A vehicle scheduling method, device, medium and optical quantum computer

Abstract

The application provides a vehicle scheduling method and device, a medium and a quantum computer. The method comprises the following steps: obtaining scheduling reference data; determining a plurality of candidate scheduling schemes according to the scheduling reference data, and determining, in each candidate scheduling scheme, a first time required for each to-be-parked vehicle to arrive at a corresponding parking space and a second time required for each to-be-parked vehicle to park in the corresponding parking space; determining a total cost of each candidate scheduling scheme according to the first time and the second time of each to-be-parked vehicle in the candidate scheduling scheme; determining a target scheduling scheme from the plurality of candidate scheduling schemes according to the total cost of each candidate scheduling scheme; and guiding the plurality of to-be-parked vehicles to park in the corresponding parking spaces based on the target scheduling scheme. By introducing the parking time of the vehicle into the selection of the path scheme, the traffic congestion caused by the parking operation is reduced, the traffic flow in the parking lot is ensured to be smooth, and the space utilization and the turnover rate of the parking lot are improved.

Description

Technical Field

[0001] This invention relates to the field of logistics system optimization, specifically to a vehicle scheduling method, apparatus, medium, and optical quantum computer. Background Technology

[0002] With the development of the automobile manufacturing industry, the number of new cars that have completed final assembly and rolled off the production line is increasing, and the models and configurations of the vehicles coming off the production line are becoming more and more diverse, leading to a sharp increase in the complexity of parking lot management.

[0003] In existing technologies, parking routes for vehicles are typically planned based on human experience or pre-set scheduling rules. However, existing scheduling methods only focus on the vehicle's journey along the route, neglecting the obstruction caused by parking operations after the vehicle arrives at the target parking space, resulting in low space utilization and turnover rates in parking lots. Summary of the Invention

[0004] In view of this, the present invention aims to provide a vehicle scheduling method, device, medium, and optical quantum computer to solve the problem that existing scheduling methods only focus on the vehicle's journey along the path, while ignoring the low space utilization and turnover rate of parking lots due to road congestion caused by parking operations after the vehicle arrives at the target parking space.

[0005] This invention provides a vehicle dispatching method, which includes:

[0006] Obtain scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and the network diagram of the parking lot;

[0007] Based on the scheduling reference data, multiple candidate scheduling schemes are determined, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space, and the second time required for each vehicle to be transported to park in the corresponding parking space, wherein each candidate scheduling scheme includes the parking space, driving route, and passage order corresponding to each vehicle to be transported;

[0008] The total cost of a candidate scheduling scheme is determined based on the first and second times corresponding to the plurality of vehicles to be transported in each candidate scheduling scheme.

[0009] Based on the total cost of each candidate scheduling scheme, a target scheduling scheme is determined from the plurality of candidate scheduling schemes, and the plurality of vehicles to be transported are guided to park in the corresponding parking spaces based on the target scheduling scheme.

[0010] In some embodiments of this application, in response to a received scheduling task, a first vehicle to be scheduled and a second vehicle that is not currently parked in a corresponding parking space in the parking lot are determined; based on the first vehicle and the second vehicle, the plurality of vehicles to be transported are determined.

[0011] In some embodiments of this application, the step of determining the total cost of a candidate scheduling scheme based on the first time and the second time corresponding to the plurality of vehicles to be transported in each candidate scheduling scheme specifically includes: determining, based on the scheduling reference data, the operation set and congestion matrix corresponding to the plurality of vehicles to be transported when parking in the corresponding parking spaces, wherein the congestion matrix is ​​used to represent the degree of road congestion caused by each parking operation of the vehicles to be transported; determining the collision probability corresponding to each candidate scheduling scheme based on the operation set and the congestion matrix; determining the congestion time corresponding to each candidate scheduling scheme based on the congestion matrix and the operation set, as the parking cost of the candidate scheduling scheme; determining the total path length of the plurality of vehicles to be transported corresponding to each candidate scheduling scheme based on the scheduling reference data, as the management cost of the candidate scheduling scheme; and determining the total cost of the candidate scheduling scheme based on at least one of the collision probability, the parking cost, and the management cost corresponding to each candidate scheduling scheme, and the first time and the second time corresponding to the plurality of vehicles to be transported in the candidate scheduling scheme.

[0012] In some embodiments of this application, the step of determining the total path length of the plurality of vehicles to be transported corresponding to each candidate scheduling scheme as the management cost of the candidate scheduling scheme based on the scheduling reference data specifically includes: determining the decommissioning order of the plurality of vehicles to be transported; for each vehicle to be transported, determining a first cost for each parking space relative to the vehicle to be transported based on the decommissioning order and the distance between the parking space in the parking lot and the vehicle to be transported; determining a second cost corresponding to each candidate scheduling scheme based on the comprehensive cost of each parking space relative to each vehicle to be transported; determining the path length corresponding to each candidate scheduling scheme based on the scheduling reference data; and determining the management cost of the candidate scheduling scheme based on the second cost and the path length, wherein the management cost is used to redetermine the parking space corresponding to each vehicle to be transported.

[0013] In some embodiments of this application, the step of determining a target scheduling scheme from the plurality of candidate scheduling schemes based on the total cost of each candidate scheduling scheme specifically includes: determining a target scheduling scheme from the plurality of candidate scheduling schemes based on at least one of the following constraints: each vehicle to be transported has one and only one travel path; each parking space holds only one vehicle to be transported at any given time; at any given time, the number of vehicles to be transported traveling on each road in the network graph does not exceed the maximum capacity of that road; the departure time of each vehicle to be transported is not earlier than the offline time of that vehicle; when any two vehicles to be transported occupy overlapping areas when parking in a parking space, the parking times of the two vehicles to be transported do not coincide; at any given time, vehicles to be transported do not travel into roads that are completely blocked by parking operations.

[0014] In some embodiments of this application, determining the target scheduling scheme from the plurality of candidate scheduling schemes based on at least one of the following constraints and the total cost of each candidate scheduling scheme specifically includes: converting each parameter in the candidate scheduling scheme into a decision variable, converting the total cost into an objective function, converting the constraint into a penalty term, and determining a vehicle scheduling model; inputting the vehicle scheduling model and the scheduling reference data into a quantum computer, and determining the target scheduling scheme based on the output of the quantum computer.

[0015] In some embodiments of this application, the method further includes: executing the target scheduling scheme in real time through a simulation system; when the simulation result differs from the estimated result of the target scheduling scheme, re-determining the target scheduling scheme, and guiding the plurality of vehicles to be transported to park in the corresponding parking spaces through the re-determined target scheduling scheme.

[0016] Secondly, embodiments of this application provide a vehicle dispatching device, comprising:

[0017] The acquisition module is used to acquire scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot;

[0018] The generation module is used to determine multiple candidate scheduling schemes based on the scheduling reference data, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space, and the second time required for each vehicle to be transported to park in the corresponding parking space, wherein each candidate scheduling scheme includes the parking space, driving route and passage order corresponding to each vehicle to be transported;

[0019] The cost module is used to determine the total cost of the candidate scheduling scheme based on the first time and the second time corresponding to the plurality of vehicles to be transported in each candidate scheduling scheme;

[0020] The determining module is used to determine a target scheduling scheme from the plurality of candidate scheduling schemes based on the total cost of each candidate scheduling scheme, and guide the plurality of vehicles to be transported to park in the corresponding parking spaces based on the target scheduling scheme.

[0021] Thirdly, embodiments of this application provide an optical quantum computer, which includes a quantum part and a classical computing part, wherein:

[0022] The classical computation part is used to transform the vehicle scheduling model constructed based on the vehicle scheduling method described in any of the above embodiments into a quadratic unconstrained binary optimization QUBO model.

[0023] The quantum part is used to output a binary bit string according to the QUBO model;

[0024] The classical computation section is used to decode the binary bit string and determine the target scheduling scheme.

[0025] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a computer program for executing the vehicle scheduling method described above.

[0026] According to the embodiments of this application, by incorporating the parking time of vehicles into the selection of the route plan, traffic congestion caused by parking operations is reduced, ensuring smooth traffic flow inside the parking lot and improving the space utilization and turnover rate of the parking lot. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the process of a vehicle scheduling method provided in an embodiment of this application.

[0028] Figure 2 This is a schematic diagram of a parking lot network provided in an embodiment of this application.

[0029] Figure 3 This is a schematic diagram of determining a network graph according to an embodiment of this application.

[0030] Figure 4 This is a schematic diagram of a vehicle dispatching device provided in this specification.

[0031] Figure 5 A method based on the embodiment of the bit-base application is provided. Figure 1 A schematic diagram of the electronic device using the method shown. Detailed Implementation

[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0033] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0034] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0035] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0036] With the development of the automobile manufacturing industry, the models and configurations of new cars that have completed final assembly and rolled off the production line are becoming increasingly diverse. However, as the number of vehicles produced increases, the complexity of parking lot management also rises sharply.

[0037] Currently, vehicle off-line scheduling typically relies on manual experience or pre-configured scheduling rules. However, manual scheduling cannot calculate the globally optimal path, easily leading to vehicle congestion within the factory area, long total transportation time, and low parking lot turnover rate. Therefore, this application provides a vehicle scheduling method to solve the above problems, such as... Figure 1 As shown.

[0038] Figure 1 This is a schematic diagram illustrating the flow of a vehicle dispatching method provided in an embodiment of this application. It includes the following steps:

[0039] S100: Obtain scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot.

[0040] In one or more embodiments of this application, the specific device executing the vehicle scheduling method is not limited, such as a mobile terminal, a server, etc. However, since subsequent steps involve data acquisition, cost calculation, and scheme selection, these steps are generally executed by a server. Therefore, this application describes the vehicle scheduling method as being executed by a server, where the server can be a single device or composed of multiple devices, such as a distributed service or cloud service server, etc. This application does not impose any restrictions on this.

[0041] To efficiently and safely transport vehicles to the parking lot, the server can first obtain scheduling reference data to determine the target scheduling plan. It should be noted that, in one or more embodiments of this application, the scheduling reference data obtained by the server includes at least the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot.

[0042] It should be noted that the aforementioned multiple vehicles awaiting transfer refer to all vehicles that the server determines need to be dispatched from their current location to the target parking space after receiving the dispatch task. In one or more embodiments of this application, the specific number of vehicles awaiting transfer is not limited and is generally determined in real time based on the received dispatch task. For example, when the server receives the dispatch task, it can determine all offline vehicles within the time period between the current moment and the most recent time the dispatch task was received, and then use all offline vehicles within this time period as multiple vehicles awaiting transfer in the dispatch task received at the current moment. Of course, the initial coordinates of each vehicle awaiting transfer are not limited to any specific coordinate system, such as the world coordinate system or the coordinate system established based on the parking lot. They can be set according to actual needs, and this application does not impose any restrictions on this.

[0043] Furthermore, in one or more embodiments of this application, the aforementioned parking lot refers to a parking lot used for temporarily storing new cars that have completed final assembly and rolled off the production line. Of course, the vehicle scheduling method in this application can also be applied to parking lots in other scenarios, and this application does not impose any limitations on it.

[0044] like Figure 2 As shown, Figure 2This application provides a schematic diagram of a parking lot network graph. The network graph, composed of edges and nodes, abstractly represents the traffic environment of the parking lot and serves as the basic geographic information model for path planning by the server. Each edge represents a road, and nodes represent key locations such as road intersections, production line exits, and parking lot entrances. Alternatively, the network graph can be represented by a set G = (N, E), where nodes n ∈ N represent key locations such as road intersections, production line exits, and parking lot entrances, and edges e ∈ E represent road segments connecting nodes. Their weights can represent length, travel time, or congestion level. In one or more embodiments of this application, the network graph refers to a model that abstractly describes the internal and surrounding traffic structure of the parking lot using edges and nodes. Whether the network graph describes the internal and surrounding traffic structure of the parking lot in the form of a graph, a set, or other forms, these are all different representations of the network graph in this application. This application does not limit the representation and allows for setting the form of the network graph according to actual needs.

[0045] Furthermore, in one or more embodiments of this application, the specific method by which the server obtains the scheduling reference data is not limited. It may obtain the scheduling reference data from the system, the memory of other data acquisition devices, etc. through real-time communication, or it may obtain the scheduling reference data according to the received scheduling task. The acquisition method can be set according to actual needs, and this application does not impose any restrictions on it.

[0046] S102: Based on the scheduling reference data, determine multiple candidate scheduling schemes, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space, and the second time required for each vehicle to be transported to park in the corresponding parking space, wherein each candidate scheduling scheme includes the parking space, driving route and passage order corresponding to each vehicle to be transported.

[0047] After determining the scheduling reference data for multiple vehicles to be transported, the server can pre-generate multiple candidate scheduling schemes based on the acquired scheduling reference data. This allows for the selection of a target scheduling scheme from among the candidate schemes to transport the vehicles to their corresponding parking spaces. Each scheduling scheme refers to a set of paths that dispatch multiple vehicles from their initial coordinates to their corresponding parking spaces. This set includes the parking space, driving route, and passage order for each vehicle. At least one of the different scheduling schemes will have a different parking space, driving route, or passage order for each vehicle compared to the others.

[0048] Specifically, in one or more embodiments of this application, the server can first determine the optional path for each vehicle to be transported to enter the corresponding parking space based on the initial coordinates of each vehicle to be transported, the target of the corresponding parking space, and the network map of the parking lot in the scheduling reference data. Then, it generates multiple candidate scheduling schemes based on these optional paths. Each candidate scheduling scheme includes the driving path and passage order corresponding to each vehicle to be transported.

[0049] It should be noted that, in one or more embodiments of this application, the specific method used by the server to determine the parking space corresponding to each vehicle to be transported is not limited. The server can generate all possible candidate scheduling schemes by traversing all situations. For example, if the parking lot contains three empty parking spaces, then the parking space corresponding to a vehicle to be transported can be any one of the three parking spaces. The server can generate corresponding candidate scheduling schemes based on these three situations.

[0050] Of course, when a new car rolls off the production line, a preset allocation system can be used to assign the coordinates of a corresponding parking space to each newly produced vehicle. The server can obtain the coordinates of the parking space corresponding to each vehicle to be transported by acquiring data from this allocation system. Alternatively, the nearest available parking space can be assigned sequentially according to the order in which the vehicles are produced. This specification does not impose any restrictions on this; the settings can be configured according to actual needs. Furthermore, in one or more embodiments of this application, the coordinate system under which the determined parking space coordinates are located is not limited. It can be the world coordinate system, the parking lot coordinate system, etc. This coordinate system can be in the same coordinate system as the aforementioned initial coordinates, or it can be in a different coordinate system. When in different coordinate systems, the server can first determine the transformation matrix between the coordinate systems. This application does not impose any restrictions on this; the settings can be configured according to actual needs.

[0051] Then, for each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space is determined, i.e., the first time the vehicle to be transported travels on the road. The second time required for each vehicle to be transported to park in the corresponding parking space is also determined. It should be noted that, in one or more embodiments of this application, "parking" refers to the entire process of a vehicle moving from the production line to the parking space, while "parking" refers to the process of a vehicle entering the parking space after arriving at the roadside. That is, this application divides the parking of vehicles to be transported into two operations: traveling from the initial coordinates to the corresponding parking space, and parking from the side of the parking space into the parking space. The first time refers to the time spent by the vehicle to be transported from the initial coordinates to the side of the corresponding parking space, and the second time refers to the time spent by the vehicle to be transported from the side of the parking space into the parking space.

[0052] For ease of understanding, this application also provides an embodiment for determining each candidate scheduling scheme, as shown below.

[0053] like Figure 3 As shown, Figure 3 This is a schematic diagram of a network diagram provided in an embodiment of this application, wherein the vehicles to be transported include vehicle A and vehicle B. Vehicle A needs to be parked in parking space a, and vehicle B needs to be parked in parking space b. Figure 3 It can be seen that there are three possible routes for car A to park in parking space a. ,Right now Figure 3 The path shown by the thick solid line indicates that there are two possible routes for car B to park in parking space b. ,Right now Figure 3 The path shown by the dashed line indicates that the server can determine six candidate scheduling schemes. , , , , , .

[0054] Furthermore, in one or more embodiments of this application, the specific method used by the server to determine the first and second times is not limited. For example, the first time for each vehicle to be transported can be calculated by the server based on the length of the vehicle's travel path and its preset travel speed. The second time for each vehicle to be transported can be determined by the server through simulated parking operations based on the vehicle's model and the road conditions near the parking space. Alternatively, the server can determine the second time by simulating the parking operations of the vehicle multiple times and calculating the average parking time. Since there are many possible methods, this application does not list them all; the method can be set according to actual needs.

[0055] Of course, when determining candidate scheduling schemes, in order to further improve scheduling efficiency, the server can also pre-screen multiple candidate scheduling schemes to reduce the amount of computation on the server and improve scheduling efficiency.

[0056] Specifically, the server can select from candidate scheduling schemes that allow the total path length of the vehicles to be transported to not exceed a preset value. Alternatively, it can select scheduling schemes with a path overlap rate less than a preset value. Since there are many possible filtering strategies, this application does not list them all; they can be set according to actual needs, and this application does not impose any restrictions on them.

[0057] S104: Determine the total cost of the candidate scheduling scheme based on the first time and the second time corresponding to the plurality of vehicles to be transported in each candidate scheduling scheme.

[0058] After determining multiple candidate scheduling schemes and their corresponding first and second times for each vehicle to be transported, the server can determine the total cost of each candidate scheduling scheme based on the determined first and second times. This allows for the selection of a target scheduling scheme based on the total cost of each candidate scheme. The total cost of each candidate scheduling scheme serves as the basis for evaluating it. Different methods used to obtain the total cost will result in different scheduling schemes and optimization directions when selecting a scheduling scheme based on these total costs.

[0059] Specifically, for each candidate scheduling scheme, the server can determine the sum of the first time and the second time for each vehicle to be transported within that scheme, and use the sum of the first time and the second time as the total cost of that candidate scheduling scheme. = Where i represents the vehicle number to be transported, t1 represents the first time, and t2 represents the second time.

[0060] In addition, the weights of the first and second time periods can be dynamically adjusted according to actual needs to further determine the total cost of focusing on the first or second time period.

[0061] For example, if a scheduling scheme with a shorter berthing time is required, =m Where n>m. If the travel time of the vehicle to be transported is shorter, then m>n.

[0062] S106: Based on the total cost of each candidate scheduling scheme, determine the target scheduling scheme from the plurality of candidate scheduling schemes, and guide each vehicle to be transported to park in the corresponding parking space based on the target scheduling scheme.

[0063] After determining the total cost corresponding to each candidate scheduling scheme, the server can select the target scheduling scheme based on the total cost of each candidate scheduling scheme, and guide the vehicles to be transported to park in the corresponding parking spaces based on the target scheduling scheme.

[0064] It should be noted that, in one or more embodiments of this application, the specific method used by the server to select the target scheduling scheme from multiple candidate scheduling schemes is not limited. It can be selecting the candidate scheduling scheme with the lowest total cost as the target scheduling scheme, selecting the candidate scheduling scheme with the lowest total first time among candidate scheduling schemes with a total cost less than a preset value, or selecting the candidate scheduling scheme with the lowest total second time among candidate scheduling schemes with a total cost less than a preset value. Since there are many possible methods, this application does not list them all; the server can be configured according to actual needs.

[0065] Furthermore, in one or more embodiments of this application, there is no limitation on how each vehicle to be transported stops at the corresponding parking space from the initial coordinates. It can be done through an autonomous driving system, using driverless technology to stop at the corresponding destination coordinates; it can also be guided manually by an in-vehicle voice system or navigation system; or a corresponding driving scheme can be selected based on the model, configuration, and other parameters of the vehicle to be transported. Since there are many possible solutions, this application does not list them all; the specific solution can be set according to actual needs.

[0066] It should be noted that, in one or more embodiments of this application, the specific method by which the server guides the vehicles to be transported to the corresponding parking spaces is not limited. This could include generating voice commands, generating a set of operation instructions, or generating a route guidance map for manual execution of the transport task. Since there are many possible methods, they are not listed here; the specific method can be set according to actual needs.

[0067] In such Figure 1 The vehicle scheduling method shown reduces traffic congestion caused by parking operations by incorporating the parking time factor into the route selection, ensuring smooth traffic flow within the parking lot and improving the space utilization and turnover rate of the parking lot.

[0068] Furthermore, due to the high efficiency of vehicle production line turnover in the automotive manufacturing industry, when the server is scheduling vehicles, there may be vehicles waiting to be transported that are not yet parked in parking spaces in the parking lot. However, the server has already received a new scheduling task. To prevent these vehicles from blocking the scheduling paths of subsequent vehicles entering the parking lot, further reducing the risk of vehicle collisions, and improving the parking lot's turnover rate, the server can also respond to the received scheduling task by identifying the first vehicle to be dispatched and the second vehicle currently not parked in a corresponding parking space. Then, based on the first and second vehicles, multiple vehicles to be transported are determined. Here, the second vehicle refers to the vehicle that is not yet parked in a parking space when the server receives the scheduling task, and the first vehicle refers to the vehicle waiting to be transported from the production line in this received scheduling task.

[0069] Furthermore, since the maximum number of vehicles allowed on each road is limited, the probability of collisions increases when there are too many vehicles on the road. Therefore, the server can also introduce additional cost items when determining the total cost to address safety concerns.

[0070] Specifically, the server can determine the corresponding operation sets and blocking matrices for multiple vehicles waiting to be transported when parking in their respective parking spaces, based on scheduling reference data. The operation set refers to the set of operations required for each vehicle to complete its parking space entry, such as turning the steering wheel one and a half turns to the left, reversing, straightening the steering wheel, and turning the steering wheel to the right. Transport personnel or vehicles waiting to be transported can determine the parking operations and their order based on each operation in this operation set and its position within the set, thus completing the vehicle parking. The operation set can be defined as { , ,..., } where each item represents a vector corresponding to an operation. Of course, in one or more embodiments of this application, the specific method used by the server to convert the specific operation into a vector or matrix is ​​not limited; it can be set according to actual needs. The blocking matrix refers to a matrix representing the degree of road congestion caused by each parking operation of the vehicle to be transported. It should be noted that in one or more embodiments of this application, the specific method used by the server to determine the blocking matrix corresponding to each scheduling scheme is not limited. It can be the theoretical degree of congestion corresponding to each operation obtained by the server through simulating parking operations, or it can be the degree of congestion estimated by the server based on the actual degree of congestion of each operation when the vehicle to be transported is parking in the parking space in history. There are many possible methods, which are not listed one by one in this application.

[0071] Then, based on the determined set of operations and the blocking matrix, the collision probability corresponding to each candidate scheduling scheme is determined, i.e. = That is, for each candidate scheduling scheme, the overlap between the corresponding paths of each vehicle to be transported is calculated in that candidate scheduling scheme.

[0072] Then, based on each blocking matrix and each operation set, the blocking time corresponding to each candidate scheduling scheme is determined as the docking cost of that candidate scheduling scheme. It should be noted that, in one or more embodiments of this application, the specific method used by the server to determine the blocking time corresponding to each candidate scheduling scheme is not limited. It can be the theoretical blocking time obtained by the server through simulation, or it can be the blocking time estimated by the server based on the blocking matrix and operation set. Since there are many possible methods, this application does not limit them and will not list them all.

[0073] Next, based on the scheduling reference data, the path length of each vehicle to be transported corresponding to each candidate scheduling scheme is determined, which serves as the management cost of that candidate scheduling scheme.

[0074] Finally, based on at least one of the collision probability, parking cost, and management cost corresponding to each candidate scheduling scheme, as well as the first and second times corresponding to multiple vehicles waiting to be transported in the candidate scheduling scheme, the total cost of the candidate scheduling scheme is determined so that the globally optimal path can be obtained subsequently based on the determined total cost.

[0075] In addition, when determining the total cost, the server can also dynamically adjust the focus on the above parameters by weighting and summing at least one of the collision probability, berthing cost, and management cost with the first and second time points, so as to obtain a path more suitable for the current scenario according to actual needs.

[0076] It should be noted that, when determining the collision probability, the server can also calculate... = I (Path Overlap) The probability threshold is obtained by applying a penalty term I to each candidate scheduling scheme when the overlap between the driving paths of any two vehicles to be transported exceeds the probability threshold. The collision penalty is used as the determined collision probability.

[0077] Furthermore, since the upstream pre-set allocation system may not have considered the actual operation of the roads in the parking lot when allocating parking spaces to vehicles that are offline, for example, when car A is parking, car C may be unable to move while car A is parking. However, parking space c is the closest vacant parking spot to car C, and this road is the only way for car C to park in the corresponding parking space c. There are parking spaces nearby where car C can park, but in the target scheduling scheme selected based on path length, car C can only park in parking space c, which greatly prolongs the congestion time.

[0078] Therefore, when determining management costs, the server can also determine the decommissioning order of multiple vehicles awaiting transfer. Then, for each vehicle awaiting transfer, based on its decommissioning order and the distance between the parking space in the parking lot and the vehicle, a first cost for each parking space relative to the vehicle is determined. Next, based on the comprehensive cost of each parking space relative to each vehicle, a second cost corresponding to each candidate scheduling scheme is determined. Based on scheduling reference data, the path length corresponding to each candidate scheduling scheme is determined. Finally, based on the second cost and path length of each candidate scheduling scheme, the management cost of that candidate scheduling scheme is determined, where the management cost is used to re-determine the parking space corresponding to each vehicle awaiting transfer.

[0079] Furthermore, in order to obtain the globally optimal path, the server can also select the target scheduling scheme from the candidate scheduling schemes by combining the constraints and the total cost.

[0080] Specifically, the constraints include: each vehicle to be transported has one and only one travel path; each parking space can only hold one vehicle to be transported at any given time; at any given time, the number of vehicles to be transported traveling on each road in the network diagram does not exceed the maximum capacity of that road; the departure time of each vehicle to be transported is not earlier than its offline time; when any two vehicles to be transported occupy overlapping parking areas when parking, the parking times of the two vehicles to be transported do not coincide; at any given time, a vehicle to be transported does not travel into at least one of the roads that are completely blocked by parking operations.

[0081] Specifically, in each scheduling scheme, each vehicle awaiting transport has exactly one travel route. When multiple travel routes exist, the vehicle may be unable to determine the optimal route. Therefore, the server can use "each vehicle awaiting transport has exactly one travel route" as a constraint. Similarly, each parking space can only hold one vehicle at a time. When two vehicles share the same parking space with overlapping times, regardless of the duration of the overlap, the probability of collisions between the vehicles increases significantly. Therefore, the server can also use "each parking space can only hold one vehicle at a time" as a constraint.

[0082] Similarly, the constraint that "at any given time, the number of vehicles waiting to be transported on each road in the network graph does not exceed the maximum capacity of that road" is also problematic. When the number of vehicles waiting to be transported exceeds the maximum capacity of a road, it not only increases the probability of collisions between vehicles but also potentially increases the overall time cost of the scheduling scheme due to vehicles yielding to each other. Therefore, the server can also include the constraint that "at any given time, the number of vehicles waiting to be transported on each road in the network graph does not exceed the maximum capacity of that road" as a constraint.

[0083] Furthermore, the departure time of each vehicle awaiting transfer is no earlier than its offline time, which would cause the scheduling scheme to deviate from objective laws and become unfeasible. Additionally, the server can use the constraint that "when any two vehicles awaiting transfer occupy overlapping parking areas, their parking times do not coincide" to reduce the probability of collisions between vehicles. Specifically, if the overlapping area between parking areas exceeds an area threshold, it can be determined that there is an overlapping area between the two vehicles. If there is an overlapping area between the parking areas of two vehicles awaiting transfer, it can also be determined that there is an interval between their parking times, or that the time overlap does not exceed a time threshold; otherwise, the parking times of the two vehicles are considered to coincide. This candidate scheduling scheme will either be disregarded or its priority will be reduced when it is selected as the target scheduling scheme. Of course, the area threshold, time threshold, etc. mentioned above are all set by the server according to actual needs. Different thresholds can be determined according to the model of the vehicle to be transported, or a uniform value can be determined. This application does not restrict this.

[0084] In addition, the server can also include a constraint that "vehicles waiting to be transported should not travel on roads that are completely blocked by parking operations at any time" to further reduce the probability of collisions between vehicles.

[0085] It should be noted that the above-described constraints are only one embodiment provided in this application. The server can also set other constraints according to actual needs, and this application does not limit this. Furthermore, this application does not limit the specific number of constraints set by the server, nor does it limit the specific content of each constraint; they can be set according to actual needs.

[0086] It should be noted that, in one or more embodiments of this application, the specific method used by the server to transform the above constraints into a form that can be processed by the algorithm or hardware is not limited. Different constraints may include various transformation methods, which are not listed one by one in this application, and can be set according to actual needs.

[0087] Furthermore, as the number of vehicles increases and parking lot sizes expand, traditional optimization algorithms encounter bottlenecks in terms of solution speed and quality, making it difficult to meet the demands of real-time scheduling. Therefore, this server can convert each parameter in candidate scheduling schemes into decision variables, the total cost into an objective function, and constraints into penalty terms to determine the vehicle scheduling model. This model is then converted into a form that can be input into a quantum computer, allowing the model and scheduling reference data to be fed into the quantum computer. Based on the quantum computer's output, the target scheduling scheme is determined. By enabling quantum computing to escape local optima and find global or near-global optimal solutions, transportation efficiency is significantly improved and total costs reduced. Simultaneously, leveraging quantum computing's advantage in handling combinatorial explosions, near-real-time scheduling is achieved, meeting the timeliness requirements of automated transport.

[0088] Specifically, the server can transform the vehicle scheduling model into a quadratic unconstrained binary optimization (QUBO) form: Here, x represents a binary variable vector, and Q represents a matrix. Encoding the decision variables into binary means that the decision variables... , , All using a set of binary variables { } represents this. Then, each term in the objective function is represented as a linear or quadratic function of binary variables. Then, the constraints are represented as penalty terms, for example, for the constraint "each of the vehicles to be transported has one and only one travel path", i.e. ( This term is 0 if and only if the sum is 1; otherwise, it is a positive penalty. Finally, based on the determined decision variables, objective function, and penalty term, a QUBO model of the vehicle scheduling model is constructed. Then, the QUBO model is submitted to a quantum computer, and the scheduling reference data is input into the quantum computer. The output of the quantum computer is decoded to determine the target scheduling scheme.

[0089] It should be noted that, in one or more embodiments of this application, the quantum computer described above may be any one or a combination of photonic quantum computers, ion trap quantum computers, quantum dot quantum computers, and neutral atom quantum computers, and no specific limitation is made herein.

[0090] In addition, in order to achieve real-time scheduling of vehicles awaiting transfer, the server can also execute the target scheduling scheme in real time through a simulation system, such as a digital twin system. When the simulation result is different from the estimated result of the target scheduling scheme, the target scheduling scheme is re-determined, and the multiple vehicles awaiting transfer are guided to park in the corresponding parking spaces through the re-determined target scheduling scheme, thereby achieving dynamic rescheduling.

[0091] This application also provides an optical quantum computer, which includes a quantum part and a classical computing part, wherein:

[0092] The classical computation part is used to transform the vehicle scheduling model constructed based on the vehicle scheduling method described in any of the above embodiments into a quadratic unconstrained binary optimization QUBO model.

[0093] The quantum part is used to output a binary bit string according to the QUBO model;

[0094] The classic part is used to decode the binary bit string and determine the target scheduling scheme.

[0095] Specifically, an optical quantum computer is a quantum computing device that uses photons (light particles) as qubits for information processing. An optical quantum computer mainly consists of two parts: the quantum part and the classical computing part. The quantum part includes a single-photon source, an optical quantum chip, and a single-photon detector. The single-photon source generates high-quality single photons, which serve as the carriers of qubits, by exciting quantum dots with lasers or by spontaneous parametric down-conversion (SPDC). The optical quantum chip is composed of optical components such as optical fibers, waveguides, beam splitters, phase modulators, and mirrors to realize optical transmission and logical operations (such as Hadamard gates and CNOT gates). The single-photon detector can measure the final state of the photon (such as polarization or path) and output the calculation results.

[0096] Then, when determining the target scheduling scheme, a single-photon source generates photons and injects them into a quantum chip. The calculation results from the quantum chip are then detected by a single-photon detector. These results are then input into the classical computing part of the quantum computer to decode and obtain the target scheduling scheme.

[0097] Based on the same idea as the vehicle dispatching method provided in one or more embodiments of this specification, this specification also provides a corresponding vehicle dispatching device, such as... Figure 4 As shown.

[0098] Figure 4 This specification provides a schematic diagram of a vehicle dispatching device, which specifically includes:

[0099] The acquisition module 400 is used to acquire scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot;

[0100] The generation module 401 is used to determine multiple candidate scheduling schemes based on the scheduling reference data, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space, and the second time required for each vehicle to be transported to park in the corresponding parking space, wherein each candidate scheduling scheme includes the parking space, driving route and passage order corresponding to each vehicle to be transported;

[0101] The cost module 402 is used to determine the total cost of the candidate scheduling scheme based on the first time and the second time corresponding to the plurality of vehicles to be transported in each candidate scheduling scheme;

[0102] The determining module 403 is used to determine a target scheduling scheme from the plurality of candidate scheduling schemes based on the total cost of each candidate scheduling scheme, and guide the plurality of vehicles to be transported to park in the corresponding parking spaces based on the target scheduling scheme.

[0103] Optionally, the acquisition module 400 is specifically used to, in response to the received scheduling task, determine the first vehicle to be scheduled and the second vehicle in the parking lot that is not currently parked in the corresponding parking space; and determine the plurality of vehicles to be transported based on the first vehicle and the second vehicle.

[0104] Optionally, the generation module 401 is specifically configured to: determine, based on the scheduling reference data, the operation set and congestion matrix corresponding to the plurality of vehicles to be transported when parking in the corresponding parking spaces, respectively, wherein the congestion matrix is ​​used to represent the degree of road congestion caused by each parking operation of the vehicle to be transported; determine the collision probability corresponding to each candidate scheduling scheme based on the operation set and the congestion matrix; determine the congestion time corresponding to each candidate scheduling scheme based on the congestion matrix and the operation set, as the parking cost of the candidate scheduling scheme; determine the total path length of the plurality of vehicles to be transported corresponding to each candidate scheduling scheme based on the scheduling reference data, as the management cost of the candidate scheduling scheme; and determine the total cost of the candidate scheduling scheme based on at least one of the collision probability, the parking cost, and the management cost corresponding to each candidate scheduling scheme, and the first time and the second time corresponding to the plurality of vehicles to be transported in the candidate scheduling scheme.

[0105] Optionally, the generation module 401 is specifically used to determine the decommissioning order of the plurality of vehicles to be transported; for each vehicle to be transported, based on the decommissioning order and the distance between the parking space in the parking lot and the vehicle to be transported, determine a first cost for each parking space for the vehicle to be transported; based on the comprehensive cost of each parking space for each vehicle to be transported, determine a second cost corresponding to each candidate scheduling scheme; based on the scheduling reference data, determine the path length corresponding to each candidate scheduling scheme; based on the second cost corresponding to each candidate scheduling scheme and the path length, determine the management cost of the candidate scheduling scheme, wherein the management cost is used to redetermine the parking space corresponding to each vehicle to be transported.

[0106] Optionally, the cost module 402 is specifically used to determine a target scheduling scheme from the plurality of candidate scheduling schemes based on at least one of the following constraints, according to the total cost of each candidate scheduling scheme: each vehicle to be transported has one and only one travel path; each parking space can only hold one vehicle to be transported at any given time; at any given time, the number of vehicles to be transported traveling on each road in the network graph does not exceed the maximum capacity of that road; the departure time of each vehicle to be transported is not earlier than the time it goes offline; when any two vehicles to be transported occupy overlapping areas when parking in a parking space, the parking times of the two vehicles to be transported do not coincide; at any given time, vehicles to be transported do not travel into roads that are completely blocked by parking operations.

[0107] Optionally, the cost module 402 is specifically used to convert each parameter in the candidate scheduling scheme into a decision variable, the total cost into an objective function, and the constraints into penalty terms to determine the vehicle scheduling model; input the vehicle scheduling model and the scheduling reference data into a quantum computer, and determine the target scheduling scheme based on the output of the quantum computer.

[0108] Optionally, the device further includes a simulation module 404, specifically used to execute the target scheduling scheme in real time through a simulation system; when the simulation result differs from the estimated result of the target scheduling scheme, the target scheduling scheme is re-determined, and the multiple vehicles to be transported are guided to park in the corresponding parking spaces through the re-determined target scheduling scheme.

[0109] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or device embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The professional and apparatus embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0110] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0111] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0112] in, Figure 5 An exemplary architecture of an electronic device is shown, which may include a processor 510, a video display adapter 511, a disk drive 512, an input / output interface 513, a network interface 514, and a memory 520. The processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, and memory 520 can communicate with each other via a communication bus 530.

[0113] The processor 510 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0114] The memory 520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 520 can store the operating system 521 for controlling the operation of the electronic device 500, and the basic input / output system (BIOS) 522 for controlling the low-level operations of the electronic device 500. Additionally, it can store a web browser 523, a data storage management system 524, and a media file playback device 600, etc. The aforementioned media file playback device 600 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 520 and is called and executed by the processor 510.

[0115] Input / output interface 513 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0116] Network interface 514 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0117] Bus 530 includes a pathway for transmitting information between various components of the device, such as processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, and memory 520.

[0118] It should be noted that although the above-described device only shows the processor 510, video display adapter 511, disk drive 512, input / output interface 513, network interface 514, memory 520, bus 530, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0119] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0120] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A vehicle dispatching method, characterized in that, include: Obtain scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot; Based on the scheduling reference data, multiple candidate scheduling schemes are determined, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space and the second time required for each vehicle to be transported to park in the corresponding parking space are determined. Each candidate scheduling scheme includes the parking space, driving route and passage order corresponding to each vehicle to be transported. Based on the scheduling reference data, the operation set and blocking matrix corresponding to the plurality of vehicles to be transported are determined when they park in the corresponding parking spaces, wherein the blocking matrix is ​​used to represent the degree of road obstruction caused by each parking operation of the vehicle to be transported. Based on the operation set and the blocking matrix, determine the collision probability corresponding to each candidate scheduling scheme; Based on the blocking matrix and the operation set, the blocking time corresponding to each candidate scheduling scheme is determined as the berthing cost of the candidate scheduling scheme; Based on the scheduling reference data, the total path length of the multiple vehicles to be transported corresponding to each candidate scheduling scheme is determined as the management cost of the candidate scheduling scheme; The total cost of a candidate scheduling scheme is determined based on at least one of the collision probability, the parking cost, and the management cost corresponding to each candidate scheduling scheme, as well as the first time and the second time corresponding to the plurality of vehicles to be transported in the candidate scheduling scheme. Based on the total cost of each candidate scheduling scheme, a target scheduling scheme is determined from the plurality of candidate scheduling schemes, and the plurality of vehicles to be transported are guided to park in the corresponding parking spaces based on the target scheduling scheme.

2. The vehicle dispatching method as described in claim 1, characterized in that, Before the step of obtaining the scheduling reference data, the method further includes: In response to the received scheduling task, determine the first vehicle to be scheduled, and the second vehicle in the parking lot that is not currently parked in the corresponding parking space; Based on the first vehicle and the second vehicle, the plurality of vehicles to be transferred are determined.

3. The vehicle dispatching method as described in claim 1, characterized in that, The step of determining the total path length of the plurality of vehicles to be transported corresponding to each candidate scheduling scheme based on the scheduling reference data, as the management cost of the candidate scheduling scheme, specifically includes: Determine the order in which the plurality of vehicles to be transported will be removed from the production line; For each of the vehicles to be transported, a first cost for each parking space for the vehicle to be transported is determined based on the order of vehicle decommissioning and the distance between the parking space in the parking lot and the vehicle to be transported. Based on the comprehensive cost of each parking space for each vehicle to be transported, determine the second cost corresponding to each candidate scheduling scheme; Based on the scheduling reference data, determine the path length corresponding to each candidate scheduling scheme; The management cost of each candidate scheduling scheme is determined based on the second cost corresponding to each candidate scheduling scheme and the path length, wherein the management cost is used to redetermine the parking space corresponding to each vehicle to be transported.

4. The vehicle dispatching method according to any one of claims 1-3, characterized in that, The step of determining the target scheduling scheme from the plurality of candidate scheduling schemes based on the total cost of each candidate scheduling scheme specifically includes: Based on at least one of the following constraints, a target scheduling scheme is determined from the plurality of candidate scheduling schemes according to the total cost of each candidate scheduling scheme; Each of the aforementioned vehicles to be transported has one and only one route; Each parking space may only hold one of the vehicles to be transported at any given time. At any given time, the number of vehicles waiting to be transported traveling on each road in the network diagram does not exceed the maximum capacity of that road. The departure time of each of the aforementioned vehicles to be transported shall not be earlier than the vehicle's off-line time; If the parking areas occupied by any two vehicles waiting to be transported overlap when they are parked in a parking space, the parking times of the two vehicles waiting to be transported do not coincide. At any time, vehicles awaiting transport shall not travel onto roads that are completely blocked by parking operations.

5. The vehicle dispatching method as described in claim 4, characterized in that, The determination of the target scheduling scheme from the plurality of candidate scheduling schemes based on at least one of the following constraints and according to the total cost of each candidate scheduling scheme specifically includes: Each parameter in the candidate scheduling scheme is converted into a decision variable, the total cost is converted into an objective function, and the constraints are converted into penalty terms to determine the vehicle scheduling model. The vehicle scheduling model and the scheduling reference data are input into a quantum computer, and the target scheduling scheme is determined based on the output of the quantum computer.

6. The vehicle dispatching method as described in claim 1, characterized in that, The method further includes: The target scheduling scheme is executed in real time through a simulation system; When the simulation results differ from the predicted results of the target scheduling scheme, the target scheduling scheme is redefined, and the multiple vehicles to be transported are guided to park in the corresponding parking spaces using the redefined target scheduling scheme.

7. A vehicle dispatching device, characterized in that, include: The acquisition module is used to acquire scheduling reference data, wherein the scheduling reference data includes the initial coordinates of multiple vehicles to be transported and a network diagram of the parking lot; The generation module is used to determine multiple candidate scheduling schemes based on the scheduling reference data, and in each candidate scheduling scheme, the first time required for each vehicle to be transported to reach the corresponding parking space, and the second time required for each vehicle to be transported to park in the corresponding parking space, wherein each candidate scheduling scheme includes the parking space, driving route and passage order corresponding to each vehicle to be transported; The cost module is used to determine, based on the scheduling reference data, the operation set and congestion matrix corresponding to the plurality of vehicles to be transported when parking in the corresponding parking spaces, wherein the congestion matrix is ​​used to represent the degree of road congestion caused by each parking operation of the vehicle to be transported; determine the collision probability corresponding to each candidate scheduling scheme based on the operation set and the congestion matrix; determine the congestion time corresponding to each candidate scheduling scheme based on the congestion matrix and the operation set, as the parking cost of the candidate scheduling scheme; determine the total path length of the plurality of vehicles to be transported corresponding to each candidate scheduling scheme based on the scheduling reference data, as the management cost of the candidate scheduling scheme; and determine the total cost of the candidate scheduling scheme based on at least one of the collision probability, the parking cost, and the management cost corresponding to each candidate scheduling scheme, as well as the first time and the second time corresponding to the plurality of vehicles to be transported in the candidate scheduling scheme. The determining module is used to determine a target scheduling scheme from the plurality of candidate scheduling schemes based on the total cost of each candidate scheduling scheme, and guide the plurality of vehicles to be transported to park in the corresponding parking spaces based on the target scheduling scheme.

8. A quantum optical computer, characterized in that, The optical quantum computer comprises a quantum component and a classical computing component, wherein: The classical computation part is used to transform the vehicle scheduling model constructed based on the vehicle scheduling method described in any one of claims 1-6 into a quadratic unconstrained binary optimization QUBO model. The quantum part is used to output a binary bit string according to the QUBO model; The classical computation section is used to decode the binary bit string and determine the target scheduling scheme.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for executing the vehicle scheduling method according to any one of claims 1 to 6.

Images