Real-time analysis and prediction method, system and equipment for online car-hailing transport capacity

Abstract

The invention relates to the technical field of data processing, in particular to a real-time analysis and prediction method, system and device for online car-hailing transport capacity, and the method comprises the steps: obtaining the order data of a passenger end and the report point data of a driver end; dividing the order data and the report point data in continuous time slices based on a preset time length; based on the order data of the current time slice, the order placing amount and the order receiving amount are calculated; dividing the order data of the current time slice into a target number of continuous time windows, and calculating an unquickly matched order quantity, an external quickly matched order quantity and an internal quickly matched order quantity; determining the transport capacity of the driver based on the point reporting data of the current time slice; and on the basis of the order index and the driver transport capacity, determining online car-hailing real-time transport capacity matching information and predicting online car-hailing future transport capacity matching information. Therefore, the dynamic change between the passenger car demand and the driver transport capacity can be accurately and comprehensively analyzed in real time, so that the driver is reminded of business, and the business is ensured to be carried out efficiently and smoothly.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, system and device for real-time analysis and prediction of online car-hailing capacity. Background Art

[0002] In the online ride-hailing business, understanding the dynamic relationship between passenger demand and driver capacity can provide accurate business reminders to drivers, ensuring that they can meet passenger demand while also ensuring the number of orders handled by drivers. However, current technology cannot accurately and comprehensively understand and analyze the dynamic relationship between passenger demand and driver capacity in real time. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a real-time analysis and prediction method, system and equipment for online car-hailing capacity, so as to overcome the current problem of being unable to understand and analyze the dynamic changes between passengers' car demand and drivers' capacity in real time, accurately and comprehensively.

[0004] To achieve the above objectives, the present invention adopts the following technical solutions: In a first aspect, the present application provides a method for real-time analysis and prediction of online ride-hailing capacity, comprising: Obtain order data from the passenger side and reporting data from the driver side; Based on a preset time length, the order data and the reporting point data are divided into continuous time slices; Based on the order data of the current time slice, calculate the order volume and the order volume; divide the order data of the current time slice into a target number of consecutive time windows, and calculate the number of unmatched orders, externally matched orders, and internally matched orders; among them, the number of unmatched orders is the number of orders whose order placement time and order acceptance or cancellation time are not within the same time window, the number of externally matched orders is the number of orders whose order placement time and cancellation time are within the same time window, and the number of internally matched orders is the number of orders whose order placement time and order acceptance time are within the same time window; Determine the driver's capacity based on the reporting data of the current time slice; Determine the real-time capacity matching information of online ride-hailing vehicles based on the order indicators and driver capacity of the same time slice; wherein the order indicators include the order volume, the order volume, the number of unmatched orders, the number of externally matched orders, and the number of internally matched orders; Based on order indicators and driver capacity of multiple consecutive time slices or time windows, predict future capacity matching information of online ride-hailing.

[0005] Furthermore, in some embodiments of the present application, the method further includes: determining corresponding honeycomb information based on the order data and the location information in the reporting data; Calculating the order quantity and the order quantity based on the order data of the current time slice includes: determining the order quantity and the order quantity for each city, honeycomb, and order level based on the order data of the current time slice; The method of dividing the order data of the current time slice into a target number of continuous time windows and calculating the amount of un-quickly matched orders, the amount of externally quickly matched orders, and the amount of internally quickly matched orders includes: dividing the order data of the current time slice into a target number of continuous time windows, and calculating the amount of un-quickly matched orders, the amount of externally quickly matched orders, and the amount of internally quickly matched orders for each city, hive, and order level.

[0006] Furthermore, in some embodiments of the present application, before dividing the order data and the reporting data into consecutive time slices based on a preset time length, the method further includes: Generate a deduplication identifier for each order based on the target fields in the order data; wherein the target fields include the passenger ID, the time slice, and the starting and ending coordinates; For multiple orders with the same deduplication identifier, only the data of one order is retained.

[0007] Furthermore, in some embodiments of the present application, determining the driver's capacity based on the reporting data of the current time slice includes: The reporting data of the current time slice is divided into a target number of continuous time windows, and the reporting data in the time windows are accumulated as the driver's capacity corresponding to the time windows; wherein the duration corresponding to the time window is the same as the time interval between the driver's two reporting of the reporting data.

[0008] Furthermore, in some embodiments of the present application, obtaining the order data from the passenger side and the reporting data from the driver side includes: Collect order data from the passenger side and store it in the preset basic database; Collect the driver's reporting data and store it in the preset message queue; Obtain the order data from the basic database through the cloud transmission service, and obtain the order data from the message queue through the Flink computing engine, and connect them to the big data real-time warehouse in the form of data stream for storage; The Flink computing engine processes data stored in the big data real-time warehouse in real time and obtains the corresponding honeycomb information to build a data detail layer in the big data real-time warehouse. The constructed data detail layer stores the real-time processed data. The real-time processing includes parsing, filtering, and integration. The data stored in the data detail layer is synchronized to the Doris database through the Flink computing engine, wherein the data synchronized to the Doris database is stored in the form of a data table.

[0009] Furthermore, in some embodiments of the present application, the following is further included: Generate vehicle guidance prompts based on real-time and future capacity matching information of online ride-hailing vehicles; The vehicle guidance prompts include driving prompts for guiding the vehicle to drive and service prompts for guiding the vehicle to change the service level.

[0010] Furthermore, in some embodiments of the present application, determining the real-time capacity matching information of online ride-hailing services based on order indicators and driver capacity in the same time slice includes: Determine the matching ratio of online ride-hailing capacity in real time based on order volume, accepted order volume, and driver capacity; Based on the number of non-quickly matched orders, externally quickly matched orders, and internally quickly matched orders, the matching efficiency information of the real-time capacity of online ride-hailing is calculated.

[0011] Furthermore, in some embodiments of the present application, The matching ratio information includes: supply-demand ratio and order matching rate; wherein the supply-demand ratio is the ratio of the number of orders placed in a time slice to the driver's transportation capacity, and the order matching rate is the ratio of the number of orders received in a time slice to the number of orders placed; The matching efficiency information includes: the proportion of non-quick matches, the proportion of internal quick matches and the proportion of external quick matches; among them, the proportion of non-quick matches is the ratio of the number of non-quick matches to the number of orders placed in the corresponding time window, the proportion of internal quick matches is the ratio of the number of internal quick matches to the number of orders placed in the corresponding time window, and the proportion of external quick matches is the ratio of the number of external quick matches to the number of orders placed in the corresponding time window.

[0012] In a second aspect, the present application provides a real-time analysis and prediction system for online ride-hailing capacity, including: The acquisition module is used to obtain order data from the passenger side and reporting data from the driver side; A division module, configured to divide the order data and the reporting point data into continuous time slices based on a preset time length; An indicator calculation module is used to calculate the order volume and order volume based on the order data of the current time slice; divide the order data of the current time slice into a target number of consecutive time windows, and calculate the number of unmatched orders, externally matched orders, and internally matched orders; wherein the unmatched orders are the number of orders whose order placement time and order acceptance or cancellation time are not within the same time window, the externally matched orders are the number of orders whose order placement time and cancellation time are within the same time window, and the internally matched orders are the number of orders whose order placement time and order acceptance time are within the same time window; and determine the driver's transportation capacity based on the reporting data of the current time slice; The capacity matching calculation module is used to determine the real-time capacity matching information of online ride-hailing based on the order indicators and driver capacity of the same time slice; wherein the order indicators include the order volume, the order volume, the non-quickly matched order volume, the externally quickly matched order volume and the internally quickly matched order volume; and based on the order indicators and driver capacity of multiple consecutive time slices or time windows, predict the future capacity matching information of online ride-hailing.

[0013] In a third aspect, the present application provides a real-time analysis and prediction device for online ride-hailing capacity, including a processor and a memory, wherein the processor is connected to the memory: The processor is configured to call and execute the program stored in the memory; The memory is used to store the program, which is at least used for the above-mentioned real-time analysis and prediction method of online car-hailing capacity The present invention relates to the field of data processing technology, and specifically to a real-time analysis and prediction method, system and device for online car-hailing capacity, the method comprising: obtaining order data from a passenger side and reporting data from a driver side; dividing the order data and reporting data into continuous time slices based on a preset time length; calculating the order quantity and the order quantity based on the order data of the current time slice; dividing the order data of the current time slice into a target number of continuous time windows, and calculating the quantity of un-quickly matched orders, the quantity of externally quickly matched orders and the quantity of internally quickly matched orders; wherein the quantity of un-quickly matched orders is the number of orders whose order placement time and order acceptance or cancellation time are not within the same time window, the quantity of externally quickly matched orders is the number of orders whose order placement time and cancellation time are within the same time window, and the quantity of internally quickly matched orders is the number of orders whose order placement time and order acceptance or cancellation time are within the same time window; determining the driver capacity based on the reporting data of the current time slice; determining the real-time capacity matching information of the online car-hailing based on the order indicators and driver capacity of the same time slice; and predicting the future capacity matching information of the online car-hailing based on the order indicators and driver capacity of multiple continuous time slices or time windows. In this way, the dynamic changes between passengers' car demand and drivers' capacity can be analyzed in real time, accurately and comprehensively, so as to provide business reminders to drivers and ensure that the business is carried out efficiently and smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 1 is a flow chart of a method for real-time analysis and prediction of online ride-hailing capacity provided by an embodiment of the present invention; Figure 2 2 is a schematic diagram of the structure of a real-time analysis and prediction system for online car-hailing capacity provided by an embodiment of the present invention; Figure 3 It is a structural diagram of the real-time analysis and prediction device for online car-hailing capacity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without inventive effort are within the scope of protection of the present invention.

[0017] Figure 1 This is a flow chart of the real-time analysis and prediction method for online car-hailing capacity provided by an embodiment of the present invention. Figure 1 , this embodiment may include the following steps: S101. Obtain order data from the passenger side and reporting data from the driver side.

[0018] Specifically, the real-time analysis and prediction method of online car-hailing capacity provided in this application can use the preset database and message queue to obtain the above data during the data collection stage, and then collect data from the database and message queue through cloud transmission services and the Flink computing engine, and then connect it to the constructed big data real-time warehouse in the form of data streams; then use the Flink computing engine to process the data in the big data real-time warehouse, such as parsing, filtering and integration, and synchronize the processed data to the Doris database and store it in the form of data tables.

[0019] S102: Based on a preset time length, the order data and the reporting point data are divided into continuous time slices.

[0020] Specifically, the preset time length may be 10 minutes, and the data table processed in the above steps is divided into time slices every 10 minutes.

[0021] S103. Calculate the order quantity and the order quantity based on the order data of the current time slice; divide the order data of the current time slice into a target number of continuous time windows, and calculate the quantity of un-quickly matched orders, the quantity of externally quickly matched orders, and the quantity of internally quickly matched orders.

[0022] Among them, the number of non-quickly matched orders is the number of orders whose order placement time and order acceptance or cancellation time are not in the same time window, the number of externally quickly matched orders is the number of orders whose order placement time and cancellation time are in the same time window, and the number of internally quickly matched orders is the number of orders whose order placement time and order acceptance time are in the same time window.

[0023] It should be noted that among the above-mentioned order indicators, external quick matching orders are orders that come from other platforms or systems (which are not the same as the real-time analysis and prediction system for online car-hailing capacity used to execute the real-time analysis and prediction method for online car-hailing capacity in this application), and are canceled within a short period of time. In this case, it can be considered that the order is digested by the external platform itself, that is, external quick matching.

[0024] S104: Determine the driver's transport capacity based on the reporting data of the current time slice.

[0025] Among them, the reported point data is the data reported by the driver to show his or her geographic location.

[0026] S105. Determine the real-time capacity matching information of the online car-hailing service based on the order indicators and driver capacity of the same time slice.

[0027] S106. Based on the order indicators and driver capacity of multiple consecutive time slices or time windows, predict the future capacity matching information of the online car-hailing service.

[0028] The order metrics are the aforementioned order volume, order volume, unmatched orders, externally matched orders, and internally matched orders. A specific prediction method involves calculating and analyzing the changing trends of each of these order metrics using known values ​​for multiple consecutive time periods. This trend analysis then derives the corresponding future values ​​(the same applies to driver capacity), allowing the corresponding capacity matching information to be calculated. This analysis can be performed using precise mathematical calculations or pre-defined models.

[0029] In addition, in other embodiments of the present application, the changing trend of the real-time capacity matching information of multiple consecutive time slices can also be directly analyzed to directly predict the capacity matching information in the future.

[0030] The real-time analysis and prediction method of online car-hailing capacity provided in this application obtains the order data of the passenger side and the reporting data of the driver side in the above-mentioned manner; divides the order data and reporting data into continuous time slices based on the preset time length; calculates the order quantity and the order quantity based on the order data of the current time slice; divides the order data of the current time slice into a target number of continuous time windows, and calculates the quantity of un-quickly matched orders, the quantity of externally quickly matched orders, and the quantity of internally quickly matched orders; and determines the driver's capacity based on the reporting data of the current time slice; determines the real-time capacity matching information of the online car-hailing based on the order indicators and driver capacity of the same time slice, and predicts the future capacity matching information of the online car-hailing based on the order indicators and driver capacity of multiple continuous time slices or time windows. It can analyze the dynamic changes between passenger car demand and driver capacity in real time, accurately and comprehensively, thereby making business reminders for drivers to ensure efficient and smooth business.

[0031] Furthermore, in some embodiments of the present application, obtaining order data from the passenger side and reporting data from the driver side may include: collecting order data from the passenger side and storing it in a preset basic database; collecting reporting data from the driver side and storing it in a preset message queue; obtaining order data from the basic database through a cloud transmission service, and obtaining reporting data from the message queue through a Flink computing engine, and connecting them to a big data real-time warehouse for storage in the form of a data stream; performing real-time processing on the data stored in the big data real-time warehouse through the Flink computing engine, and obtaining corresponding honeycomb information to construct a data detail layer in the big data real-time warehouse, and storing the real-time processed data through the constructed data detail layer; synchronizing the data stored in the data detail layer to the Doris database through the Flink computing engine, wherein the data synchronized to the Doris database is stored in the form of a data table.

[0032] Specifically, for example, passenger order data is stored in MySQL, while driver check-in data is uploaded and stored in the RabbitMQ message queue. Cloud transmission services such as Alibaba Cloud's transmission service are then used to collect the order data from MySQL, while the check-in data from RabbitMQ is collected using the Flink computing engine. Both data streams are then connected to the operational data store (ODS) layer of Kafka, a real-time big data warehouse.

[0033] On this basis, the Flink computing engine is used to process the data in the ODS layer in real time, including data parsing, filtering, and integration. Pre-defined algorithms, such as the UberH3 algorithm, are used to calculate and retrieve corresponding honeycomb information based on the location coordinates of order data and point-of-delivery data. Furthermore, a data warehouse detail (DWD) layer is constructed to support subsequent data analysis.

[0034] On this basis, the Flink computing engine is used to synchronize order data and reporting data to Doris's data table in real time, including synchronizing order data to the order table and synchronizing reporting data to the capacity indicator aggregation.

[0035] Specifically, in this application, the order table is designed using a unique key model. The unique key in the table defines information including order time, city ID, hive ID, and order ID. The main indicator fields include order level, order acceptance time, cancellation time, and duplicate ID.

[0036] It should be noted that in the embodiments of the present application, when calculating real-time order indicators, to ensure accuracy, the order data must be deduplicated. The deduplication process specifically includes: based on the target field in the order data, generating a deduplication identifier, i.e., a deduplication ID, for each order based on the data corresponding to each order; wherein the target field includes the passenger ID, the time slice to which the order time belongs, and the starting and ending point coordinates; and for multiple orders with the same deduplication identifier, only retaining the data of one order.

[0037] In practical applications, the principle of scheduled task scheduling can be used in the Doris database. For example, in the Doris database, a scheduled task scheduling system can be used to start a task after a 10-second delay in each ten-minute cycle. Calculation and analysis can be performed on various order indicators.

[0038] Specifically, for the order volume, the number of orders placed within the ten minutes before the current time point is counted, and the number of orders received ....

[0039] And for the current time slice, multiple boundaries are defined to divide the time slice into multiple time windows corresponding to 30 seconds, so as to calculate the number of non-quickly matched orders, externally quickly matched orders and internally quickly matched orders, including counting the number of non-quickly matched orders whose order placement time is within a certain 30-second window but whose order acceptance or cancellation time is not within the window; counting the number of externally quickly matched orders whose order placement time and cancellation time are both within a 30-second window; and counting the number of internally quickly matched orders whose order placement time and order acceptance time are both within a 30-second window.

[0040] In the above process, calculation and analysis are performed through delayed time. That is, after each ten-minute period, the task will be started after a 10-second delay, which can ensure data integrity. At the same time, by dividing the ten minutes into 30-second windows, real-time data statistics and analysis can be achieved in a fine-grained manner. And by generating deduplication IDs to deduplicate order data, the accuracy of the statistical results can be ensured.

[0041] Furthermore, in an embodiment of the present application, the driver's capacity is determined based on the reporting data of the current time slice, including: dividing the reporting data of the current time slice into a target number of continuous time windows, and accumulating the reporting data in the time windows as the driver's capacity corresponding to the time windows; wherein the duration corresponding to the time window is the same as the time interval between the driver's two reporting of the reporting data.

[0042] Specifically, as mentioned above, the Flink computing engine can be used to synchronize the driver's point reporting data in real time to Doris's capacity index aggregation table, which uses Doris's aggregation model for data aggregation. The aggregation key of the table consists of the following fields: city, time slice, hive ID, vehicle type, time, and time window information. On this basis, the sum of the number of drivers who receive orders is used as the driver's capacity. It should be noted that in actual applications, the duration corresponding to the time window can be the same as the time interval between the two driver's point reporting data. For example, if the driver's point reporting data is recorded every 30 seconds, the time corresponding to the time window is also set to 30 seconds. In this way, when the driver's capacity is calculated based on the cumulative calculation within the time window, no additional deduplication operation is required.

[0043] On this basis, the calculation of order quantity and order quantity based on the order data of the current time slice mentioned in the above embodiment includes: based on the order data of the current time slice, determining the order quantity and order quantity for each city, honeycomb and order level respectively.

[0044] Specifically, the matching ratio information of the real-time capacity of online ride-hailing can be determined based on the order volume, the order volume and the driver's capacity; and the matching efficiency information of the real-time capacity of online ride-hailing can be calculated based on the number of non-quickly matched orders, the number of externally quickly matched orders and the number of internally quickly matched orders.

[0045] Matching ratio information includes the supply-demand ratio and the order matching rate. The supply-demand ratio is the ratio of the number of orders placed in a time slot to the driver's capacity, while the order matching rate is the ratio of the number of orders received to the number of orders placed in a time slot.

[0046] Matching efficiency information includes the proportion of non-quick matches, the proportion of internal quick matches, and the proportion of external quick matches. The proportion of non-quick matches is the ratio of the number of non-quick matches to the number of orders placed in the corresponding time window, the proportion of internal quick matches is the ratio of the number of internal quick matches to the number of orders placed in the corresponding time window, and the proportion of external quick matches is the ratio of the number of external quick matches to the number of orders placed in the corresponding time window.

[0047] And the above-mentioned embodiment mentioned that the order data of the current time slice is divided into a target number of continuous time windows, and the amount of non-quickly matched orders, the amount of externally quickly matched orders and the amount of internally quickly matched orders include: dividing the order data of the current time slice into a target number of continuous time windows, and calculating the amount of non-quickly matched orders, the amount of externally quickly matched orders and the amount of internally quickly matched orders for each city, hive and order level respectively.

[0048] It should be noted that the above analysis and calculation process of this application can be performed separately for different dimensions, such as determining the order volume and order volume for each city, hive, and order level. And for each city, hive, and order level, calculating the number of unmatched orders, externally matched orders, and internally matched orders separately.

[0049] On this basis, vehicle guidance prompts can be generated based on the real-time capacity matching information of online ride-hailing vehicles and the future capacity matching information of online ride-hailing vehicles; among them, vehicle guidance prompts include driving prompts to guide vehicles to drive, and service prompts to guide vehicles to change service levels (such as prompting vehicles providing luxury services to lower their service levels in order to increase the number of completed orders, such as lowering them to comfort services or economy services).

[0050] For example, in some embodiments, when the real-time capacity matching information of online ride-hailing shows that the supply and demand of a certain honeycomb, i.e., an area, is greater than or equal to a preset judgment threshold, and the predicted future capacity matching information of online ride-hailing shows that this state may continue for the next preset minutes (multiple conditions can be set by using multiple information such as the calculated supply and demand ratio and order matching rate at the same time), a driving reminder can be pushed to drivers who are within the target kilometers of the honeycomb and currently have no orders: "The current demand for orders in XX area is strong, and it is recommended to take a specific route"; and when it is shown that the internal quick matching ratio of "luxury" orders in a certain area is less than or equal to the preset judgment threshold, and the supply and demand ratio of "economy" orders is greater than or equal to the preset judgment threshold, a push notification can be sent to luxury drivers in the area: "The current demand for economy orders is high, and it is recommended to temporarily switch the service level to economy", etc.

[0051] The real-time analysis and prediction method for online car-hailing capacity provided by the present invention combines spatial and temporal dimensions and uses multiple continuous time segments for data analysis and comparison. It can not only perform real-time analysis in a shorter time and significantly reduce the delay of calculation and analysis, but also more sensitively and accurately determine the relationship between passenger car demand and online car-hailing capacity; at the same time, by using the Flink computing engine, real-time data processing is performed on data from multiple data sources, and the data is synchronized to the Doris database for storage in the form of data tables, and then the data tables are used for calculation and analysis, which can ensure the consistency of multiple data streams at a certain moment.

[0052] Based on the same inventive concept, this application also provides a real-time analysis and prediction system for online car-hailing capacity, which is used to implement the above method embodiment. Figure 2 : is a structural diagram of a real-time analysis and prediction system for online car-hailing capacity provided by an embodiment of the present invention. Figure 2 As shown, the system includes: The acquisition module 11 is used to obtain the order data from the passenger side and the reporting data from the driver side.

[0053] The division module 12 is used to divide the order data and the reporting point data into continuous time slices based on a preset time length.

[0054] The indicator calculation module 13 is used to calculate the order volume and the order volume based on the order data of the current time slice; divide the order data of the current time slice into a target number of continuous time windows, and calculate the non-quickly matched order volume, the externally quickly matched order volume and the internally quickly matched order volume; among which, the non-quickly matched order volume is the number of orders whose order placement time and order acceptance or cancellation time are not in the same time window, the externally quickly matched order volume is the number of orders whose order placement time and cancellation time are in the same time window, and the internally quickly matched order volume is the number of orders whose order placement time and order acceptance time are in the same time window; and determine the driver's transportation capacity based on the reporting data of the current time slice.

[0055] The capacity matching calculation module 14 is used to determine the real-time capacity matching information of the online car-hailing service based on the order indicators and driver capacity of the same time slice; wherein the order indicators include the order quantity, the order quantity, the non-quickly matched order quantity, the external quick matching order quantity and the internal quick matching order quantity; and based on the order indicators and driver capacity of multiple consecutive time slices or time windows, predict the future capacity matching information of the online car-hailing service.

[0056] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0057] The present invention also provides a real-time analysis and prediction device for online car-hailing capacity, which is used to implement the above method embodiment. Figure 3 : is a structural diagram of a real-time analysis and prediction device for online car-hailing capacity provided by an embodiment of the present invention, such as Figure 3 As shown, the real-time analysis and prediction device for online ride-hailing capacity in this embodiment includes a processor 21 and a memory 22, wherein the processor 21 is connected to the memory 22. The processor 21 is used to call and execute the program stored in the memory 22; the memory 22 is used to store the program, which is used to at least execute the real-time analysis and prediction method for online ride-hailing capacity in the above embodiment.

[0058] The specific implementation plan of the real-time analysis and prediction device for online car-hailing capacity provided in the embodiments of this application can refer to the implementation plan of the real-time analysis and prediction method for online car-hailing capacity in any of the above embodiments, and will not be repeated here.

[0059] 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.

[0060] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" is at least two.

[0061] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising 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 be performed out of 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 pertain.

[0062] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0063] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0064] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0065] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0066] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0067] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A real-time analysis and prediction method for online car-hailing capacity, characterized by: include: Obtain order data from the passenger side and reporting data from the driver side; Based on a preset time length, the order data and the reporting point data are divided into continuous time slices; Based on the order data of the current time slice, calculate the order volume and the order volume; divide the order data of the current time slice into a target number of consecutive time windows, and calculate the number of unmatched orders, externally matched orders, and internally matched orders; among them, the number of unmatched orders is the number of orders whose order placement time and order acceptance or cancellation time are not within the same time window, the number of externally matched orders is the number of orders whose order placement time and cancellation time are within the same time window, and the number of internally matched orders is the number of orders whose order placement time and order acceptance time are within the same time window; Determine the driver's capacity based on the reporting data of the current time slice; Determine the real-time capacity matching information of online ride-hailing vehicles based on the order indicators and driver capacity of the same time slice; wherein the order indicators include the order volume, the order volume, the number of unmatched orders, the number of externally matched orders, and the number of internally matched orders; Based on order indicators and driver capacity of multiple consecutive time slices or time windows, predict future capacity matching information of online ride-hailing.

2. The real-time analysis and prediction method for online car-hailing capacity according to claim 1 is characterized in that: Also includes: Determining corresponding honeycomb information based on the order data and the location information in the reporting data; Calculating the order quantity and the order quantity based on the order data of the current time slice includes: determining the order quantity and the order quantity for each city, honeycomb, and order level based on the order data of the current time slice; The method of dividing the order data of the current time slice into a target number of continuous time windows and calculating the amount of un-quickly matched orders, the amount of externally quickly matched orders, and the amount of internally quickly matched orders includes: dividing the order data of the current time slice into a target number of continuous time windows, and calculating the amount of un-quickly matched orders, the amount of externally quickly matched orders, and the amount of internally quickly matched orders for each city, hive, and order level.

3. The real-time analysis and prediction method for online car-hailing capacity according to claim 1, characterized in that: Before dividing the order data and the reporting data into consecutive time slices based on a preset time length, the method further includes: Generate a deduplication identifier for each order based on the target fields in the order data; wherein the target fields include the passenger ID, the time slice, and the starting and ending coordinates; For multiple orders with the same deduplication identifier, only the data of one order is retained.

4. The real-time analysis and prediction method for online car-hailing capacity according to claim 1, characterized in that: Determining the driver's transport capacity based on the reporting data of the current time slice includes: The reporting data of the current time slice is divided into a target number of continuous time windows, and the reporting data in the time windows are accumulated as the driver's capacity corresponding to the time windows; wherein the duration corresponding to the time window is the same as the time interval between the driver's two reporting of the reporting data.

5. The real-time analysis and prediction method for online car-hailing capacity according to claim 1, characterized in that: The acquisition of order data from the passenger side and reporting data from the driver side includes: Collect order data from the passenger side and store it in the preset basic database; Collect the driver's reporting data and store it in the preset message queue; Obtain the order data from the basic database through the cloud transmission service, and obtain the order data from the message queue through the Flink computing engine, and connect them to the big data real-time warehouse in the form of data stream for storage; The Flink computing engine processes data stored in the big data real-time warehouse in real time and obtains the corresponding honeycomb information to build a data detail layer in the big data real-time warehouse. The constructed data detail layer stores the real-time processed data. The real-time processing includes parsing, filtering, and integration. The data stored in the data detail layer is synchronized to the Doris database through the Flink computing engine, wherein the data synchronized to the Doris database is stored in the form of a data table.

6. The real-time analysis and prediction method for online car-hailing capacity according to claim 1, characterized in that: Also includes: Generate vehicle guidance prompts based on real-time and future capacity matching information of online ride-hailing vehicles; The vehicle guidance prompts include driving prompts for guiding the vehicle to drive and service prompts for guiding the vehicle to change the service level.

7. The real-time analysis and prediction method for online car-hailing capacity according to claim 1, characterized in that: Determining the real-time capacity matching information for online ride-hailing services based on order indicators and driver capacity in the same time slice includes: Determine the matching ratio of online ride-hailing capacity in real time based on order volume, accepted order volume, and driver capacity; Based on the number of non-quickly matched orders, externally quickly matched orders, and internally quickly matched orders, the matching efficiency information of the real-time capacity of online ride-hailing is calculated.

8. The real-time analysis and prediction method for online car-hailing capacity according to claim 7, characterized in that: The matching ratio information includes: supply-demand ratio and order matching rate; wherein the supply-demand ratio is the ratio of the number of orders placed in a time slice to the driver's transportation capacity, and the order matching rate is the ratio of the number of orders received in a time slice to the number of orders placed; The matching efficiency information includes: the proportion of non-quick matches, the proportion of internal quick matches and the proportion of external quick matches; among them, the proportion of non-quick matches is the ratio of the number of non-quick matches to the number of orders placed in the corresponding time window, the proportion of internal quick matches is the ratio of the number of internal quick matches to the number of orders placed in the corresponding time window, and the proportion of external quick matches is the ratio of the number of external quick matches to the number of orders placed in the corresponding time window.

9. A real-time analysis and prediction system for online car-hailing capacity, characterized by: include: The acquisition module is used to obtain order data from the passenger side and reporting data from the driver side; A division module, configured to divide the order data and the reporting point data into continuous time slices based on a preset time length; An indicator calculation module is used to calculate the order volume and order volume based on the order data of the current time slice; divide the order data of the current time slice into a target number of consecutive time windows, and calculate the number of unmatched orders, externally matched orders, and internally matched orders; wherein the unmatched orders are the number of orders whose order placement time and order acceptance or cancellation time are not within the same time window, the externally matched orders are the number of orders whose order placement time and cancellation time are within the same time window, and the internally matched orders are the number of orders whose order placement time and order acceptance time are within the same time window; and determine the driver's transportation capacity based on the reporting data of the current time slice; The capacity matching calculation module is used to determine the real-time capacity matching information of online ride-hailing based on the order indicators and driver capacity of the same time slice; wherein the order indicators include the order volume, the order volume, the non-quickly matched order volume, the externally quickly matched order volume and the internally quickly matched order volume; and based on the order indicators and driver capacity of multiple consecutive time slices or time windows, predict the future capacity matching information of online ride-hailing.

10. A real-time analysis and prediction device for online car-hailing capacity, characterized in that: The device comprises a processor and a memory, wherein the processor is connected to the memory: The processor is configured to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute the real-time analysis and prediction method of online car-hailing capacity as described in any one of claims 1-8.

Images