Vehicle scheduling method and device

Abstract

The invention relates to the technical field of online car-hailing, and discloses a vehicle scheduling method and device, and the method comprises the steps: obtaining the scene information of an area; wherein the scene information comprises weather information, traffic information and activity information; determining a prediction result corresponding to the region according to the scene information by using the prediction model; wherein the prediction result indicates whether there is insufficient vehicle supply and demand in the area; determining a scene scheduling result according to the number of the current vehicles in the region when the prediction result indicates that the vehicles are insufficient in supply and demand in the region; wherein the scene scheduling result indicates the number of vehicles needing to be scheduled to the area; and according to the scene scheduling result, scheduling the target vehicle, so that the target vehicle is scheduled to the area.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing, and in particular to a vehicle dispatching method and device. Background Art

[0002] With the acceleration of urbanization, online ride-hailing, as a new sharing economy model, has gradually become one of the important choices for people's daily travel.

[0003] In related technologies, historical order records are set with fixed time periods, and each area is divided into areas with different regional status (hot areas or cold areas) according to the fixed time periods. For hot areas, a certain number of vehicles can be dispatched to these places in advance to wait for orders.

[0004] However, due to the influence of scene factors (such as rain, etc.), some cold areas may change. The method of setting a fixed time period through historical order records cannot accurately determine the regional status of the area, resulting in traffic congestion and other phenomena. Summary of the Invention

[0005] In view of this, the present invention provides a vehicle dispatching method and device.

[0006] In a first aspect, the present invention provides a vehicle scheduling method, the method comprising: obtaining scene information of an area; wherein the scene information comprises: weather information, traffic information and activity information; utilizing a prediction model to determine a prediction result corresponding to the area based on the scene information; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the area; when the prediction result indicates that there is a shortage of vehicle supply and demand in the area, determining a scene scheduling result based on the current number of vehicles in the area; wherein the scene scheduling result indicates the number of vehicles that need to be scheduled to the area; and scheduling a target vehicle based on the scene scheduling result so that the target vehicle is scheduled to the area.

[0007] The vehicle scheduling method provided by the embodiment of the present disclosure comprehensively considers scenario information such as weather information, traffic information, and activity information. In terms of weather, different weather conditions have a significant impact on travel demand. By integrating these multi-dimensional information, the prediction model can more comprehensively understand the various influencing factors in the region, thereby more accurately predicting the supply and demand of vehicles and more accurately indicating whether there is a shortage of vehicle supply and demand in the region. Compared with the method of distinguishing between cold and hot areas only by fixed time periods, it can avoid misjudgments due to incomplete information and provide a reliable basis for subsequent vehicle scheduling.

[0008] In one possible implementation, target vehicles are dispatched according to scenario scheduling results, including: determining whether the number of target vehicles within a preset range corresponding to an area is not less than a target number according to the scenario scheduling results; wherein the target number is the number of target vehicles that need to be dispatched to the area; if the number of target vehicles within the preset range corresponding to the area is not less than the target number, dispatching the target number of target vehicles.

[0009] The vehicle dispatch method provided by the disclosed embodiments first determines whether the number of target vehicles within a preset range of the target area meets the demand (or is not less than the target number) before deciding to dispatch a vehicle. This step is equivalent to verifying the dispatchable resources. In this way, sufficient vehicles can be ensured when the dispatch operation is implemented, avoiding the embarrassing situation of blindly issuing a dispatch instruction and then finding that there are not enough vehicles to dispatch, thereby improving the feasibility and effectiveness of the dispatch operation.

[0010] In one possible implementation, when there are multiple areas, target vehicles are dispatched according to the scenario scheduling results, including: detecting whether there is a common area between the geofence of the first area and the geofence of the second area; if there is a common area between the geofence of the first area and the geofence of the second area and the total number of target vehicles within the geofence of the first area and the geofence of the second area is less than the target supply and demand requirements, determining the priority of the first area and the priority of the second area respectively; wherein the target supply and demand requirements indicate the total number of target vehicles that need to be dispatched in the first area and the number of target vehicles that need to be dispatched in the second area; when the priority of the first area is greater than the priority of the second area, the target vehicles in the common area are dispatched to travel to the first area.

[0011] The vehicle dispatching method provided by the disclosed embodiments can be used to dispatch vehicles arbitrarily without proper planning when there is a simultaneous shortage of vehicle supply and demand in multiple areas. This can lead to the dispersion of vehicle resources and an inability to centrally address the most pressing needs. By detecting common areas between geo-fences and determining regional priorities when the total number of vehicles is less than the target supply and demand, limited vehicle resources can be centrally deployed to higher-priority areas, avoiding inefficient resource dispersion across multiple areas and improving overall dispatching efficiency.

[0012] In one possible implementation, the method further includes: expanding the radius of the geo-fence of the second area to obtain a target geo-fence of the second area; and dispatching the target vehicle to travel to the second area according to the target geo-fence of the second area.

[0013] In the vehicle dispatching method provided by the embodiments of the present disclosure, the original second-area geofence may be relatively small, and the number of target vehicles that can be dispatched within and near it is limited. When the supply and demand of vehicles in the area is insufficient, the radius of the geofence is expanded, and the area covered by the target geofence becomes larger, allowing the search for more dispatchable vehicles that were not originally within the original fence. For example, during peak hours in a commercial center, the demand for vehicles increases significantly, and the number of vehicles within the original fence is insufficient. By expanding the fence radius, dispatchable vehicles within several surrounding blocks or even further can be included in the dispatch range.

[0014] In one possible implementation, the method further includes: obtaining information of a target object corresponding to a vehicle to be dispatched within a preset range corresponding to the area; detecting whether the information of the target object corresponding to the vehicle to be dispatched meets a preset condition; if the information of the target object corresponding to the vehicle to be dispatched meets the preset condition, determining the vehicle to be dispatched of the target object as the target vehicle; wherein the preset condition indicates that the driver's working hours are not greater than a preset time.

[0015] The vehicle dispatch method provided in the disclosed embodiments stipulates that a driver's working hours must not exceed a preset duration, effectively preventing driver fatigue caused by prolonged continuous work. Fatigue driving not only threatens the driver's own life, but also increases the risk of traffic accidents and affects the safety of other road users. By screening drivers who meet the required working hours, ensuring that they have adequate rest time, this demonstrates concern for the driver's personal safety and health.

[0016] In a second aspect, the present invention provides a vehicle scheduling device, which includes: an acquisition module for acquiring scene information of an area; a first determination module for using a prediction model to determine a prediction result corresponding to the area based on the scene information; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the area; a second determination module for determining a scene scheduling result based on the current number of vehicles in the area when the prediction result indicates that there is a shortage of vehicle supply and demand in the area; wherein the scene scheduling result indicates the number of vehicles that need to be scheduled to the area; and a scheduling module for scheduling a target vehicle based on the scene scheduling result so that the target vehicle is scheduled to the area.

[0017] In one possible implementation, the scheduling module includes: a first determination unit, used to determine whether the number of target vehicles within a preset range corresponding to the area is not less than a target number based on the scene scheduling result; wherein the target number is the number of target vehicles that need to be scheduled to the area; and a scheduling unit, used to schedule the target number of target vehicles if the number of target vehicles within the preset range corresponding to the area is not less than the target number.

[0018] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the vehicle dispatching method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the vehicle dispatching method of the first aspect or any corresponding embodiment thereof.

[0020] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the vehicle dispatching method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 is a flow chart of a vehicle dispatching method according to an embodiment of the present invention;

[0023] Figure 2 is a structural block diagram of a vehicle dispatching device according to an embodiment of the present invention;

[0024] Figure 3 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0026] Based on relevant technologies, historical order records are set with fixed time periods, and each area is divided into areas with different regional status (hot areas or cold areas) according to the fixed time periods. For hot areas, a certain number of vehicles can be dispatched to these places in advance to wait for orders.

[0027] However, due to the influence of scene factors (such as rain, etc.), some cold areas may change. The method of setting a fixed time period through historical order records cannot accurately determine the regional status of the area, resulting in traffic congestion and other phenomena.

[0028] Based on this, the vehicle scheduling method provided by the embodiment of the present disclosure comprehensively considers scene information such as weather information, traffic information, and activity information. In terms of weather, different weather conditions have a significant impact on travel demand. By integrating these multi-dimensional information, the prediction model can more comprehensively understand the various influencing factors in the region, thereby more accurately predicting the supply and demand of vehicles and more accurately indicating whether there is a shortage of vehicle supply and demand in the region. Compared with the method of distinguishing between cold and hot areas only by fixed time periods, it can avoid misjudgments due to incomplete information and provide a reliable basis for subsequent vehicle scheduling.

[0029] According to an embodiment of the present invention, an embodiment of a vehicle scheduling method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] In this embodiment, a vehicle dispatching method is provided, which can be used in computer equipment, such as computers, servers, etc. Figure 1 FIG. 1 is a flow chart of a vehicle dispatching method according to an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the process includes the following steps:

[0031] Step S101, obtaining scene information of the area; wherein the scene information includes: weather information, traffic information and activity information.

[0032] The area may be a pre-defined area. The scene information may include weather information, traffic information, and activity information. The weather information may indicate rainfall, strong winds, etc. The computer device may obtain the scene information of the area in real time.

[0033] For example, in a commercial center area of ​​a city, the weather forecast for the next 24 hours is obtained through the meteorological department interface, such as whether there will be rain, snow, strong winds, etc.; the traffic management department's data interface or a third-party traffic data platform is used to obtain the area's road congestion index, average vehicle speed, traffic accident information, etc.; at the same time, information is collected from event organizers, social media platforms, or local life service platforms to determine whether there are any large-scale events in the area in the near future, such as concerts, exhibitions, promotional activities, etc.

[0034] Step S102: using the prediction model, based on the scenario information, determining a prediction result corresponding to the region; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the region.

[0035] The collected scenario information is fed into a pre-trained prediction model, which analyzes and calculates the scenario information and outputs a prediction result on whether there is a shortage of vehicles in the area. The prediction result indicates whether there is a shortage of vehicles in the area.

[0036] The prediction model may be a long short-term memory network model (LSTM) or a convolutional neural network model, and is not specifically limited here.

[0037] In one scenario, the trained prediction model is fed with weather information (e.g., heavy rain), traffic information (e.g., a road congestion index of 8, indicating severe congestion), and event information (e.g., a large concert that evening with an expected attendance of 5,000 people). After computational analysis, the prediction model outputs a "yes" prediction, indicating a risk of vehicle supply and demand shortage in the area.

[0038] In one possible implementation, historical data can be obtained. The historical data may include: GPS data, for example: obtaining real-time location information from mobile devices such as taxis, online ride-hailing vehicles, and logistics vehicles, including latitude and longitude, timestamp, speed, etc. Traffic camera data, for example: accessing the city traffic monitoring system to obtain video analysis results such as real-time road traffic, vehicle speed, occupancy, etc. Social media data, for example: capturing traffic-related social media content (such as Weibo, Twitter) through an API interface to extract geographic location, time, keywords, and other information. Historical order data, for example: collecting past travel order information, including departure place, destination, time, cost, etc. External variables, for example: integrating weather data (temperature, precipitation, wind speed, etc.), holiday information, special event calendars, and other factors that may affect traffic.

[0039] Missing data due to GPS signal loss, camera malfunction, etc. is filled in using interpolation methods (such as linear interpolation and spline interpolation) or predicted values ​​based on historical data. Data points that significantly deviate from the normal range are identified and removed through statistical methods or rules based on domain knowledge.

[0040] Convert GPS data into gridded spatial features and calculate statistics such as flow and density over different time periods. Extract time attributes such as date, day of the week, and hour and encode them (e.g., one-hot encoding). Integrate weather, holiday information, and other spatiotemporal features to form a complete input feature set.

[0041] The LSTM model is used for model training. The input layer defines the dimensions of the input data, including the time step (e.g., data from the past 24 hours) and the number of features (e.g., latitude and longitude, vehicle speed, and traffic volume). The input data is appropriately reshaped to meet the input requirements of the LSTM layer.

[0042] LSTM layers: Select an appropriate number of LSTM layers and neurons per layer, for example, 2-3 LSTM layers with 64-128 neurons per layer. Configure LSTM parameters, such as the activation function (typically tanh or ReLU) and the dropout rate (to prevent overfitting, typically set to 0.2-0.5).

[0043] Fully connected layer: Add a fully connected layer after the LSTM layer to map the LSTM output to the dimension of the prediction target. You can add as many fully connected layers as needed and use appropriate activation functions (such as linear activation function for regression tasks).

[0044] Output layer: For regression tasks, the output layer is usually a neuron that directly outputs the predicted value (such as whether the number of vehicles is less than the target number, etc.).

[0045] Model Training: Loss Function Selection: For regression tasks, commonly used loss functions include mean squared error (MSE) and mean absolute error (MAE). Use an adaptive optimizer such as Adam or RMSprop, setting an appropriate learning rate (e.g., 0.001-0.01). Input the training data into the model in batches, and perform forward propagation to calculate the loss. Update the model parameters through backpropagation, repeating the iterations until the preset number of iterations is reached or the loss function converges. During training, regularly evaluate model performance using the validation set, monitoring changes in the loss value and evaluation metrics.

[0046] Step S103: When the prediction result indicates that there is a shortage of vehicle supply and demand in the area, a scenario scheduling result is determined based on the current number of vehicles in the area; wherein the scenario scheduling result indicates the number of vehicles that need to be scheduled to the area.

[0047] The current number of vehicles refers to the number of online ride-hailing vehicles currently operating or idle in the area. This information can be obtained through the online ride-hailing platform's vehicle positioning system and operational database. The scenario scheduling result indicates the number of vehicles that need to be dispatched to the area based on the current number of vehicles in the area and the predicted supply and demand shortage, which is used to guide subsequent vehicle scheduling operations.

[0048] When the prediction model determines that there is a shortage of vehicle supply and demand in the area, it further obtains the current number of vehicles in the area and combines other relevant factors (such as historical data, regional characteristics, etc.) to calculate the number of vehicles that need to be dispatched to the area, which is the scenario scheduling result.

[0049] In one scenario, the ride-hailing platform's operational data indicates that 50 ride-hailing vehicles are currently in operation in the commercial center area, while 20 are idle, for a total of 70 vehicles. Based on historical data and the characteristics of the area, it is predicted that demand for vehicles will increase by 150 during the concert. Therefore, the scenario scheduling result is to dispatch 80 (150 - 70 = 80) ride-hailing vehicles from other areas to the commercial center area.

[0050] Step S104: dispatching the target vehicle according to the scene dispatching result, so that the target vehicle is dispatched to the area.

[0051] Target vehicles can be online ride-hailing vehicles selected from other areas based on scenario scheduling results and dispatched to areas with insufficient supply and demand. Dispatch instructions can be instructions sent by the ride-hailing platform to target vehicles, including destination information and travel routes, to guide them to the designated area. Target vehicles that meet the criteria are screened from other areas and dispatch instructions are sent to them, guiding them to areas with insufficient supply and demand.

[0052] For example, a dispatch instruction can be sent to the driver of a target vehicle through the online ride-hailing driver app. The driver can view the instruction details on the app and confirm whether to accept the dispatch. A text message notification can also be sent to the driver of the target vehicle to inform them of the dispatch information. The driver can then reply to the text message or call customer service to confirm the dispatch.

[0053] In one scenario, the ride-hailing platform, based on the scenario scheduling results, selected 80 ride-hailing vehicles that met certain criteria (e.g., drivers with sufficient working hours and vehicles in good condition) from an area with relatively abundant and nearby vehicles as target vehicles. It then sent dispatch instructions to these vehicles, instructing them to head to the central business district and providing the optimal route for quick arrival.

[0054] The vehicle scheduling method provided by the embodiment of the present disclosure comprehensively considers scenario information such as weather information, traffic information, and activity information. In terms of weather, different weather conditions have a significant impact on travel demand. By integrating these multi-dimensional information, the prediction model can more comprehensively understand the various influencing factors in the region, thereby more accurately predicting the supply and demand of vehicles and more accurately indicating whether there is a shortage of vehicle supply and demand in the region. Compared with the method of distinguishing between cold and hot areas only by fixed time periods, it can avoid misjudgments due to incomplete information and provide a reliable basis for subsequent vehicle scheduling.

[0055] In one possible implementation, step S104 includes:

[0056] Step S1041, based on the scene scheduling result, determine whether the number of target vehicles within the preset range corresponding to the area is not less than the target number; wherein the target number is the number of target vehicles that need to be scheduled to the area.

[0057] The preset range may indicate a pre-set geographic area within which to filter dispatchable target vehicles. The size and shape of the preset range may be adjusted based on actual conditions, such as traffic flow, road conditions, and vehicle density.

[0058] Based on the scene scheduling result obtained in step S103 (i.e., the number of target vehicles that need to be dispatched to the target area, that is, the target number), the number of target vehicles is counted within a preset range corresponding to the target area (this preset range can be a circular area with a certain radius centered on the target area, or a specific area delineated based on traffic, geography, and other factors), and a determination is made as to whether the number reaches or exceeds the target number.

[0059] In one scenario, the target area is a large commercial center. According to the scene scheduling result of step S103, it is determined that 50 online-hailing vehicles need to be dispatched to the commercial center (that is, the target number is 50 vehicles). The preset range is set to a circular area with a radius of 5 kilometers with the commercial center as the center. Through the vehicle positioning system and operation database of the online-hailing platform, the number of online-hailing vehicles that meet the scheduling conditions (such as the driver's working hours do not exceed 8 hours, the vehicle has sufficient remaining power or fuel, etc.) within the preset range is counted as 60. Then it is determined whether the 60 vehicles are not less than 50 vehicles, and the result is yes.

[0060] Step S1042: If the number of target vehicles within the preset range corresponding to the area is not less than the target number, the target number of target vehicles is dispatched.

[0061] If the target number of vehicles counted within the preset range meets or exceeds the target number, the platform selects an appropriate number of vehicles from these target vehicles and sends dispatch instructions to them, guiding them to the target area. For example, if the target number of vehicles within the preset range (60) is not less than the target number (50), the ride-hailing platform randomly selects 50 of the 60 target vehicles and sends dispatch instructions to the drivers of these vehicles through the driver-side app, instructing them to go to the commercial center and providing the optimal route.

[0062] As an example, when the number of target vehicles within a preset range is sufficient, a target number of vehicles may be selected from these vehicles for dispatch by random selection.

[0063] For example, vehicles that are closer to the target area can be prioritized for dispatching, which can reduce vehicle travel time and costs and improve dispatch efficiency. This can be done by calculating the distance between the vehicle location and the center of the target area, sorting the vehicles from closest to farthest, and then selecting the vehicles closest to the target area.

[0064] As an example, in addition to distance, other factors such as the driver's service score and vehicle comfort can also be considered. For example, different weights can be assigned to indicators such as distance, service score, and vehicle comfort. The combined score of each target vehicle is calculated, and then the vehicles are sorted from high to low based on the combined score to select the target number of vehicles.

[0065] The vehicle dispatch method provided by the disclosed embodiments first determines whether the number of target vehicles within a preset range of the target area meets the demand (or is not less than the target number) before deciding to dispatch a vehicle. This step is equivalent to verifying the dispatchable resources. In this way, sufficient vehicles can be ensured when the dispatch operation is implemented, avoiding the embarrassing situation of blindly issuing a dispatch instruction and then finding that there are not enough vehicles to dispatch, thereby improving the feasibility and effectiveness of the dispatch operation.

[0066] In a possible implementation, when there are multiple regions, step S104 includes:

[0067] Step S1043 , detecting whether there is a common area between the geo-fence of the first area and the geo-fence of the second area.

[0068] The common area indicates the overlapping or adjacent portion of two geofences, representing the intersection or adjoining area of ​​the two areas in geographic space.

[0069] The range of the geo-fence of the first area and the range of the geo-fence of the second area may be the same or different and may be preset.

[0070] During specific implementation, it is checked whether the geographic fences (ie, the geographic range defined by the virtual boundary) of two areas (the first area and the second area) have overlapping or adjacent areas.

[0071] Step S1044: If there is a common area between the geofence of the first area and the geofence of the second area and the total number of target vehicles within the geofence of the first area and the geofence of the second area is less than the target supply and demand requirements, determine the priority of the first area and the priority of the second area respectively; wherein the target supply and demand requirements indicate the total number of target vehicles that need to be dispatched in the first area and the number of target vehicles that need to be dispatched in the second area.

[0072] The target supply and demand requirement indicates the sum of the number of target vehicles that need to be dispatched in the first area and the number of target vehicles that need to be dispatched in the second area. If there is a common area between the two areas and the total number of target vehicles in the two areas is not enough to meet the target supply and demand requirements, the priorities of the two areas are calculated separately.

[0073] As an example, the priority is determined based on the demand gap in each region (i.e., the difference between the target supply and demand requirement and the current number of vehicles), with the larger the demand gap, the higher the priority.

[0074] As an example, considering the importance of a region, important areas such as commercial centers, transportation hubs, etc. can be given higher priorities.

[0075] As an example, a comprehensive scoring model is established to calculate a priority score for each region by considering factors such as demand gap, regional importance, and time sensitivity.

[0076] Step S1045 : When the priority of the first area is greater than the priority of the second area, the target vehicle in the public area is dispatched to travel to the first area.

[0077] If the priority of the first area is higher than that of the second area, a vehicle is dispatched from the target vehicles in the public area to the first area.

[0078] In one application scenario, the first area is a large commercial center, and the second area is a nearby train station. Using geofencing technology, the boundaries of the two areas are defined. Detection revealed that the geofences of the two areas partially overlap near an intersection, indicating the presence of a common area. After detecting the common area, it was discovered that the total number of target vehicles in both areas was 40, while the target supply and demand was 50, resulting in a shortfall. At this point, the priority of the two areas needed to be determined. Analysis revealed that the commercial center had a larger demand gap (30 vehicles required, only 20 vehicles available), while the train station had a smaller demand gap (20 vehicles required, 20 vehicles available). Therefore, the commercial center received a higher priority. Due to its higher priority, a vehicle was dispatched from the target vehicles in the common area to the commercial center. Assuming there are 10 eligible vehicles in the common area, these vehicles will be dispatched to the commercial center to alleviate the vehicle supply and demand shortfall.

[0079] The vehicle dispatching method provided by the disclosed embodiments can be used to dispatch vehicles arbitrarily without proper planning when there is a simultaneous shortage of vehicle supply and demand in multiple areas. This can lead to the dispersion of vehicle resources and an inability to centrally address the most pressing needs. By detecting common areas between geo-fences and determining regional priorities when the total number of vehicles is less than the target supply and demand, limited vehicle resources can be centrally deployed to higher-priority areas, avoiding inefficient resource dispersion across multiple areas and improving overall dispatching efficiency.

[0080] In one possible implementation, the method further includes:

[0081] Step S201 : expanding the radius of the geo-fence of the second area to obtain a target geo-fence of the second area.

[0082] For the geo-fence originally set for the second area, the radius value is increased to expand the geographical range covered by the geo-fence, and finally a new geo-fence with a larger range is obtained, namely the target geo-fence of the second area.

[0083] As an example, the original geo-fence radius is expanded according to a pre-set fixed ratio (such as 1.5 times, 2 times, etc.). For example, if the original radius is 1 kilometer, after expanding by 2 times, the new radius is 2 kilometers.

[0084] As an example, the radius expansion can be dynamically determined based on the gap between vehicle supply and demand in the second area. If the gap is large, the radius is expanded to a larger value; if the gap is small, the radius is expanded to a smaller value. This can be achieved by establishing a functional relationship between the gap and the radius expansion factor.

[0085] As an example, analyze the distribution of vehicles in the area surrounding the second zone. If the density of vehicles in the surrounding area is high, appropriately expand the geofence radius to obtain more dispatchable vehicles. For example, use a heat map to display the distribution of surrounding vehicles and adjust the radius based on the density of the heat map.

[0086] Step S202 : dispatching the target vehicle to travel to the second area according to the target geographic fence of the second area.

[0087] Based on the target geographic fence determined in step S201, target vehicles that meet the scheduling conditions within the target geographic fence are screened out, and scheduling instructions are sent to these vehicles to guide them to the second area (here the second area is defined by the target geographic fence in the scheduling context).

[0088] In one scenario, the second area was originally a circular area with a radius of 1 km, centered on a subway station. Due to insufficient supply and demand for vehicles in this area, in order to increase the number of dispatchable vehicles, it was decided to expand the radius of the geofence. By expanding the radius from 1 km to 2 km, a new circular area is obtained, which is the target geofence for the second area. After obtaining the target geofence, the vehicle positioning system and operation database of the online car-hailing platform are used to screen out target vehicles that are within this target geofence (a circular area with a radius of 2 km) and meet the dispatch conditions (such as the driver's working hours do not exceed 8 hours, and the vehicle has sufficient power or fuel). Assume that 30 qualified vehicles are screened out, and then dispatch instructions are sent to the drivers of these vehicles through the driver-side APP, informing them to go to the second area (that is, the area covered by the target geofence) and provide the optimal driving route.

[0089] In the vehicle dispatching method provided by the embodiments of the present disclosure, the original second-area geofence may be relatively small, and the number of target vehicles that can be dispatched within and near it is limited. When the supply and demand of vehicles in the area is insufficient, the radius of the geofence is expanded, and the area covered by the target geofence becomes larger, allowing the search for more dispatchable vehicles that were not originally within the original fence. For example, during peak hours in a commercial center, the demand for vehicles increases significantly, and the number of vehicles within the original fence is insufficient. By expanding the fence radius, dispatchable vehicles within several surrounding blocks or even further can be included in the dispatch range.

[0090] In one possible implementation, the method further includes:

[0091] Step S301: obtaining information of target objects corresponding to vehicles to be dispatched within a preset range corresponding to an area.

[0092] Within the designated area and its preset range, determine the vehicles to be dispatched and collect relevant information of the target objects (such as drivers) corresponding to these vehicles.

[0093] Step S302 , detecting whether the information of the target object corresponding to the vehicle to be dispatched meets a preset condition; wherein the preset condition indicates that the working time of the driver is not greater than a preset time.

[0094] Check the acquired target object information to determine whether the information meets the pre-set conditions.

[0095] Step S303: If the information of the target object corresponding to the vehicle to be dispatched meets a preset condition, the vehicle to be dispatched of the target object is determined as the target vehicle.

[0096] If the target vehicle's information matches the pre-set conditions, the vehicle driven by the target vehicle will be determined as the final target vehicle for dispatch. In this scenario, the pre-set conditions specifically emphasize that the driver's working hours cannot exceed a pre-set time limit.

[0097] As an example, a flag field is added to the vehicle information table for vehicles that meet the preset conditions, marked as "target vehicle". In the subsequent scheduling process, only the vehicles marked as "target vehicles" are scheduled.

[0098] As an example, vehicle information that meets preset conditions is filtered out to form a target vehicle list, from which the dispatch system selects vehicles for dispatch.

[0099] As an example, when a vehicle is detected that meets the preset conditions, the vehicle information is pushed to the scheduling module in real time, and the scheduling module immediately determines it as a target vehicle and performs subsequent scheduling.

[0100] In one scenario, the target area is the venue of a large-scale event, and the preset range is a circular area with a radius of 5 kilometers centered on the event venue. The ride-hailing platform uses its vehicle positioning system to identify all vehicles to be dispatched within this preset range and collects relevant information about their drivers, such as driver A's work hours of 6 hours and a service rating of 4.8; driver B's work hours of 9 hours and a service rating of 4.5. The platform sets the preset conditions that the driver's work hours must be no more than 8 hours and the service rating must be no less than 4. The driver information collected in step S301 is then tested sequentially. For driver A, the work hours are 6 hours ≤ 8 hours and the service rating is 4.8 points ≥ 4 points, meeting the preset conditions. For driver B, the work hours are 9 hours > 8 hours, which does not meet the preset conditions. Because driver A's information meets the preset conditions, the vehicle to be dispatched driven by driver A is identified as the target vehicle and will be dispatched to the target area (the venue of the large-scale event). Driver B's vehicle is not identified as a target vehicle.

[0101] The vehicle dispatch method provided in the disclosed embodiments stipulates that a driver's working hours must not exceed a preset duration, effectively preventing driver fatigue caused by prolonged continuous work. Fatigue driving not only threatens the driver's own life, but also increases the risk of traffic accidents and affects the safety of other road users. By screening drivers who meet the required working hours, ensuring that they have adequate rest time, this demonstrates concern for the driver's personal safety and health.

[0102] In this embodiment, a vehicle dispatching device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0103] This embodiment provides a vehicle dispatching device, such as Figure 2 As shown, including:

[0104] The device includes: an acquisition module 201, which is used to acquire scene information of an area; a first determination module 202, which is used to use a prediction model to determine a prediction result corresponding to the area according to the scene information; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the area; a second determination module 203, which is used to determine a scene scheduling result according to the number of current vehicles in the area when the prediction result indicates that there is a shortage of vehicle supply and demand in the area; wherein the scene scheduling result indicates the number of vehicles that need to be scheduled to the area; and a scheduling module 204, which is used to schedule a target vehicle according to the scene scheduling result, so that the target vehicle is scheduled to the area.

[0105] In one possible implementation, the scheduling module 204 includes: a first determination unit, used to determine whether the number of target vehicles within a preset range corresponding to the area is not less than a target number based on the scene scheduling result; wherein the target number is the number of target vehicles that need to be scheduled to the area; and a scheduling unit, used to schedule the target number of target vehicles if the number of target vehicles within the preset range corresponding to the area is not less than the target number.

[0106] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0107] The vehicle dispatching device in this embodiment is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0108] The embodiment of the present invention also provides a computer device having the above Figure 2 The vehicle dispatching device is shown.

[0109] See also Figure 3 , Figure 3 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 3As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0110] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0111] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0112] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0113] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0114] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 3 The bus connection is taken as an example.

[0115] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0116] The computer device further includes a communication interface for the computer device to communicate with other devices or a communication network.

[0117] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0118] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0119] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A vehicle dispatching method, characterized in that: The method comprises: Acquire scene information of the area; wherein the scene information includes: weather information, traffic information and activity information; Determining a prediction result corresponding to the area based on the scenario information using a prediction model; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the area; When the prediction result indicates that there is a shortage of vehicle supply and demand in the area, determining a scenario scheduling result based on the current number of vehicles in the area; wherein the scenario scheduling result indicates the number of vehicles that need to be dispatched to the area; According to the scenario scheduling result, the target vehicle is scheduled so that the target vehicle is scheduled to the area.

2. The vehicle dispatching method according to claim 1, characterized in that: The step of dispatching the target vehicle according to the scenario dispatch result includes: Determine, based on the scenario scheduling result, whether the number of target vehicles within a preset range corresponding to the area is not less than a target number; wherein the target number is the number of target vehicles that need to be scheduled to the area; If the number of the target vehicles within the preset range corresponding to the area is not less than the target number, the target number of target vehicles is dispatched.

3. The vehicle dispatching method according to claim 1, characterized in that: When there are multiple areas, dispatching the target vehicle according to the scenario dispatch result includes: detecting whether a common area exists between the geofence of the first area and the geofence of the second area; If a common area exists between the geofence of the first area and the geofence of the second area and the total number of target vehicles within the geofence of the first area and the geofence of the second area is less than a target supply and demand requirement, determining the priority of the first area and the priority of the second area respectively; wherein the target supply and demand requirement indicates the total number of target vehicles that need to be dispatched in the first area and the total number of target vehicles that need to be dispatched in the second area; When the priority of the first area is greater than the priority of the second area, the target vehicle in the public area is dispatched to travel to the first area.

4. The vehicle dispatching method according to claim 3, characterized in that: The method further comprises: Expanding the radius of the geo-fence of the second area to obtain a target geo-fence of the second area; The target vehicle is dispatched to travel to the second area according to the target geo-fence of the second area.

5. The vehicle dispatching method according to claim 1, characterized in that: The method further comprises: Obtain information about the target object corresponding to the vehicle to be dispatched within a preset range corresponding to the area; Check whether the information of the target object corresponding to the vehicle to be dispatched meets the preset conditions; If the information of the target object corresponding to the vehicle to be dispatched meets a preset condition, the vehicle to be dispatched of the target object is determined as the target vehicle; wherein the preset condition indicates that the working hours of the driver are not greater than a preset time.

6. A vehicle dispatching device, characterized in that: The device comprises: An acquisition module is used to acquire scene information of a region; the scene information includes weather information, traffic information, and activity information; A first determination module is configured to determine a prediction result corresponding to the area based on the scenario information using a prediction model; wherein the prediction result indicates whether there is a shortage of vehicle supply and demand in the area; A second determination module is configured to determine a scenario scheduling result based on the current number of vehicles in the area when the prediction result indicates that there is a shortage of vehicle supply and demand in the area; wherein the scenario scheduling result indicates the number of vehicles that need to be dispatched to the area; The scheduling module is used to schedule the target vehicle according to the scenario scheduling result, so that the target vehicle is scheduled to the area.

7. The vehicle dispatching device according to claim 6, characterized in that: The scheduling module includes: A first determining unit is configured to determine, based on the scenario scheduling result, whether the number of target vehicles within a preset range corresponding to the area is not less than a target number; wherein the target number is the number of target vehicles that need to be scheduled to the area; The scheduling unit is configured to schedule the target number of target vehicles if the number of the target vehicles within the preset range corresponding to the area is not less than the target number.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the vehicle dispatching method according to any one of claims 1 to 5 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the vehicle dispatching method according to any one of claims 1 to 5.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the vehicle dispatching method according to any one of claims 1 to 5.

Images