Bus scheduling method and system based on limited edge camera equipment

Abstract

The invention provides a bus scheduling method and system based on limited edge camera equipment, and relates to the technical field of bus management, all buses are provided with bases for plugging the edge camera equipment, the total number of the edge camera equipment is smaller than the total number of the buses, and the limiting edge camera equipment is arranged on the bases. Comprising the following steps: S1, acquiring historical event information collected in the driving process of a bus through edge camera equipment; s2, acquiring an attention event preset by a user and a corresponding event attention degree; s3, according to the historical event information, the concerned event and the corresponding event concerning degree, carrying out weighted calculation on the concerned event; s4, establishing a track interaction diagram with the bus station as the y axis and the time as the x axis; s5, establishing a trajectory directed graph according to bus routes and route fitting weight values in the trajectory interaction graph; and S6, changing the carrying number of the edge camera devices of the buses in the bus scheduling table according to the trajectory directed graph, and generating a new bus scheduling table.

Description

Technical Field

[0001] The present invention relates to the technical field of bus management, and in particular to a bus scheduling method and system based on limited edge camera equipment. Background Art

[0002] At present, cameras are installed on buses and corresponding edge computing devices are placed, so that they can sense events outside the bus through algorithms, such as illegal parking on the road and littering, and upload illegal events captured by the camera to relevant departments for timely processing. However, due to the large number of buses in a wide range, it is costly to install cameras and edge computing devices on all buses; if cameras and edge computing devices are installed on some buses, it is impossible to achieve full coverage of all time periods and all sections, resulting in low event collection efficiency and the inability of relevant departments to effectively control. Summary of the invention

[0003] The purpose of the present invention is to provide a bus scheduling method and system based on limited edge camera devices. While reducing costs, limited pluggable edge camera devices are used for flexibly setting on different buses. The edge camera devices are switched according to user needs and historical event information collected by the edge camera devices, so that the limited edge camera devices can capture more events, increase the probability of event discovery, and facilitate relevant departments to effectively control illegal time.

[0004] In order to solve the above technical problems, the present invention adopts the following solutions: A bus scheduling method based on limited edge camera devices, wherein all buses are provided with bases for plugging and unplugging edge camera devices, and the total number of the edge camera devices is less than the total number of buses; the method comprises the following steps: S1. Obtain the bus where the edge camera device is located according to the bus schedule, and obtain the historical event information collected during the driving of the bus through the edge camera device; S2. Obtaining the user's preset attention events and the corresponding event attention levels; S3, performing weighted calculation on the events of interest according to historical event information, events of interest, and corresponding event attention levels, to obtain weight values ​​of events of interest in different sections and time periods; S4, establishing a trajectory interaction diagram with the bus station as the y-axis and time as the x-axis, mapping all bus routes in the bus schedule into the trajectory interaction diagram, and calculating the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and different time periods; S5. Establish a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtain the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; S6. According to the line fitting weight value of the node and the connection relationship between the nodes, the number of edge camera devices carried by the buses in the bus schedule is replaced to generate a new bus schedule.

[0005] Furthermore, the bus schedule includes bus schedules, bus routes, and the number of edge camera devices carried; the bus schedule indicates that buses on the same bus route are scheduled according to different time periods; the number of edge camera devices carried is 1 or 0.

[0006] Furthermore, the historical event information includes the road section where the event occurred, the time when the event occurred, and the event type, and the user can preset the event attention level of the event by paying attention to the event type of the event.

[0007] Furthermore, S3 includes the following steps: S31, calculating the probability of the event occurring according to the road section where the event occurred and the time when the event occurred in the historical event information, and obtaining the probability of the event occurring at different sections and at different times; S32. Calculate the weights of the events of interest according to the occurrence probabilities of the events of interest at different road sections and at different times and the corresponding event attention levels, and obtain the weight values ​​of the events of interest at different road sections and at different time periods.

[0008] Furthermore, in S4, the bus route includes several bus stops where the bus stops in sequence during its travel, and some routes between adjacent bus stops are formed by connecting several continuous road sections. The bus routes of all buses in the bus schedule are mapped in the trajectory interaction diagram, and the weight values ​​of the events of interest in different time periods on different road sections are substituted into the corresponding partial routes, and the weight values ​​of the events of interest on the partial routes are weighted fitted to obtain the corresponding route fitting weight values.

[0009] Furthermore, the trajectory interaction diagram includes overlapping routes. When different buses overlap in time periods at the same bus station, overlapping routes exist in the trajectory interaction diagram.

[0010] Further, in S5, the process of establishing a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph is as follows: According to the trajectory interaction diagram, the bus routes with overlapping time periods are extracted, and the bus routes are processed separately. Some routes between adjacent bus stations are used as nodes, and the corresponding route fitting weight values ​​are used as node values. The nodes are connected in sequence according to their respective bus routes. Then, different bus lines are processed according to the overlapping routes, and the nodes corresponding to different bus lines are connected in sequence according to the overlapping routes.

[0011] Further, in S6, the process of changing the number of edge camera devices carried by the buses in the bus schedule according to the line fitting weight values ​​of the nodes and the connection relationship between the nodes is as follows: According to the trajectory interaction diagram, the line fitting weight value of the node and the connection relationship between the nodes corresponding to different bus lines are obtained. According to the connection relationship between the nodes, the values ​​of the corresponding nodes are compared in turn, and the nodes with larger values ​​are obtained according to the comparison results; the number of edge camera devices on the bus is replaced to the nodes with larger values, that is, the number of edge camera devices on some routes corresponding to the nodes with larger values ​​in the bus schedule is updated to 1 to produce a new bus schedule.

[0012] A bus scheduling system based on limited edge camera devices, using the bus scheduling method based on limited edge camera devices, all buses are provided with bases for plugging and unplugging edge camera devices, and the total number of edge camera devices is less than the total number of buses; comprising: Historical event information collection module: obtains the bus where the edge camera device is located according to the bus schedule, and obtains the historical event information collected during the driving of the bus through the edge camera device; Focus event definition module: obtains the focus events preset by the user and the corresponding event focus levels; Concern event weight calculation module: weighted calculation of concerned events is performed according to historical event information, concerned events and corresponding event attention levels, and weight values ​​of concerned events in different sections and time periods are obtained; Trajectory interaction graph construction module: establish a trajectory interaction graph with bus stations as the y-axis and time as the x-axis, map all bus routes in the bus schedule into the trajectory interaction graph, and calculate the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and time periods; Trajectory directed graph construction module: establishes a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtains the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; Bus schedule update module: replaces the number of edge camera devices carried by buses in the bus schedule according to the line fitting weight value of the node and the connection relationship between the nodes to generate a new bus schedule.

[0013] Beneficial effects of the present invention: The present invention provides a bus scheduling method and system based on limited edge camera devices, which changes the fixed settings of cameras and edge computing devices on buses in the prior art into flexible settings, integrates the existing cameras and edge computing devices into edge camera devices, and fixes a base for plugging and unplugging edge camera devices on the bus, so that the same edge camera device can be set on different buses to collect event information outside the bus, without the need to set up equipment on all buses, thereby reducing costs.

[0014] While reducing costs, edge camera devices can be switched according to user needs and historical event information collected by edge camera devices, so that limited edge camera devices can capture more events, increase the probability of event detection, and facilitate relevant departments to effectively control illegal time. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a bus scheduling method based on a limited edge camera device in Example 1 of the present invention.

[0016] Figure 2 This is a schematic diagram of a trajectory interaction diagram in Example 1 of the present invention.

[0017] Figure 3 Schematic diagram of the trajectory directed graph in Example 1 of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0020] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0021] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness.One of ordinary skill in the art will recognize that various changes and modifications may be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0022] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0023] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0024] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments: Example 1 In this embodiment, in order to solve the problem of high cost caused by fixed installation of cameras and edge computing devices on all buses in the prior art, the present invention mainly adopts limited cameras and edge computing devices, integrates the existing cameras and edge computing devices together as a camera perception module, namely, edge camera devices, and adopts limited edge camera devices so that the total number of edge camera devices is less than the total number of buses. In addition, all buses are provided with bases for plugging and unplugging edge camera devices, so that the edge camera devices can be flexibly moved. When the bus arrives at the bus station, the driver will make a short stop at the current bus station. At this time, the driver can choose to remove the edge camera device on the bus and move it to another bus, so that the other bus can insert the edge camera device for collection; when the bus arrives at the final bus station, namely the terminal, the edge camera device on the bus can be removed and the events collected on the edge camera device can be uploaded.

[0025] Specifically, the camera module is used to capture images outside the vehicle; the edge computing module is used to calculate the images captured by the camera module, generate corresponding events, and obtain the event type of the event. Moreover, when the edge computing module collects the event type of the current event, the current collection time is expanded to obtain the time when the event occurred, and the road section where the event occurred is obtained in combination with the GPS information of the bus itself.

[0026] In one embodiment, a base for plugging and unplugging edge camera devices is provided on all buses. The base is fixed on the bus, and a power source is provided in the base, which can be charged through the base.

[0027] In order to capture more events through limited edge camera devices and improve the probability of event discovery, the present invention proposes a bus scheduling method based on limited edge camera devices based on the above-mentioned edge camera devices, such as Figure 1 As shown, the method comprises the following steps: S1. Obtain the bus where the edge camera device is located according to the bus schedule, and obtain the historical event information collected during the driving of the bus through the edge camera device; S2. Obtaining the user's preset attention events and the corresponding event attention levels; S3, performing weighted calculation on the events of interest according to historical event information, events of interest, and corresponding event attention levels, to obtain weight values ​​of events of interest in different sections and time periods; S4, establishing a trajectory interaction diagram with the bus station as the y-axis and time as the x-axis, mapping all bus routes in the bus schedule into the trajectory interaction diagram, and calculating the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and different time periods; S5. Establish a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtain the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; S6. According to the line fitting weight value of the node and the connection relationship between the nodes, the number of edge camera devices carried by the buses in the bus schedule is replaced to generate a new bus schedule.

[0028] Specifically, the bus schedule includes the bus serial number, bus schedule, bus route and the number of edge camera devices carried by the bus, as shown in Table 1. The buses on the same bus route are scheduled in sequence according to the time period according to the bus schedule, so the bus schedule can be obtained, and each section of the bus during the driving process and its section time period can be obtained according to the bus route, such as the section 1 time period. The number of edge camera devices carried is 1 or 0, and the number of edge camera devices carried corresponds to one section. In Table 1, it can be seen that the bus route of bus A1 is 1, the bus schedule is 1, and the section time period of section 1 is 9:00-9:05, and the number of edge camera devices carried on section 1 is 1, that is, when bus A1 is driving on section 1, an edge camera device is inserted on the base, and event information outside the vehicle can be collected through the edge camera device.

[0029] Table 1 In one embodiment, events can be collected intensively according to the needs of different users. For example, if the current user's need is to pay attention to the cleanliness of trash cans around the road, the user's preset attention events and their event types and event attention levels are obtained. The event attention level of the attention event corresponding to the cleanliness of trash cans around the road is increased, and the event attention levels of other events can be appropriately reduced.

[0030] In one embodiment, S3 includes the following steps: S31, calculating the probability of the event occurring according to the road section where the event occurred and the time when the event occurred in the historical event information, and obtaining the probability of the event occurring at different sections and at different times; S32. Calculate the weights of the events of interest according to the occurrence probabilities of the events of interest at different road sections and at different times and the corresponding event attention levels, and obtain the weight values ​​of the events of interest at different road sections and at different time periods.

[0031] Specifically, the historical event information is the event information collected in advance by the edge camera device. For bus scheduling, the historical event information can be the event information of the previous period. The current bus schedule is updated according to the event information of the previous period. The event information includes the road section where the event occurred, the time when the event occurred, and the event type; the probability of the same event type occurring in the same road section and the same time period in the event information of the previous period is statistically calculated. The statistical calculation is a prior art means and will not be repeated here. For example, through statistical calculation, it can be obtained that there is a 50% probability that the trash can is not tidy on road section 1 and the time period of road section 1 is 9:00-9:05. In this way, the probability of the occurrence of events of concern at different times in different roads can be obtained.

[0032] Furthermore, after obtaining the probability of sending the event of interest in the historical event information, since different users have different attention needs, in this embodiment, the event of interest can also be weighted according to the probability of occurrence of the event of interest at different sections and at different times and the corresponding event attention level. For example, the optional range of a user's event attention level is preset to be 1-10. If the current event attention level of an untidy trash can is 7, there is a 50% probability of an untidy trash can on section 1 and the time period of section 1 is 9:00-9:05, then the weight value of the untidy trash can on section 1 and the time period of section 1 is 9:00-9:05 is 3.5. The event of interest is weighted according to the user's attention level, the event attention level of the event of interest corresponding to the cleanliness of the trash cans around the road is increased, and the event attention level of other events can be appropriately reduced, so that the subsequent focus is on finding that the trash cans are untidy and the number of edge camera devices carried by the bus is replaced.

[0033] In one embodiment, in S4, the bus route includes several bus stations where the bus stops in sequence during its travel, and part of the route between adjacent bus stations is formed by connecting several continuous road sections. The bus routes of all buses in the bus schedule are mapped in the trajectory interaction diagram, and the weight values ​​of the events of interest in different time periods on different road sections are substituted into the corresponding partial routes, and the weight values ​​of the events of interest on the partial routes are weight-fitted to obtain the corresponding route fitting weight values.

[0034] like Figure 2 As shown in the figure, a trajectory interaction diagram with the bus station as the y-axis and time as the x-axis is established, and the bus routes of bus A1 and bus B1 are mapped in the trajectory interaction diagram. In addition, the line fitting weight value of part of line n1 on the current bus route of bus A1 is 1, the line fitting weight value of part of line n2 is 2, the line fitting weight value of part of line n3 is 3, and the line fitting weight value of part of line n4 is 4; and the line fitting weight value of part of line m1 on the current bus route of bus B1 is 6, the line fitting weight value of part of line m2 is 7, the line fitting weight value of part of line m3 is 8, and the line fitting weight value of part of line m4 is 9.

[0035] When the bus route of bus A1 traveling along route 1 is mapped in the trajectory interaction map, and the bus route of bus B1 traveling along route 2 is also mapped in the trajectory interaction map, the time periods of the two bus routes overlap in the trajectory interaction map, and both travel in the time period T0-T7, indicating that bus A1 and bus B1 are buses that depart and travel in the same time period and may have overlapping routes. In another embodiment, when establishing the trajectory interaction map, multiple trajectory interaction maps can be established according to the time period, and the bus routes of the buses traveling in the same time period can be mapped in the same trajectory interaction map.

[0036] Currently, bus A1 arrives at bus station 1 from bus station 2, and bus B1 arrives at bus station 1 from bus station 0, and the stay time of bus A1 and bus B1 at bus station 1 overlaps, then there is an overlapping route in the trajectory interaction diagram, indicating that there is time for bus A1 and bus B1 to exchange the number of edge camera devices carried by each other. At this time, if the number of edge camera devices carried by the current bus A1 on part of the route between bus station 2 and bus station 1 is 1, and the number of edge camera devices carried by the current bus B1 on part of the route between bus station 0 and bus station 1 is 0, then the edge camera device of bus A1 can be transferred to bus B1 at bus station 1, so that the present invention determines whether there is time to transfer the edge camera device between buses according to the overlapping routes in the trajectory interaction diagram, and then performs weight fitting according to part of the routes between bus stations in the trajectory interaction diagram to obtain the corresponding route fitting weight value, which is convenient for the subsequent scheduling of the edge camera device transfer.

[0037] In one embodiment, in S5, the process of establishing a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph is as follows: According to the trajectory interaction diagram, the bus routes with overlapping time periods are extracted, and the bus routes are processed separately. Some routes between adjacent bus stations are used as nodes, and the corresponding route fitting weight values ​​are used as node values. The nodes are connected in sequence according to their respective bus routes. Then, different bus lines are processed according to the repeated routes, and the nodes corresponding to different bus lines are connected in sequence according to the repeated routes.

[0038] like Figure 3 As shown, based on Figure 2 The trajectory interaction diagram in the figure establishes a trajectory directed graph. The specific process of establishing the graph is as follows: first, the bus routes of bus A1 and bus B1 are processed respectively, with some routes as nodes, the route fitting weight values ​​of some routes as the values ​​of the nodes, and the nodes are connected in sequence according to their respective bus routes. At this time, two paths can be obtained, namely 1-2-3-4 and 6-7-8-9; then the bus routes of bus A1 and bus B1 are processed according to the repeated routes in the trajectory interaction diagram. For example: Figure 2 It can be obtained that the line between the partial line n1 and the partial line n2 and the line between the partial line m1 and the partial line m2 form a repeated route, indicating that bus A1 and bus B1 can transfer the edge camera device at the corresponding bus station 1, then the node corresponding to the partial line n1 is connected to the node corresponding to the partial line m2, and the node corresponding to the partial line m1 is connected to the node corresponding to the partial line n2, so as to form a trajectory directed graph.

[0039] In one embodiment, in S6, the process of changing the number of edge camera devices carried by buses in the bus schedule according to the line fitting weight values ​​of the nodes and the connection relationship between the nodes is as follows: According to the trajectory interaction diagram, the line fitting weight value of the node and the connection relationship between the nodes corresponding to different bus lines are obtained. According to the connection relationship between the nodes, the values ​​of the corresponding nodes are compared in turn, and the nodes with larger values ​​are obtained according to the comparison results; the number of edge camera devices on the bus is replaced to the nodes with larger values, that is, the number of edge camera devices on some routes corresponding to the nodes with larger values ​​in the bus schedule is updated to 1 to produce a new bus schedule.

[0040] Specifically, when the bus's daily operation time is over, the bus schedule and the collected historical event information can be obtained, and a Figure 3 The trajectory directed graph is obtained, and according to the number of edge camera devices carried in the bus schedule, the current path of carrying edge cameras is 1-2-3-4, that is, bus A1 has edge cameras inserted in the current bus route, and through historical event information, it is obtained that other routes may have events that users pay attention to with higher attention. The trajectory directed graph can be used to realize the transfer of the path carrying edge cameras. At this time, the sizes of the nodes are compared in turn, and it is found that node 7 is larger than node 1. The path is transferred, and the path carrying edge cameras is updated to 1-7-8-9. In the bus schedule, the path 1-7 -The number of edge camera devices carried on the corresponding part of the route 8-9 is updated to 1 to produce a new bus schedule so that the buses for the next day can run based on the new bus schedule. When bus A1 arrives at bus station 1, an edge camera device transfer notification is sent to bus A1, and the driver of bus B1 is notified to insert the edge camera device into bus B1 to complete subsequent event collection work and realize flexible switching of edge camera devices. With limited edge camera devices, we can focus on certain events according to user needs, monitor the sections where the event is more likely to occur, and realize dynamic updates.

[0041] Example 2 A bus scheduling system based on limited edge camera devices, using the bus scheduling method based on limited edge camera devices, all buses are provided with bases for plugging and unplugging edge camera devices, and the total number of edge camera devices is less than the total number of buses; comprising: Historical event information collection module: obtains the bus where the edge camera device is located according to the bus schedule, and obtains the historical event information collected during the driving of the bus through the edge camera device; Focus event definition module: obtains the focus events preset by the user and the corresponding event focus levels; Concern event weight calculation module: weighted calculation of concerned events is performed according to historical event information, concerned events and corresponding event attention levels, and weight values ​​of concerned events in different sections and time periods are obtained; Trajectory interaction graph construction module: establish a trajectory interaction graph with bus stations as the y-axis and time as the x-axis, map all bus routes in the bus schedule into the trajectory interaction graph, and calculate the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and time periods; Trajectory directed graph construction module: establishes a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtains the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; Bus schedule update module: replaces the number of edge camera devices carried by buses in the bus schedule according to the line fitting weight value of the node and the connection relationship between the nodes to generate a new bus schedule.

[0042] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. According to the technical essence of the present invention, within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A bus scheduling method based on limited edge camera equipment, characterized in that: All buses are provided with bases for plugging and unplugging edge camera devices, and the total number of edge camera devices is less than the total number of buses; the method comprises the following steps: S1. Obtain the bus where the edge camera device is located according to the bus schedule, and obtain the historical event information collected during the driving of the bus through the edge camera device; S2. Obtaining the user's preset attention events and the corresponding event attention levels; S3, performing weighted calculation on the events of interest according to historical event information, events of interest, and corresponding event attention levels, to obtain weight values ​​of events of interest in different sections and time periods; S4, establishing a trajectory interaction diagram with the bus station as the y-axis and time as the x-axis, mapping all bus routes in the bus schedule into the trajectory interaction diagram, and calculating the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and different time periods; S5. Establish a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtain the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; S6. According to the line fitting weight value of the node and the connection relationship between the nodes, the number of edge camera devices carried by the buses in the bus schedule is replaced to generate a new bus schedule.

2. A bus scheduling method based on a limited edge camera device according to claim 1, characterized in that: The bus schedule includes bus schedules, bus routes, and the number of edge camera devices carried by the bus; the bus schedule indicates that buses on the same bus route are scheduled according to different time periods; The number of edge camera devices carried is 1 or 0.

3. A bus scheduling method based on a limited edge camera device according to claim 1, characterized in that: The historical event information includes the road section where the event occurred, the time when the event occurred, and the event type. The user can preset the event attention level of the event by focusing on the event type.

4. A bus scheduling method based on a limited edge camera device according to claim 3, characterized in that: The S3 includes the following steps: S31, calculating the probability of the event occurring according to the road section where the event occurred and the time when the event occurred in the historical event information, and obtaining the probability of the event occurring at different sections and at different times; S32. Calculate the weights of the events of interest according to the occurrence probabilities of the events of interest at different road sections and at different times and the corresponding event attention levels, and obtain the weight values ​​of the events of interest at different road sections and at different time periods.

5. A bus scheduling method based on a limited edge camera device according to claim 1, characterized in that: In S4, the bus route includes several bus stations where the bus stops in sequence during its travel, and some routes between adjacent bus stations are formed by connecting several continuous road sections. The bus routes of all buses in the bus schedule are mapped in the trajectory interaction diagram, and the weight values ​​of the events of interest in different sections and different time periods are substituted into the corresponding partial routes, and the weight values ​​of the events of interest on the partial routes are weighted fitted to obtain the corresponding route fitting weight values.

6. A bus scheduling method based on a limited edge camera device according to claim 1, characterized in that: The trajectory interaction diagram includes overlapping routes. When different buses overlap in time periods at the same bus station, overlapping routes exist in the trajectory interaction diagram.

7. A bus scheduling method based on a limited edge camera device according to claim 6, characterized in that: In S5, the process of establishing a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph is as follows: According to the trajectory interaction diagram, the bus routes with overlapping time periods are extracted, and the bus routes are processed separately. Some routes between adjacent bus stations are used as nodes, and the corresponding route fitting weight values ​​are used as node values. The nodes are connected in sequence according to their respective bus routes. Then, different bus lines are processed according to the overlapping routes, and the nodes corresponding to different bus lines are connected in sequence according to the overlapping routes.

8. A bus scheduling method based on a limited edge camera device according to claim 7, characterized in that: In S6, the process of changing the number of edge camera devices carried by buses in the bus schedule according to the line fitting weight value of the node and the connection relationship between the nodes is as follows: According to the trajectory interaction diagram, the line fitting weight value of the node and the connection relationship between the nodes corresponding to different bus lines are obtained. According to the connection relationship between the nodes, the values ​​of the corresponding nodes are compared in turn, and the nodes with larger values ​​are obtained according to the comparison results; the number of edge camera devices on the bus is replaced to the nodes with larger values, that is, the number of edge camera devices on some routes corresponding to the nodes with larger values ​​in the bus schedule is updated to 1 to produce a new bus schedule.

9. A bus scheduling system based on limited edge camera equipment, characterized in that: A bus scheduling method based on limited edge camera devices as described in any one of claims 1 to 8 is applied, wherein all buses are provided with bases for plugging and unplugging edge camera devices, and the total number of edge camera devices is less than the total number of buses; comprising: Historical event information collection module: obtains the bus where the edge camera device is located according to the bus schedule, and obtains the historical event information collected during the driving of the bus through the edge camera device; Focus event definition module: obtains the focus events preset by the user and the corresponding event focus levels; Concern event weight calculation module: weighted calculation of concerned events is performed according to historical event information, concerned events and corresponding event attention levels, and weight values ​​of concerned events in different sections and time periods are obtained; Trajectory interaction graph construction module: establish a trajectory interaction graph with bus stations as the y-axis and time as the x-axis, map all bus routes in the bus schedule into the trajectory interaction graph, and calculate the route fitting weight values ​​between adjacent bus stations on different bus routes according to the weight values ​​of the events of interest in different sections and time periods; Trajectory directed graph construction module: establishes a trajectory directed graph according to the bus routes and route fitting weight values ​​in the trajectory interaction graph, and obtains the route fitting weight values ​​of the nodes in the trajectory directed graph and the connection relationship between the nodes; Bus schedule update module: replaces the number of edge camera devices carried by buses in the bus schedule according to the line fitting weight value of the node and the connection relationship between the nodes to generate a new bus schedule.

Images