Intelligent electronic stop board data management system and method based on big data

Abstract

The invention discloses an intelligent electronic stop board data management system and method based on big data, and relates to the technical field of electronic stop board data management, and the method comprises the steps: S10, predicting a continuing coefficient between target vehicles stopping at two adjacent travel nodes; s20, planning an emergency travel plan and a normal travel plan of the target passenger; s30, the adaptation degree between the target passenger and each type of travel plan is analyzed, and a target travel plan of the target passenger is obtained through adjustment; and S40, the intelligent terminal of the target passenger calls the target stop board data on each target intelligent electronic stop board according to the target travel plan. According to the invention, by acquiring the intelligent electronic stop board data, the emergency travel demand of the passenger can be met and the most comfortable travel demand can also be planned for the passenger before the passenger arrives at the riding station, so that the management effect of the intelligent electronic stop board data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic bus stop sign data management, and in particular to an intelligent electronic bus stop sign data management system and method based on big data. Background Art

[0002] Smart electronic bus stops are public transportation facilities that integrate modern information technology. They typically feature high-definition displays that display bus arrival times, route information, and vehicle status in real time. Connected to the bus dispatch system, these smart electronic bus stops provide passengers with accurate and timely bus travel information, helping them better plan their journeys and reduce waiting anxiety.

[0003] Currently, the electronic display board in the bus dispatch system can display the real-time information of the vehicle. This requires passengers to arrive at the boarding station to understand the boarding information displayed on the electronic board. For passengers with urgent travel needs, it is impossible to obtain the real-time information of the vehicle in advance, so that there is no guarantee that the passengers can take the target vehicle of the nearest trip. At the same time, the passengers cannot know whether the target vehicle can meet the passengers' travel needs. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent electronic bus stop sign data management system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a data management method for intelligent electronic bus stop signs based on big data, the method comprising:

[0006] S10: Based on the passenger's preset travel trajectory, obtain the real-time driving information and real-time number of people waiting to board the target vehicle displayed on each target intelligent electronic bus stop, integrate the real-time information of the target vehicle, and predict the connection coefficient between the target vehicles parked at two adjacent travel nodes;

[0007] S20: Plan emergency travel plans and normal travel plans for target passengers;

[0008] S30: Analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger;

[0009] S40: The target passenger's smart terminal retrieves the target bus stop data on each target smart electronic bus stop according to the target travel plan, and the target passenger completes the travel plan according to the retrieved information.

[0010] Furthermore, the S10 includes:

[0011] S101: Based on the travel trajectory preset by the target passenger, the travel nodes in the travel trajectory are identified. The travel nodes in the travel trajectory are sequentially numbered according to the movement order of the target passenger on the travel trajectory. The numbering result is: i = 1, 2, ..., m, where m represents the total number of travel nodes. The real-time driving information of the target vehicle and the real-time number of people waiting to board the vehicle displayed on the intelligent electronic bus stop installed at each travel node are obtained. The intelligent electronic bus stop installed at travel node i is recorded as the target intelligent electronic bus stop i, and the target vehicle traveling to the target intelligent electronic bus stop i is recorded as the target vehicle i.

[0012] S102: The driving information includes the real-time capacity value of the target vehicle and the estimated time for the target vehicle to arrive at the target intelligent electronic bus stop. At time u, the estimated time T for the target vehicle i+1 that is closest to the travel node i+1 to arrive at the target intelligent electronic bus stop i+1 is u(i+1) , and the estimated arrival time T of the target vehicle i that recently stopped at travel node i at the target intelligent electronic bus stop i ui The difference between u(i+1→i) Calculate the average transfer time R between the passenger travel node i and the travel node i+1 u(i+1→i) To obtain, u(i+1→i) With R u(i+1→i) The difference between R′ u(i+1→i) Calculate if(R′ u(i+1→i) ≥0,R′ u(i+1→i) ,-1)+0.5, and calculate the first screening coefficient x of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) ;

[0013] In [u, T u(i+1) ] time period, the number of people waiting to board displayed on the target intelligent electronic bus stop i+1 and the capacity value of the target vehicle i+1 parked at the travel node i+1 are collected at time intervals y. Based on the linear model Y=k×X+b, a model D1 of the number of people waiting to board-time and a model D2 of the capacity value-time are constructed, and the slope constants k1 of the model D1 and k2 of the model D2 are obtained;

[0014] At time u, the ratio W between the number of people waiting to board the bus displayed on the target intelligent electronic bus stop i+1 and the maximum number of passengers G that the target vehicle i+1 can accommodate at the travel node i+1 is calculated. u(i+1) Calculate and calculate W u(i+1) ×(1+k1) and [Q u(i+1) ×(1+k2) / G] and the sum P u(i+1) Calculate, where Q u(i+1)represents the capacity value of target vehicle i+1 that stops at travel node i+1 at time u. u(i+1) >1,-1,1-P u(i+1) )+0.5, and calculate the second screening coefficient y of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) ;

[0015] S103: At time u, according to K u(i+1) =g1×x u(i+1→i) +g2×y u(i+1→i) The connection coefficient between the target vehicle i that recently stopped at the travel node i and the target vehicle i+1 that recently stopped at the travel node i+1 is predicted, where g1 and g2 both represent proportional coefficients and g1+g2=1.

[0016] Furthermore, the S20 includes:

[0017] S201: When 0.2<K u(i+1) When ≤1, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the first target vehicle screening set M as a set of data;

[0018] When 0≤K u(i+1) When ≤0.2, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the second target vehicle screening set N as a set of data; u(i+1) +V i+1 The train number and serial number of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the third target vehicle screening set C as a set of data, where V i+1 represents the interval departure time of the target vehicle that stops at travel node i+1;

[0019] When K u(i+1) When <0, it will u(i+1) +V i+1 The train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the fourth target vehicle screening set Z as a set of data;

[0020] S202: Integrate the first target vehicle screening set M, the second target vehicle screening set N, and the fourth target vehicle screening set Z in ascending order of travel node numbers to obtain an emergency travel plan for the target passenger;

[0021] S203: Integrate the first target vehicle screening set M, the third target vehicle screening set C, and the fourth target vehicle screening set Z in ascending order of the travel node numbers to obtain a normal travel plan of the target passenger.

[0022] Furthermore, the S30 includes:

[0023] S301: When a target passenger boards target vehicle 1 that stops at travel node 1, the target passenger's emergency travel plan and normal travel plan are determined, and an intersection travel node between the determined emergency travel plan and normal travel plan is obtained;

[0024] S302: Identify abnormal behavior of the target passenger when riding various modes of transportation. The abnormal behavior is identified by the smart device worn by the target passenger. Based on the identification results, analyze the compatibility between the target passenger and the travel plans of various types at each intersection travel node.

[0025] S303: The travel plan at the intersection travel node corresponding to the maximum fitness value is retained, and the emergency travel plan is adjusted based on the retained travel plan to obtain the target travel plan of the target passenger.

[0026] Furthermore, the specific method of analyzing the compatibility between the target passenger and the travel plans of each type at each intersection travel node in S302 is as follows:

[0027] Obtain the target passenger's historical abnormal reaction behavior when riding a travel tool. Abnormal reaction behavior refers to actions that are inconsistent with the target passenger's normal behavior. Collect the probability values of the target user's travel plan being adjusted in different adjustment directions under each historical abnormal reaction behavior. The adjustment direction includes postponing the boarding time at the next travel node and maintaining the boarding time at the next travel node;

[0028] Randomly select an intersection travel node and number the selected intersection travel node as τ, τ = 1, 2, ..., m, identify the abnormal reaction behavior of the target passenger when riding the target vehicle τ, and match the identified abnormal reaction behavior with the historical abnormal reaction behavior;

[0029] Obtain the probability value λ1 of the target user's travel plan being adjusted to postpone the boarding time at the next travel node under the historical abnormal reaction behavior of successful matching, and the probability value λ2 of the travel plan being adjusted to maintain the boarding time at the next travel node. Take λ1 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the normal travel plan, and take λ2 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the emergency travel plan.

[0030] An intelligent electronic bus stop data management system based on big data, the system includes a bus stop data analysis module, a travel plan planning module, a target travel plan determination module and a bus stop data management module;

[0031] The bus stop data analysis module is used to predict the connection coefficient between target vehicles parked at two adjacent travel nodes;

[0032] The travel plan planning module is used to plan the emergency travel plan and normal travel plan of the target passenger;

[0033] The target travel plan determination module is used to analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger;

[0034] The bus stop data management module is used to retrieve the target bus stop data on each target intelligent electronic bus stop according to the target travel plan.

[0035] Furthermore, the bus stop data analysis module includes a travel node identification unit, a screening coefficient calculation unit and a connection coefficient prediction unit;

[0036] The travel node identification unit identifies the travel nodes in the travel trajectory according to the preset travel trajectory of the target passenger, and obtains the real-time driving information of the target vehicle and the real-time number of people waiting to board the vehicle displayed on the intelligent electronic bus stop installed at each travel node;

[0037] The screening coefficient calculation unit obtains a first screening coefficient and a second screening coefficient of the target vehicle that has recently stopped at each travel node based on the real-time driving information of the target vehicle and the real-time number of people waiting to get on the vehicle displayed on the intelligent electronic bus stop installed at each travel node;

[0038] The connection coefficient prediction unit calculates the connection coefficients between target vehicles that have recently stopped at adjacent travel nodes based on the first screening coefficient and the second screening coefficient.

[0039] Furthermore, the travel plan planning module includes a target vehicle screening set acquisition unit, an emergency travel plan planning unit and a normal travel plan planning unit;

[0040] The target vehicle screening set acquisition unit obtains the first, second, third and fourth target vehicle screening sets according to the connection coefficients between the target vehicles that have recently stopped at adjacent travel nodes;

[0041] The emergency travel plan planning unit integrates the first target vehicle screening set, the second target vehicle screening set, and the fourth target vehicle screening set in ascending order of travel node numbers to obtain an emergency travel plan for the target passenger;

[0042] The normal travel plan planning unit integrates the first target vehicle screening set, the third target vehicle screening set and the fourth target vehicle screening set in ascending order of travel node numbers to obtain a normal travel plan for the target passenger.

[0043] Furthermore, the target travel plan determination module includes an intersection travel node acquisition unit, a fitness calculation unit and a target travel plan determination unit;

[0044] The intersection travel node acquisition unit acquires the intersection travel node between the determined emergency travel plan and the normal travel plan;

[0045] The fitness calculation unit analyzes the fitness between the target passenger and the ride plan at each intersection travel node in each type of travel plan;

[0046] The target travel plan determination unit reserves the travel plan at the intersection travel node corresponding to the maximum fitness value, and adjusts the emergency travel plan based on the reserved travel plan to obtain the target travel plan of the target passenger.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention analyzes the real-time driving information of vehicles and the real-time number of people waiting to board displayed on the intelligent electronic bus stop, analyzes the connection coefficient between the target vehicles that have recently stopped at two adjacent bus stops, and plans the emergency travel plan and normal travel plan of the target passengers. Before the passengers arrive at the boarding station, the present invention can not only meet the passengers' emergency travel needs, but also plan the most comfortable travel needs for the passengers, thereby improving the management effect of the intelligent electronic bus stop data.

[0049] 2. When planning a travel plan, the present invention takes into account whether the vehicle's capacity can meet the passengers' travel needs, ensuring that planning a travel plan based on the data of the intelligent electronic bus stop is practical.

[0050] 3. The present invention is based on the historical abnormal reaction behavior of the target passenger when riding a travel tool, and analyzes the adjustment of the travel plan of the target passenger under different adjustment directions under each historical abnormal reaction behavior. Based on the analysis results, the adaptability between the target passenger and the travel plan at each intersection travel node in each type of travel plan is analyzed, and the target travel plan of the target passenger is obtained, thereby improving the adaptability between the target travel plan and the target passenger. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a workflow diagram of a big data-based intelligent electronic bus stop data management method of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] Example: Figure 1 As shown, the present invention provides a big data-based intelligent electronic bus stop data management system and method technical solution, a big data-based intelligent electronic bus stop data management method, the method includes:

[0054] S10: Based on the passenger's preset travel trajectory, obtain the real-time driving information and real-time number of people waiting to board the target vehicle displayed on each target intelligent electronic bus stop, integrate the real-time information of the target vehicle, and predict the connection coefficient between the target vehicles parked at two adjacent travel nodes;

[0055] The S10 includes:

[0056] S101: Based on the travel trajectory preset by the target passenger, the travel nodes in the travel trajectory are identified. The travel nodes refer to the passenger's boarding stations. For example, if a passenger wants to travel from place A to place B, the passenger enters the starting point and the end point in the navigation system. The starting point is place A and the end point is place B. If the passenger selects the bus as a means of transportation, the route trajectory generated by the navigation system by default is the passenger's preset travel trajectory. The point where the passenger starts to board the selected means of transportation in the travel trajectory is the travel node. The travel nodes in the travel trajectory are numbered in sequence according to the movement order of the target passenger on the travel trajectory. The result is: i = 1, 2, …, m; m represents the total number of travel nodes. The real-time driving information and the real-time number of people waiting to board the target vehicle displayed on the smart electronic bus stop installed at each travel node are obtained. The smart electronic bus stop installed at travel node i is recorded as the target smart electronic bus stop i, and the target vehicle traveling to the target smart electronic bus stop i is recorded as the target vehicle i. If the passenger's travel trajectory between travel node i and travel node i+1 is consistent with the travel trajectory of vehicle A between travel node i and travel node i+1, then vehicle A is considered to be the target vehicle displayed on the smart electronic bus stop installed at travel node i.

[0057] S102: Driving information includes the target vehicle's real-time capacity value and the target vehicle's estimated arrival time at the target intelligent electronic bus stop. The real-time capacity value = the total number of passengers the vehicle can accommodate in real time / the maximum number of passengers the vehicle can accommodate. The target vehicle's estimated arrival time at the target intelligent electronic bus stop is calculated based on real-time road conditions and historical data. This is a prior art method. At time u, the target vehicle i+1 that is closest to the travel node i+1 is estimated to arrive at the target intelligent electronic bus stop i+1 at time T. u(i+1) , and the estimated arrival time T of the target vehicle i that recently stopped at travel node i at the target intelligent electronic bus stop i ui The difference between u(i+1→i) Calculate the average transfer time R between the passenger travel node i and the travel node i+1 u(i+1→i) To obtain, u(i+1→i) With R u(i+1→i) The difference between R′ u(i+1→i) Calculate if(R′ u(i+1→i) ≥0,R′ u(i+1→i) ,-1)+0.5, and calculate the first screening coefficient x of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) The basic syntax of the if function = if(condition, value if true, value if false), the target vehicle i+1 that was most recently parked at travel node i+1 has not arrived at travel node i+1 at time u.

[0058] In [u, T u(i+1) ] time period, the number of people waiting to get on the target intelligent electronic bus stop i+1 and the capacity value of the target vehicle i+1 parked at the travel node i+1 are collected at time intervals y. Based on the linear model Y=k×X+b, a number-of-people-waiting-boarding-time model D1 and a capacity value-of-capacity-time model D2 are constructed, where time is the independent variable, the number of people waiting to get on the bus and the capacity value are the dependent variables, and the slope constant k1 of model D1 and the slope constant k2 of model D2 are obtained;

[0059] At time u, the ratio W between the number of people waiting to board the bus displayed on the target intelligent electronic bus stop i+1 and the maximum number of passengers G that the target vehicle i+1 can accommodate at the travel node i+1 is calculated. u(i+1) Calculate and calculate W u(i+1) ×(1+k1) and [Q u(i+1) ×(1+k2) / G] and the sum P u(i+1) For calculation, it is assumed that the maximum number of passengers that target vehicles parked at the same travel node can accommodate is the same, where Q u(i+1) represents the capacity value of target vehicle i+1 that stops at travel node i+1 at time u.u(i+1) >1,-1,1-P u(i+1) )+0.5, and calculate the second screening coefficient y of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) ;

[0060] S103: At time u, according to K u(i+1) =g1×x u(i+1→i) +g2×y u(i+1→i) Predict the connection coefficient between the target vehicle i that recently stopped at travel node i and the target vehicle i+1 that recently stopped at travel node i+1, where g1 and g2 represent proportional coefficients and g1+g2=1;

[0061] S20: Plan emergency travel plans and normal travel plans for target passengers;

[0062] The S20 includes:

[0063] S201: When 0.2<K u(i+1) When ≤1, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the first target vehicle screening set M as a set of data. The representation format of this set of data is: (train number, i+1);

[0064] When 0≤K u(i+1) When ≤0.2, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the second target vehicle screening set N as a set of data; u(i+1) +V i+1 The train number and serial number of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the third target vehicle screening set C as a set of data, where V i+1 represents the interval departure time of the target vehicle that stops at travel node i+1;

[0065] When K u(i+1) When <0, it will u(i+1) +V i+1 The train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the fourth target vehicle screening set Z as a set of data;

[0066] S202: Integrate the first target vehicle screening set M, the second target vehicle screening set N, and the fourth target vehicle screening set Z in ascending order of travel node numbers to obtain an emergency travel plan for the target passenger;

[0067] S203: Integrate the first target vehicle screening set M, the third target vehicle screening set C, and the fourth target vehicle screening set Z in ascending order of travel node numbers to obtain a normal travel plan of the target passenger;

[0068] S30: Analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger;

[0069] The S30 includes:

[0070] S301: When a target passenger boards target vehicle 1 that stops at travel node 1, the target passenger's emergency travel plan and normal travel plan are determined, and an intersection travel node between the determined emergency travel plan and normal travel plan is obtained;

[0071] S302: Identify the target passenger's abnormal reaction behavior when riding various modes of transportation. The abnormal reaction behavior is identified by the smart device worn by the target passenger. The identification data is obtained to obtain the target passenger's authorization. Based on the identification results, the compatibility between the target passenger and the travel plans of various types at each intersection travel node is analyzed. The specific method is as follows:

[0072] Obtain the target passenger's historical abnormal reaction behaviors when riding a transportation tool. Abnormal reaction behaviors refer to actions that are inconsistent with the target passenger's normal behavior. For example, the target passenger checks the time on the target vehicle at a frequency of S, while the target passenger normally checks the time at a frequency of s. When S>s(1+β), if the target passenger frequently checks the time and the checking frequency>s(1+β), it is considered that frequent time checking is an abnormal reaction behavior of the target passenger. Where β represents the error coefficient. Collect the probability values of the target user's travel plan being adjusted in different adjustment directions under each historical abnormal reaction behavior. The adjustment directions include postponing the boarding time at the next travel node and maintaining the boarding time at the next travel node.

[0073] Randomly select an intersection travel node and number the selected intersection travel node as τ, τ = 1, 2, ..., m, identify the abnormal reaction behavior of the target passenger when riding the target vehicle τ, and match the identified abnormal reaction behavior with the historical abnormal reaction behavior;

[0074] Obtain the probability value λ1 of the target user's travel plan being adjusted to postpone the boarding time at the next travel node under the historical abnormal reaction behavior of the target user that is successfully matched, and the probability value λ2 of the travel plan being adjusted to maintain the boarding time at the next travel node. Use λ1 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the normal travel plan, and use λ2 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the emergency travel plan;

[0075] S303: The travel plan at the intersection travel node corresponding to the maximum fitness value is retained. Based on the retained travel plan, the emergency travel plan is adjusted. The adjustment method is as follows: a random intersection travel node is selected, and the travel plan at the selected intersection travel node in the emergency travel plan is replaced with the retained travel plan at the selected intersection travel node to obtain the target travel plan of the target passenger.

[0076] S40: The target passenger's smart terminal retrieves the target bus stop data on each target smart electronic bus stop according to the target travel plan, and the target passenger completes the travel plan based on the retrieved information. The target bus stop data refers to the estimated arrival time of the target vehicle at the target smart electronic bus stop and the train number of the target vehicle.

[0077] An intelligent electronic bus stop data management system based on big data, the system includes a bus stop data analysis module, a travel plan planning module, a target travel plan determination module and a bus stop data management module;

[0078] The bus stop data analysis module is used to predict the connection coefficient between target vehicles parked at two adjacent travel nodes;

[0079] The bus stop data analysis module includes a travel node identification unit, a screening coefficient calculation unit, and a connection coefficient prediction unit;

[0080] The travel node identification unit identifies the travel nodes in the travel trajectory according to the preset travel trajectory of the target passenger, and obtains the real-time driving information of the target vehicle and the real-time number of people waiting to board the vehicle displayed on the intelligent electronic bus stop installed at each travel node;

[0081] The screening coefficient calculation unit obtains the first screening coefficient and the second screening coefficient of the target vehicle that is closest to each travel node according to the real-time driving information of the target vehicle and the real-time number of people waiting to get on the vehicle displayed on the intelligent electronic bus stop board installed at each travel node;

[0082] The connection coefficient prediction unit calculates the connection coefficients between target vehicles that have recently stopped at adjacent travel nodes based on the first screening coefficient and the second screening coefficient;

[0083] The travel plan module is used to plan the emergency travel plan and normal travel plan of the target passengers;

[0084] The travel plan planning module includes a target vehicle screening set acquisition unit, an emergency travel plan planning unit, and a normal travel plan planning unit;

[0085] The target vehicle screening set acquisition unit obtains the first, second, third, and fourth target vehicle screening sets according to the connection coefficients between the target vehicles that have recently stopped at adjacent travel nodes;

[0086] The emergency travel plan planning unit integrates the first target vehicle screening set, the second target vehicle screening set, and the fourth target vehicle screening set in ascending order of the travel node numbers to obtain an emergency travel plan for the target passenger;

[0087] The normal travel plan planning unit integrates the first target vehicle screening set, the third target vehicle screening set, and the fourth target vehicle screening set in ascending order of the travel node numbers to obtain the normal travel plan of the target passenger;

[0088] The target travel plan determination module is used to analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger;

[0089] The target travel plan determination module includes an intersection travel node acquisition unit, a fitness calculation unit and a target travel plan determination unit;

[0090] The intersection travel node acquisition unit acquires the intersection travel node between the determined emergency travel plan and the normal travel plan;

[0091] The fitness calculation unit analyzes the fitness between the target passenger and the ride plan at each intersection travel node in each type of travel plan;

[0092] The target travel plan determination unit retains the travel plan at the intersection travel node corresponding to the maximum fitness value, and adjusts the emergency travel plan based on the retained travel plan to obtain the target travel plan of the target passenger;

[0093] The bus stop data management module is used to retrieve the target bus stop data on each target intelligent electronic bus stop according to the target travel plan.

[0094] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for managing intelligent electronic bus stop data based on big data, characterized by: The method comprises: S10: Based on the passenger's preset travel trajectory, obtain the real-time driving information and real-time number of people waiting to board the target vehicle displayed on each target intelligent electronic bus stop, integrate the real-time information of the target vehicle, and predict the connection coefficient between the target vehicles parked at two adjacent travel nodes; S20: Plan emergency travel plans and normal travel plans for target passengers; S30: Analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger; S40: The target passenger's smart terminal retrieves the target bus stop data on each target smart electronic bus stop according to the target travel plan, and the target passenger completes the travel plan according to the retrieved information.

2. The method for managing data of an intelligent electronic bus stop sign based on big data according to claim 1, characterized in that: The S10 includes: S101: Based on the travel trajectory preset by the target passenger, the travel nodes in the travel trajectory are identified. The travel nodes in the travel trajectory are sequentially numbered according to the movement order of the target passenger on the travel trajectory. The numbering result is: i = 1, 2, ..., m, where m represents the total number of travel nodes. The real-time driving information of the target vehicle and the real-time number of people waiting to board the vehicle displayed on the intelligent electronic bus stop installed at each travel node are obtained. The intelligent electronic bus stop installed at travel node i is recorded as the target intelligent electronic bus stop i, and the target vehicle traveling to the target intelligent electronic bus stop i is recorded as the target vehicle i. S102: The driving information includes the real-time capacity value of the target vehicle and the estimated time for the target vehicle to arrive at the target intelligent electronic bus stop. At time u, the estimated time T for the target vehicle i+1 that is closest to the travel node i+1 to arrive at the target intelligent electronic bus stop i+1 is u(i+1) , and the estimated arrival time T of the target vehicle i that recently stopped at travel node i at the target intelligent electronic bus stop i ui The difference between u(i+1→i) Calculate the average transfer time R between the passenger travel node i and the travel node i+1 u(i+1→i) To obtain, u(i+1→i) With R u(i+1→i) The difference between R′ u(i+1→i) Calculate if(R′ u(i+1→i) ≥0,R′ u(i+1→i) ,-1)+0.5, and calculate the first screening coefficient x of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) ; In [u, T u(i+1) ] time period, the number of people waiting to board displayed on the target intelligent electronic bus stop i+1 and the capacity value of the target vehicle i+1 parked at the travel node i+1 are collected at time intervals y. Based on the linear model Y=k×X+b, a model D1 of the number of people waiting to board-time and a model D2 of the capacity value-time are constructed, and the slope constants k1 of the model D1 and k2 of the model D2 are obtained; At time u, the ratio W between the number of people waiting to board the bus displayed on the target intelligent electronic bus stop i+1 and the maximum number of passengers G that the target vehicle i+1 can accommodate at the travel node i+1 is calculated. u(i+1) Calculate and calculate W u(i+1) ×(1+k1) and [Q u(i+1) ×(1+k2) / G] and the sum P u(i+1) Calculate, where Q u(i+1) represents the capacity value of target vehicle i+1 that stops at travel node i+1 at time u. u(i+1) >1,-1,1-P u(i+1) )+0.5, and calculate the second screening coefficient y of the target vehicle i+1 that is closest to the travel node i+1. u(i+1→i) ; S103: At time u, according to K u(i+1) =g1×x u(i+1→i) +g2×y u(i+1→i) The connection coefficient between the target vehicle i that recently stopped at the travel node i and the target vehicle i+1 that recently stopped at the travel node i+1 is predicted, where g1 and g2 both represent proportional coefficients and g1+g2=1.

3. The method for managing data of an intelligent electronic bus stop sign based on big data according to claim 2, characterized in that: The S20 includes: S201: When 0.2<K u(i+1) When ≤1, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the first target vehicle screening set M as a set of data; When 0≤K u(i+1) When ≤0.2, the train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at time u are put into the second target vehicle screening set N as a set of data; u(i+1) +V i+1 The train number and serial number of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the third target vehicle screening set C as a set of data, where V i+1 represents the interval departure time of the target vehicle that stops at travel node i+1; When K u(i+1) When <0, it will u(i+1) +V i+1 The train number and serial number i+1 of the target vehicle i+1 that stops at the travel node i+1 at the moment are put into the fourth target vehicle screening set Z as a set of data; S202: Integrate the first target vehicle screening set M, the second target vehicle screening set N, and the fourth target vehicle screening set Z in ascending order of travel node numbers to obtain an emergency travel plan for the target passenger; S203: Integrate the first target vehicle screening set M, the third target vehicle screening set C, and the fourth target vehicle screening set Z in ascending order of the travel node numbers to obtain a normal travel plan of the target passenger.

4. The method for managing data of an intelligent electronic bus stop sign based on big data according to claim 3, characterized in that: The S30 includes: S301: When a target passenger boards target vehicle 1 that stops at travel node 1, the target passenger's emergency travel plan and normal travel plan are determined, and an intersection travel node between the determined emergency travel plan and normal travel plan is obtained; S302: Identify abnormal behavior of the target passenger when riding various modes of transportation. The abnormal behavior is identified by the smart device worn by the target passenger. Based on the identification results, analyze the compatibility between the target passenger and the travel plans of various types at each intersection travel node. S303: The travel plan at the intersection travel node corresponding to the maximum fitness value is retained, and the emergency travel plan is adjusted based on the retained travel plan to obtain the target travel plan of the target passenger.

5. The method for managing data of an intelligent electronic bus stop sign based on big data according to claim 4, characterized in that: The specific method of analyzing the compatibility between the target passenger and the travel plans of each type at each intersection travel node in S302 is as follows: Obtain the target passenger's historical abnormal reaction behavior when riding a travel tool. Abnormal reaction behavior refers to actions that are inconsistent with the target passenger's normal behavior. Collect the probability values of the target user's travel plan being adjusted in different adjustment directions under each historical abnormal reaction behavior. The adjustment direction includes postponing the boarding time at the next travel node and maintaining the boarding time at the next travel node; Randomly select an intersection travel node and number the selected intersection travel node as τ, τ = 1, 2, ..., m, identify the abnormal reaction behavior of the target passenger when riding the target vehicle τ, and match the identified abnormal reaction behavior with the historical abnormal reaction behavior; Obtain the probability value λ1 of the target user's travel plan being adjusted to postpone the boarding time at the next travel node under the historical abnormal reaction behavior of successful matching, and the probability value λ2 of the travel plan being adjusted to maintain the boarding time at the next travel node. Take λ1 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the normal travel plan, and take λ2 as the fitness between the target passenger and the boarding plan at the intersection travel node τ in the emergency travel plan.

6. A big data-based intelligent electronic bus stop sign data management system for implementing the big data-based intelligent electronic bus stop sign data management method according to any one of claims 1 to 5, characterized in that: The system includes a bus stop data analysis module, a travel plan planning module, a target travel plan determination module and a bus stop data management module; The bus stop data analysis module is used to predict the connection coefficient between target vehicles parked at two adjacent travel nodes; The travel plan planning module is used to plan the emergency travel plan and normal travel plan of the target passenger; The target travel plan determination module is used to analyze the compatibility between the target passenger and various types of travel plans, and adjust the target travel plan of the target passenger; The bus stop data management module is used to retrieve the target bus stop data on each target intelligent electronic bus stop according to the target travel plan.

7. The big data-based intelligent electronic bus stop sign data management system according to claim 6, characterized in that: The bus stop data analysis module includes a travel node identification unit, a screening coefficient calculation unit and a connection coefficient prediction unit; The travel node identification unit identifies the travel nodes in the travel trajectory according to the preset travel trajectory of the target passenger, and obtains the real-time driving information of the target vehicle and the real-time number of people waiting to board the vehicle displayed on the intelligent electronic bus stop installed at each travel node; The screening coefficient calculation unit obtains a first screening coefficient and a second screening coefficient of the target vehicle that has recently stopped at each travel node based on the real-time driving information of the target vehicle and the real-time number of people waiting to get on the vehicle displayed on the intelligent electronic bus stop installed at each travel node; The connection coefficient prediction unit calculates the connection coefficients between target vehicles that have recently stopped at adjacent travel nodes based on the first screening coefficient and the second screening coefficient.

8. The big data-based intelligent electronic bus stop sign data management system according to claim 7, characterized in that: The travel plan planning module includes a target vehicle screening set acquisition unit, an emergency travel plan planning unit and a normal travel plan planning unit; The target vehicle screening set acquisition unit obtains the first, second, third and fourth target vehicle screening sets according to the connection coefficients between the target vehicles that have recently stopped at adjacent travel nodes; The emergency travel plan planning unit integrates the first target vehicle screening set, the second target vehicle screening set, and the fourth target vehicle screening set in ascending order of travel node numbers to obtain an emergency travel plan for the target passenger; The normal travel plan planning unit integrates the first target vehicle screening set, the third target vehicle screening set and the fourth target vehicle screening set in ascending order of travel node numbers to obtain a normal travel plan for the target passenger.

9. The big data-based intelligent electronic bus stop sign data management system according to claim 8, characterized in that: The target travel plan determination module includes an intersection travel node acquisition unit, a fitness calculation unit and a target travel plan determination unit; The intersection travel node acquisition unit acquires the intersection travel node between the determined emergency travel plan and the normal travel plan; The fitness calculation unit analyzes the fitness between the target passenger and the ride plan at each intersection travel node in each type of travel plan; The target travel plan determination unit reserves the travel plan at the intersection travel node corresponding to the maximum fitness value, and adjusts the emergency travel plan based on the reserved travel plan to obtain the target travel plan of the target passenger.

Images