when the target passenger determines to use the target seat, the crowdedness information and the temperature distribution information of the remaining seats are updated and synchronized to all intelligent bus shelters, and the updated data is used to continue seat recommendation for the next passenger.

[0010] Preferably, the temperature distribution information of different seats is calculated according to the seat usage information and the air conditioner usage state, comprising:

[0011]

[0012] In the formula, T i represents the temperature of the i-th seat, is the average temperature in the car, ΔT a (d i ) represents the air conditioner influence factor, the size of which is determined by the distance d ia from the seat i to the nearest air outlet of the air conditioner; ΔT hu (n j , d ij ) represents the heat dissipation increment of the human body, the size of which is determined by the distance d ij from the i-th seat to the adjacent seat j and the number n j of passengers on the adjacent seat j, and N represents the total number of seats.

[0013] Preferably, the seat recommendation model is constructed according to the temperature distribution information and the crowdedness information, the riding preference behavior of the target passenger and the expected distance, and the target seat recommended for the target passenger is outputted, comprising:

[0014] The seat recommendation model is constructed:

[0015] G i = w1G(T i ) + w2G(C i ) + w3G(D i ) + w4G(P i ) + b

[0016] In the formula, G i represents the matching score of the i-th seat and the target passenger, w1, w2, w3 and w4 are weight factors, b is a constant, and 0 < b ≤ 0.1; G(T i ), G(C i ), G(D i ) and G(P i ) are the matching scores of the temperature, crowdedness, distance and riding preference of the i-th seat and the target passenger, respectively.

[0017]

[0018]

[0019]

[0020]

[0021] wherein T i represents the temperature of the ith seat, T min , T max are the minimum and maximum values of the ideal temperature of the target passenger demand, T avg is the intermediate value of T min and T max ; M ij is the number of adjacent seats of the ith seat, m is the number of occupied seats in M ij ; d io is the distance of the ith seat to the exit, d min , d max are the minimum and maximum values of the expected distance of the target passenger;

[0022] According to the seat recommendation model, the matching degree score of each seat with the target passenger is calculated, and the seat with the highest matching degree score is identified from the unoccupied seats as the target seat recommended to the target passenger.

[0023] Preferably, after the response of the target passenger to the confirmation result, it further comprises:

[0024] When the target passenger refuses to use the target seat, a continue matching instruction and an autonomous seat selection instruction are sent for the target passenger to select;

[0025] When the target passenger responds to the continue matching instruction, other seats are recommended to the target passenger in order from high to low according to the matching degree score until the target passenger confirms to use a seat, and the seat usage state is updated;

[0026] When the target passenger responds to the autonomous seat selection instruction, the seat autonomously selected by the target passenger is assigned to the target passenger, and the seat usage state is updated.

[0027] In a second aspect, the present application further provides a smart bus shelter data processing system based on digital analysis, which comprises:

[0028] A data acquisition unit is configured to collect seat usage information and air conditioner usage state in a target vehicle, wherein the target vehicle is a bus departing from a previous bus shelter of the current smart bus shelter;

[0029] The data sharing unit is used to calculate the temperature distribution information of different seats based on seat usage information and air conditioning usage status; calculate the crowding information around different seats based on seat usage information; send the temperature distribution information and crowding information to the current smart bus shelter and share the data with other bus shelters.

[0030] The demand identification unit is used to identify the first passenger in the queue based on the current queuing order of passengers at the smart bus shelter; receive the request instructions from the target passenger; identify the target passenger's historical travel records and current travel demand information; predict the target passenger's travel preference behavior based on historical travel records; and assess the target passenger's expected distance from the desired seat to the alighting point based on current travel demand information.

[0031] The seat recommendation unit is used to build a seat recommendation model based on temperature distribution information, crowding information, the travel preferences of the target passengers, and the expected distance, and outputs the target seats recommended to the target passengers.

[0032] The data update unit is used to respond to the confirmation result of the target passenger. When the target passenger confirms that he / she will use the target seat, it updates the crowding information and temperature distribution information of the remaining seats and synchronizes them to all smart bus shelters. The updated data is then used to continue to recommend seats for the next passenger.

[0033] Preferably, the data sharing unit is used to calculate temperature distribution information for different seats based on seat usage information and air conditioning usage status, including:

[0034]

[0035] In the formula, T i This represents the temperature of the i-th seat. The average temperature inside the carriage, ΔT a (d i The symbol represents the air conditioning impact factor, with its magnitude varying from seat i to the nearest air conditioning vent d. ia Decision; ΔT hu (n j d ij The value represents the increase in heat dissipation from the human body, and its magnitude is determined by the distance d between the i-th seat and its neighboring seat j. ij and the number of passengers n in adjacent seat j j The decision is made by N, where N represents the total number of seats.

[0036] Preferably, the seat recommendation unit is further configured to:

[0037] Building a seat recommendation model:

[0038] G i =w1G(T i )+w2G(Ci )+w3G(D i )+w4G(P i )+b

[0039] In the formula, G i Let w1, w2, w3, and w4 represent the matching score between the i-th seat and the target passenger, where w1, w2, w3, and w4 are weighting factors, and b is a constant that satisfies 0. <b≤0.1;G(T i ), G(C i ), G(D i ), G(P i ) are the matching scores between the i-th seat and the target passenger based on temperature, crowding level, distance, and travel preferences;

[0040]

[0041]

[0042]

[0043]

[0044] In the formula, T i T represents the temperature of the i-th seat. min T max T represents the minimum and maximum values ​​of the ideal temperature required by the target passengers. avg For T min With T max The median value; M ij Let m be the number of seats adjacent to the i-th seat, and m be M. ij Number of seats already occupied; d io Let d be the distance from the i-th seat to the exit. min d max These are the minimum and maximum values ​​of the target passenger's desired distance;

[0045] The matching score between each seat and the target passenger is calculated based on the seat recommendation model. The seat with the highest matching score is identified from the unoccupied seats and recommended to the target passenger as the target seat.

[0046] Preferably, the data update unit, after receiving the confirmation result from the target passenger, further includes:

[0047] When the target passenger refuses to use the target seat, send a continue matching instruction and a self-selection seat instruction for the target passenger to choose from.

[0048] When the target passenger responds to the continue matching instruction, other seats are recommended to the target passenger in order of the matching degree score from high to low until the target passenger confirms to use a certain seat, and the seat use state is updated;

[0049] When the target passenger responds to the autonomous seat selection instruction, the seat autonomously selected by the target passenger is assigned to the target passenger, and the seat use state is updated.

[0050] In a third aspect, the present application also provides an electronic device, comprising a processor and a memory, the memory is used to store computer program code, the computer program code comprises computer instructions, when the processor executes the computer instructions, the electronic device executes the method of the above first aspect and any possible implementation manner thereof.

[0051] In a fourth aspect, the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program comprises program instructions, when the program instructions are executed by a processor of an electronic device, the processor executes the method of the above first aspect and any possible implementation manner thereof.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] The intelligent bus shelter data processing method based on digital analysis provided by the present application collects and analyzes the seat use information and air conditioner state in the target vehicle, calculates the temperature distribution and crowding degree information of different seats, and sends these information to the current intelligent bus shelter and other bus shelters for sharing, solving the information asymmetry problem in the prior art. At the same time, for each target passenger queuing and waiting, the present application can identify its historical ride record and current demand, predict its preferred behavior, and construct a seat recommendation model combined with the temperature distribution and crowding degree information, thereby providing the target passenger with the optimal seat suggestion. This process not only improves passenger satisfaction, but also realizes more reasonable resource allocation and improves the use efficiency of the in-vehicle space. Finally, when the target passenger confirms to use a recommended seat, the system will immediately update the relevant data and synchronize between all intelligent bus shelters, ensuring that subsequent passengers can also enjoy precise seat recommendation services. Therefore, the present application effectively improves the intelligent level and service quality of the public transportation system, and provides a new solution for urban traffic management.

[0054] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background, the accompanying drawings needed to be used in the present application or the background will be described below.

[0056] The accompanying drawings incorporated in the specification hereof and forming a part thereof illustrate embodiments consistent with the present disclosure and together with the description serve to explain the technical solutions of the present disclosure.

[0057] Figure 1 A flowchart of a smart bus shelter data processing method based on digital analysis provided by the embodiment of the present application is shown in the figure.

[0058] Figure 2 A structural diagram of a smart bus shelter data processing system based on digital analysis provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0059] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work fall within the scope of protection of the present application.

[0060] In this paper, the phrase "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0061] At present, when passengers take a bus, due to information asymmetry and lack of reasonable seat recommendation mechanism, passengers can only choose seats blindly, which causes passengers to need to change seats frequently, low resource utilization rate and poor passenger experience, etc. Therefore, the present application aims to provide a method, which can obtain information such as temperature in the car, seat usage state, seat distribution and distance from the door, so as to recommend seats that meet the needs of passengers, greatly improve the passenger experience, optimize the resource allocation in the car and improve the utilization rate.

[0062] Please refer to Figure 1 , Figure 1 A flowchart of a smart bus shelter data processing method based on digital analysis provided by the embodiment of the present application is shown in the figure. Figure 1 As shown in the figure, the method comprises:

[0063] S10, taking a bus departing from a previous bus stop of a current smart bus stop as a target vehicle, collecting seat usage information and air conditioner usage state in the target vehicle.

[0064] The target vehicle refers to a bus departing from a previous bus stop of a current smart bus stop. For example, there are two bus stops A and B, and the next stop of A is B. Therefore, all buses stopping at A and B can be regarded as target vehicles. Because the bus door is usually not opened and closed during the period from A to B, that is, there is no passenger flow, the usage state information of the carriage in this interval is relatively stable, and the subsequent analysis process is also relatively effective. Once more bus stops are selected, for example, several stations in front of A are analyzed, the usage of these several stations will dynamically change, and the data cannot be accurately collected.

[0065] Generally, the seat usage information in the target vehicle is counted by a camera in the vehicle, so that the crowded degree in the carriage can be understood. Preferably, the number of passengers on each row of seats can also be estimated by an infrared sensor. The air conditioner usage state refers to the switch state of the air conditioner and the parameter size state when the air conditioner is used. Because most of the current buses are equipped with intelligent air conditioning systems, the most direct way is to read the state information from the control system of the air conditioner, such as the instantaneous output power, temperature and wind speed of the air conditioner and the like.

[0066] S20, calculating temperature distribution information of different seats according to the seat usage information and the air conditioner usage state; calculating crowdedness information around different seats according to the seat usage information; sending the temperature distribution information and the crowdedness information to the current smart bus stop, and sharing data with other bus stops.

[0067] The temperature is mainly displayed by the air conditioner controller in the carriage, but the temperature displayed by the air conditioner is usually the average temperature level in the carriage, and cannot accurately predict the temperature of each position, for example, the temperature near the air outlet is different from that of other positions, the temperature of the passenger crowded area is different from that of the dispersed area, and the temperature distribution of the seat that can be ventilated and the seat that cannot be ventilated is different. If temperature sensors are installed around each seat, although the temperature of different seats can be accurately obtained, this way is too high in cost and is not conducive to large-scale promotion. In order to solve this problem, the embodiment aims to predict the temperature of different seats by modeling to provide more accurate passenger comfort prediction.

[0068] In a preferred embodiment, calculating temperature distribution information of different seats according to the seat usage information and the air conditioner usage state comprises:

[0069]

[0070] In the formula, Ti T i represents the temperature of the ith seat, T is the average temperature inside the vehicle cabin, ΔT a (d i ) represents the air conditioning impact factor, which is determined by the distance d ia from the seat i to the nearest air conditioning outlet. hu (n j , d ij ) represents the human body heat dissipation increment, which is determined by the distance d ij between the ith seat and the neighboring seat j and the number of passengers n j in the neighboring seat j. N represents the total number of seats.

[0071] In the above formula, data is collected using multiple temperature sensors installed inside the vehicle cabin, and the average value of these data is calculated as the average temperature inside the vehicle cabin According to the distance d ia from each seat to the nearest air conditioning outlet, the impact of air conditioning on each seat is determined using a pre-established empirical formula or simulation results. Generally speaking, the closer the distance, the more obvious the effect of air conditioning, and therefore the greater the temperature change. The air conditioning impact factor ΔT a (d i ) takes into account factors such as the working mode of the air conditioner (cooling / heating), air speed, etc., ensuring that the model can reflect real physical phenomena. For each seat, analyze the situation of the surrounding neighboring seats, especially the number of occupied seats and their distance d ij to the neighboring seats. Using heat conduction theory and human engineering knowledge, combined with experimental data or simulation results, a function is constructed to describe the influence of human body heat dissipation on the surrounding environment temperature. This function gradually weakens with increasing distance, and when more people are close, the total heat contribution also increases accordingly. Combine the above three parts together, and calculate the actual temperature T i of each seat according to the given formula. This not only obtains the temperature distribution of the entire vehicle cabin, but also can be personalized and optimized for specific locations.

[0072] In another preferred embodiment, the temperature distribution of different seats can also be predicted by combining models of heat conduction, convection and radiation, etc., and the specific steps are as follows:

[0073] 1) Establish initial conditions and boundary conditions:

[0074] Vehicle cabin structure parameters: including vehicle cabin size, seat layout, window position and area, door position, etc.

[0075] Material properties: different materials (such as metal frame, plastic seat, glass window) have different thermal conductivity coefficients, which are crucial for accurate modeling.

[0076] External environmental conditions: Obtain vehicle location through GPS and combine with weather API to get external temperature, humidity, wind speed, etc.

[0077] 2) Define heat sources and heat sinks:

[0078] Human heat source: Assume each passenger emits a certain amount of heat per minute (e.g. 70-100 watts), calculate the total human heat generation according to the real-time monitored passenger density.

[0079] Air conditioning system: Determine the location, air volume and set temperature of the air conditioning outlet; at the same time, consider the effect of return air outlet to ensure reasonable air circulation.

[0080] Solar radiation: If there is a direct sunlight area in the car, the effect of solar radiation needs to be considered, especially during the daytime.

[0081] 3) Apply thermodynamic principles for modeling:

[0082] Use steady-state heat conduction equation, transient heat conduction equation, natural convection and forced convection, and radiation heat transfer four equations to calculate the temperature influence under these conditions.

[0083] 4) Introduce dynamic factors:

[0084] Passenger movement: As the vehicle travels, passengers getting on and off will cause changes in the distribution of personnel inside the vehicle, which will affect the local temperature field. The passenger position can be tracked by sensors or cameras to update the model input.

[0085] Air conditioning adjustment: According to the temperature difference between the inside and outside of the car and the preset temperature, automatically adjust the working mode (cooling / heating), air speed and direction of the air conditioner to maintain a comfortable indoor environment.

[0086] 5) Numerical solution and simulation:

[0087] Discretize the grid: Divide the car space into finite element grids to facilitate the numerical solution of partial differential equations.

[0088] Iterative algorithm: Use numerical methods such as finite difference method, finite volume method or finite element method to solve the above equation set to get the temperature value at each node.

[0089] Software tools: Existing CFD (Computational Fluid Dynamics) and FEA (Finite Element Analysis) software can be used for efficient simulation calculation.

[0090] 6) Results visualization and interaction:

[0091] Temperature cloud map display: visually present the calculated temperature distribution in color-coded form on a three-dimensional model, helping users understand the temperature conditions around each seat.

[0092] Real-time feedback mechanism: combined with smart bus stop signs or mobile applications, provide passengers waiting for the bus with a preview of the seat temperature of the approaching vehicle, helping them make better choices.

[0093] In this way, only the temperature at key locations needs to be collected, and a thermodynamic model is used to accurately predict the temperature distribution of different seats. Therefore, through fine modeling of temperature distribution, the indoor environment can be better understood and improved, making the passenger's journey more comfortable. In this way, we can understand which areas need more cooling or heating resources, so as to accurately control the air conditioning system and avoid unnecessary energy waste. Especially during the flu season or other public health events, reasonable ventilation and temperature management can help reduce the risk of disease transmission.

[0094] Further, the crowdedness can be determined according to the number of seat occupancy and the number of seats, and after obtaining the temperature distribution of different seats and the number of seat occupancy, the temperature distribution information and the crowdedness information are sent to the current smart bus shelter and shared with other bus shelters. Specifically, the processed temperature distribution information and crowdedness information can be directly sent to the display screen of the current smart bus shelter for passengers waiting to view. It can also be pushed to users who have subscribed to the service through a mobile application, providing personalized recommendations. In order to interconnect the city bus system, a bus information sharing network needs to be built to enable each bus shelter to exchange the latest vehicle status information. In this way, passengers can more intuitively and accurately understand the use environment of the car, solving the problem of information asymmetry and information silos. Passengers can choose the most suitable time and place to take the bus according to the information provided, reducing waiting time and discomfort, and thus improving the overall travel experience.

[0095] S30, based on the queuing order of the passengers at the current smart bus shelter, the passenger at the top of the queue is selected as the target passenger; receive the request instruction of the target passenger, identify the historical bus riding record and current bus riding demand information of the target passenger; predict the bus riding preference behavior of the target passenger based on the historical bus riding record, and evaluate the expected distance from the demand seat to the drop-off point of the target passenger based on the current bus riding demand information.

[0096] Generally, the entire bus system adopts the following architecture design:

[0097] Smart bus shelter: equipped with cameras, sensors, touch screens and other devices to monitor passenger queuing order and provide interactive interface.

[0098] Mobile application: for passengers to input personal preferences and travel demand information in advance, support data synchronization with intelligent bus stop board.

[0099] Cloud server: responsible for processing data, running prediction models and seat recommendation algorithms, and feeding back results to the waiting shelter or application.

[0100] In order to maintain order when boarding, passengers need to queue up, so when recommending seats, it is also in the order of first come first served, with a certain priority. Use the camera installed in the waiting shelter to automatically detect and record the position of the queuing passengers combined with AI vision technology. When the vehicle is about to arrive at the station, the system will confirm the passenger at the front as the target passenger based on the latest image analysis results. Through facial recognition or other biometric identification technology, ensure the identity of the target passenger is accurate.

[0101] Further, receiving the request instruction of the target passenger, identifying the historical travel record and current travel demand information of the target passenger; through the touch screen or mobile application, receiving the specific requirements of the target passenger for this trip, such as whether to carry large luggage, whether to have special health conditions (such as fear of cold), estimated alighting station, etc. Retrieve the historical travel record of the target passenger from the cloud server, including frequently traveled lines, time, habitually selected seat types (window / corridor), etc. Based on a large amount of existing travel data, train a machine learning model that can predict passenger preferences. This model can identify which types of seats passengers tend to choose (such as close to the door, away from noise sources) and their preferences for temperature, lighting, etc. When evaluating the target passenger's demand for a seat to the expected distance to the alighting port, consider the layout of the bus, combined with the destination information of the target passenger, calculate the optimal path length from different seats to the alighting port. Preferably recommend seats that allow passengers to quickly get off the bus near their destination. Considering that the bus may be very crowded during peak hours, the system will also evaluate potential obstacles (such as standing passengers) on each path to ensure that the recommended seat not only meets the preferences but also ensures convenience.

[0102] S40, constructing a seat recommendation model according to the temperature distribution information and the congestion degree information, the travel preference behavior of the target passenger and the expected distance, and outputting the target seat recommended for the target passenger.

[0103] In step S20, the temperature distribution information of different seats is obtained, and in step S30, the travel preference behavior of the target passenger and the expected distance from the demand seat to the alighting port are obtained. This embodiment aims to model and recommend seats based on these data.

[0104] Specifically, the seat recommendation model is constructed according to the temperature distribution information and the congestion degree information, the travel preference behavior of the target passenger and the expected distance, and the target seat recommended for the target passenger is output, including:

[0105] The seat recommendation model is constructed:

[0106] G i = w1G(T i ) + w2G(C i ) + w3G(D i ) + w4G(P i ) + b

[0107] In the formula, G i represents the matching degree score of the ith seat and the target passenger, w1, w2, w3, and w4 are weight factors, b is a constant, and 0 < b ≤ 0.1 is satisfied; G(T i ), G(C i ), G(D i ), and G(P i ) are the matching degree scores of the ith seat and the target passenger in terms of temperature, crowding, distance, and riding preference, respectively.

[0108]

[0109]

[0110]

[0111]

[0112] In the formula, T i represents the temperature of the ith seat, T min and T max are the minimum and maximum values of the ideal temperature required by the target passenger, and T avg is the intermediate value of T min and T max ; M ij is the number of adjacent seats of the ith seat, and m is the number of occupied seats in M ij ; d io is the distance from the ith seat to the exit, and d min and d max are the minimum and maximum values of the expected distance of the target passenger.

[0113] According to the seat recommendation model, the matching degree score of each seat and the target passenger is calculated, and the seat with the highest matching degree score is identified from the unoccupied seats as the target seat and recommended to the target passenger.

[0114] By collecting and analyzing a large amount of ride behavior data, this embodiment can help the bus company better understand passenger demand and thus optimize operation strategy and service quality. By comprehensively considering factors such as temperature, crowding, distance, and personal preferences, the system can provide each passenger with a seat recommendation that best meets their needs, greatly improving passenger satisfaction. Finally, the final seat recommendation is presented to the target passenger in an intuitive way, such as through a large screen on the bus shelter or a map annotation on the mobile app.

[0115] Therefore, by matching the first passenger with a suitable seat in advance, the search time after boarding is reduced, especially during peak hours, which helps to speed up passenger flow and reduce congestion. Personalized seat recommendations take into account the passenger's personal preferences and actual needs, making the journey more comfortable and enjoyable; at the same time, clear disembarking path guidance also increases safety. The system can reasonably arrange seats according to real-time conditions to avoid excessive concentration in certain areas and vacancy in other places, thereby more efficiently utilizing the carriage space.

[0116] S50, in response to the confirmation result of the target passenger, when the target passenger determines to use the target seat, updating the crowding information and temperature distribution information of the remaining seats and synchronizing to all smart bus shelters, using the updated data to continue seat recommendation for the next passenger.

[0117] When the target passenger determines to use the target seat recommended by the system, the target passenger's selection confirmation of the recommended seat is received through the touch screen or mobile application. Then mark the seat selected by the target passenger as occupied, and record the relevant information of the passenger (such as boarding time, destination, etc.). Then update the crowding information and temperature distribution information and push them from the cloud server to all related smart bus shelters. Ensure that each bus shelter can receive the latest data in time to provide accurate seat recommendations for the next passenger.

[0118] In another embodiment, if the passenger is not satisfied with the target seat recommended by the system, it also includes:

[0119] When the target passenger refuses to use the target seat, send a continue matching instruction and a self-select seat instruction for the target passenger to choose;

[0120] When the target passenger responds to the continue matching instruction, other seats are recommended to the target passenger in order of matching score from high to low until the target passenger confirms to use a seat, and the seat usage state is updated;

[0121] When the target passenger responds to the self-select seat instruction, the seat selected by the target passenger is assigned to the target passenger, and the seat usage state is updated.

[0122] Through the system, the passenger is matched to a suitable seat in combination with the passenger confirmation, so that the user experience is greatly improved.

[0123] In summary, the data processing method for smart bus shelters based on digital analysis provided by the present application solves the problem of information asymmetry in the prior art by collecting and analyzing seat usage information and air conditioning status in the target vehicle, calculating temperature distribution and crowding information for different seats, and sending this information to the current smart bus shelter and other shelters for sharing. At the same time, for each target passenger waiting in line, the present application can identify their historical ride records and current needs, predict their preferred behavior, and construct a seat recommendation model based on temperature distribution and crowding information, thereby providing the target passenger with the optimal seat recommendation. This process not only improves passenger satisfaction but also achieves more rational resource allocation and improves the efficiency of using the space inside the vehicle. Finally, when the target passenger confirms the use of a recommended seat, the system will immediately update the relevant data and synchronize between all smart bus shelters, ensuring that subsequent passengers can also enjoy precise seat recommendation services. Therefore, the present application effectively improves the intelligence level and service quality of the public transportation system and provides a new solution for urban traffic management.

[0124] Reference Figure 2 In one embodiment, the present application also provides a data processing system for smart bus shelters based on digital analysis, which comprises:

[0125] The data collection unit 100 is used to collect seat usage information and air conditioning usage status in the target vehicle by taking the bus departing from the previous bus shelter as the target vehicle;

[0126] The data sharing unit 200 is used to calculate temperature distribution information for different seats based on the seat usage information and air conditioning usage status, calculate crowding information around different seats based on the seat usage information, and send the temperature distribution information and crowding information to the current smart bus shelter and share the data with other bus shelters;

[0127] The demand identification unit 300 is used to take the passenger at the top of the queue as the target passenger based on the queue order of passengers at the current smart bus shelter, receive the request instruction of the target passenger, identify the historical ride records and current ride demand information of the target passenger, predict the ride preference behavior of the target passenger based on the historical ride records, and evaluate the expected distance from the demand seat to the drop-off point of the target passenger based on the current ride demand information;

[0128] The seat recommendation unit 400 is used to construct a seat recommendation model based on the temperature distribution information and crowding information, the ride preference behavior of the target passenger, and the expected distance, and output the target seat recommended for the target passenger;

[0129] The data updating unit 500 is configured to update the crowdedness information and the temperature distribution information of the remaining seats and synchronize to all smart bus shelters in response to the confirmation result of the target passenger, and continue to recommend seats for the next passenger by using the updated data when the target passenger determines to use the target seat.

[0130] Preferably, the data sharing unit 200 is configured to calculate the temperature distribution information of different seats according to the seat usage information and the air conditioner usage state, and the temperature distribution information comprises:

[0131]

[0132] In the formula, T i represents the temperature of the i-th seat, is the average temperature in the vehicle compartment, ΔT a (d i ) represents the air conditioner influence factor, which is determined by the distance d ia from the i-th seat to the nearest air outlet of the air conditioner; ΔT hu (n j , d ij ) represents the human body heat dissipation increment, which is determined by the distance d ij from the i-th seat to the adjacent seat j and the number n j of passengers on the adjacent seat j, and N represents the total number of seats.

[0133] Preferably, the seat recommendation unit 400 is further configured to:

[0134] build a seat recommendation model:

[0135] G i = w1G(T i ) + w2G(C i ) + w3G(D i ) + w4G(P i ) + b

[0136] In the formula, G i represents the matching degree score of the i-th seat and the target passenger, w1, w2, w3, and w4 are weight factors, b is a constant, and 0 < b ≤ 0.1; G(T i ), G(C i ), G(D i ), and G(P i ) are the matching degree scores of the temperature, crowdedness, distance, and riding preference of the i-th seat and the target passenger, respectively.

[0137]

[0138]

[0139]

[0140]

[0141] In the formula, T i represents the temperature of the ith seat, T min , T max is the minimum and maximum value of the ideal temperature of the target passenger demand, T avg is the intermediate value of f min and T max ; M ij is the number of adjacent seats of the ith seat, and m is the number of occupied seats in M ij ; d io is the distance of the ith seat to the exit, d min , d max is the minimum and maximum value of the expected distance of the target passenger;

[0142] According to the seat recommendation model, the matching score of each seat with the target passenger is calculated, and the seat with the highest matching score is identified from the unoccupied seats as the target seat recommended to the target passenger.

[0143] Preferably, the data updating unit 500, after the confirmation result of the target passenger, further comprises:

[0144] When the target passenger refuses to use the target seat, a continue matching instruction and an autonomous seat selection instruction are sent for the target passenger to select;

[0145] When the target passenger responds to the continue matching instruction, other seats are sequentially recommended to the target passenger in descending order of matching scores until the target passenger confirms to use a seat, and the seat usage state is updated;

[0146] When the target passenger responds to the autonomous seat selection instruction, the seat autonomously selected by the target passenger is assigned to the target passenger, and the seat usage state is updated.

[0147] It can be understood that the system provided by the embodiment has functions or contains modules that can be used to execute the method described in the above method embodiment, and the specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0148] The application also provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device executes the method of any one of the above possible implementation manners.

[0149] The application further provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, the computer program comprises program instructions, and the program instructions, when executed by a processor of an electronic device, cause the processor to perform the method of any one of the possible implementation manners described above.

[0150] Those skilled in the art can clearly understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software manner depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein. Those skilled in the art can also clearly understand that each embodiment of the application describes each with emphasis, and for the convenience and brevity of description, the same or similar parts in different embodiments can not be described in detail, and therefore, the parts not described or not described in detail in a certain embodiment can be referred to in the description of other embodiments.

Claims

1. A smart bus shelter data processing method based on digitized analysis, characterized in that, The method comprises: The bus departing from the previous bus stop of the current intelligent bus shelter is taken as a target vehicle, and seat usage information and air conditioner usage state in the target vehicle are collected; Temperature distribution information of different seats is calculated according to the seat usage information and the air conditioner usage state; crowdedness information around different seats is calculated according to the seat usage information; the temperature distribution information and the crowdedness information are sent to the current intelligent bus shelter and shared with other bus shelters; Based on the queuing order of passengers at the current intelligent bus shelter, a passenger at the first place is taken as a target passenger; a request instruction of the target passenger is received, and historical riding records and current riding demand information of the target passenger are identified; riding preference behavior of the target passenger is predicted according to the historical riding records, and expected distance from a demand seat to an alighting port of the target passenger is evaluated according to the current riding demand information; A seat recommendation model is constructed according to the temperature distribution information and the crowdedness information, the riding preference behavior of the target passenger and the expected distance, and a target seat recommended for the target passenger is outputted; In response to a confirmation result of the target passenger, when the target passenger determines to use the target seat, crowdedness information and temperature distribution information of remaining seats are updated and synchronized to all intelligent bus shelters, and updated data is used to continue seat recommendation for the next passenger.

2. The data processing method of the smart bus shelter based on digitized analysis according to claim 1, characterized in that, The temperature distribution information of different seats is calculated according to the seat usage information and the air conditioner usage state, comprising: where T i represents the temperature of the ith seat, is the average temperature in the vehicle cabin, ΔT a (d ia ) represents the air conditioning influence factor, which is determined by the distance d ia from the seat i to the nearest air outlet; ΔT hu (n j ,d ij ) represents the human body heat dissipation increment, which is determined by the distance d ij from the ith seat to the adjacent seat j and the number of passengers n j of the adjacent seat j, and N represents the total number of seats. 3.The digital analysis-based intelligent bus shelter data processing method according to claim 2, characterized in that, The seat recommendation model is constructed according to the temperature distribution information and the crowdedness information, the riding preference behavior of the target passenger and the expected distance, and the target seat recommended for the target passenger is outputted, comprising: The seat recommendation model is constructed: G i = w1G(T i ) + w2G(C i ) + w3G(D i ) + w4G(P i ) + b In the formula, G i represents the matching degree score of the ith seat and the target passenger, w1, w2, w3, and w4 are weight factors, b is a constant, and satisfies 0 < b ≤ 0.1; G(T i ), G(C i ), G(D i ), and G(P i ) are respectively the matching degree scores of the ith seat and the target passenger in temperature, crowding degree, distance, and ride preference. where T i represents the temperature of the ith seat, T min , max are the minimum and maximum values of the ideal temperature of the target passenger demand, T avg is the intermediate value of T min and T max ; M ij is the number of adjacent seats j of the ith seat, m ij is the number of occupied seats among M ij ; d io is the distance of the ith seat to the exit, d min , d max are the minimum and maximum values of the desired distance of the target passenger; The matching degree score of each seat to the target passenger is calculated according to the seat recommendation model, and the seat with the highest matching degree score is identified from unoccupied seats as the target seat recommended to the target passenger.

4. The data processing method of the smart bus shelter based on digitized analysis according to claim 3, characterized in that, After the response to the confirmation result of the target passenger, it further comprises: When the target passenger refuses to use the target seat, a continue matching instruction and a self-selection instruction are sent for the target passenger to select; When the target passenger responds to the continue matching instruction, other seats are recommended to the target passenger in order of descending matching degree score until the target passenger confirms to use a seat, and the seat usage state is updated; When the target passenger responds to the self-selection instruction, the seat selected by the target passenger is assigned to the target passenger, and the seat usage state is updated.

5. A smart bus shelter data processing system based on digitized analysis, characterized by, The system comprises: A data collection unit configured to take a bus departing from a previous bus stop of a current intelligent bus shelter as a target vehicle, and collect seat usage information and air conditioner usage state in the target vehicle; A data sharing unit configured to calculate temperature distribution information of different seats according to the seat usage information and the air conditioner usage state; calculate crowdedness information around different seats according to the seat usage information; send the temperature distribution information and the crowdedness information to the current intelligent bus shelter, and share data with other bus shelters; The demand identification unit is configured to take a passenger in the first place in a queue as a target passenger based on a queuing order of current passengers of the smart bus shelter, receive a request instruction of the target passenger, identify historical bus-riding records and current bus-riding demand information of the target passenger, predict a bus-riding preference behavior of the target passenger based on the historical bus-riding records, and evaluate an expected distance from a seat to an alighting port of the target passenger based on the current bus-riding demand information. The seat recommendation unit is configured to construct a seat recommendation model based on temperature distribution information and congestion degree information, the bus-riding preference behavior of the target passenger, and the expected distance, and output a target seat recommended for the target passenger. The data updating unit is configured to update the congestion degree information and the temperature distribution information of remaining seats and synchronize the updated information to all smart bus shelters in response to a confirmation result of the target passenger, and continue to recommend seats for a next passenger by using the updated data.

6. The digitized analysis based intelligent bus shelter data processing system according to claim 5, wherein, The data sharing unit is configured to calculate temperature distribution information of different seats based on seat usage information and an air conditioner usage state, including: where T i represents the temperature of the ith seat, is the average temperature in the car, ΔT a (d ia ) represents the air conditioning influence factor, the size of which is determined by the distance d ia from the seat i to the nearest air outlet of the air conditioner; ΔT hu (n j , d ij ) represents the heat dissipation increment of the human body, the size of which is determined by the distance d ij from the ith seat to the adjacent seat j and the number of passengers n j of the adjacent seat j, and N represents a total of N seats.

7. The digitized analysis based intelligent bus shelter data processing system according to claim 6, characterized in that, The seat recommendation unit is further configured to: construct a seat recommendation model, G i = w1G(T i ) + w2G(C i ) + w3G(D i ) + w4G(P i ) + b In the formula, G i represents the matching degree score of the ith seat and the target passenger, w1, w2, w3, and w4 are weight factors, b is a constant, and 0 < b ≤ 0.1 is satisfied; G(T i ), G(C i ), G(D i ), and G(P i ) are respectively the matching degree scores of the ith seat and the target passenger in temperature, crowding degree, distance, and ride preference. where T i represents the temperature of the ith seat, T min , T max are the minimum and maximum values of the ideal temperature of the target passenger demand, T avg is the intermediate value of T min and T max ; M ij is the number of adjacent seats j of the ith seat, m ij is the number of occupied seats among M ij ; d io is the distance of the ith seat to the exit, d min , d max are the minimum and maximum values of the desired distance of the target passenger; calculate a matching degree score of each seat with the target passenger, and identify a seat with the highest matching degree score from unoccupied seats as the target seat recommended for the target passenger. 8.The smart bus shelter data processing system based on digitized analysis of claim 7, wherein, The data updating unit is further configured to, after the response to the confirmation result of the target passenger, when the target passenger refuses to use the target seat, send a continue matching instruction and a self-selected seat instruction for the target passenger to select; when the target passenger responds to the continue matching instruction, recommend other seats to the target passenger in a descending order of matching degree scores until the target passenger confirms to use a seat, and update a seat usage state; when the target passenger responds to the self-selected seat instruction, assign a seat selected by the target passenger to the target passenger, and update the seat usage state.

9. An electronic device, comprising: including: a processor and a memory, the memory being configured to store computer program code including computer instructions, when the processor executes the computer instructions, the electronic device executes the smart bus shelter data processing method based on digital analysis according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program including program instructions, when the program instructions are executed by a processor of an electronic device, the processor executes the smart bus shelter data processing method based on digital analysis according to any one of claims 1 to 4.

Images