Method and device for predicting transport capacity of online car-hailing

Abstract

The invention discloses an online car-hailing transport capacity prediction method and device, and relates to the technical field of intelligent traffic data processing. According to the main technical scheme, processed data is calculated according to historical operation data obtained by monitoring a target territorial range on an online car-hailing platform, and by means of the data, an online car-hailing travel turnover acquisition logic and an online car-hailing total effective mileage acquisition logic are constructed; determining an online car-hailing transport capacity interval value under demand time balance by taking uniform distribution of passenger demands reflected in a preset time range as a constraint condition; in combination with different concentration degrees of passenger demands reflected in a preset time range as a constraint condition, the number of corresponding participated operation scheduling in a driver is reflected as a constraint condition, and finally an online car-hailing reasonable transport capacity interval value comprehensively considering the demands of two factors of aggregation time and operation is obtained. And the reasonable demand of a certain target territorial range on the transport capacity of the online car-hailing is represented.

Description

Technical Field

[0001] The present application relates to the field of intelligent traffic data processing technology, and in particular to a method and device for predicting the capacity of online ride-hailing vehicles. Background Art

[0002] Online ride-hailing capacity refers to the total amount of vehicle resources dispatched and deployed by the online ride-hailing platform to meet the travel needs of passengers. It not only includes the number of registered vehicles, but also covers key factors such as the number of active vehicles, the number of drivers and their distribution.

[0003] With the increasing popularity of online ride-hailing services in daily life, the market in many cities across the country is nearing saturation. Whether to restrict new ride-hailing companies is a matter of careful consideration for governments. For example, if the number of online ride-hailing companies is too low, they will not be able to fully meet the transportation needs of citizens; conversely, if the number is too high, it may exacerbate traffic congestion while wasting vehicle resources.

[0004] Therefore, in terms of the total amount of vehicle resources that can be deployed, by utilizing the current operational data on the online car-hailing platform, if it is possible to predict the reasonable demand for online car-hailing capacity in a certain geographical area, and obtain such forecast data, and if it is provided to the government, it will provide high-quality reference analysis for the government to formulate relevant policies (such as suspending new online car-hailing registrations, adjusting the entry threshold for online car-hailing, etc.), thereby more reasonably controlling the reasonable deployment of online car-hailing in the target geographical area. Therefore, how to design a method for predicting online car-hailing capacity is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present application provides a method and device for predicting the capacity of online ride-hailing vehicles. The main purpose is to utilize the analyzed and processed data of the current operating data on the online ride-hailing platform (such as the average effective number of passengers, mileage utilization rate interval value, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, and average travel distance corresponding to a single trip), comprehensively consider the two factors of aggregation time and operation to construct a technical logic for automated prediction, thereby obtaining an efficient and automated method for predicting the capacity of online ride-hailing vehicles, and then obtain a more reasonable online ride-hailing capacity interval value that comprehensively considers the above two factors, thereby representing the reasonable demand for online ride-hailing capacity in a certain target geographical area.

[0006] In order to achieve the above objectives, this application mainly provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for predicting the capacity of online ride-hailing vehicles, which is applied to an online ride-hailing platform. The method comprises:

[0008] Determine the target geographical scope corresponding to the predicted online ride-hailing capacity to be executed;

[0009] Obtaining the future annual online ride-hailing travel volume, where the future annual online ride-hailing travel volume is determined based on a pre-planned future annual travel volume and a preset future annual online ride-hailing travel ratio, where the future annual travel volume and the future annual online ride-hailing travel ratio are set for the target geographical area;

[0010] Based on the historical operational data obtained from monitoring the target geographical area on the online ride-hailing platform, the average effective passenger capacity, mileage utilization interval, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, and average travel distance corresponding to a single trip corresponding to the target geographical area are calculated;

[0011] Determine the online ride-hailing trip turnover based on the online ride-hailing trip volume in the future year and the average travel distance corresponding to a single trip;

[0012] Determine the total effective mileage of the online ride-hailing vehicle based on the online ride-hailing vehicle travel turnover volume and the average effective number of passengers carried;

[0013] Determine a first online car-hailing capacity interval value based on the total effective mileage of the online car-hailing vehicle and the mileage utilization interval value, the average operating time of the full-time driver, and the average vehicle speed, with the constraint of reflecting the uniform distribution of passenger demand within a preset time range. The first online car-hailing capacity is the online car-hailing capacity interval value under demand time equilibrium;

[0014] Determine a second online ride-hailing capacity interval based on the first online ride-hailing capacity interval and the concentration time coefficient, with the constraint of reflecting the different concentration levels of passenger demand within a preset time range. The second online ride-hailing capacity is an online ride-hailing capacity interval that takes time concentration into account.

[0015] Based on the second online car-hailing capacity interval value and the non-operation coefficient, the third online car-hailing capacity interval value is determined with the number of drivers participating in operation scheduling as a constraint condition.

[0016] A second aspect of the present application provides a device for predicting online car-hailing capacity, which is applied to an online car-hailing platform. The device includes:

[0017] A labeling unit, used to determine the target geographical range corresponding to the predicted online ride-hailing capacity to be executed;

[0018] A first acquisition unit is configured to acquire a future annual online ride-hailing travel volume, where the future annual online ride-hailing travel volume is determined based on a pre-planned future annual travel volume and a preset future annual online ride-hailing travel ratio, where the future annual travel volume and the future annual online ride-hailing travel ratio are set for the target geographical area;

[0019] The second acquisition unit is configured to calculate, based on historical operation data obtained from monitoring the target geographical area on the online ride-hailing platform, the average number of effective passengers, the mileage utilization interval value, the average operating time of full-time drivers, the average vehicle speed, the concentration time coefficient, the non-operation coefficient, and the average travel distance corresponding to a single trip within the target geographical area;

[0020] A first determining unit is configured to determine the online ride-hailing trip turnover volume based on the online ride-hailing trip volume in the future year and the average travel distance corresponding to a single trip;

[0021] A second determining unit is configured to determine the total effective mileage of the online-hailing vehicle based on the online-hailing vehicle travel turnover volume and the average effective number of passengers;

[0022] a third determining unit, configured to determine a first online-hailing vehicle capacity interval value based on the total effective mileage of the online-hailing vehicle and the mileage utilization interval value, the average operating time of the full-time driver, and the average vehicle speed, with the constraint of reflecting a uniform distribution of passenger demand within a preset time range, wherein the first online-hailing vehicle capacity is the online-hailing vehicle capacity interval value under time-balanced demand;

[0023] a fourth determining unit, configured to determine a second online ride-hailing capacity interval value based on the first online ride-hailing capacity interval value and the clustering time coefficient, with the constraint of reflecting different concentration levels of passenger demand within a preset time range, wherein the second online ride-hailing capacity is an online ride-hailing capacity interval value that takes time clustering into account;

[0024] The fifth determination unit is used to determine the third online car-hailing capacity interval value based on the second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers participating in operation scheduling as a constraint condition.

[0025] A third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for predicting the online car-hailing capacity as described above is implemented.

[0026] A fourth aspect of the present application provides an electronic device, the device comprising at least one processor, and at least one memory and a bus connected to the processor;

[0027] The processor and the memory communicate with each other via the bus.

[0028] The processor is used to call the program instructions in the memory to execute the above-mentioned method for predicting the online car-hailing capacity.

[0029] By means of the above technical solution, the technical solution provided by this application has at least the following advantages:

[0030] The present application provides a method and device for predicting the capacity of an online car-hailing service. The present application calculates processed data (such as the average effective number of passengers, mileage utilization rate interval value, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, and average travel distance corresponding to a single trip) based on historical operating data obtained from monitoring the target geographical area on the online car-hailing platform; using these processed data, the present application constructs the logic for obtaining the online car-hailing service turnover volume and the logic for obtaining the total effective mileage of the online car-hailing service, and then combines the uniform distribution of passenger demand reflected in a preset time range as a constraint condition to determine the online car-hailing service capacity interval value under demand time equilibrium; combining the different concentration levels of passenger demand reflected in the preset time range as a constraint condition and the number of drivers participating in operation scheduling as a constraint condition, finally obtains a reasonable online car-hailing service capacity interval value that comprehensively considers the needs of the two factors of aggregation time and operation.

[0031] Compared with the existing need to more reasonably meet the demand for the number of online ride-hailing vehicles, this application designs a technical logic for an efficient and automated method of predicting online ride-hailing capacity by comprehensively considering the two factors of aggregation time and operation, thereby obtaining a more reasonable online ride-hailing capacity interval value that comprehensively considers the above two factors, representing the reasonable demand for online ride-hailing capacity in a certain target geographical area.

[0032] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0034] Figure 1 A flow chart of a method for predicting online car-hailing capacity provided in an embodiment of the present application;

[0035] Figure 2 A flow chart of another method for predicting online ride-hailing capacity provided in an embodiment of the present application;

[0036] Figure 3 A block diagram of a device for predicting the capacity of online ride-hailing vehicles provided in an embodiment of the present application;

[0037] Figure 4A block diagram of another device for predicting the capacity of an online ride-hailing vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0039] As a product of the deep integration of internet technology and transportation services, online ride-hailing platforms provide passengers with efficient and safe online ride-hailing travel services through the collaborative operation of multiple modules. The core functional modules of online ride-hailing platforms include: user-side functions, driver-side functions, back-end operations functions, technical support modules, etc. The following is an illustrative explanation of these core functional modules and their operational effects, including but not limited to the following:

[0040] (1) User-side functions;

[0041] Login, registration and third-party login: support login via mobile phone number, email address and social account to ensure the accuracy and security of user information.

[0042] Positioning and mapping services: Integrate with AutoNavi and Baidu Maps to achieve precise positioning and navigation, and support real-time updates of vehicle and passenger locations.

[0043] Ride-hailing and order management: Provides instant ride-hailing, scheduled ride-hailing, carpooling, designated driver and other services, and supports order status tracking and history query.

[0044] Payment and evaluation system: supports mainstream payment methods such as WeChat and Alipay. After the trip, you can rate and provide feedback on the driver's service.

[0045] Safety Center: Includes functions such as itinerary sharing, emergency contacts, and one-click alarm to ensure passenger safety.

[0046] (2) Driver-side functions;

[0047] Registration and certification: You need to submit your ID card, driver's license and other documents, and the platform will only accept orders after review and approval.

[0048] Order taking and navigation: Automatically match nearby orders and provide real-time navigation services.

[0049] Income and Settlement: Statistics of daily income and support withdrawal to bound accounts.

[0050] Feedback: Drivers can make suggestions on platform rules, service experience, etc.

[0051] (3) Back-end operation functions;

[0052] Order management: monitor order status in real time and handle abnormal orders.

[0053] Driver management: review driver qualifications, monitor service ratings, and handle complaints and violations.

[0054] Data analysis: Analyze user behavior and order distribution through big data to optimize order dispatch strategies.

[0055] Safety monitoring: Real-time audio recording and video monitoring of the journey to ensure the safety of drivers and passengers.

[0056] (4) Technical support module;

[0057] Real-time communication: Use WebSocket or long polling technology to achieve instant communication between passengers and drivers.

[0058] Intelligent dispatching algorithm: Dynamically matches drivers and passengers based on location, time, vehicle type and other conditions.

[0059] Dynamic pricing model: adjusts prices based on time, distance, supply and demand to ensure fairness and rationality.

[0060] Based on the core functional modules listed above, the online car-hailing platform can analyze and process the collected raw data, such as analyzing and processing the online car-hailing orders submitted by each passenger within a certain geographical range and time range, and obtain information such as: the average effective number of passengers, mileage utilization interval value, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, average travel distance corresponding to a single trip, etc. The embodiments of this application do not limit the processing process of obtaining these data.

[0061] However, the inventors have discovered through research that the data analyzed and processed on the online car-hailing platform is equivalent to the current operating data of the online car-hailing within a certain geographical range and a certain time range, which can also be called historical operating data. The embodiments of this application can use historical operating data to predict the online car-hailing capacity in the future. For example, these processed data can be used to construct the logic for obtaining the online car-hailing travel turnover and the logic for obtaining the total effective mileage of the online car-hailing, so as to more efficiently obtain more complex and high-quality data information, so as to be used to build an automated technical logic for predicting the online car-hailing capacity based on the two factors of aggregation time and operation, thereby comprehensively considering the above two factors and obtaining a more reasonable online car-hailing capacity interval value. In addition, using this technical logic for automated prediction of online car-hailing capacity, a function for predicting online car-hailing capacity can also be added to the online car-hailing platform.

[0062] Based on the above considerations, the present application embodiment provides a method for predicting the capacity of online car-hailing services. Figure 1 As shown, the embodiment of the present invention provides the following specific steps:

[0063] 101. Determine the target geographical scope corresponding to the predicted online ride-hailing capacity to be executed.

[0064] In the embodiment of the present application, the city's administrative divisions, population size, and number of motor vehicles are comprehensively considered to select the target geographical area where the online car-hailing capacity forecast needs to be implemented.

[0065] 102. Obtain the future annual online ride-hailing travel volume. The future annual online ride-hailing travel volume is determined based on the pre-planned future annual travel volume and the preset future annual online ride-hailing travel ratio. The future annual travel volume and the future annual online ride-hailing travel ratio are set for the target geographical area.

[0066] The country will formulate overall planning requirements for transportation in different cities. According to the relevant data information involved in this overall planning requirement, relevant calculations can be used to obtain the future annual online car-hailing travel volume and the future annual online car-hailing travel ratio. This embodiment of the application does not specifically limit the acquisition process of these two data sources. Instead, these two data sources are used as the data basis for the subsequent construction of the automated technical logic for predicting online car-hailing capacity in this embodiment of the application. Below, this embodiment of the application mainly provides an illustrative explanation of the concepts and measurement units of the future annual travel volume, the future annual online car-hailing travel ratio, and the future annual online car-hailing travel volume.

[0067] The future annual travel volume is the total number of times people use public transportation within a certain timeframe within the first geographical area, with the core indicator (i.e., unit of measurement) being "person-times." The future annual online ride-hailing travel ratio is the proportion of online ride-hailing travel in the future annual travel volume, expressed as a percentage.

[0068] The number of online ride-hailing trips in future years = the proportion of online ride-hailing trips in future years * the total number of trips in future years; the number of online ride-hailing trips in future years is the total number of trips completed by passengers through the online ride-hailing platform (including the split of carpooling passengers), and the unit is "person-times"; it is different from the number of online ride-hailing orders. For example: if a passenger completes 3 trips (orders) using an online ride-hailing service on the same day, it will be counted as 3 person-times (trip volume).

[0069] 103. Based on the historical operational data obtained from monitoring the target geographical area on the online ride-hailing platform, calculate the average effective passenger capacity, mileage utilization interval value, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, and average travel distance corresponding to a single trip corresponding to the target geographical area.

[0070] By using the core functional modules (1)-(4) listed above, the online car-hailing platform can analyze and process the collected raw data, such as analyzing and processing the online car-hailing orders submitted by each passenger within a certain geographical range and time range, and obtain the following information: the average effective number of passengers, the mileage utilization interval value, the average operating time of full-time drivers, the average vehicle speed, the aggregation time coefficient, the non-operation coefficient, the average travel distance corresponding to a single trip, etc. The embodiment of this application does not limit the processing process of obtaining these data.

[0071] It should be noted that in 103, the embodiment of the present application does not explain these analyzed and processed data one by one, but in order to facilitate the understanding of these data information, they are explained one by one in combination with examples in the subsequent 104-108.

[0072] 104. Determine the turnover of online ride-hailing trips based on the number of online ride-hailing trips in future years and the average travel distance corresponding to a single trip.

[0073] Average travel distance for a single trip: The average mileage of a single trip, reflecting the travel range, in kilometers.

[0074] Online ride-hailing trip turnover = future annual online ride-hailing trip volume * average trip distance. The calculation steps include the following:

[0075] Step 1: Determine the future annual ride-hailing volume (e.g., 2 million trips / day in 2030);

[0076] Step 2: Estimate the average travel distance (e.g., 9 kilometers in 2030);

[0077] Step 3: Substitute into the formula to calculate: 2 million passengers / day × 9 kilometers = 18 million person-kilometers.

[0078] The unit of online ride-hailing travel turnover is "person-kilometers", which directly reflects the total passenger transportation volume carried by the online ride-hailing industry. For example, the online ride-hailing turnover in a certain city in 2024 was 18 million person-kilometers, which means that the total travel distance of passengers throughout the day reached 18 million kilometers.

[0079] 105. Determine the total effective mileage of online ride-hailing vehicles based on their travel turnover and average effective passenger capacity.

[0080] Among them, the average effective passenger capacity is the average number of passengers actually carried in a single trip (including carpooling passengers). For example, if 50% of the orders are carpooling (2 people per order) and 50% are solo rides (1 person per order), the average passenger capacity is 1.5 people.

[0081] Average effective passenger capacity = total number of passengers carried by online ride-hailing vehicles / total number of passenger trips; the unit of average effective passenger capacity is "person / time". The functions of average effective passenger capacity include but are not limited to the following:

[0082] (1) Quantify operational efficiency;

[0083] Reflects vehicle utilization: the higher the average passenger capacity, the more efficient the resource utilization, and the fewer vehicles are needed to meet transportation needs.

[0084] (2) Evaluate the effectiveness of carpooling;

[0085] Measuring ridesharing penetration: An increase in ridesharing orders directly increases the average number of passengers carried.

[0086] Formula correlation: proportion of carpooling orders × average number of carpooling passengers (e.g. 2 people) + proportion of solo orders × average number of solo passengers (1 person).

[0087] (3) Support cost and pricing strategies;

[0088] Cost sharing: The higher the average passenger count, the lower the cost per passenger. Dynamic pricing: When the average passenger count decreases during peak hours, prices can be raised to balance supply and demand.

[0089] The total effective mileage of online ride-hailing vehicles = online ride-hailing vehicle turnover / average number of effective passengers. The total effective mileage of online ride-hailing vehicles is expressed in kilometers, representing the total distance (in kilometers) traveled by the vehicle while carrying passengers. It reflects the vehicle's operating efficiency while carrying passengers, excluding idle mileage. The calculation steps include the following:

[0090] Step 1: Determine the online ride-hailing travel turnover (e.g., 18 million person-kilometers in a city in 2024);

[0091] Step 2: Estimate the average effective passenger capacity (e.g. 1.2 people);

[0092] Step 3: Substitute into the formula to calculate: 18 million person-kilometers ÷ 1.2 person-kilometers = 21.6 million kilometers.

[0093] 106. Based on the total effective mileage and mileage utilization interval values ​​of online ride-hailing vehicles, the average operating time and average speed of full-time drivers, and with the uniform distribution of passenger demand within the preset time range as a constraint condition, the first online ride-hailing capacity interval value is determined. The first online ride-hailing capacity is the online ride-hailing capacity interval value under the demand time equilibrium.

[0094] It should be noted that in order to distinguish the different online car-hailing capacities determined by 105-107, the embodiment of the present application uses the words "first", "second" and "third" for identification. These three words only serve as identification and there is no other sorting ambiguity.

[0095] Total effective mileage of online ride-hailing vehicles: The total distance (in kilometers) that a vehicle actually travels while carrying passengers. Example: If the total effective mileage of online ride-hailing vehicles in a city is 18 million passenger kilometers, this reflects the operating efficiency of the vehicles when carrying passengers.

[0096] Mileage utilization rate: The ratio of actual passenger mileage to total mileage. Example: If the mileage utilization rate is 70%, then 70 out of every 100 kilometers are passenger mileage.

[0097] Average operating time for full-time drivers: The number of hours a driver spends accepting rides daily. For example, if the average operating time is 8 hours, it reflects the driver's effective daily working time. Furthermore, a full-time driver is generally defined as one who spends 4 hours or more online per day operating ride-hailing services.

[0098] Average speed: The average speed of vehicles during operation (km / h). Example: If the average speed is 30 km / h, it reflects road congestion and operational efficiency.

[0099] The online car-hailing capacity under demand time equilibrium = total effective mileage of online car-hailing vehicles / (mileage utilization rate * average operating time of full-time drivers * average vehicle speed); the unit of online car-hailing capacity is "vehicle".

[0100] The online ride-hailing capacity under time-balanced demand refers to the minimum capacity (number of drivers) required by the online ride-hailing platform if passenger demand is evenly distributed throughout the day or within a certain period of time. For example, if there are no peaks / valleys, demand is stable, and drivers can evenly cover all orders, this is a relatively ideal online ride-hailing operation model.

[0101] It should be noted that in the embodiment of the present application, since the mileage utilization rate used is an interval value, the first online car-hailing capacity obtained is also an interval value.

[0102] 107. Based on the first online car-hailing capacity interval value and the aggregation time coefficient, the second online car-hailing capacity interval value is determined with the constraint condition reflecting the different concentration levels of passenger demand within the preset time range. The second online car-hailing capacity is the online car-hailing capacity interval value that takes time aggregation into consideration.

[0103] For example, if we assume that there are no peaks / valleys, demand is stable, and drivers can evenly cover all orders, this is a relatively idealized online car-hailing operation model. However, in the actual operation of online car-hailing, for example, there may be a large number of online car-hailing orders during peak hours in the morning and evening, etc., which makes the demand for online car-hailing unevenly distributed throughout the day. Therefore, in the embodiment of the present application, based on the first online car-hailing capacity also being an interval value, the constraint condition is adopted to reflect the different concentration levels of passenger demand in the preset time range, so as to obtain an online car-hailing capacity that is more in line with the actual operation situation, that is, to obtain a second online car-hailing capacity interval value, which is an online car-hailing capacity interval value that takes time aggregation into consideration.

[0104] The clustering time coefficient reflects the temporal concentration of ride-hailing demand (e.g., morning and evening peaks). For example, the clustering time coefficient = peak demand / average demand. For example, if peak demand is three times the average, the coefficient is 3. Therefore, after accounting for temporal clustering, the actual required capacity must be multiplied by the clustering time coefficient (e.g., a coefficient of 3), reflecting the need for the platform to reserve more drivers during peak hours to cope with concentrated demand.

[0105] The online car-hailing capacity considering time clustering = the online car-hailing capacity under demand time equilibrium / the clustering time coefficient; the unit of the online car-hailing capacity considering time clustering is "vehicle".

[0106] Exemplarily, it is applicable to obtaining the annual online car-hailing capacity. The embodiment of the present application provides a method for collecting the aggregation time coefficient, which may include, but is not limited to: selecting the distribution of online car-hailing orders for 12 consecutive months, randomly selecting one day each month, and calculating the aggregation time coefficients respectively, denoted as a1, a2...a12. Then calculate the total online car-hailing orders for each of the 12 months, denoted as OR1, OR2...OR12, and calculate the weights, respectively, W1=OR1 / MAX(OR1, OR2...OR12), and so on. The aggregation time coefficient a=a1*W1+a2*W2+...+a12*W12.

[0107] 108. Based on the second online car-hailing capacity range value and the non-operation coefficient, the third online car-hailing capacity range value is determined with the corresponding number of drivers participating in operation scheduling as the constraint condition.

[0108] In the actual operation of online ride-hailing services, it is also necessary to consider the situation where some vehicles are unable to depart due to factors such as driver rest and vehicle maintenance, such as the non-operation coefficient. Therefore, based on the second online ride-hailing capacity interval value, the embodiment of the present application adopts a constraint condition that reflects the number of drivers participating in operation scheduling to further obtain an online ride-hailing capacity that is more in line with actual operation conditions, that is, to obtain a third online ride-hailing capacity interval value.

[0109] The third online car-hailing capacity interval value = the second online car-hailing capacity interval value / (1-non-operation coefficient), and the unit of the third online car-hailing capacity interval value is "vehicle".

[0110] As described above, the embodiment of the present application provides a method for predicting the capacity of online ride-hailing vehicles. Compared with the existing need to more reasonably meet the demand for the number of online ride-hailing vehicles, the present application designs an efficient and automated method for predicting the capacity of online ride-hailing vehicles by comprehensively considering the two factors of aggregation time and operation, thereby obtaining a more reasonable range of online ride-hailing capacity values ​​that comprehensively considers the above two factors, providing high-quality reference data for the government to formulate relevant policies.

[0111] In some modified embodiments, such as 107, in addition to considering the time concentration aspect, the embodiment of the present application also provides further optimization, such as considering not only the time factor but also the space factor, which is referred to as considering the time-space heterogeneity. Time-space heterogeneity includes two aspects: time heterogeneity and space heterogeneity. Time heterogeneity refers to the fact that there is a high demand for online car-hailing during the day and less demand at night; space heterogeneity refers to the fact that some popular areas require more vehicles (such as business districts) and some areas have less demand. Therefore, after obtaining the online car-hailing capacity under demand equilibrium, the unevenness of demand should be considered and the capacity should be increased. Based on such requirements, the embodiment of the present application also provides the following specific implementation steps for obtaining the time-space heterogeneity coefficient, including the following:

[0112] A1. Perform a grid division operation on the target area to obtain multiple grid areas.

[0113] In the embodiment of the present application, according to different accuracy requirements, the target area is divided into multiple grid areas. It should be noted that the spatial differences between different grid areas are as small as possible.

[0114] A2. Select feature areas from multiple grid areas.

[0115] The embodiments of the present application may, but are not limited to, obtain the order transaction volume in each grid area based on the length of one day, such as taking the order starting point in the grid area as the transaction order belonging to the grid area, and then sorting the completed orders from large to small. From this sorting, multiple feature areas are selected from multiple grid areas at a certain interval, so that the order transaction situation in each feature area is different. As representative grid areas, the embodiments of the present application do not specifically limit the number of selected feature areas.

[0116] A3. Obtain the completed orders corresponding to each feature area. The starting point of the completed orders occurs in the feature area.

[0117] A4. For the characteristic area, divide a day into N unit time periods. Calculate the price per kilometer corresponding to the completed orders in each unit time period, and obtain N prices per kilometer, where N is a positive integer.

[0118] For example, if a day is divided into four-hour units starting at midnight, that means a day is divided into six units. Then, calculating the price per kilometer for orders completed during each unit would yield N prices per kilometer. This price per kilometer is actually the average of all orders completed during a unit. Specifically, during the calculation process, different vehicle models can be classified and weighted to adjust the bias of the final result.

[0119] A5. Calculate a first mean of the prices based on the N prices per kilometer corresponding to each characteristic area.

[0120] If the unit duration is N, then step A4 will result in N prices per kilometer. The average of the N prices per kilometer is calculated and marked as the first average a.

[0121] A6. Based on the first mean, obtain price data that is higher than the first mean from the N prices per kilometer corresponding to each characteristic area.

[0122] A7. Calculate the second mean corresponding to the price based on the price data.

[0123] Then find the value higher than the first mean a from these N prices per kilometer, calculate the mean, and mark it as the second mean b.

[0124] A8. Use the ratio of the second mean to the first mean to obtain the spatiotemporal nonuniformity coefficient corresponding to the target area. For example, the spatiotemporal nonuniformity coefficient calculation formula is: =b / a.

[0125] Combined with the spatiotemporal nonuniformity coefficients obtained from A1-A8 above, and using the first online car-hailing capacity interval value obtained from 106 (i.e., the online car-hailing capacity interval under time-balanced demand), the following logic is executed:

[0126] The online car-hailing capacity that takes into account spatiotemporal unevenness = the online car-hailing capacity under time equilibrium of demand / the spatiotemporal unevenness coefficient; the unit of the online car-hailing capacity that takes into account time concentration is "vehicle"; in order to distinguish and refer to it, this online car-hailing capacity that takes into account spatiotemporal unevenness is marked as the fourth online car-hailing capacity interval value.

[0127] In some modified embodiments, the fourth online car-hailing capacity interval value can be used instead of the second online car-hailing capacity interval value to perform 108 calculation to obtain the third online car-hailing capacity interval value, thereby obtaining a prediction result of the online car-hailing capacity that takes into account the two factors of temporal and spatial heterogeneity and the investment in operation.

[0128] Alternatively, in some modified embodiments, the second online car-hailing capacity interval value can be adjusted by comprehensively considering the temporal and spatial unevenness, such as averaging the two interval values, or increasing the weight to obtain an adjusted interval value that tends to consider time clustering or temporal and spatial unevenness. This adjusted interval value is applied to the third online car-hailing capacity interval value calculated in 108 above, which will reflect the three factors of considering time clustering, temporal and spatial unevenness, and putting into operation, thereby providing a more reasonable prediction result for the online car-hailing capacity demand.

[0129] In order to improve the accuracy of the spatiotemporal inhomogeneity coefficient, the present embodiment also provides a method for periodically calibrating parameters, specifically including the following:

[0130] Use order data to calculate the temporal and spatial non-uniformity coefficient: Calculate the transaction volume of all grids once every hour for 24 hours a day, and the average of the orders above the average / the average of the orders

[0131] If the difference between the temporal and spatial nonuniformity coefficients obtained in A1-A8 above and the temporal and spatial nonuniformity coefficients calculated using order data is within a certain threshold, they can continue to be used. If the difference is greater than a certain threshold, the temporal and spatial nonuniformity coefficients calculated using order data are used as the basic parameter, and the trend of change is calculated using price data to obtain new parameters, as follows:

[0132] On day X, the spatiotemporal unevenness coefficient calculated using order data is c, and the spatiotemporal unevenness coefficient calculated using price data is d. On day X+Y, the spatiotemporal unevenness coefficient calculated using price data is e. The spatiotemporal unevenness coefficient of day X+Y is c*((ed) / d).

[0133] In some modified embodiments, in order to explain in more detail, the embodiment of the present application also provides another method for predicting the capacity of online car-hailing, such as Figure 2 As shown, in addition to comprehensively considering the two factors of gathering time and operation, the two factors of average daily income of drivers and working hours are also taken into account to obtain a more reasonable online ride-hailing deployment volume that better meets the actual operation needs of online ride-hailing. To this end, the embodiment of the present invention provides the following specific steps:

[0134] 201. Based on the third range value of online car-hailing capacity, the average daily income of online car-hailing drivers reaching the preset threshold is used as a constraint condition to obtain the first target online car-hailing capacity.

[0135] In the embodiment of the present application, the preset threshold is a boundary value set to meet the daily economic needs of the driver. Specifically, using the average daily income of the online ride-hailing driver reaching the preset threshold as a constraint condition, the detailed steps include the following:

[0136] B1. Determine the first boundary value and the second boundary value of the third online car-hailing capacity interval value, and the second boundary value is greater than the first boundary value.

[0137] B2. Determine the average daily number of completed orders per driver based on the future annual online ride-hailing trip volume, the average effective number of passengers, and the second boundary value of the third-party online ride-hailing capacity.

[0138] In the embodiment of the present application, the second boundary value is used as the basic capacity of the online car-hailing service, and the following is adopted:

[0139] The average daily number of orders completed by a driver per vehicle = (future year online ride-hailing trip volume / average effective number of passengers) / online ride-hailing basic capacity; by dividing the total travel demand (trip volume / number of passengers) with the supply capacity (online ride-hailing basic capacity), the average daily order volume per vehicle is calculated, reflecting the efficiency of supply and demand matching. For example, the following steps are used:

[0140] Assume that in a certain city: the number of online car-hailing trips in the future will be 2 million times; the average effective number of passengers will be 1.4 people; the basic capacity of online car-hailing will be 100,000 vehicles; then the average daily number of orders completed per vehicle will be (2 million times / 1.4) / 100,000 ≈ 14.3 orders / day.

[0141] B3. Determine the average daily turnover of online ride-hailing drivers based on the average daily number of orders completed per driver and the average price per order. For example, the average daily turnover of online ride-hailing drivers = the average daily number of orders completed per driver * the average price per order.

[0142] B4. Determine the average daily income of online ride-hailing drivers based on their average daily turnover and the proportion of income to turnover. For example, the average daily income of a driver = the average daily turnover of the online ride-hailing driver * the proportion of income to turnover. For example, the proportion of income to turnover is , taking into account necessary costs such as platform commission, car rental fees, insurance, and fuel.

[0143] B5. Determine whether the average daily income of online ride-hailing drivers is greater than the preset threshold.

[0144] B61. If the average daily income of an online car-hailing driver is greater than the preset threshold, the second boundary value will be determined as the reasonable capacity of the first online car-hailing driver.

[0145] In the embodiment of the present application, for the first boundary value and the second boundary value of the third online car-hailing capacity interval value, as involved in the calculation process of B2-B4, it can be seen that the larger the value of the online car-hailing basic capacity in B2, the smaller the average daily income of the online car-hailing driver obtained in A4. Therefore, under the premise that the third online car-hailing capacity interval value is a constraint condition, when the second boundary value is selected from it, the minimum value of the average daily income of the online car-hailing driver will be obtained. If the minimum value is greater than the preset threshold, the second boundary value can be directly selected as a reasonable capacity for an online car-hailing. It represents the minimum number of online car-hailing vehicles required to be deployed under the premise of comprehensively considering the average daily income of the drivers and the resource cost of deploying online car-hailing vehicles.

[0146] B62. If the average daily income of the online car-hailing driver is not greater than the preset threshold, a new capacity value is obtained from the third online car-hailing capacity interval value to be used for re-determining the average daily income of the online car-hailing driver and comparing it with the preset threshold. The iterative operation is performed until it is determined that the new average daily income of the online car-hailing driver is greater than the preset threshold, and the iterative operation is stopped; the target capacity value corresponding to the new average daily income of the online car-hailing driver is determined as the reasonable capacity of the first online car-hailing vehicle.

[0147] Continuing with the explanation of B61, if the second boundary value of the third online car-hailing capacity interval is used as the basic capacity of the online car-hailing, and the average daily income of the driver is no more than the preset threshold, the basic capacity of the online car-hailing can be adjusted to recalculate the average daily income of the driver and then re-compare it with the preset threshold.

[0148] It should be noted that the basic capacity for online car-hailing is selected from the third online car-hailing capacity interval value. It can be adjusted by reducing several fixed steps based on the second boundary value with a fixed step size, but is not limited to. If a new online car-hailing basic capacity is obtained after reducing the fixed step size once, if the average daily income of the driver calculated by the new online car-hailing basic capacity is still not greater than the preset threshold, the basic capacity for online car-hailing can be updated by reducing the fixed step size for the second time. This iterative operation is used until a new online car-hailing basic capacity is obtained to apply it to the calculation of the driver's average daily income, so that the latest average daily income of the driver is greater than the preset threshold.

[0149] In addition, in order to reduce the number of iterative operations, the embodiment of the present application is preferably that, when the average daily income of the driver is calculated to be no greater than the preset threshold value in one calculation, before entering the subsequent iterative operation, the embodiment of the present application uses the first boundary value of the third online car-hailing capacity interval value to calculate the average daily income of the driver. As shown in the calculation process involved in B2-B4, the larger the value of the online car-hailing basic capacity in B2, the smaller the average daily income of the online car-hailing driver obtained in B4. Therefore, when the first boundary value is selected as the online car-hailing basic capacity, the maximum average daily income of the driver will be obtained. The embodiment of the present application compares this average daily income of the driver with the preset threshold value. If it is not greater than, it indicates that the third online car-hailing capacity interval value should be adjusted. Therefore, it can be, but is not limited to, in 105 above, by adjusting the mileage interest rate interval value to obtain the third online car-hailing capacity interval value again, thereby re-investing in the process of calculating the average daily income of the driver.

[0150] 202. On the basis of the first target online car-hailing capacity, the working hours of full-time drivers and part-time drivers are used as constraints to optimize the first target online car-hailing capacity to obtain the second target online car-hailing capacity.

[0151] C1. Obtain the average operating time and proportion of part-time drivers from the historical operating data of the online ride-hailing platform.

[0152] In the embodiments of the present application, generally speaking, a full-time driver is defined as a ride-hailing driver whose online time for ride-hailing operations is greater than or equal to 4 hours per day, and a part-time driver is defined as a ride-hailing driver whose online time for ride-hailing operations is less than 4 hours per day.

[0153] In addition, based on the data processing capabilities of the online ride-hailing platform, the embodiments of this application do not specifically limit the steps for obtaining the average operating time and proportion of part-time drivers.

[0154] C2. On the basis of the reasonable capacity of the first online car-hailing service, according to the average operating time of full-time drivers, the average operating time of part-time drivers, and the proportion of part-time drivers, the reasonable capacity of the first online car-hailing service is optimized to obtain the reasonable capacity of the second online car-hailing service by utilizing the drivers' working hours as constraints.

[0155] Taking into account the differences in working hours between full-time drivers and part-time drivers, the embodiment of the present application adopts the following method:

[0156] The reasonable capacity of the second online car-hailing service = (the reasonable capacity of the first online car-hailing service * the average operating time of full-time drivers) / (the proportion of part-time drivers * the average operating time of part-time drivers + (1-the proportion of part-time drivers) * the average operating time of full-time drivers); by constructing and utilizing the working hours of drivers as constraints, the reasonable capacity of the first online car-hailing service is optimized to obtain the reasonable capacity of the second online car-hailing service.

[0157] In some modified embodiments, the embodiments of the present application also adopt the following 203-207 to measure the contribution of the driver's average daily income factor and the driver's working hours factor in determining the reasonable transportation capacity of the online car-hailing service.

[0158] 203. Determine a first boundary value and a second boundary value of the third online car-hailing capacity interval value, where the second boundary value is greater than the first boundary value.

[0159] 204. Determine a first ratio between the first target online car-hailing capacity and the second boundary value.

[0160] To simplify the comparison process, the embodiment of the present application assumes that the second boundary value of the third online car-hailing capacity interval value obtained by 107 is the basic capacity of the online car-hailing. On the basis of the basic capacity of the online car-hailing, the contribution of the driver's average daily income constraint (i.e., the driver's average daily income factor) to the prediction of the reasonable capacity of the online car-hailing is measured, such as determining the first ratio between the first target online car-hailing capacity and the second boundary value.

[0161] 205. Determine the difference between the second target online car-hailing capacity and the first online car-hailing capacity.

[0162] On the basis of the basic transport capacity of the online ride-hailing service, the contribution amount brought to the number of online ride-hailing services deployed by those that meet the constraints of driver working hours (i.e. driver working hours factor) is obtained.

[0163] 206. Based on the difference between the second target online car-hailing capacity and the first online car-hailing capacity, determine a second ratio between the difference and the second boundary value.

[0164] Furthermore, based on 204-205, and based on the basic capacity of online ride-hailing vehicles as determined by 204, the contribution of the driver's working hours constraint (i.e., the driver's working hours factor) to the prediction of the reasonable capacity of online ride-hailing vehicles is measured, such as determining the second proportion between the difference and the second boundary value.

[0165] 207. By comparing the first proportion and the second proportion, we can measure the impact of the average daily income and average daily operating time of drivers on predicting the reasonable capacity of online ride-hailing services.

[0166] The embodiment of the present application converts the respective contributions of these two factors (i.e., the driver's average daily income factor and the driver's working hours factor) to the basic transportation capacity of online ride-hailing into a comparison between percentages through 203-206 above. That is, the data in units of "10,000 vehicles" obtained based on different factors is simplified into a comparison between percentages, thereby simplifying the comparison process and clearly showing the difference in the contribution of the two factors.

[0167] Furthermore, as a response to the above Figure 1 、 Figure 2The embodiment of the present application provides a device for predicting the capacity of a car-hailing network. This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will no longer describe the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. This device is used to predict a more reasonable capacity of a car-hailing network, specifically as follows Figure 3 As shown, the device includes:

[0168] The marking unit 31 is used to determine the target area corresponding to the predicted online car-hailing capacity to be executed

[0169] A first acquisition unit 32 is configured to acquire a future annual online ride-hailing trip volume, where the future annual online ride-hailing trip volume is determined based on a pre-planned future annual trip volume and a preset future annual online ride-hailing trip ratio, where the future annual trip volume and the future annual online ride-hailing trip ratio are set for the target geographical area.

[0170] The second acquisition unit 33 is configured to calculate, based on historical operation data obtained from monitoring the target geographical area on the online ride-hailing platform, the average number of effective passengers, the mileage utilization interval, the average operating time of full-time drivers, the average vehicle speed, the concentration time coefficient, the non-operation coefficient, and the average travel distance corresponding to a single trip within the target geographical area;

[0171] A first determining unit 34 is configured to determine the online ride-hailing trip turnover volume based on the online ride-hailing trip volume in the future year and the average travel distance corresponding to a single trip;

[0172] A second determining unit 35 is configured to determine the total effective mileage of the online-hailing vehicle based on the online-hailing vehicle travel turnover volume and the average effective number of passengers carried;

[0173] A third determining unit 36 ​​is configured to determine a first online-hailing vehicle capacity interval value based on the total effective mileage of the online-hailing vehicle and the mileage utilization interval value, the average operating time of the full-time driver, and the average vehicle speed, with the constraint of reflecting a uniform distribution of passenger demand within a preset time range, wherein the first online-hailing vehicle capacity is the online-hailing vehicle capacity interval value under time-balanced demand;

[0174] a fourth determining unit 37 configured to determine a second online ride-hailing capacity interval value based on the first online ride-hailing capacity interval value and the clustering time coefficient, with the constraint of reflecting different concentration levels of passenger demand within a preset time range, wherein the second online ride-hailing capacity is an online ride-hailing capacity interval value that takes time clustering into account;

[0175] The fifth determination unit 38 is used to determine the third online car-hailing capacity interval value based on the second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers participating in the operation scheduling as a constraint condition.

[0176] Further, such as Figure 4 As shown, the device also includes:

[0177] A third acquisition unit 39 is configured to obtain a first target online car-hailing capacity based on the third online car-hailing capacity interval value and using the average daily income of online car-hailing drivers reaching a preset threshold as a constraint condition;

[0178] The fourth acquisition unit 310 is used to optimize the first target online car-hailing capacity based on the first target online car-hailing capacity by using the working hours of full-time drivers and part-time drivers as constraints to obtain the second target online car-hailing capacity.

[0179] Further, such as Figure 4 As shown, the third obtaining unit 39 includes:

[0180] A first determining module 391 is configured to determine a first boundary value and a second boundary value of the third online car-hailing capacity interval value, wherein the second boundary value is greater than the first boundary value;

[0181] A second determining module 392 is configured to determine an average daily number of completed orders per driver based on the future annual online ride-hailing travel volume, the average effective number of passengers, and the second boundary value of the third online ride-hailing capacity;

[0182] The third determination module 393 is used to determine the average daily turnover of the online ride-hailing driver based on the average daily number of orders completed by the driver and the average price per order;

[0183] The fourth determining module 394 is configured to determine the average daily income of the online ride-hailing driver based on the average daily turnover and the proportion of income to turnover;

[0184] A judgment module 395 is used to determine whether the average daily income of the online car-hailing driver is greater than a preset threshold;

[0185] A fifth determining module 396 is configured to determine the second boundary value as the reasonable transport capacity of the first online ride-hailing vehicle if the average daily income of the online ride-hailing vehicle driver is greater than a preset threshold;

[0186] The first execution module 397 is used to re-obtain a capacity value from the third online car-hailing capacity interval value if the average daily income of the online car-hailing driver is not greater than the preset threshold value, so as to be used for re-determining the average daily income of the online car-hailing driver and the comparison operation with the preset threshold value, and through iterative operation, until it is determined that the new average daily income of the online car-hailing driver is greater than the preset threshold value, then the iterative operation is stopped; the target capacity value corresponding to the new average daily income of the online car-hailing driver is determined as the reasonable capacity of the first online car-hailing vehicle.

[0187] Further, such as Figure 4 As shown, the fourth acquiring unit 310 includes:

[0188] An acquisition module 3101 is used to obtain the average operating time and proportion of part-time drivers from the historical operating data of the online ride-hailing platform;

[0189] The second execution module 3102 is used to optimize the reasonable capacity of the first online car-hailing vehicle based on the reasonable capacity of the first online car-hailing vehicle and according to the average operating time of the full-time drivers, the average operating time of the part-time drivers, and the proportion of part-time drivers, so as to construct a constraint condition using the driver's working hours to obtain the reasonable capacity of the second online car-hailing vehicle.

[0190] Further, such as Figure 4 As shown, the device further includes: an analysis unit 311, specifically configured to:

[0191] Determine a first boundary value and a second boundary value of the third online car-hailing capacity interval value, wherein the second boundary value is greater than the first boundary value;

[0192] Determine a first ratio between the first target online ride-hailing capacity and the second boundary value;

[0193] Determining a difference between the second target online ride-hailing capacity and the first online ride-hailing capacity;

[0194] Determining a second ratio between the difference and the second boundary value;

[0195] By comparing the first proportion and the second proportion, the impact of the driver's average daily income and the driver's average daily operating time on the prediction of online car-hailing capacity is measured.

[0196] Further, such as Figure 4 As shown, the device further includes: a sixth determining unit 312; the sixth determining unit 312 is specifically configured to, before determining the third online car-hailing capacity interval value:

[0197] Performing a grid division operation on the target area to obtain a plurality of grid areas;

[0198] Selecting a feature region from multiple grid regions;

[0199] Obtaining a completed order corresponding to each of the characteristic areas, where the order starting point of the completed order occurs in the characteristic area;

[0200] For the characteristic area, a day is divided into N unit time periods, and the price per kilometer corresponding to the completed order occurring in each unit time period is calculated to obtain N prices per kilometer, where N is a positive integer;

[0201] Calculating a first mean value corresponding to the price based on the N prices per kilometer corresponding to each of the characteristic areas;

[0202] According to the first mean value, obtaining price data higher than the first mean value from the N prices per kilometer corresponding to each of the characteristic areas;

[0203] Calculate a second mean value corresponding to the price based on the price data;

[0204] Obtaining a spatiotemporal non-uniformity coefficient corresponding to the target area using a ratio between the second mean and the first mean;

[0205] Based on the first online car-hailing capacity interval value and the temporal and spatial unevenness coefficient, a fourth online car-hailing capacity interval value is determined, and the fourth online car-hailing capacity interval value is an online car-hailing capacity interval value that takes temporal and spatial unevenness into consideration.

[0206] Further, such as Figure 4 As shown, before determining the third online car-hailing capacity interval value, the fourth determining unit 37 is further specifically used to:

[0207] Adjusting the second online car-hailing capacity interval value using the fourth online car-hailing capacity interval value;

[0208] The determining of the third online car-hailing capacity interval value based on the second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers correspondingly participating in operation scheduling as a constraint condition, includes: using the adjusted second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers correspondingly participating in operation scheduling as a constraint condition, to determine the third online car-hailing capacity interval value; or,

[0209] The third online car-hailing capacity interval value is determined based on the fourth online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers participating in operation scheduling as a constraint condition.

[0210] In summary, the online car-hailing capacity prediction device provided in the embodiment of the present application includes a processor and a memory. The above-mentioned labeling unit, first acquisition unit, second acquisition unit, first determination unit, second determination unit, third determination unit, fourth determination unit and fifth determination unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0211] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be configured, and by adjusting kernel parameters, a more reasonable method for predicting online ride-hailing capacity can be provided.

[0212] In summary, the embodiment of the present application provides a method and device for predicting the capacity of online car-hailing. The embodiment of the present application calculates processed data based on the historical operating data obtained from monitoring the target geographical range on the online car-hailing platform, such as: the average effective number of passengers, the mileage utilization rate interval value, the average operating time of full-time drivers, the average vehicle speed, the aggregation time coefficient, the non-operation coefficient, the average travel distance corresponding to a single trip, the average price per order, the proportion of income to turnover, the average operating time of full-time drivers, the average operating time of part-time drivers, and the proportion of part-time drivers; using these processed data, the present application constructs the logic for obtaining the turnover of online car-hailing and the logic for obtaining the total effective mileage of online car-hailing. Combined with the uniform distribution of passenger demand in the preset time range as a constraint, the capacity interval value of the online car-hailing service under the demand time equilibrium is determined; combined with the different concentration levels of passenger demand in the preset time range as a constraint, and the number of drivers participating in the operation and scheduling as a constraint, a reasonable capacity interval value of the online car-hailing service that comprehensively considers the three factors of aggregation time, spatiotemporal heterogeneity, and operation is finally obtained; and further adding some constraints, such as the constraint condition that meets the driver's average daily income demand and the constraint condition that meets the driver's working hours, on the reasonable capacity interval value of the online car-hailing service obtained above, a more reasonable and specific online car-hailing service capacity is further obtained. Therefore, the embodiment of the present application comprehensively considers the five factors of aggregation time, spatiotemporal heterogeneity, operation, driver's average daily income, and driver's working hours, and constructs an automated technical logic for predicting online car-hailing service capacity, so as to efficiently obtain a more reasonable online car-hailing service capacity that comprehensively considers the above five factors, and more accurately and comprehensively characterizes the reasonable demand for online car-hailing service capacity in a certain target area.

[0213] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for predicting the online car-hailing capacity as described above is implemented.

[0214] An embodiment of the present application provides an electronic device, which includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the online car-hailing capacity prediction method as described above.

[0215] The present application also provides a computer program product which, when executed on a data processing device, is suitable for executing the program steps of the method for initializing the prediction of online ride-hailing capacity.

[0216] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0217] In a typical configuration, the device includes one or more processors (CPUs), memory, and a bus. The device may also include input / output interfaces, network interfaces, and the like.

[0218] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip. Memory is an example of a computer-readable medium.

[0219] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0220] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0221] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0222] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for predicting the capacity of online ride-hailing vehicles, characterized in that: Applied to an online ride-hailing platform, the method includes: Determine the target geographical scope corresponding to the predicted online ride-hailing capacity to be executed; Obtaining the future annual online ride-hailing travel volume, where the future annual online ride-hailing travel volume is determined based on a pre-planned future annual travel volume and a preset future annual online ride-hailing travel ratio, where the future annual travel volume and the future annual online ride-hailing travel ratio are set for the target geographical area; Based on the historical operational data obtained from monitoring the target geographical area on the online ride-hailing platform, the average effective passenger capacity, mileage utilization interval, average operating time of full-time drivers, average vehicle speed, aggregation time coefficient, non-operation coefficient, and average travel distance corresponding to a single trip corresponding to the target geographical area are calculated; Determine the online ride-hailing trip turnover based on the online ride-hailing trip volume in the future year and the average travel distance corresponding to a single trip; Determine the total effective mileage of the online ride-hailing vehicle based on the online ride-hailing vehicle travel turnover volume and the average effective number of passengers carried; Determine a first online car-hailing capacity interval value based on the total effective mileage of the online car-hailing vehicle and the mileage utilization interval value, the average operating time of the full-time driver, and the average vehicle speed, with the constraint of reflecting the uniform distribution of passenger demand within a preset time range. The first online car-hailing capacity is the online car-hailing capacity interval value under demand time equilibrium; Determine a second online ride-hailing capacity interval based on the first online ride-hailing capacity interval and the concentration time coefficient, with the constraint of reflecting the different concentration levels of passenger demand within a preset time range. The second online ride-hailing capacity is an online ride-hailing capacity interval that takes time concentration into account. Based on the second online car-hailing capacity interval value and the non-operation coefficient, the third online car-hailing capacity interval value is determined with the number of drivers participating in operation scheduling as a constraint condition.

2. The method according to claim 1, characterized in that The method further comprises: Based on the third online car-hailing capacity interval value, the first target online car-hailing capacity is obtained by using the average daily income of online car-hailing drivers reaching a preset threshold as a constraint condition; On the basis of the first target online ride-hailing capacity, the working hours of full-time drivers and part-time drivers are used as constraints to optimize the first target online ride-hailing capacity to obtain the second target online ride-hailing capacity.

3. The method according to claim 2, characterized in that The first target online car-hailing capacity is obtained based on the third online car-hailing capacity interval value and using the average daily income of online car-hailing drivers reaching a preset threshold as a constraint condition, including: Determine a first boundary value and a second boundary value of the third online car-hailing capacity interval value, wherein the second boundary value is greater than the first boundary value; Determine the average daily number of completed orders per driver based on the future annual online ride-hailing travel volume, the average effective number of passengers, and the second boundary value of the third online ride-hailing capacity; Determine the average daily turnover of online ride-hailing drivers based on the average number of orders completed per day and the average price per order; Determine the average daily income of online ride-hailing drivers based on their average daily turnover and the proportion of their income to turnover; Determining whether the average daily income of the online ride-hailing driver is greater than a preset threshold; If so, the second boundary value is determined as the reasonable capacity of the first online car-hailing service; If not, a new capacity value is obtained from the third online car-hailing capacity interval value for re-determining the average daily income of the online car-hailing driver and comparing it with the preset threshold. Through iterative operation, until it is determined that the new average daily income of the online car-hailing driver is greater than the preset threshold, the iterative operation is stopped; the target capacity value corresponding to the new average daily income of the online car-hailing driver is determined as the reasonable capacity of the first online car-hailing vehicle.

4. The method according to claim 2, characterized in that Based on the first target online ride-hailing capacity, the working hours of full-time and part-time drivers are used as constraints to optimize the first target online ride-hailing capacity to obtain a second target online ride-hailing capacity, including: From the historical operating data of the online ride-hailing platform, we can obtain the average operating time and proportion of part-time drivers; On the basis of the reasonable capacity of the first online car-hailing vehicle, according to the average operating time of the full-time drivers, the average operating time of the part-time drivers, and the proportion of part-time drivers, the reasonable capacity of the first online car-hailing vehicle is optimized to obtain the reasonable capacity of the second online car-hailing vehicle by utilizing the driver's working hours as a constraint condition.

5. The method according to any one of claims 2 to 4, characterized in that The method further comprises: Determine a first boundary value and a second boundary value of the third online car-hailing capacity interval value, wherein the second boundary value is greater than the first boundary value; Determine a first ratio between the first target online ride-hailing capacity and the second boundary value; Determining a difference between the second target online ride-hailing capacity and the first online ride-hailing capacity; Determining a second ratio between the difference and the second boundary value; By comparing the first proportion and the second proportion, the impact of the driver's average daily income and the driver's average daily operating time on the prediction of online car-hailing capacity is measured.

6. The method according to claim 1, characterized in that After obtaining the first online car-hailing capacity interval value, the method further includes: Performing a grid division operation on the target area to obtain a plurality of grid areas; Selecting a feature region from multiple grid regions; Obtaining a completed order corresponding to each of the characteristic areas, where the order starting point of the completed order occurs in the characteristic area; For the characteristic area, a day is divided into N unit time periods, and the price per kilometer corresponding to the completed order occurring in each unit time period is calculated to obtain N prices per kilometer, where N is a positive integer; Calculating a first mean value corresponding to the price based on the N prices per kilometer corresponding to each of the characteristic areas; According to the first mean value, obtaining price data higher than the first mean value from the N prices per kilometer corresponding to each of the characteristic areas; Calculate a second mean value corresponding to the price based on the price data; Obtaining a spatiotemporal non-uniformity coefficient corresponding to the target area using a ratio between the second mean and the first mean; Based on the first online car-hailing capacity interval value and the temporal and spatial unevenness coefficient, a fourth online car-hailing capacity interval value is determined, and the fourth online car-hailing capacity interval value is an online car-hailing capacity interval value that takes temporal and spatial unevenness into consideration.

7. The method according to claim 6, characterized in that Before determining the third online car-hailing capacity interval value, the method further includes: Adjusting the second online car-hailing capacity interval value using the fourth online car-hailing capacity interval value; The determining of the third online car-hailing capacity interval value based on the second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers correspondingly participating in operation scheduling as a constraint condition, includes: using the adjusted second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers correspondingly participating in operation scheduling as a constraint condition, to determine the third online car-hailing capacity interval value; or, The third online car-hailing capacity interval value is determined based on the fourth online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers participating in operation scheduling as a constraint condition.

8. A device for predicting the capacity of online car-hailing services, characterized in that: Applied to online car-hailing platforms, the device includes: A labeling unit, used to determine the target geographical range corresponding to the predicted online ride-hailing capacity to be executed; A first acquisition unit is configured to acquire a future annual online ride-hailing travel volume, where the future annual online ride-hailing travel volume is determined based on a pre-planned future annual travel volume and a preset future annual online ride-hailing travel ratio, where the future annual travel volume and the future annual online ride-hailing travel ratio are set for the target geographical area; The second acquisition unit is configured to calculate, based on historical operation data obtained from monitoring the target geographical area on the online ride-hailing platform, the average number of effective passengers, the mileage utilization interval value, the average operating time of full-time drivers, the average vehicle speed, the concentration time coefficient, the non-operation coefficient, and the average travel distance corresponding to a single trip within the target geographical area; A first determining unit is configured to determine the online ride-hailing trip turnover volume based on the online ride-hailing trip volume in the future year and the average travel distance corresponding to a single trip; A second determining unit is configured to determine the total effective mileage of the online-hailing vehicle based on the online-hailing vehicle travel turnover volume and the average effective number of passengers; a third determining unit, configured to determine a first online-hailing vehicle capacity interval value based on the total effective mileage of the online-hailing vehicle and the mileage utilization interval value, the average operating time of the full-time driver, and the average vehicle speed, with the constraint of reflecting a uniform distribution of passenger demand within a preset time range, wherein the first online-hailing vehicle capacity is the online-hailing vehicle capacity interval value under time-balanced demand; a fourth determining unit, configured to determine a second online ride-hailing capacity interval value based on the first online ride-hailing capacity interval value and the clustering time coefficient, with the constraint of reflecting different concentration levels of passenger demand within a preset time range, wherein the second online ride-hailing capacity is an online ride-hailing capacity interval value that takes time clustering into account; The fifth determination unit is used to determine the third online car-hailing capacity interval value based on the second online car-hailing capacity interval value and the non-operation coefficient, with the number of drivers participating in operation scheduling as a constraint condition.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for predicting the online car-hailing capacity as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: The device includes at least one processor, and at least one memory and a bus connected to the processor; The processor and the memory communicate with each other via the bus. The processor is used to call the program instructions in the memory to execute the online car-hailing capacity prediction method as described in any one of claims 1-7.

Images