Vehicle scheduling method and device, computer device, storage medium and program product

Abstract

The application relates to a vehicle scheduling method, device and computer equipment. The method comprises the following steps: obtaining a historical device quantity set of a target area in a historical time period and a device quantity set in a preset time period, performing flow aggregation index value prediction on the target area according to the historical device quantity set and the device quantity set, and obtaining a flow aggregation index value corresponding to the target area. In the case that the target area is determined to exist flow aggregation according to the flow aggregation index value, the number of target objects in the target area in the preset time period is determined according to the historical device quantity set and the device quantity set, vehicle screening is performed according to historical vehicle single data associated with the target area, a schedulable vehicle is determined, a vehicle scheduling strategy corresponding to the target area is generated according to the number of target objects and the schedulable vehicle, and vehicle scheduling processing is performed through the vehicle scheduling strategy. The method can reduce the waiting time for calling a vehicle, improve the rationality of vehicle scheduling, and reduce resource waste.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a vehicle dispatching method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of computer technology and the expansion and improvement of transportation networks, various modes of transportation have emerged to facilitate people's travel, including public transportation, hailing a taxi offline, or ride-hailing services. However, due to differences in users' hailing time and the area where they are located, the distribution of taxis varies, which can easily lead to situations where users cannot hail a vehicle on the roadside for a long time or have to spend a lot of time waiting for a ride-hailing service.

[0003] In traditional technologies, to address the problem of long waiting times for users to hail a ride and the inability to board a vehicle in a timely manner, a method has emerged that triggers dispatch based on user demand, simultaneously publishing the user's ride request to multiple different taxis in order to increase the vehicle's order acceptance rate and reduce waiting time.

[0004] However, the traditional method of triggering dispatch based on user demand and simultaneously publishing user demand to different taxis can easily result in users' ride requests being published to taxis that are already in operation or taxis that are far away. This can lead to a failure to respond to users' ride requests in a timely manner, and the problems of long waiting times and unreasonable vehicle dispatch still exist. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle dispatching method, device, computer equipment, computer-readable storage medium, and computer program product that can reduce users' waiting time for hailing a taxi and effectively improve the rationality of vehicle dispatching, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a vehicle dispatching method, comprising: acquiring a historical set of device counts for a target area within a historical time period and a set of device counts within a preset time period; predicting a traffic aggregation index value for the target area based on the historical set of device counts and the set of device counts to obtain a traffic aggregation index value corresponding to the target area; determining the number of target objects in the target area within the preset time period based on the traffic aggregation index value and the set of device counts based on the historical set of device counts and the set of device counts; acquiring historical vehicle order data associated with the target area, filtering vehicles based on the historical vehicle order data, and determining dispatchable vehicles; and generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the dispatchable vehicles, so as to perform vehicle dispatching processing through the vehicle dispatching strategy.

[0007] Secondly, this application also provides a vehicle dispatching device, comprising: a device quantity set acquisition module, used to acquire a historical device quantity set of a target area within a historical time period and a device quantity set within a preset time period; a traffic aggregation index value prediction module, used to predict the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set, and obtain a traffic aggregation index value corresponding to the target area; a target object quantity determination module, used to determine the number of target objects in the target area within the preset time period based on the historical device quantity set and the device quantity set when it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value; a dispatchable vehicle determination module, used to acquire historical vehicle order data associated with the target area, and filter vehicles based on the historical vehicle order data to determine dispatchable vehicles; and a vehicle dispatching processing module, used to generate a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the dispatchable vehicles, so as to perform vehicle dispatching processing through the vehicle dispatching strategy.

[0008] Thirdly, this application also provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: obtaining a historical set of the number of devices in a target area within a historical time period and a set of the number of devices within a preset time period; predicting a traffic aggregation index value for the target area based on the historical set of the number of devices and the set of devices, and obtaining a traffic aggregation index value corresponding to the target area; if it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value, determining the number of target objects in the target area within the preset time period based on the historical set of the number of devices and the set of devices; obtaining historical vehicle order data associated with the target area, filtering vehicles based on the historical vehicle order data, and determining dispatchable vehicles; generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the dispatchable vehicles, so as to perform vehicle dispatching processing through the vehicle dispatching strategy.

[0009] Fourthly, this application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program performs the following steps: obtaining a historical set of device counts for a target area within a historical time period and a set of device counts within a preset time period; predicting a traffic aggregation index value for the target area based on the historical set of device counts and the set of device counts to obtain a traffic aggregation index value corresponding to the target area; determining the number of target objects in the target area within the preset time period based on the historical set of device counts and the set of device counts when it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value; obtaining historical vehicle order data associated with the target area, filtering vehicles based on the historical vehicle order data, and determining dispatchable vehicles; generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the dispatchable vehicles, so as to perform vehicle dispatching processing through the vehicle dispatching strategy.

[0010] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps: obtaining a historical set of device counts for a target area within a historical time period and a set of device counts within a preset time period; predicting a traffic aggregation index value for the target area based on the historical set of device counts and the set of device counts to obtain a traffic aggregation index value corresponding to the target area; if, based on the traffic aggregation index value, it is determined that there is traffic aggregation in the target area, determining the number of target objects in the target area within the preset time period based on the historical set of device counts and the set of device counts; obtaining historical vehicle order data associated with the target area, filtering vehicles based on the historical vehicle order data, and determining dispatchable vehicles; and generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the dispatchable vehicles, so as to perform vehicle dispatching processing through the vehicle dispatching strategy.

[0011] In the aforementioned vehicle dispatching method, apparatus, computer equipment, computer-readable storage medium, and computer program product, by acquiring the historical device quantity set of the target area within a historical time period and the device quantity set within a preset time period, the traffic aggregation index value of the target area is predicted based on the historical device quantity set and the device quantity set, thereby obtaining the traffic aggregation index value corresponding to the target area. Thus, it is possible to determine whether there is traffic aggregation in the target area based on the traffic aggregation index value, and to promptly identify areas with traffic aggregation and ride-hailing demand, dispatching vehicles to areas with ride-hailing demand, reducing user queuing time and vehicle vacancy. Furthermore, if traffic aggregation is determined in the target area based on the traffic aggregation index value, the number of target objects in the target area within a preset time period is determined based on the historical device quantity set and the device quantity set. Vehicles are then filtered based on the historical vehicle order data associated with the target area to determine dispatchable vehicles. Thus, a vehicle dispatch strategy corresponding to the target area can be generated based on the number of target objects and dispatchable vehicles. Vehicle dispatching is then carried out through the vehicle dispatch strategy to reduce user waiting time, vehicle vacancy status, and vehicle waiting time, effectively improving the rationality of vehicle dispatching, reducing resource waste, and further improving resource utilization. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a diagram illustrating the application environment of the vehicle scheduling method in one embodiment;

[0014] Figure 2 This is a flowchart illustrating a vehicle dispatching method in one embodiment;

[0015] Figure 3 This is a schematic diagram of the distribution of the target area in one embodiment;

[0016] Figure 4 This is a schematic diagram of the process for obtaining the traffic aggregation index value corresponding to the target area in one embodiment;

[0017] Figure 5 This is a schematic diagram illustrating the correspondence between historical time windows and current time windows in one embodiment;

[0018] Figure 6 This is a flowchart illustrating the process of obtaining the number of target objects in a target area within a preset time period in one embodiment.

[0019] Figure 7 This is a schematic diagram of the process for generating historical vehicle order data associated with a target area in one embodiment;

[0020] Figure 8 This is a schematic diagram of at least one historical vehicle location unit corresponding to the target area in one embodiment;

[0021] Figure 9 This is a flowchart illustrating the process of generating a vehicle scheduling strategy corresponding to a target area in one embodiment.

[0022] Figure 10 This is a schematic diagram of the overall processing flow of a vehicle dispatching method in one embodiment;

[0023] Figure 11 This is a structural block diagram of a vehicle dispatching device in one embodiment;

[0024] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0026] The vehicle dispatching method provided in this application can be applied to various scenarios such as intelligent transportation, map navigation, assisted driving, and online media. Specifically, it can be applied to, for example... Figure 1In the application environment shown, both the first terminal 102 and the second terminal 104 can communicate with the server 106 via a network. The data storage system can store the data that the server 106 needs to process. The data storage system can be integrated onto the server 106 or placed on the cloud or other network servers. The first terminal 102 and the second terminal 104 can be, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, portable wearable devices, and aircraft. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 106 can be a standalone physical server, a server cluster consisting of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The first terminal 102, the second terminal 104, and the server 104 can be directly or indirectly connected via wired or wireless communication, and this embodiment does not impose any restrictions on this.

[0027] In this embodiment, the first terminal 102, the second terminal 104, and the server 106 can each be used individually to execute the task processing method provided in this application embodiment, or they can work together to execute the task processing method provided in this application embodiment. For example, taking the first terminal 102, the second terminal 104, and the server 106 working together to execute the task processing method provided in this application embodiment as an example, the server 106 can obtain the historical device quantity set of the target area within a historical time period and the device quantity set within a preset time period for each first terminal 102 in the target area, and predict the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set to obtain the traffic aggregation index value corresponding to the target area. Wherein, if the server 106 determines that there is traffic aggregation in the target area based on the traffic aggregation index value, it then determines the number of target objects in the target area within the preset time period based on the historical device quantity set and the device quantity set. Furthermore, the server 106 can obtain historical vehicle order data associated with each second terminal 104 associated with the target area, and filter vehicles based on the historical vehicle order data to determine dispatchable vehicles. Thus, based on the number of target objects and dispatchable vehicles, a vehicle dispatching strategy corresponding to the target area can be generated, and vehicle dispatching processing can be carried out through the vehicle dispatching strategy.

[0028] In one exemplary embodiment, such as Figure 2 As shown, a vehicle dispatching method is provided. This method can be executed by a terminal or server alone, or by a terminal and server working together. This method can be applied to… Figure 1 Taking server 106 as an example, the explanation includes the following steps S202 to S210. Wherein:

[0029] Step S202: Obtain the historical device count set of the target area within a historical time period and the device count set within a preset time period.

[0030] The target area can specifically include designated areas of different area types, such as one or more areas within a city, such as transportation hubs (e.g., train stations, airports, and bus stations), venues (e.g., stadiums and gymnasiums), and commercial districts (e.g., a commercial pedestrian street or a shopping mall). When there are multiple target areas, it is necessary to obtain the historical device quantity set and the device quantity set within the preset time period for each target area. This allows for separate judgment for each target area to determine whether there is traffic aggregation in the corresponding target area, so as to dispatch vehicles for target areas with traffic aggregation.

[0031] Specifically, for a target area, such as a transportation hub in a city (e.g., a train station), the server obtains the historical device count set for that target area over a historical time period. Specifically, it can obtain the historical device count for a particular train station per minute per day over the past six months, thus obtaining the historical device count set for that train station over the past six months. This can be achieved by collecting LBS (Location-Based Services) data for the target area over a historical time period, thereby obtaining the number of location-based devices (e.g., mobile phones) in the target area over that historical time period, thus obtaining the historical device count set. The historical time period can be set and adjusted according to actual needs and application scenarios, and is not limited to a specific value.

[0032] Furthermore, for the same target area, the server also needs to obtain the set of device counts in that target area within a preset time period. The preset time period can also be set and adjusted according to actual needs and application scenarios, and is not limited to a certain or certain specific values. For example, the preset time period can be set as a time window unit, such as 15 minutes. When predicting the traffic aggregation index value of the target area, the time window unit is used as the basis. Based on the set of device counts in the target area within the preset time period (i.e., one time window unit), and the historical set of device counts in the same time window unit in historical time periods, the traffic aggregation index value of the target area can be predicted.

[0033] For example, by setting a preset time period as a time window unit, such as 15 minutes, the number of historically located devices in the target area within a historical time period can be obtained, with 15 minutes as a time window unit. Specifically, for the historical device count set within the historical time period, the historical device count set for the time window unit of 10:00-10:15 on a certain day is obtained, and the device count set within the preset time period, i.e., the time window unit of 10:00-10:15 on the current day, is also obtained. Based on the historical device count set and the device count set, the traffic aggregation index value of the target area can be predicted.

[0034] In one exemplary embodiment, such as Figure 3 As shown, a schematic diagram of the distribution of a target area is provided. Figure 3 It can be seen that, for a certain city, the target areas include: 1) Transportation hubs: railway station A1, railway station A2, airport B1, passenger station C1 and passenger station C2; 2) Venues: such as stadium D1 and stadium D2; 3) Business districts: commercial pedestrian street X1, commercial pedestrian street X2, shopping mall Y1 and shopping mall Y2.

[0035] Step S204: Based on the historical device quantity set and the device quantity set, predict the traffic aggregation index value of the target area to obtain the traffic aggregation index value corresponding to the target area.

[0036] Specifically, the server can determine the historical device data and the current device count for the same time window node from the historical device dataset and the device count set, respectively. Since there is at least one historical time window in the historical time period and at least one current time window in the preset time period, at least one historical time window-current time window pair located in the same time window unit can be determined. Thus, for at least one historical time window-current time window pair located in the same time window unit, the device count pair corresponding to the historical device count-current device count for each of the at least one time window pair can be determined. Based on the device count pair of at least one historical device count-current device count, traffic aggregation index value prediction can be performed to obtain the traffic aggregation index value corresponding to the target area.

[0037] Step S206: If it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value, the number of target objects in the target area within the preset time period is determined based on the historical device quantity set and the device quantity set.

[0038] Specifically, the server obtains the traffic aggregation indicator threshold set for the target area and compares the traffic aggregation indicator value with the traffic aggregation indicator threshold. If the traffic aggregation indicator value is greater than the traffic aggregation indicator threshold, it is determined that there is traffic aggregation in the target area.

[0039] The traffic aggregation index threshold can be specifically calculated and constrained based on historical device traffic statistics, the number of active local devices in the city, and the total number of objects in the city. The calculation process includes: using the total number of objects in the city divided by the number of active local devices as the device expansion coefficient; and taking the top 10 historical device traffic statistics ranked by day as the threshold line, and multiplying the historical device traffic statistics of the top 10 days by the device expansion coefficient to obtain the traffic aggregation index threshold. It is understood that the traffic aggregation index threshold can be calculated and adjusted according to actual needs and is not limited to a specific value.

[0040] Furthermore, when the traffic aggregation index value is determined to be greater than the traffic aggregation index threshold, i.e., when it is determined that there is traffic aggregation in the target area, the server can determine the historical traffic sequence characteristics of the target area in the historical time period and the device data volume characteristics corresponding to the target area based on the historical device quantity set and the device quantity set. Based on the historical traffic sequence characteristics, device data volume characteristics and time dimension characteristics corresponding to the preset time period, the server can predict the number of objects in the target area and obtain the number of target objects in the target area in the preset time period.

[0041] For example, the historical traffic sequence features, device data volume features, and time dimension features corresponding to a preset time period can be input into a trained prediction network model. The prediction network model then calculates and predicts the number of target objects in the target area within the preset time period based on these features. Specifically, the prediction network model can be a recurrent neural network, such as LSTM (Long Short-Term Memory). LSTM is used to calculate and predict the number of target objects in the target area within the preset time period based on the historical traffic sequence features, device data volume features, and time dimension features.

[0042] Step S208: Obtain historical vehicle order data associated with the target area, filter vehicles based on the historical vehicle order data, and determine dispatchable vehicles.

[0043] Specifically, the server obtains historical vehicle order data associated with the target area, and determines the historical dispatch record set corresponding to the target area based on the historical vehicle order data. Then, based on the historical dispatch record set, it can further determine each candidate vehicle in the target area, and determine the dispatchable vehicle by screening each candidate vehicle.

[0044] Specifically, the historical vehicle order data associated with the target area can be records of vehicle orders successfully dispatched to the target area. The historical order dispatch record set corresponding to the target area can be a collection of historical order dispatch records for different candidate vehicles in the target area. This can be understood as records obtained after dispatching orders to multiple different candidate vehicles in the entire target area at least once. Based on each historical order dispatch record in the historical order dispatch record set, the candidate vehicle corresponding to the historical order dispatch record can be identified, and the distance between the candidate vehicle and the target area, the arrival time of the vehicle to the target area, and the vehicle's empty status (used to determine the vehicle's utilization rate) can be determined, so as to further reconstruct the vehicle dispatch orders that have been completed and those that have not been completed in the target area.

[0045] Furthermore, after identifying each candidate vehicle in the target area, the server further determines the vehicle association parameters corresponding to each candidate vehicle based on historical vehicle order data and historical order dispatch records. Based on the vehicle association parameters and preset vehicle screening conditions, the server filters each candidate vehicle to obtain dispatchable vehicles.

[0046] Based on historical vehicle order data and historical order dispatch records for the target area, vehicle dispatch orders that have been completed and those that have not can be identified within the target area. This includes candidate vehicles corresponding to historical order dispatch records that have been successfully dispatched and those that have not been successfully dispatched, as well as the distance between the candidate vehicle and the target area, the arrival time of the vehicle to the target area, and the vehicle's empty status. This allows for the determination of vehicle association parameters corresponding to each candidate vehicle. These vehicle association parameters specifically include vehicle response rate, arrival time satisfaction, and vehicle utilization rate.

[0047] For example, vehicle response rate refers to the proportion of drivers on candidate vehicles in the target area who accept dispatch suggestions or prompts. Arrival time satisfaction refers to the satisfaction with the estimated arrival time (eta, Estimated Time of Arrival) of candidate vehicles. Based on the same straight-line distance, the historical actual arrival times of candidate vehicles are distributed, including exponential normalization of the maximum, minimum, and median values, to obtain a data distribution value for arrival time. The larger this data distribution value, the higher the satisfaction with the estimated arrival time of the candidate vehicle. Vehicle utilization rate refers to the overall utilization rate of candidate vehicles in the target area. This can be determined by obtaining the full-load and empty-load status of vehicles within a unit of time (e.g., one month).

[0048] Specifically, when filtering candidate vehicles based on vehicle association parameters and preset vehicle filtering conditions, the preset vehicle filtering conditions set for the target area can be obtained. These conditions include factors such as the distance between the candidate vehicle and the target area, and the vehicle's passenger status (including empty, partially loaded, and fully loaded). Based on these preset vehicle filtering conditions and the vehicle association parameters of each candidate vehicle, the candidate vehicles can be filtered to obtain dispatchable vehicles.

[0049] For example, vehicles can be recommended based on proximity. For instance, if a taxi is close to the target area, then that taxi is a dispatchable vehicle for that target area. Alternatively, vehicles can be matched based on whether the passenger's location is within the target area. For example, if a taxi currently has a passenger whose destination is the target area and can reach the target area within 5-15 minutes, then that taxi is also a dispatchable vehicle for that target area.

[0050] Step S210: Based on the number of target objects and available vehicles, generate a vehicle scheduling strategy corresponding to the target area, so as to perform vehicle scheduling processing through the vehicle scheduling strategy.

[0051] Specifically, the server obtains the current vehicle association parameters corresponding to each schedulable vehicle, as well as the initial vehicle scheduling coefficient set for the current vehicle association parameters. Based on the current vehicle association parameters and the number of target objects, the server optimizes the initial vehicle scheduling coefficient to obtain the optimized vehicle scheduling coefficient. Based on the optimized vehicle scheduling coefficient and vehicle association parameters, the server generates a vehicle scheduling strategy corresponding to the target area.

[0052] The vehicle scheduling strategy can be understood as determining the required number of target vehicles based on the number of target objects, and determining the processing strategy for the target vehicles of each target object based on the current vehicle association parameters of the schedulable vehicles. It can determine the priority of each schedulable vehicle, determine the corresponding vehicle scheduling order according to the priority, and schedule each schedulable vehicle in turn.

[0053] Optionally, the initial vehicle scheduling coefficients set for the current vehicle-related parameters may specifically include a first initial scheduling coefficient, a second initial scheduling coefficient, and a third initial scheduling coefficient set for vehicle response rate, arrival time satisfaction, and vehicle utilization rate, respectively.

[0054] For example, based on the historical vehicle order data of the target area, candidate vehicles are identified, and vehicle screening is performed based on each candidate vehicle to determine the dispatchable vehicles and the vehicle-related parameters of the dispatchable vehicles, including vehicle response rate, arrival time satisfaction, and vehicle utilization rate. The parameters are solved using a polynomial solution method such as the LM algorithm (i.e., gradient descent method). The locally optimal solution is used as the initial vehicle dispatch coefficients, including the first initial dispatch coefficient, the second initial dispatch coefficient, and the third initial dispatch coefficient.

[0055] In one exemplary embodiment, vehicle scheduling processing is performed using a vehicle scheduling strategy, including:

[0056] According to the vehicle dispatching strategy, generate vehicle dispatching prompt information corresponding to at least one dispatchable vehicle; for each dispatchable vehicle, feed back the vehicle dispatching prompt information to the dispatchable vehicle and obtain the vehicle dispatching acceptance information corresponding to the dispatchable vehicle; based on the vehicle dispatching acceptance information corresponding to at least one dispatchable vehicle, determine the number of vehicles that have accepted dispatching for the target area; when it is determined that the number of vehicles that have accepted dispatching has reached the target number, end the vehicle dispatching process.

[0057] Specifically, when the server performs vehicle scheduling processing according to the vehicle scheduling strategy, it can generate vehicle scheduling prompt information corresponding to at least one schedulable vehicle, and feed back each vehicle scheduling prompt information to the schedulable vehicle corresponding to each vehicle scheduling prompt information, and obtain the vehicle scheduling acceptance information fed back by the vehicle terminal of the schedulable vehicle in response to the vehicle scheduling prompt information.

[0058] Furthermore, based on the vehicle dispatch acceptance information corresponding to each of the at least one dispatchable vehicle, the number of vehicles that have accepted dispatch requests corresponding to the target area is determined. This number is then compared with the number of target objects. The vehicle dispatch process ends when the number of vehicles that have accepted dispatch requests reaches the number of target objects. Conversely, if the number of vehicles that have accepted dispatch requests does not reach the number of target objects, vehicle dispatch notification information is sent to other dispatchable vehicles that have not yet received such notifications.

[0059] In one exemplary embodiment, depending on the type of area to which the target area belongs (area types include transportation hubs, venues, and commercial districts), there are different numbers of target objects and different vehicle dispatching requirements, wherein:

[0060] 1) Target areas based on venue type: For example, if a venue is hosting a concert and the concert ends at a certain time, then within a preset time period starting from the end time, the area within 500 meters of the venue is designated as the target area. The number of people needing to hail a taxi (i.e., the target audience) is set to a relatively high number, such as 50% of the total number of concert attendees. Similarly, if a venue is hosting a sporting event and the sporting event ends at a certain time, then within a preset time period starting from the end time, the area within 500 meters of the venue is designated as the target area. The number of people needing to hail a taxi (i.e., the target audience) is set to a relatively high number, such as 60% of the total number of sporting event attendees.

[0061] 2) Target areas for transportation hubs: For example, a train station where multiple trains are expected to arrive within the next hour, resulting in a large number of passengers disembarking, would be the target area for that specific time period. The number of people needing taxis (i.e., the target population) would be set at a high level, such as 60% of the total number of passengers on the multiple trains. Similarly, an airport where multiple flights are expected to land within the next hour, resulting in a large number of arriving passengers, would also be the target area for that specific time period. The number of people needing taxis (i.e., the target population) would be set at a high level, such as 50% of the total number of passengers on the multiple flights.

[0062] For example, if public transportation in a certain area malfunctions, such as a subway station malfunctioning and trains no longer passing through that station, resulting in a standstill, then there will be many passengers at that station and a high demand for taxis. In this case, the area where the subway station is located will be designated as the target area for the next hour, and the number of people who need to take a taxi, i.e., the target population, will be set to a high number, such as 200 or 300 people.

[0063] 3) For target areas of business district categories, for example, if a business district has a large number of people hailing rides and a long queue of people, such as more than 100 people in the queue, then that area is designated as a ride-hailing area. The number of people who need to hail a ride, i.e. the number of target users, is set to a high number, such as 50% of the total number of people in the ride-hailing queue. The waiting time for people in the middle of the queue is then set as the duration of a specific time period.

[0064] In the aforementioned vehicle dispatching method, by acquiring the historical device count set of the target area within a historical time period and the device count set within a preset time period, traffic aggregation index values ​​are predicted for the target area based on these historical and device count sets. This yields a traffic aggregation index value corresponding to the target area, allowing for the determination of whether traffic aggregation exists in the target area. This enables the timely identification of areas with traffic aggregation and ride-hailing demand, allowing vehicles to be dispatched to these areas, reducing user waiting time and vehicle vacancy. Furthermore, if traffic aggregation is determined in the target area based on the traffic aggregation index value, the number of target objects in the target area within the preset time period is determined based on the historical and device count sets. Vehicles are then filtered based on historical vehicle order data associated with the target area to determine dispatchable vehicles. Based on the number of target objects and dispatchable vehicles, a vehicle dispatching strategy corresponding to the target area is generated. This strategy is then used for vehicle dispatching, reducing user waiting time, vehicle vacancy, and overall vehicle waiting time, effectively improving the rationality of vehicle dispatching, reducing resource waste, and further enhancing resource utilization.

[0065] In one exemplary embodiment, such as Figure 4 As shown, the steps for obtaining the traffic aggregation index value corresponding to the target area, namely, predicting the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set, specifically include the following steps S402 to S408. Wherein:

[0066] Step S402: Determine at least one historical time window based on historical time periods, and determine at least one current time window based on preset time periods.

[0067] Specifically, the server obtains a pre-set time window unit, such as 15 minutes, and determines at least one historical time window based on the historical time period, that is, at least one historical time window with a length of 15 minutes, and determines at least one current time window based on the preset time period, that is, at least one current time window with a length of 15 minutes.

[0068] Step S404: For each current time window, determine a historical time window that matches the current time window from at least one historical time window.

[0069] Specifically, for each current time window within at least one current time window, the server determines a historical time window that matches the current time window from at least one historical time window. Specifically, it determines a pair of current time windows and historical time windows that are at the same time window node, that is, a mutual match between current time windows and historical time windows that are at the same time window node.

[0070] For example, taking a day as a unit, a day includes multiple time windows of 15 minutes in length. Then, based on the historical time period, at least one historical time window of 15 minutes in length can be determined, and based on the preset time period, at least one current time window of 15 minutes in length can be determined. The current time window and the historical time window at the same time window node are used as a matching time window pair. For example, for the historical time period, if 10:00 to 10:15 on a certain day is taken as the time window node, then the historical time window of 10:00 to 10:15 can be determined from the historical time period, and the current time window of 10:00 to 10:15 can also be determined from the preset time period. The historical time window of 10:00 to 10:15 and the current time window of 10:00 to 10:15 are used as a matching time window pair.

[0071] In one exemplary embodiment, such as Figure 5 As shown, a correspondence between historical time windows and the current time window is provided, referencing... Figure 5 It can be seen that, based on the historical time period and the current time period, taking a time window unit of 15 minutes as an example, two time window pairs belonging to the same time window node are determined, including the time window pair of 9:00-9:15 (including the current time window-historical time window of 9:00-9:15) and the time window pair of 9:30-9:45 (including the current time window-historical time window of 9:30-9:45).

[0072] Step S406: Determine the number of historical devices corresponding to the historical time window from the set of historical device counts, and determine the number of current devices corresponding to the current time window from the set of device counts.

[0073] Specifically, after determining the current time window and the historical time window that matches the current time window, i.e., obtaining the time window pair of the current time window and the historical time window, the server determines the number of historical devices corresponding to the historical time window from the set of historical device counts for the time window pair, and determines the number of current devices corresponding to the current time window from the set of device counts.

[0074] Since there is at least one current time window and at least one historical time window, the number of current devices corresponding to each of the at least one current time window and the number of historical devices corresponding to each of the at least one historical time window can be determined respectively.

[0075] Step S408: Based on at least one historical number of devices and at least one current number of devices, predict the traffic aggregation index value to obtain the traffic aggregation index value corresponding to the target area.

[0076] Specifically, the server calculates and predicts the traffic aggregation index value for the target area based on at least one historical number of devices and at least one current number of devices, using a traffic aggregation index value calculation formula, and obtains the traffic aggregation index value corresponding to the target area.

[0077] For example, the following formula (1) can be used to determine the traffic aggregation index value W corresponding to the target area:

[0078] Formula (1)

[0079] Where W represents the traffic aggregation index value corresponding to the target area, i represents the i-th time window, and n represents the existence of n time windows. This represents the number of historical devices corresponding to the i-th historical time window. This represents the number of current devices corresponding to the i-th current time window.

[0080] In this embodiment, at least one historical time window is determined based on a historical time period, and at least one current time window is determined based on a preset time period. For each current time window, a historical time window matching the current time window is determined from at least one historical time window. This allows for the determination of the number of historical devices corresponding to the historical time window from the set of historical device counts, and the determination of the number of current devices corresponding to the current time window from the set of device counts. Based on the number of at least one historical device and at least one current device, traffic aggregation index values ​​can be predicted to obtain the traffic aggregation index values ​​corresponding to the target area. This enables the timely identification of areas with traffic aggregation and ride-hailing demand, allowing vehicles to be dispatched to these areas, reducing user waiting time and vehicle vacancy, further improving the rationality of vehicle dispatching, and reducing resource waste.

[0081] In one exemplary embodiment, such as Figure 6 As shown, the step of obtaining the number of target objects in the target area within a preset time period, that is, determining the number of target objects in the target area within the preset time period based on the historical device quantity set and the device quantity set, specifically includes the following steps S602 to S606. Wherein:

[0082] Step S602: Based on the historical device quantity set, determine the historical traffic sequence characteristics of the target area within the historical time period.

[0083] Specifically, for the set of historical devices within a historical time period, the server performs feature normalization processing according to the time sequence of the historical time period, such as the time sequence of the past six months, to obtain the historical traffic sequence features of the target area within the historical time period.

[0084] Step S604: Perform feature encoding processing on the device quantity set to obtain the device data quantity characteristics corresponding to the target area.

[0085] Specifically, for the set of device numbers, the server performs feature encoding processing on the set of device numbers, such as one-hot encoding, to obtain the device data volume characteristics corresponding to the target area.

[0086] Step S606: Determine the time dimension features corresponding to the preset time period, and based on the time dimension features, historical traffic sequence features, and device data volume features, predict the number of objects in the target area to obtain the number of target objects in the target area within the preset time period.

[0087] Specifically, the server obtains time attribute information corresponding to a preset time period, including the current time of the preset time period (e.g., year, month, day), whether the current time is a holiday or a workday, and what day of the week it is, etc., and then performs feature encoding processing on the time attribute information corresponding to the preset time period, such as one-hot encoding, to obtain the time dimension features corresponding to the preset time period.

[0088] Furthermore, the server inputs historical traffic sequence features, device data volume features, and time dimension features corresponding to a preset time period into a trained prediction network model. The prediction network model then calculates and predicts the number of target objects in the target area within the preset time period based on the historical traffic sequence features, device data volume features, and time dimension features.

[0089] Specifically, the prediction network model can be a recurrent neural network, such as an LSTM (Long Short-Term Memory) model. The LSTM model calculates and predicts the number of target objects in a target area within a preset time period by analyzing historical traffic sequence features, device data volume features, and time dimension features. The historical traffic sequence features can specifically include traffic sequence features from different historical time periods, such as the number of location devices at the same time in the past six months or the number of location devices per minute in the past hour.

[0090] For example, taking an LSTM model as the prediction network model, the LSTM model includes an input layer, an LSTM layer, an output layer, and an attention mechanism. Wherein:

[0091] 1) For the input layer, the input features specifically include historical traffic sequence features, device data volume features, and time dimension features. The data shape of the input features is (batch_size, time_step, feature_dim), for example, 32*60*20, indicating that each batch includes 32 samples, each sample includes data from the most recent 60 minutes, and there are 20 features per minute. Specifically, the input features for the input layer can also include multiple regional category features corresponding to different areas. For example, areas in a city include: shopping malls, train stations, bus stations, residential areas, schools, hospitals, hotels, and airports, etc. By counting the number of areas under different regional categories, a single-dimensional continuous feature is obtained to obtain the regional category features.

[0092] 2) For the LSTM layers, a multi-layered stack of LSTMs is used, including: 1) First LSTM layer: learns short-term trends, such as fine-grained changes over 15 minutes; 2) Second LSTM layer: learns long-term trends, such as changes over larger time windows like 30 minutes and 60 minutes; 3) Third LSTM layer: integrates time series features to generate a high-dimensional feature representation. Each LSTM layer is a bidirectional LSTM used to capture the sequential relationships within the time series. Dropout is incorporated into each LSTM layer to prevent overfitting during training. By randomly discarding (i.e., setting) the output of a portion of neurons to zero during the training phase, the model's generalization ability is improved.

[0093] 3) For the output layer, the output dimension of the LSTM transport layer is (batch_size, time_step, hidden_units), and the predicted value is the number of target objects in the target region within a preset time period.

[0094] 4) The attention mechanism (i.e., the attention layer) is used to enhance the impact of important time points on the prediction results.

[0095] In this embodiment, by determining the historical traffic sequence characteristics of the target area within a historical time period based on the historical device quantity set, and by performing feature encoding processing on the device quantity set, the device data volume characteristics corresponding to the target area are obtained, and the time dimension characteristics corresponding to the preset time period are determined. Thus, based on multiple perspectives such as time dimension characteristics, historical traffic sequence characteristics, and device data volume characteristics, the number of objects in the target area can be comprehensively considered to accurately obtain the number of target objects in the target area within the preset time period, reducing the cumbersome operations in the process of determining the number of target objects and improving the processing efficiency of determining the number of target objects.

[0096] In one exemplary embodiment, such as Figure 7 As shown, the steps for generating historical vehicle order data associated with the target area specifically include steps S702 to S706. Wherein:

[0097] Step S702: Obtain at least one historical vehicle location unit corresponding to the target area, and for each historical vehicle location unit, obtain the historical dispatch record corresponding to the historical vehicle location unit.

[0098] Specifically, the server obtains at least one historical vehicle location unit for dispatching orders to the target area, such as a 50-meter grid or a 100-meter grid as a historical vehicle location unit, and thus obtains the historical dispatch record corresponding to each historical vehicle location unit. Here, the historical dispatch record refers to the dispatch record obtained after dispatching orders to vehicles in each historical vehicle location unit at least once when dispatching orders to the target area.

[0099] In one exemplary embodiment, such as Figure 8 As shown, a schematic diagram of at least one historical vehicle location unit corresponding to a target area is provided, with reference to... Figure 8 It is known that when dispatching vehicle orders to a target area, the locations of vehicles that have been dispatched to that target area in the past need to be considered. For example, vehicle orders can be dispatched to vehicles within a 1-kilometer or 2-kilometer range from the target area. The 1-kilometer or 2-kilometer range can be divided into at least one historical vehicle location unit of multiple 50-meter or 100-meter grids, so that the historical dispatch records corresponding to each of the at least one historical vehicle location unit can be obtained.

[0100] Step S704: Based on the historical dispatch records, determine the historical vehicle order data of different candidate vehicles included in the historical vehicle location unit.

[0101] Specifically, for each historical vehicle location unit's historical order dispatch records, the server can identify the candidate vehicles corresponding to the historical order dispatch records, determine the vehicle dispatch orders that have been completed and those that have not been completed within the target area, and determine data such as the distance between the candidate vehicle and the target area, the arrival time of the vehicle to the target area, and the vehicle's empty status, thereby obtaining the historical vehicle order completion data for each of the different candidate vehicles included in the historical vehicle location unit.

[0102] Among them, the historical order completion data of candidate vehicles can be understood as the order completion status of candidate vehicles. Since a complete historical order includes data such as user initiation of request, driver acceptance, driver pick-up, passenger boarding, estimated time when the driver accepted the order, and actual arrival time, etc., during the order dispatch process, there may be situations where the driver abandons the order or the passenger abandons the order. For a vehicle to be considered a successful order, the driver must accept the order, the customer must not abandon the order, and the distance and travel time must be within the expectations of both parties. Therefore, based on the historical order dispatch records, the success rate of the order being completed when the driver accepts the order and the customer does not abandon the order can be determined, which is the vehicle order completion data.

[0103] Step S706: Generate historical vehicle order data associated with the target area based on the historical vehicle order data of different candidate vehicles included in at least one historical vehicle location unit.

[0104] Specifically, since at least one historical vehicle location unit is set up when dispatching vehicle orders to a target area, it is necessary to determine the historical vehicle order data of different candidate vehicles included in each of the at least one historical vehicle unit. By combining the historical vehicle order data of different candidate vehicles included in each of the at least one historical vehicle location unit, the historical vehicle order data associated with the target area can be obtained.

[0105] In this embodiment, by acquiring at least one historical vehicle location unit corresponding to the target area, and for each historical vehicle location unit, acquiring the historical dispatch record corresponding to the historical vehicle location unit, the historical vehicle order completion data of different candidate vehicles included in the historical vehicle location unit can be determined based on the historical dispatch record. By combining the historical vehicle order completion data of different candidate vehicles included in each of the at least one historical vehicle location unit, historical vehicle order completion data associated with the target area can be obtained. This achieves the goal of avoiding dispatching vehicles that are too far from the target area by considering the vehicle locations of each candidate vehicle that has been dispatched in the past when dispatching orders to the target area. Furthermore, by combining the historical vehicle order completion data associated with the target area, vehicle screening can be further performed to determine dispatchable vehicles, reduce the number of candidate vehicles, reduce the number of vehicle dispatch failures, and further improve the success rate of dispatching vehicles that are dispatchable.

[0106] In one exemplary embodiment, such as Figure 9 As shown, the steps for generating a vehicle dispatching strategy corresponding to the target area, that is, the steps for generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the available vehicles, specifically include the following steps S902 to S906. Wherein:

[0107] Step S902: Obtain the current vehicle association parameters corresponding to each schedulable vehicle, and the initial vehicle scheduling coefficient set for the current vehicle association parameters.

[0108] Specifically, after the server filters out the schedulable vehicles for the target area, it obtains the current vehicle association parameters corresponding to each schedulable vehicle, and obtains the initial vehicle scheduling coefficient set for the current vehicle association parameters of each schedulable vehicle.

[0109] The parameters associated with the current schedulable vehicles include vehicle response rate, arrival time satisfaction rate, and vehicle utilization rate. The initial vehicle scheduling coefficients set for these parameters can specifically include a first initial scheduling coefficient, a second initial scheduling coefficient, and a third initial scheduling coefficient set for the vehicle response rate, arrival time satisfaction rate, and vehicle utilization rate, respectively.

[0110] Step S904: Optimize the initial vehicle scheduling coefficient based on the current vehicle association parameters and the number of target objects to obtain the optimized vehicle scheduling coefficient.

[0111] Specifically, the server can determine the actual number of vehicles that need to be scheduled based on the number of target objects. Based on the current vehicle-related parameters of the schedulable vehicles, including vehicle response rate, arrival time satisfaction, and vehicle utilization, the initial vehicle scheduling coefficients, including the first initial scheduling coefficient, the second initial scheduling coefficient, and the third initial scheduling coefficient set for vehicle response rate, arrival time satisfaction, and vehicle utilization respectively, are optimized to obtain the optimized first vehicle scheduling coefficient, the second vehicle scheduling coefficient, and the third vehicle scheduling coefficient.

[0112] For example, the initial vehicle scheduling coefficient is optimized using the following formula (2) to obtain the optimized vehicle scheduling coefficient:

[0113] ;Formula (2)

[0114] in, , as well as These represent the first initial scheduling coefficient, the second initial scheduling coefficient, and the third initial scheduling coefficient, respectively. , as well as Let represent the optimized first vehicle scheduling coefficient, second vehicle scheduling coefficient, and third vehicle scheduling coefficient, respectively, and J represent the scheduling priority of the schedulable vehicles. This represents the learning rate, also known as the gradient rate of change. Its value is constant and can be set and adjusted according to actual needs.

[0115] Furthermore, in formula (2) , as well as It is calculated using the following formula (3):

[0116] ;Formula (3)

[0117] Step S906: Based on the optimized vehicle scheduling coefficient and vehicle association parameters, determine the vehicle scheduling priority for each schedulable vehicle, so as to generate a vehicle scheduling strategy corresponding to the target area based on the number of target objects and vehicle scheduling priority.

[0118] Specifically, for each schedulable vehicle, the server obtains the current vehicle association parameters corresponding to the schedulable vehicle, and calculates the scheduling priority of the schedulable vehicle based on the current vehicle association parameters and the optimized vehicle scheduling coefficient, so as to determine the priority of vehicle scheduling processing for the schedulable vehicle through the scheduling priority.

[0119] For example, the vehicle scheduling priority J corresponding to the schedulable vehicle is determined by the following formula (4):

[0120] ;Formula (4)

[0121] in, , as well as Let J represent the optimized first vehicle scheduling coefficient, second vehicle scheduling coefficient, and third vehicle scheduling coefficient, respectively, and J represent the scheduling priority of the schedulable vehicles.

[0122] Furthermore, the server generates a vehicle scheduling strategy corresponding to the target area based on the number of target objects and vehicle scheduling priority. This strategy generates a processing plan for scheduling each schedulable vehicle in the target area. Based on the vehicle scheduling strategy, vehicle scheduling prompts can be generated for the schedulable vehicles. The server can send these prompts to the schedulable vehicles, and each vehicle's terminal can respond with a vehicle scheduling acceptance message to the server. The server can then determine the number of vehicles that have accepted scheduling for the target area based on the vehicle scheduling acceptance messages for at least one schedulable vehicle. When the number of vehicles that have accepted scheduling reaches the target number, the vehicle scheduling process ends.

[0123] In this embodiment, by obtaining the current vehicle association parameters corresponding to each schedulable vehicle and the initial vehicle scheduling coefficient set for the current vehicle association parameters, and optimizing the initial vehicle scheduling coefficient according to the current vehicle association parameters and the number of target objects, an optimized vehicle scheduling coefficient is obtained. Based on the optimized vehicle scheduling coefficient and vehicle association parameters, the vehicle scheduling priority for each schedulable vehicle is determined. Thus, a vehicle scheduling strategy corresponding to the target area can be generated according to the number of target objects and the vehicle scheduling priority. This achieves the goal of vehicle scheduling processing according to the vehicle scheduling strategy, reducing user waiting time, vehicle vacancy status, and vehicle waiting time, further improving the rationality of vehicle scheduling, reducing resource waste, and improving resource utilization.

[0124] In one exemplary embodiment, such as Figure 10 As shown, a vehicle scheduling method is provided, which can be applied to... Figure 1Taking server 106 as an example, this vehicle dispatching method specifically includes the following steps:

[0125] Step S1001: Obtain the historical device count set of the target area within a historical time period and the device count set within a preset time period.

[0126] Specifically, for a target area, such as a transportation hub in a city (e.g., a train station), the server obtains the historical device count set of the target area within a historical time period. Specifically, it can obtain the historical device count of a train station per day per minute over the past six months, thereby obtaining the historical device count set of the train station over the past six months.

[0127] Furthermore, for the same target area, the server also needs to obtain the set of device counts in that target area within a preset time period. The preset time period can also be set and adjusted according to actual needs and application scenarios, and is not limited to a certain or certain specific values. For example, the preset time period can be set as a time window unit, such as 15 minutes, so that when predicting traffic aggregation index values ​​for the target area, the time window unit is used as the basis, based on the set of device counts in the target area within the preset time period (i.e., a time window unit).

[0128] Step S1002: Based on the historical time period, determine at least one historical time window, and based on the preset time period, determine at least one current time window. For each current time window, determine a historical time window that matches the current time window from at least one historical time window.

[0129] Specifically, the server obtains a pre-set time window unit, such as 15 minutes, and determines at least one historical time window based on the historical time period, that is, at least one historical time window with a length of 15 minutes, and determines at least one current time window based on the preset time period, that is, at least one current time window with a length of 15 minutes.

[0130] Furthermore, for each current time window within at least one current time window, the server determines a historical time window that matches the current time window from at least one historical time window. Specifically, it determines a pair of current time windows and historical time windows that are at the same time window node, i.e., the current time windows and historical time windows that are at the same time window node are mutually matched.

[0131] Step S1003: Determine the number of historical devices corresponding to the historical time window from the set of historical device counts, and determine the number of current devices corresponding to the current time window from the set of device counts.

[0132] Specifically, after determining the current time window and the historical time window that matches the current time window, i.e., obtaining the time window pair of the current time window and the historical time window, the server determines the number of historical devices corresponding to the historical time window from the set of historical device counts for the time window pair, and determines the number of current devices corresponding to the current time window from the set of device counts.

[0133] Step S1004: Based on at least one historical number of devices and at least one current number of devices, predict the traffic aggregation index value to obtain the traffic aggregation index value corresponding to the target area.

[0134] Specifically, since there is at least one current time window and at least one historical time window, the number of current devices corresponding to each of the at least one current time window and the number of historical devices corresponding to each of the at least one historical time window can be determined respectively. Then, based on the number of at least one historical device and the number of at least one current device, the traffic aggregation index value can be calculated and predicted for the target area using the traffic aggregation index value calculation formula to obtain the traffic aggregation index value corresponding to the target area.

[0135] Step S1005: Obtain the traffic aggregation index threshold set for the target area, compare the traffic aggregation index value with the traffic aggregation index threshold, and determine that there is traffic aggregation in the target area if the traffic aggregation index value is greater than the traffic aggregation index threshold.

[0136] Step S1006: If it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value, the historical traffic sequence characteristics of the target area in the historical time period are determined based on the historical device quantity set, and the device quantity set is subjected to feature encoding processing to obtain the device data volume characteristics corresponding to the target area.

[0137] Specifically, when it is determined that the traffic aggregation index value is greater than the traffic aggregation index threshold, that is, when it is determined that there is traffic aggregation in the target area, the server can determine the historical traffic sequence characteristics of the target area in the historical time period and the device data volume characteristics corresponding to the target area based on the historical device quantity set and the device quantity set.

[0138] Specifically, for the historical device count set within a historical time period, the server performs feature normalization processing according to the time sequence of the historical time period, such as the time sequence of the past six months, to obtain the historical traffic sequence features of the target area within the historical time period. For the device count set, the server performs feature encoding processing on the device count set, such as one-hot encoding, to obtain the device data volume features corresponding to the target area.

[0139] Step S1007: Determine the time dimension features corresponding to the preset time period, and based on the time dimension features, historical traffic sequence features, and device data volume features, predict the number of objects in the target area to obtain the number of target objects in the target area within the preset time period.

[0140] Specifically, the server obtains the time attribute information corresponding to the preset time period and performs feature encoding processing on the time attribute information corresponding to the preset time period, such as one-hot encoding, to obtain the time dimension features corresponding to the preset time period.

[0141] Furthermore, the server inputs historical traffic sequence features, device data volume features, and time dimension features corresponding to a preset time period into a trained prediction network model. The prediction network model then calculates and predicts the number of target objects in the target area within the preset time period based on the historical traffic sequence features, device data volume features, and time dimension features.

[0142] Step S1008: Obtain at least one historical vehicle location unit corresponding to the target area. For each historical vehicle location unit, obtain the historical dispatch record corresponding to the historical vehicle location unit, so as to determine the historical vehicle order data of different candidate vehicles included in the historical vehicle location unit based on the historical dispatch record.

[0143] Specifically, the server obtains at least one historical vehicle location unit for dispatching orders to the target area, such as a 50-meter grid or a 100-meter grid as a historical vehicle location unit, thereby obtaining the historical dispatch record corresponding to each historical vehicle location unit.

[0144] Furthermore, for each historical vehicle location unit's historical order dispatch records, the server can identify the candidate vehicles corresponding to the historical order dispatch records, determine the vehicle dispatch orders that have been completed and those that have not been completed within the target area, and determine data such as the distance between the candidate vehicle and the target area, the arrival time of the vehicle to the target area, and the vehicle's empty status, thereby obtaining the historical vehicle order completion data for each of the different candidate vehicles included in the historical vehicle location unit.

[0145] Step S1009: Generate historical vehicle order data associated with the target area based on the historical vehicle order data of different candidate vehicles included in at least one historical vehicle location unit.

[0146] Specifically, since at least one historical vehicle location unit is set up when dispatching vehicle orders to a target area, it is necessary to determine the historical vehicle order data of different candidate vehicles included in each of the at least one historical vehicle unit. By combining the historical vehicle order data of different candidate vehicles included in each of the at least one historical vehicle location unit, the historical vehicle order data associated with the target area can be obtained.

[0147] Step S1010: Based on historical vehicle order data, determine the historical order dispatch record set corresponding to the target area, and based on the historical order dispatch record set, determine each candidate vehicle in the target area.

[0148] Specifically, the server obtains historical vehicle order data associated with the target area, and determines the historical dispatch record set corresponding to the target area based on the historical vehicle order data. Then, based on the historical dispatch record set, it can further determine each candidate vehicle in the target area, and determine the dispatchable vehicle by screening each candidate vehicle.

[0149] Step S1011: Based on historical vehicle order data and historical dispatch record set, determine the vehicle association parameters corresponding to each candidate vehicle, and filter each candidate vehicle according to the vehicle association parameters and preset vehicle filtering conditions to obtain dispatchable vehicles.

[0150] Specifically, after identifying the candidate vehicles in the target area, the server further determines the vehicle association parameters corresponding to each candidate vehicle based on historical vehicle order data and historical order dispatch records. Specifically, based on the historical vehicle order data and historical order dispatch records of the target area, it can identify vehicle dispatch orders that have been completed and those that have not, including candidate vehicles corresponding to historical order dispatch records that were successfully dispatched and those that were unsuccessfully dispatched, as well as the distance between the candidate vehicle and the target area, the arrival time of the vehicle to the target area, and the vehicle's empty status. This allows for the further determination of the vehicle association parameters corresponding to each candidate vehicle, which specifically include vehicle response rate, arrival time satisfaction, and vehicle utilization rate.

[0151] Furthermore, by acquiring preset vehicle screening conditions set for the target area, including preset vehicle screening conditions set for factors such as the distance between candidate vehicles and the target area, and the passenger status of vehicles (including empty, partially loaded, and fully loaded), and by screening each candidate vehicle according to the preset vehicle screening conditions and the vehicle association parameters of each candidate vehicle, dispatchable vehicles are obtained.

[0152] Step S1012: Obtain the current vehicle association parameters corresponding to each schedulable vehicle, as well as the initial vehicle scheduling coefficient set for the current vehicle association parameters, and optimize the initial vehicle scheduling coefficient according to the current vehicle association parameters and the number of target objects to obtain the optimized vehicle scheduling coefficient.

[0153] Specifically, the server obtains the current vehicle association parameters corresponding to each schedulable vehicle, as well as the initial vehicle scheduling coefficients set for these parameters. The current vehicle association parameters corresponding to the schedulable vehicles specifically include vehicle response rate, arrival time satisfaction rate, and vehicle utilization rate. The initial vehicle scheduling coefficients set for these parameters can specifically include a first initial scheduling coefficient, a second initial scheduling coefficient, and a third initial scheduling coefficient set for the vehicle response rate, arrival time satisfaction rate, and vehicle utilization rate, respectively.

[0154] Furthermore, the server can determine the actual number of vehicles that need to be scheduled based on the number of target objects. Based on the current vehicle-related parameters of the schedulable vehicles, including vehicle response rate, arrival time satisfaction, and vehicle utilization, the initial vehicle scheduling coefficients, including the first initial scheduling coefficient, the second initial scheduling coefficient, and the third initial scheduling coefficient set for vehicle response rate, arrival time satisfaction, and vehicle utilization respectively, are optimized to obtain the optimized first vehicle scheduling coefficient, the second vehicle scheduling coefficient, and the third vehicle scheduling coefficient.

[0155] Step S1013: For each schedulable vehicle, obtain the current vehicle association parameters corresponding to the schedulable vehicle, and calculate the scheduling priority of the schedulable vehicle based on the current vehicle association parameters and the optimized vehicle scheduling coefficient to obtain the vehicle scheduling priority corresponding to the schedulable vehicle.

[0156] Specifically, for each schedulable vehicle, the server obtains the current vehicle association parameters corresponding to the schedulable vehicle, and calculates the scheduling priority of the schedulable vehicle based on the current vehicle association parameters, including vehicle response rate, arrival time satisfaction, vehicle utilization rate, and optimized vehicle scheduling coefficients, including optimized first vehicle scheduling coefficient, second vehicle scheduling coefficient, and third vehicle scheduling coefficient, to obtain the vehicle scheduling priority corresponding to the schedulable vehicle.

[0157] Step S1014: Generate a vehicle scheduling strategy corresponding to the target area based on the number of target objects and vehicle scheduling priority.

[0158] Specifically, the server generates a vehicle scheduling strategy corresponding to the target area based on the number of target objects and vehicle scheduling priority. This strategy generates a processing plan for scheduling each schedulable vehicle in the target area. Based on the vehicle scheduling strategy, the server generates vehicle scheduling prompts for the schedulable vehicles. The server can then send these prompts to the schedulable vehicles, and the vehicle terminals of these vehicles can respond by sending a message back to the server confirming receipt of the scheduling information.

[0159] Step S1015: Based on the vehicle scheduling strategy, generate vehicle scheduling prompt information corresponding to each of the at least one schedulable vehicle.

[0160] Step S1016: For each dispatchable vehicle, the vehicle dispatching prompt information is fed back to the dispatchable vehicle, and the vehicle dispatching acceptance information corresponding to the dispatchable vehicle is obtained.

[0161] Specifically, when the server performs vehicle scheduling processing according to the vehicle scheduling strategy, it can generate vehicle scheduling prompt information corresponding to at least one schedulable vehicle, and feed back each vehicle scheduling prompt information to the schedulable vehicle corresponding to each vehicle scheduling prompt information, and obtain the vehicle scheduling acceptance information fed back by the vehicle terminal of the schedulable vehicle in response to the vehicle scheduling prompt information.

[0162] Step S1017: Based on the vehicle dispatch acceptance information corresponding to each of the at least one dispatchable vehicle, determine the number of vehicles that have been accepted for dispatch corresponding to the target area. When the number of vehicles that have been accepted for dispatch reaches the target number, end the vehicle dispatch process.

[0163] Specifically, the server determines the number of vehicles that have been accepted for dispatch corresponding to the target area based on the vehicle dispatch acceptance information corresponding to each of the at least one dispatchable vehicle, compares the number of vehicles that have been accepted for dispatch with the number of target objects, and ends the vehicle dispatch process when it is determined that the number of vehicles that have been accepted for dispatch has reached the number of target objects.

[0164] Conversely, if it is determined that the number of vehicles already dispatched has not reached the target number, vehicle dispatching prompts will continue to be sent to other dispatchable vehicles that have not yet received vehicle dispatching prompts.

[0165] In the aforementioned vehicle dispatching method, by acquiring the historical device count set of the target area within a historical time period and the device count set within a preset time period, traffic aggregation index values ​​are predicted for the target area based on these historical and device count sets. This yields a traffic aggregation index value corresponding to the target area, allowing for the determination of whether traffic aggregation exists in the target area. This enables the timely identification of areas with traffic aggregation and ride-hailing demand, allowing vehicles to be dispatched to these areas, reducing user waiting time and vehicle vacancy. Furthermore, if traffic aggregation is determined in the target area based on the traffic aggregation index value, the number of target objects in the target area within the preset time period is determined based on the historical and device count sets. Vehicles are then filtered based on historical vehicle order data associated with the target area to determine dispatchable vehicles. Based on the number of target objects and dispatchable vehicles, a vehicle dispatching strategy corresponding to the target area is generated. This strategy is then used for vehicle dispatching, reducing user waiting time, vehicle vacancy, and overall vehicle waiting time, effectively improving the rationality of vehicle dispatching, reducing resource waste, and further enhancing resource utilization.

[0166] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0167] Based on the same inventive concept, this application also provides a vehicle scheduling device for implementing the vehicle scheduling method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle scheduling device embodiments provided below can be found in the limitations of the vehicle scheduling method described above, and will not be repeated here.

[0168] In one exemplary embodiment, such as Figure 11 As shown, a vehicle dispatching device is provided, including: a device quantity set acquisition module 1102, a traffic aggregation index value prediction module 1104, a target object quantity determination module 1106, a dispatchable vehicle determination module 1108, and a vehicle dispatching processing module 1110, wherein:

[0169] The device quantity set acquisition module 1102 is used to acquire the historical device quantity set of the target area within a historical time period and the device quantity set within a preset time period; the traffic aggregation index value prediction module 1104 is used to predict the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set, and obtain the traffic aggregation index value corresponding to the target area; the target object quantity determination module 1106 is used to determine the number of target objects in the target area within a preset time period based on the historical device quantity set and the device quantity set, when it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value; the schedulable vehicle determination module 1108 is used to acquire historical vehicle order data associated with the target area, filter vehicles based on the historical vehicle order data, and determine schedulable vehicles; the vehicle scheduling processing module 1110 is used to generate a vehicle scheduling strategy corresponding to the target area based on the number of target objects and schedulable vehicles, so as to perform vehicle scheduling processing through the vehicle scheduling strategy.

[0170] In the aforementioned vehicle dispatching device, by acquiring the historical device quantity set of the target area within a historical time period and the device quantity set within a preset time period, the device predicts the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set. This yields the traffic aggregation index value corresponding to the target area, allowing for the determination of whether traffic aggregation exists in the target area. This enables the timely identification of areas with traffic aggregation and ride-hailing demand, allowing vehicles to be dispatched to these areas, reducing user waiting time and vehicle vacancy. Furthermore, if traffic aggregation is determined to exist in the target area based on the traffic aggregation index value, the device determines the number of target objects in the target area within the preset time period based on the historical device quantity set and the device quantity set. It then filters vehicles based on historical vehicle order data associated with the target area to determine dispatchable vehicles. Based on the number of target objects and dispatchable vehicles, a vehicle dispatching strategy corresponding to the target area is generated. This strategy is then used for vehicle dispatching, reducing user waiting time, vehicle vacancy, and overall vehicle waiting time, effectively improving the rationality of vehicle dispatching, reducing resource waste, and further enhancing resource utilization.

[0171] In an exemplary embodiment, the traffic aggregation index prediction module is further configured to: determine at least one historical time window based on a historical time period, and determine at least one current time window based on a preset time period; for each current time window, determine a historical time window that matches the current time window from the at least one historical time window; determine the number of historical devices corresponding to the historical time window from the set of historical device counts, and determine the number of current devices corresponding to the current time window from the set of device counts; and predict the traffic aggregation index value based on the at least one historical device count and the at least one current device count to obtain the traffic aggregation index value corresponding to the target area.

[0172] In one exemplary embodiment, a vehicle dispatching device is provided, which further includes a traffic aggregation determination module, configured to: obtain a traffic aggregation index threshold set for a target area; compare the traffic aggregation index value with the traffic aggregation index threshold; and determine that there is traffic aggregation in the target area if the traffic aggregation index value is greater than the traffic aggregation index threshold.

[0173] In an exemplary embodiment, the target object quantity determination module is further configured to: determine the historical traffic sequence characteristics of the target area within a historical time period based on the historical device quantity set; perform feature encoding processing on the device quantity set to obtain the device data volume characteristics corresponding to the target area; determine the time dimension characteristics corresponding to the preset time period, so as to predict the number of objects in the target area based on the time dimension characteristics, historical traffic sequence characteristics and device data volume characteristics, and obtain the number of target objects in the target area within the preset time period.

[0174] In one exemplary embodiment, a vehicle dispatching device is provided, further comprising a historical vehicle order data generation module, configured to: acquire at least one historical vehicle location unit corresponding to a target area; acquire a historical dispatch record corresponding to each historical vehicle location unit; determine historical vehicle order data of different candidate vehicles included in the historical vehicle location unit based on the historical dispatch record; and generate historical vehicle order data associated with the target area based on the historical vehicle order data of the different candidate vehicles included in each of the at least one historical vehicle location unit.

[0175] In an exemplary embodiment, the dispatchable vehicle determination module is further configured to: determine a set of historical dispatch records corresponding to a target area based on historical vehicle order data, and determine each candidate vehicle in the target area based on the historical dispatch record set; determine vehicle association parameters corresponding to each candidate vehicle based on the historical vehicle order data and the historical dispatch record set; and perform vehicle screening on each candidate vehicle based on the vehicle association parameters and preset vehicle screening conditions to obtain dispatchable vehicles.

[0176] In an exemplary embodiment, the vehicle scheduling processing module is further configured to: obtain the current vehicle association parameters corresponding to each schedulable vehicle, and the initial vehicle scheduling coefficient set for the current vehicle association parameters; optimize the initial vehicle scheduling coefficient according to the current vehicle association parameters and the number of target objects to obtain the optimized vehicle scheduling coefficient; determine the vehicle scheduling priority for each schedulable vehicle according to the optimized vehicle scheduling coefficient and the vehicle association parameters, so as to generate a vehicle scheduling strategy corresponding to the target area according to the number of target objects and the vehicle scheduling priority.

[0177] In an exemplary embodiment, the vehicle scheduling processing module is further configured to: for each schedulable vehicle, obtain the current vehicle association parameters corresponding to the schedulable vehicle; calculate the scheduling priority of the schedulable vehicle based on the current vehicle association parameters and the optimized vehicle scheduling coefficient, and obtain the vehicle scheduling priority corresponding to the schedulable vehicle; the scheduling priority is used to determine the priority for vehicle scheduling processing of the schedulable vehicle.

[0178] In an exemplary embodiment, the vehicle dispatching processing module is further configured to: generate vehicle dispatching prompt information corresponding to each of the at least one dispatchable vehicle according to the vehicle dispatching strategy; for each dispatchable vehicle, feed back the vehicle dispatching prompt information to the dispatchable vehicle and obtain the vehicle dispatching acceptance information corresponding to the dispatchable vehicle; determine the number of vehicles that have accepted dispatching corresponding to the target area based on the vehicle dispatching acceptance information corresponding to each of the at least one dispatchable vehicle; and end the vehicle dispatching processing when it is determined that the number of vehicles that have accepted dispatching has reached the target number of objects.

[0179] Each module in the aforementioned vehicle dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0180] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. In this embodiment, the computer device is described as a server, and its internal structure diagram can be as follows. Figure 12As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores historical device counts for a target area within a historical time period, device counts for a target area within a preset time period, traffic aggregation index values ​​for the target area, the number of target objects in the target area within the preset time period, historical vehicle order data, dispatchable vehicles, and vehicle dispatching strategies. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a vehicle dispatching method.

[0181] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0182] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0183] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0184] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0185] 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, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0186] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0187] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this application. The above embodiments only illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle dispatching method, characterized in that, The method includes: Obtain the historical device count set for the target area within a historical time period, and the device count set within a preset time period; Based on the historical device count set and the device count set, the traffic aggregation index value of the target area is predicted to obtain the traffic aggregation index value corresponding to the target area; If it is determined that there is traffic aggregation in the target area based on the traffic aggregation index value, the number of target objects in the target area within a preset time period is determined based on the historical device quantity set and the device quantity set. Obtain historical vehicle order data associated with the target area, and filter vehicles based on the historical vehicle order data to determine dispatchable vehicles; Based on the number of target objects and the number of schedulable vehicles, a vehicle scheduling strategy corresponding to the target area is generated, and vehicle scheduling is performed through the vehicle scheduling strategy.

2. The method according to claim 1, characterized in that, The step of predicting the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set, and obtaining the traffic aggregation index value corresponding to the target area, includes: Based on the historical time period, at least one historical time window is determined, and based on the preset time period, at least one current time window is determined; For each current time window, a historical time window matching the current time window is determined from the at least one historical time window; From the set of historical device counts, determine the number of historical devices corresponding to the historical time window, and from the set of device counts, determine the number of current devices corresponding to the current time window; Based on at least one of the historical device counts and at least one of the current device counts, a traffic aggregation index value is predicted to obtain a traffic aggregation index value corresponding to the target area.

3. The method according to claim 1, characterized in that, The method further includes: Obtain the traffic aggregation index threshold set for the target area, and compare the traffic aggregation index value with the traffic aggregation index threshold; If the traffic aggregation index value is greater than the traffic aggregation index threshold, it is determined that there is traffic aggregation in the target area.

4. The method according to claim 1, characterized in that, The step of determining the number of target objects in the target area within a preset time period based on the historical device count set and the device count set includes: Based on the set of historical device counts, determine the historical traffic sequence characteristics of the target area within the historical time period; The set of device quantities is subjected to feature encoding processing to obtain device data quantity characteristics corresponding to the target area; Determine the time dimension features corresponding to the preset time period, and based on the time dimension features, the historical traffic sequence features, and the device data volume features, predict the number of objects in the target area to obtain the number of target objects in the target area within the preset time period.

5. The method according to any one of claims 1 to 4, characterized in that, The step of filtering vehicles based on the historical vehicle order data to determine dispatchable vehicles includes: Based on the historical vehicle order data, determine the historical order dispatch record set corresponding to the target area, and based on the historical order dispatch record set, determine each candidate vehicle in the target area; Based on the historical vehicle order data and the historical order dispatch record set, determine the vehicle association parameters corresponding to each of the candidate vehicles. Based on the vehicle association parameters and preset vehicle screening conditions, each candidate vehicle is screened to obtain dispatchable vehicles.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Obtain at least one historical vehicle location unit corresponding to the target area, and for each historical vehicle location unit, obtain the historical dispatch record corresponding to the historical vehicle location unit. Based on the historical dispatch records, determine the historical vehicle order data of different candidate vehicles included in the historical vehicle location unit; Based on the historical vehicle order data of different candidate vehicles included in each of the at least one historical vehicle location unit, historical vehicle order data associated with the target area is generated.

7. The method according to any one of claims 1 to 4, characterized in that, The step of generating a vehicle dispatching strategy corresponding to the target area based on the number of target objects and the number of dispatchable vehicles includes: Obtain the current vehicle association parameters corresponding to each of the schedulable vehicles, and the initial vehicle scheduling coefficient set for the current vehicle association parameters; Based on the current vehicle association parameters and the number of target objects, the initial vehicle scheduling coefficient is optimized to obtain the optimized vehicle scheduling coefficient. Based on the optimized vehicle scheduling coefficient and the vehicle association parameters, the vehicle scheduling priority for each of the schedulable vehicles is determined, so as to generate a vehicle scheduling strategy corresponding to the target area based on the number of target objects and the vehicle scheduling priority.

8. The method according to claim 7, characterized in that, The step of determining the vehicle scheduling priority for each of the schedulable vehicles based on the optimized vehicle scheduling coefficient and the vehicle association parameters includes: For each of the schedulable vehicles, obtain the current vehicle association parameters corresponding to the schedulable vehicle; Based on the current vehicle association parameters and the optimized vehicle scheduling coefficient, the scheduling priority of the schedulable vehicles is calculated to obtain the vehicle scheduling priority corresponding to the schedulable vehicles; the scheduling priority is used to determine the priority for vehicle scheduling processing of the schedulable vehicles.

9. The method according to any one of claims 1 to 4, characterized in that, The vehicle dispatching process using the vehicle dispatching strategy includes: Based on the vehicle scheduling strategy, generate vehicle scheduling prompt information for each of at least one schedulable vehicle. For each of the dispatchable vehicles, the vehicle dispatching prompt information is fed back to the dispatchable vehicle, and the vehicle dispatching acceptance information corresponding to the dispatchable vehicle is obtained. Based on the vehicle dispatch acceptance information corresponding to each of the at least one dispatchable vehicle, determine the number of dispatchable vehicles corresponding to the target area; The vehicle dispatching process ends when the number of vehicles that have been dispatched reaches the target number.

10. A vehicle dispatching device, characterized in that, The device includes: The device quantity set acquisition module is used to acquire the historical device quantity set of the target area within a historical time period, as well as the device quantity set within a preset time period; The traffic aggregation index prediction module is used to predict the traffic aggregation index value of the target area based on the historical device quantity set and the device quantity set, and obtain the traffic aggregation index value corresponding to the target area. The target object quantity determination module is used to determine the number of target objects in the target area within a preset time period based on the historical device quantity set and the device quantity set, when it is determined that there is traffic aggregation in the target area according to the traffic aggregation index value. The available vehicle determination module is used to acquire historical vehicle order data associated with the target area, filter vehicles based on the historical vehicle order data, and determine available vehicles. The vehicle scheduling processing module is used to generate a vehicle scheduling strategy corresponding to the target area based on the number of target objects and the number of schedulable vehicles, so as to perform vehicle scheduling processing through the vehicle scheduling strategy.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images