Supply and demand judgment method and device for online car-hailing aggregation platform and electronic equipment

Abstract

The invention provides a supply and demand judgment method and device for an online car-hailing aggregation platform and electronic equipment. The method comprises the following steps of: respectively acquiring vehicle use demand data and driver receivable order data from a flow platform and a transport capacity platform, then sampling the corresponding data according to a sampling interval, carrying out statistical aggregation on the vehicle use demand data according to the platforms and vehicle types, and carrying out statistical aggregation on the driver receivable order data according to an order listening mode and the vehicle types; and then, carrying out refined calculation on the aggregated data to obtain refined unit quantity and refined transportation capacity, and finally, carrying out supply and demand matching, so that a supply and demand scene label can be determined based on historical data. Through the arrangement, supply and demand conditions under the factors of wide vehicle use demand sources, different platforms, wide vehicle types, different order listening modes of drivers, various order listening vehicle types and the like in an online car-hailing aggregation platform mode can be depicted finely, and corresponding accurate supply and demand conditions and grade division can be given according to vehicle type categories; therefore, the platform can formulate a proper operation strategy.

Description

Technical Field

[0001] The present application relates to a method, device and electronic equipment for determining supply and demand of an online car-hailing aggregation platform, and belongs to the field of data analysis technology. Background Art

[0002] With the development of mobile Internet and the popularity of smart phones, online car-hailing services are becoming more and more popular in urban travel. Users can easily call a car and navigate through mobile apps, and this convenience has changed people's travel habits and experience needs.

[0003] In the aggregation platform model, the needs of travel users are transmitted to the capacity platform through the traffic platform, and the traffic platform will select the most suitable driver from the candidate drivers to serve the passengers. On the capacity platform side, the user needs received come from multiple traffic platforms, which will be used to characterize the needs; and the capacity platform will also characterize the supply situation based on the location and status reported by the driver. Since different operating strategies are required under different supply and demand conditions, a scientific and reasonable supply and demand judgment method is crucial.

[0004] However, under the current aggregation model, it is very difficult to judge supply and demand due to factors such as the wide range of sources of user demand for vehicles, different platforms, a wide range of vehicle models, different modes of drivers accepting orders, and a variety of vehicle models accepting orders, making it difficult to formulate appropriate operating strategies. Summary of the invention

[0005] The present application provides a method, device and electronic device for judging supply and demand of an online car-hailing aggregation platform, so as to solve the problem that under the aggregation platform model, due to factors such as a wide range of sources of user car demand, different platforms, a wide range of car models, different driver order-taking modes and a variety of order-taking models, supply and demand judgment is very difficult, which is not conducive to the formulation of appropriate operation strategies.

[0006] In a first aspect, an embodiment of the present application provides a method for determining supply and demand of an online car-hailing aggregation platform, comprising: Obtaining the user's car demand data from the traffic platform, sampling the car demand data according to a set sampling interval, and statistically aggregating the data at each sampling point according to the platform and vehicle model to obtain an unmatched order quantity sequence; Obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain the unmatched driver sequence; Based on the average winning probability of each traffic platform, the unmatched order quantity sequence is transformed to obtain the refined order quantity by vehicle type; Based on the acceptance capacity of drivers in each order-listening mode, the unmatched driver sequence is normalized and calculated to obtain refined transportation capacity by vehicle type; The refined order quantity is matched with the refined transportation capacity, and supply and demand scenario labels are determined based on historical data.

[0007] Based on the above method, optionally, the driver's available order data is obtained from the transportation platform, the available order data is sampled according to a set sampling interval, and the data of each sampling point is statistically aggregated according to the order listening mode and vehicle type to obtain an unmatched driver sequence, including: Obtain the reporting status data of drivers on each transportation platform and group them according to their order receiving mode; According to the set sampling interval, the idle drivers at the corresponding sampling points are screened, and statistical aggregation is performed according to the type of vehicles that receive orders to obtain the sequence of unmatched drivers.

[0008] Based on the above method, optionally, it also includes: Predicting the transport capacity of other transport platforms; the other transport platforms are transport platforms that have not obtained the driver's order-accepting data; Based on the driver's ability to accept the demand in each order listening mode, the unmatched driver sequence is normalized and calculated to obtain the refined transportation capacity of different vehicle types, including: Based on the ability of drivers in each order-listing mode to handle demand, the unmatched driver sequence is normalized and calculated, and the transport capacity of other transport platforms is taken into account to obtain the refined transport capacity for each vehicle type.

[0009] Based on the above method, optionally, the predicting of the transport capacity of other transport platforms includes: Based on the fast-in-and-fast-out characteristics of order timing, predict the transportation capacity of other transportation platforms.

[0010] Based on the above method, optionally, it also includes: Based on business characteristics and customized business requirements, the supply and demand data and scenario labels for the corresponding vehicle group are generated.

[0011] Based on the above method, optionally, the sampling according to the set sampling interval includes: In the sampling period of 10 minutes, sampling is performed every 30 seconds as a sampling point.

[0012] In a second aspect, the embodiment of the present application further provides a supply and demand judgment device for an online car-hailing aggregation platform, including: The order data module is used to obtain the user's car demand data from the traffic platform, sample the car demand data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the platform and model to obtain the unmatched order quantity sequence; The driver data module is used to obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain the unmatched driver sequence; An order processing module is used to perform quantity transformation on the unmatched order quantity sequence based on the average winning probability of each traffic platform to obtain refined order quantities by vehicle type; The transport capacity processing module is used to perform normalized calculation on the unmatched driver sequence based on the acceptance capacity of the drivers in each order listening mode to obtain refined transport capacity by vehicle type; The supply and demand determination module is used to match the refined order quantity with the refined transportation capacity and determine the supply and demand scenario label based on historical data.

[0013] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory and a processor; wherein the memory stores a computer program, and when the processor calls and executes the computer program, it implements the supply and demand judgment method of the online car-hailing aggregation platform as described in any one of the first aspects.

[0014] In the supply and demand judgment method, device and electronic equipment of the online car-hailing aggregation platform provided by this application, the car demand data and the driver's order data are obtained from the traffic platform and the capacity platform respectively, and then the corresponding data are sampled according to the sampling interval, and the car demand data is statistically aggregated according to the platform and the model, and the driver's order data is statistically aggregated according to the order listening mode and the model. After that, the aggregated data is refined and calculated to obtain the refined order quantity and refined transportation capacity, and finally the supply and demand are matched, so that the supply and demand scenario labels can be determined based on historical data. With such a setting, the supply and demand situation under the online car-hailing aggregation platform model, such as the wide source of car demand, different platforms, wide models, different driver order listening modes, and various order listening models, can be finely portrayed, and the corresponding accurate supply and demand situation and grade division can be given by model category, which is conducive to the platform to formulate appropriate operation strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. In addition, these drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application for those skilled in the art by referring to specific embodiments.

[0016] Figure 1 A flow chart of a method for determining supply and demand of an online car-hailing aggregation platform provided in accordance with an embodiment of the present application; Figure 2A schematic diagram of a process for generating an unmatched single quantity sequence provided in one embodiment of the present application; Figure 3 A schematic diagram of a process for generating an unmatched driver sequence provided by an embodiment of the present application; Figure 4 A schematic diagram of a process for generating a refined order quantity provided in one embodiment of the present application; Figure 5 A schematic diagram of a process for generating refined transport capacity provided in one embodiment of the present application; Figure 6 A schematic diagram of a process for generating vehicle type data and labels provided in one embodiment of the present application; Figure 7 A schematic diagram of the structure of a supply and demand judgment device for an online car-hailing aggregation platform provided in one embodiment of the present application; Figure 8 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0018] In the aggregation platform model, different operating strategies are required under different supply and demand conditions, so a scientific and reasonable supply and demand judgment method is crucial. Through analysis, there are several technical difficulties that need to be overcome in this industry context: 1. Demand side: Different traffic platforms have different strategies for selecting drivers, and these strategies are not open to the public. As a result, from the perspective of the transportation platform, the orders placed on each traffic platform have different hidden attributes, which need to be normalized in the supply and demand judgment.

[0019] 2. Supply side: The capacity platform cannot effectively obtain the capacity of its competitors, so it is difficult to effectively evaluate the market capacity. It is necessary to infer the market supply and demand through existing data performance, so as to make a reasonable estimate of the supply part.

[0020] 3. Car model category related: Different users have different experience requirements, and they will check their desired car model category during the bubble and order selection process; drivers also have different demands for the range of orders they receive, and some drivers of high-end cars may choose to accept economical orders to expand the scale of completed orders. Based on supply and demand judgment, it is necessary to convert the supply and demand of different car models and support customized car model requirements from the operation team.

[0021] To sum up, the supply and demand judgment method under the online car-hailing aggregation platform model needs to achieve a detailed characterization of demand and supply, and can give corresponding supply and demand situations and level classifications according to vehicle type categories.

[0022] In response to the above problems, this application provides a supply and demand judgment solution for an online car-hailing aggregation platform to meet the accurate judgment of the supply and demand relationship, so as to facilitate the formulation of appropriate operation strategies. It is mainly through collecting demand data from the traffic platform and the status data of self-employed drivers, and through independent demand and supply fine characterization, generating supply and demand data and scene labels for different vehicle types and custom groups. The following is a non-restrictive explanation of the specific implementation scheme through several examples or embodiments.

[0023] Reference Figure 1 , Figure 1 A flow chart of a method for determining supply and demand of a ride-hailing aggregation platform provided in one embodiment of the present application. The method of this embodiment is applied to a ride-hailing aggregation platform, and can be specifically executed by a server or other device. Based on this, Figure 1 As shown, the method comprises at least the following steps: Step S101: Obtain the user's car demand data from the traffic platform, sample the car demand data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the platform and car model to obtain an unmatched order sequence.

[0024] Specifically, the traffic platform refers to the platform where users place orders. In reality, there are many different traffic platforms A, B...X. Different users have different usage preferences and will place orders on different traffic platforms. The aggregation platform cooperates with various traffic platforms, receiving orders from each traffic platform and then allocating them to candidate drivers on the transportation platform.

[0025] When placing an order, users will select or enter their own needs, such as car model, car type and price range, and the traffic platform will generate car demand data based on this. Figure 2 As shown, the aggregation platform can obtain vehicle demand data from various cooperating traffic platforms in real time, and then process and analyze it, perform multiple sampling at a set sampling interval, and calculate the number of unmatched orders at the corresponding sampling points, and then perform statistical aggregation by platform and vehicle model to generate an unmatched order quantity sequence.

[0026] In some embodiments, sampling is performed according to a set sampling interval, specifically including: within a sampling period of 10 minutes, sampling is performed once every 30 seconds as a sampling point.

[0027] It should be noted that in practice, some orders may be matched by the platform at a later time point, but will still be recorded as unmatched orders at the sampling time. However, due to the short sampling interval, such as 30s, such situations are rare in practice and are within an acceptable range.

[0028] Step S102: Obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain an unmatched driver sequence.

[0029] Specifically, the transportation platform is the driver's order-receiving platform. In practice, drivers can regularly report their location and status data, and the transportation platform can generate order-receiving data in combination with the order-listening mode (such as assignment, on the way, grabbing orders, etc.). In this step, the aggregation platform can obtain order-receiving data from each cooperating transportation platform in real time, and then process and analyze it to generate an unmatched driver sequence.

[0030] More specifically, in some embodiments, Figure 3 As shown, step S102 may specifically include: obtaining the reporting status data of the drivers in each transportation platform from each transportation platform, and grouping them according to their order-receiving mode; according to the set sampling interval, screening the idle drivers at the corresponding sampling point, and performing statistical aggregation according to the order-receiving vehicle model to obtain an unmatched driver sequence.

[0031] Among them, grouping through the listening mode can effectively distinguish different drivers and make it easier to determine the supply situation.

[0032] In some embodiments, similarly, sampling is performed according to a set sampling interval, specifically including: within a sampling period of 10 minutes, sampling is performed once every 30 seconds as a sampling point.

[0033] It should be noted that in practice, some drivers may receive platform orders at a later time, but will still be recorded as unmatched drivers at the sampling time. However, due to the short sampling interval, such as 30 seconds, such situations are rare in practice and are within an acceptable range.

[0034] It should also be noted that, in practice, steps S101 and S102 can be performed synchronously or asynchronously, and there is no limitation to this.

[0035] Step S103: Based on the average winning probability of each traffic platform, the unmatched order quantity sequence is transformed to obtain the refined order quantity by vehicle type.

[0036] Specifically, in practice, due to the influence of factors such as the strategies and number of users of different traffic platforms, the average winning probability of different traffic platforms varies greatly. Therefore, the overall demand quantity of each vehicle type needs to be appropriately transformed according to its source. The transformed data is then re-added and calculated to calculate the final demand quantity of each vehicle type, such as Figure 4 As shown. The average winning probability of each traffic platform can be calculated based on historical data. Generally speaking, if the average winning probability of a traffic platform is greater than the set value or exceeds the set interval, the demand quantity after quantity transformation is greater than the original value; otherwise, the demand quantity after quantity transformation remains unchanged or is less than the original value.

[0037] Through the above process, refined calculation of vehicle demand is achieved, which is more in line with actual user needs.

[0038] Step S104: Based on the demand-taking capabilities of drivers in each listening mode, a normalized calculation is performed on the unmatched driver sequence to obtain refined transportation capacity by vehicle type.

[0039] Specifically, considering that the drivers in each order-listing mode have different capabilities to accept demands, the demand acceptance capacity is normalized and calculated in this method, such as Figure 5 Based on the business characteristics, the order-taking capabilities of each order-listening mode are relatively strong to weak: assigned type, on-the-way type, and grab-order type.

[0040] Through the above process, the refined calculation of transportation capacity is achieved, which is more in line with the actual driver's ability to undertake.

[0041] In addition, in some embodiments, the above method may further include: predicting the transport capacity of other transport platforms. Accordingly, in step S104, based on the acceptance capacity of drivers in each order listening mode, the unmatched driver sequence is normalized and calculated, and the transport capacity of other transport platforms is considered to obtain the refined transport capacity of different vehicle types.

[0042] Among them, other transport platforms refer to transport platforms that have not obtained the driver's order data. In other words, it refers to other transport platforms that have not cooperated with the current aggregation platform. In practice, these transport platforms will also accept orders from the traffic platform, so these transport platforms can actually provide market capacity. Therefore, in this embodiment, when calculating the refined transport capacity of different vehicle types, the transport capacity of other transport platforms is predicted and taken into account, so that the final calculation result is more in line with the actual situation, such as Figure 4 The transportation capacity of friendly competitors on the right.

[0043] In some embodiments, predicting the transportation capacity of other transportation platforms specifically includes: predicting the transportation capacity of other transportation platforms based on the fast-in-fast-out characteristics of order timing.

[0044] Specifically, the fast-in-fast-out feature refers to the system using algorithms to quickly match user needs with nearby drivers to reduce waiting time. At the same time, the intelligent dispatching system optimizes the driver's order acceptance sequence and route to reduce empty driving and waiting time. In other words, for those orders that enter the aggregation platform but are not matched with drivers in the future, they are orders accepted by other transportation platforms, and these orders are fast-in-fast-out orders. In this method, the aggregation platform can predict the transportation capacity of other transportation platforms based on this feature according to the actual fast-in-fast-out orders, and then summarize them into market transportation capacity conditions.

[0045] Step S105: Match the refined order quantity with the refined transportation capacity, and determine the supply and demand scenario label based on historical data.

[0046] Specifically, the demand (refined order quantity) and supply (refined transport capacity) data are matched and compared by vehicle type, and classified according to the historical data distribution, and then the supply and demand scenario labels are determined, such as supply is less than demand, supply is greater than demand, and supply and demand are balanced. These labels will provide a basis for application-layer strategies.

[0047] In addition, in some embodiments, the above method may also include: based on business characteristics, generating supply and demand data and scenario labels for the corresponding vehicle model group according to customized business requirements.

[0048] For example, the Huixiang Economy Premium and other models are low-end models. In the supply and demand judgment, the supply and demand data and scenario labels of the corresponding model group can be output according to the customized needs of the business, such as Figure 6 shown.

[0049] Based on the above scheme, the car demand data and driver order data are obtained from the traffic platform and the transportation capacity platform respectively, and then the corresponding data are sampled according to the sampling interval, and the car demand data is statistically aggregated according to the platform and vehicle model, and the driver order data is statistically aggregated according to the order listening mode and vehicle model. After that, the aggregated data is refined to obtain the refined order quantity and refined transportation capacity, and finally the supply and demand are matched, so that the supply and demand scenario labels can be determined based on historical data. With this setting, the supply and demand situation under the online car-hailing aggregation platform model, such as the wide sources of car demand, different platforms, a wide range of vehicle models, different driver order listening modes, and various order listening models, can be finely portrayed, and the corresponding accurate supply and demand situation and level division can be given by vehicle type category, which is conducive to the platform to formulate appropriate operation strategies.

[0050] In addition, the embodiment of the present application provides a supply and demand judgment device for an online car-hailing aggregation platform, which is applied to a smart phone, and the smart phone runs an online car-hailing APP. Figure 7 , the supply and demand judgment device of the online car-hailing aggregation platform of this embodiment includes: The order data module 21 is used to obtain the user's car demand data from the traffic platform, sample the car demand data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the platform and model to obtain the unmatched order quantity sequence; The driver data module 22 is used to obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain the unmatched driver sequence; The order processing module 23 is used to transform the quantity of the unmatched order quantity sequence based on the average winning probability of each traffic platform to obtain the refined order quantity by vehicle type; The transport capacity processing module 24 is used to perform normalized calculation on the unmatched driver sequence based on the acceptance capacity of the drivers in each order listening mode to obtain refined transport capacity for each vehicle type; The supply and demand determination module 25 is used to match the refined order quantity with the refined transportation capacity, and determine the supply and demand scenario labels based on historical data.

[0051] Among them, regarding the specific implementation methods of each module of the supply and demand judgment device of the above-mentioned online car-hailing aggregation platform, reference can be made to the corresponding contents in the aforementioned method embodiments, which will not be repeated here.

[0052] In addition, the present application also provides a smart phone, such as Figure 8 As shown, the smart phone includes a memory 31 and a processor 32; wherein the memory 31 stores a computer program, and when the processor 32 calls and executes the computer program, the supply and demand judgment method of the online car-hailing aggregation platform in any of the above-mentioned embodiments is implemented.

[0053] The electronic device may be a server or the like.

[0054] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0055] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0056] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0057] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0058] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0059] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0060] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0061] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for determining supply and demand of an online car-hailing aggregation platform, characterized in that: include: Obtaining the user's car demand data from the traffic platform, sampling the car demand data according to a set sampling interval, and statistically aggregating the data at each sampling point according to the platform and vehicle model to obtain an unmatched order quantity sequence; Obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain the unmatched driver sequence; Based on the average winning probability of each traffic platform, the unmatched order quantity sequence is transformed to obtain the refined order quantity by vehicle type; Based on the acceptance capacity of drivers in each order-listening mode, the unmatched driver sequence is normalized and calculated to obtain refined transportation capacity by vehicle type; The refined order quantity is matched with the refined transportation capacity, and supply and demand scenario labels are determined based on historical data.

2. The method according to claim 1, characterized in that The method obtains the driver's available order data from the transportation platform, samples the available order data according to a set sampling interval, and statistically aggregates the data at each sampling point according to the order listening mode and vehicle type to obtain an unmatched driver sequence, including: Obtain the reporting status data of drivers on each transportation platform and group them according to their order receiving mode; According to the set sampling interval, the idle drivers at the corresponding sampling points are screened, and statistical aggregation is performed according to the type of vehicles that receive orders to obtain the sequence of unmatched drivers.

3. The method according to claim 1, characterized in that: Also includes: Predicting the transport capacity of other transport platforms; the other transport platforms are transport platforms that have not obtained the driver's order-accepting data; Based on the driver's ability to accept the demand in each order listening mode, the unmatched driver sequence is normalized and calculated to obtain the refined transportation capacity of different vehicle types, including: Based on the ability of drivers in each order-listing mode to handle demand, the unmatched driver sequence is normalized and calculated, and the transport capacity of other transport platforms is taken into account to obtain the refined transport capacity for each vehicle type.

4. The method according to claim 3, characterized in that The forecast of the transport capacity of other transport platforms includes: Based on the fast-in-and-fast-out characteristics of order timing, predict the transportation capacity of other transportation platforms.

5. The method according to claim 1, characterized in that Also includes: Based on business characteristics and customized business requirements, the supply and demand data and scenario labels for the corresponding vehicle group are generated.

6. The method according to claim 1, characterized in that The sampling according to the set sampling interval includes: In the sampling period of 10 minutes, sampling is performed every 30 seconds as a sampling point.

7. A supply and demand judgment device for an online car-hailing aggregation platform, characterized in that: Applied to a smart phone, the smart phone runs an online car-hailing APP, and the device comprises: The order data module is used to obtain the user's car demand data from the traffic platform, sample the car demand data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the platform and model to obtain the unmatched order quantity sequence; The driver data module is used to obtain the driver's available order data from the transportation platform, sample the available order data according to the set sampling interval, and statistically aggregate the data of each sampling point according to the order listening mode and vehicle type to obtain the unmatched driver sequence; An order processing module is used to perform quantity transformation on the unmatched order quantity sequence based on the average winning probability of each traffic platform to obtain refined order quantities by vehicle type; The transport capacity processing module is used to perform normalized calculation on the unmatched driver sequence based on the acceptance capacity of the drivers in each order listening mode to obtain refined transport capacity by vehicle type; The supply and demand determination module is used to match the refined order quantity with the refined transportation capacity and determine the supply and demand scenario label based on historical data.

8. An electronic device, characterized in that: It comprises a memory and a processor; wherein the memory stores a computer program, and when the processor calls and executes the computer program, it implements the supply and demand judgment method of the online car-hailing aggregation platform as described in any one of claims 1 to 6.

Images