Online car-hailing route planning method and system based on ARIMA model and SaaS

Abstract

The present invention discloses a route planning method and system for online car-hailing based on ARIMA model and SaaS, and specifically relates to the technical field of online car-hailing management, comprising the following steps: processing road network structure information according to service information and preset processing strategies, obtaining a road network map and collecting historical road condition information and real-time road condition information, then performing preprocessing, constructing an ARIMA model, establishing a time series prediction model, and then inputting the preprocessed real-time information processing set into the constructed model to obtain prediction results and calculate the weight value of each road section in the road network map, obtaining the analysis value of each path by analyzing the path, and finally providing real-time route planning to the online car-hailing driver; the present invention can provide real-time route planning services for online car-hailing drivers, can improve the service quality of picking up passengers and sending passengers, quickly respond to the needs of drivers, and ensure the user experience, thereby improving the efficiency of order completion.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing management, and more specifically, to an online car-hailing route planning method and system based on ARIMA model and SaaS. Background Art

[0002] Online car-hailing is the abbreviation of online taxi booking service. It refers to the business activities of building a service platform based on Internet technology, connecting qualified vehicles and drivers, and providing non-cruising taxi booking services by integrating supply and demand information. Online car-hailing is convenient: users only need to enter the destination and departure time on the mobile phone application, and the system will automatically match the most suitable vehicle. There is no need to wait for a taxi or go to the station, saving time and energy; flexibility: online car-hailing is not restricted by regular buses, and can flexibly choose travel time, location and vehicle type according to their own needs, fully meeting the personalized needs of users; and in most cases, online car-hailing will follow the user's wishes to choose a specific route for driving service, but when the user's wishes are not clearly expressed, the existing path planning system may not fully consider the real-time road conditions, resulting in the provided path being inaccurate or not timely, making the path planning system unable to quickly respond to the driver's needs, and directly affecting the user experience, which is also an unfavorable factor for the development of the platform. Therefore, this paper proposes an online car-hailing path planning method and system based on ARIMA model and SaaS to solve the above problems.

[0003] Invention Project

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] The online car-hailing route planning system based on the ARI MA model and SaaS includes a road network module, an information collection module, a preprocessing module, a model building module, a monitoring module, an analysis module, and a service publishing module;

[0006] The road network module is used to store the road network structure information, and process the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtain the road network map and transmit it to the information collection module and the monitoring module;

[0007] The information collection module is used to collect the historical information of road conditions according to the received road network map, and obtain the historical information set of road conditions after aggregation and transmit it to the preprocessing module;

[0008] The monitoring module is used to collect real-time information on road conditions based on the received road network map, summarize the real-time information set on road conditions and transmit it to the preprocessing module;

[0009] The preprocessing module is used to preprocess the historical information set of road conditions, obtain the historical information processing set and transmit it to the model building module; preprocess the real-time information set of road conditions, obtain the real-time information processing set and transmit it to the model building module;

[0010] The model building module is used to build the ARI MA model based on the historical information processing set, establish a time series prediction model, and then input the real-time information processing set into the built model, and summarize the obtained prediction results and send them to the analysis module;

[0011] The analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the paths according to the weight value of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the smallest analysis value of the path to the service publishing module;

[0012] The service publishing module is used to provide real-time route planning to online car-hailing drivers through the SaaS platform, and to transmit online car-hailing order service information to the road network module through the SaaS platform.

[0013] In a preferred embodiment, the service publishing module transmits the online car-hailing order service information to the road network module through the SaaS platform, which includes pick-up order information and drop-off order information. The pick-up order information includes the current online car-hailing location information and the passenger boarding location information, and the drop-off order information includes the passenger alighting destination location information.

[0014] In a preferred embodiment, the road network module is used to store the road network structure information, and processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtains the road network map and transmits it to the information collection module and the monitoring module, which means:

[0015] The road network module stores road network structure information that integrates road network data from different sources into a unified format. The road network structure information is then processed according to the service information of the service publishing module and the preset processing strategy to obtain a pick-up map and a drop-off map, which together constitute a road network map. The pick-up map and the drop-off map are then sent to the information collection module and the monitoring module, respectively.

[0016] In a preferred embodiment, the information collection module is used to collect the road condition history information according to the received road network map, and obtain the road condition history information set after aggregation and transmit it to the preprocessing module, which means:

[0017] The information collection module collects the historical information of the car pick-up map according to the car pick-up map, and collects the historical information of the send-off map according to the send-off map. The historical information of the car pick-up map and the historical information of the send-off map together constitute the historical information of the road condition. After aggregation, the historical information set of the road condition is obtained and transmitted to the preprocessing module.

[0018] In a preferred embodiment, the monitoring module is used to collect real-time traffic information according to the received road network map, summarize the real-time traffic information set and transmit it to the preprocessing module, which means:

[0019] The monitoring module collects real-time information of the car pick-up map based on the car pick-up map, and collects real-time information of the send-off map based on the send-off map. The real-time information of the car pick-up map and the real-time information of the send-off map together constitute the real-time information of the road condition. After aggregation, the real-time information set of the road condition is obtained and transmitted to the preprocessing module.

[0020] In a preferred embodiment, the model building module is used to build an ARIMA model based on the historical information processing set, establish a time series prediction model, and then input the real-time information processing set into the built model, and summarize the obtained prediction results and transmit them to the analysis module, which means:

[0021] The data of the preset input items and the data acquisition time in the historical information processing set are selected as the input data for model training, and the data of the preset output items in the historical information processing set are selected as the output data for model training. When the prediction performance of the model meets the preset requirements, the ARI MA model is constructed, and then the real-time information processing set is input into the constructed model, and the obtained prediction results are summarized and sent to the analysis module.

[0022] In a preferred embodiment, the analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the analysis value of the smallest path to the service publishing module.

[0023] Set the target road segment number in the road network map to i, then mark the output data of the prediction result as SCi, and then calculate the weight value of the target road segment: Qi is the weight value of the target road section, Zi is the preset standard threshold value of the target road section, and the preset road condition item data of the real-time traffic information set of the target road section after processing is marked as Li, then the traffic value of the target road section is: Ki is the road condition value, m is the total number of road condition items, and fi is the preset ratio value corresponding to the road condition item; calculate the passing value of the target road section, TGi=Qi*Ki, TGi is the passing value;

[0024] The paths in the pick-up map are listed, and then the analysis values ​​of the listed paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all sections on the path. Then the path corresponding to the minimum analysis value is used as the pick-up path and transmitted to the service publishing module;

[0025] The paths in the delivery map are listed, and then the analysis values ​​of the listed paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all sections on the path. Then the path corresponding to the minimum analysis value is used as the delivery path and transmitted to the service publishing module.

[0026] In a preferred embodiment, the online car-hailing route planning method based on the ARIMA model and SaaS includes the following steps:

[0027] Step 1: Process the road network structure information according to the service information and the preset processing strategy to obtain a road network map;

[0028] Step 2: Collect historical traffic information and real-time traffic information according to the road network map to obtain a historical traffic information set and a real-time traffic information set respectively;

[0029] Step 3: Preprocess the historical traffic information set and the real-time traffic information set respectively, and construct the ARIMA model to establish a time series prediction model. Then, the preprocessed real-time information processing set is input into the constructed model to obtain the prediction result.

[0030] Step 4: Calculate the weight value of each road section in the road network map according to the prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path. Finally, provide the real-time path planning to the online car-hailing driver for the path corresponding to the smallest analysis value.

[0031] Technical effects and advantages of the present invention:

[0032] The present invention can provide real-time route planning services for online car-hailing drivers through the collaborative work of components such as the road network module, information collection module, preprocessing module, model building module, monitoring module, analysis module, and service publishing module, including route planning from the location where the order is currently received to the location where the passenger is picked up, and route planning from the location where the passenger is picked up to the delivery location specified by the passenger. This can improve the service quality for picking up passengers and the service quality for dropping off passengers, quickly respond to the needs of drivers, ensure the user experience, improve the efficiency of order completion, and promote the healthy development of the order platform.

[0033] The present invention uses the ARI MA model to perform time series prediction, combines historical traffic information and real-time information, calculates the weight values ​​of different road sections, and uses this to evaluate the cost of each possible path, selects the path with the lowest cost as the recommended route, and can dynamically adjust the road network map according to real-time traffic information to provide new paths for selection. The path planning system based on the SaaS platform facilitates the use of online car-hailing drivers. They can obtain the path planning information recommended by the system through mobile applications or web interfaces, thereby improving driving efficiency and reducing passenger waiting time and driving costs. The present invention provides powerful navigation support for online car-hailing drivers, helping them to choose the best driving route, thereby improving service quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0035] Figure 1 This is a schematic diagram of the online car-hailing route planning system based on the ARIMA model and SaaS in the present invention.

[0036] Figure 2 This is a schematic diagram of the online car-hailing route planning method based on the ARIMA model and SaaS in the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Example 1

[0039] The online car-hailing route planning system based on the ARI MA model and SaaS includes a road network module, an information collection module, a preprocessing module, a model building module, a monitoring module, an analysis module, and a service release module; the online car-hailing route planning system based on the ARI MA model and SaaS is an intelligent transportation solution that comprehensively applies time series analysis, big data processing and optimization algorithms. The system consists of a road network module, an information collection module, a preprocessing module, a model building module, a monitoring module, an analysis module and a service release module. They work together to provide real-time route planning services to online car-hailing drivers, and the real-time route planning service includes route planning from the current location where the order is received to the location where the passenger is picked up, and also includes route planning from the location where the passenger is picked up to the delivery location specified by the passenger, which can improve the service quality of picking up passengers and the service quality of delivering passengers, and also improve the efficiency of order completion, which is also a benign development for the order platform.

[0040] The road network module is used to store road network structure information, and processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtains the road network map and transmits it to the information collection module and the monitoring module; it is responsible for storing and managing basic road network structure data, including streets, highways, turn restrictions, speed limits and other information. It generates customized road network maps based on the service requests received from the service publishing module (such as pick-up orders and delivery orders) and the preset processing strategy. These maps not only reflect the physical structure of the road network, but also contain order-specific road condition information, forming a pick-up map and a drop-off map respectively, and providing them to the information collection module and the monitoring module for use, integrating the road network data from different sources into a unified format for data integration so that other parts of the system can easily access and use them. An electronic map is generated based on the road network data, which can be used by the information collection module to refer to and record traffic flow data, and also provides a visual background of real-time traffic conditions for the monitoring module. In order to assist the analysis module in path calculation, the road network module may need to provide different route selection criteria such as the shortest path, the fastest path, and the path with the most stable road conditions. The shortest path provided by the road network module is the shortest total distance, and the fastest path is the one that takes the least time, but these may not necessarily become decision-making paths. The analysis module is also required to conduct real-time analysis of the path to be more in line with the actual situation. In addition, as the city develops and road conditions change, the road network structure information needs to be updated regularly to maintain the accuracy and timeliness of the information.

[0041] The information collection module is used to collect historical road condition information based on the received road network map, summarize it to obtain a historical road condition information set and transmit it to the preprocessing module; the information collection module uses the map provided by the road network module to locate the specific location of historical information data collection.

[0042] The monitoring module is used to collect real-time traffic information based on the received road network map, summarize it to obtain a real-time traffic information set and transmit it to the preprocessing module; the information collection module uses the map provided by the road network module to locate the specific location of real-time information data collection, and updates the traffic information in real time to provide the latest data for the upcoming journey.

[0043] The preprocessing module is used to preprocess the historical road condition information set, obtain the historical information processing set and transmit it to the model building module; preprocess the real-time road condition information set, obtain the real-time information processing set and transmit it to the model building module; clean, format and standardize the collected historical and real-time road condition information to ensure that the data quality meets the requirements of model training. The above-mentioned processing methods are well known to people in this field and will not be elaborated here. The preprocessed data is sent to the model building module.

[0044] The model building module is used to build the ARIMA model based on the historical information processing set, establish a time series prediction model, and then input the real-time information processing set into the constructed model, and summarize the obtained prediction results and send them to the analysis module; in the model building module, experts use the historical information processing set to determine the optimal parameters of the ARIMA model, and can verify the accuracy of the model through methods such as cross-validation, or other methods. Once the model performance reaches the predetermined standard, the model is used to process the real-time information processing set, and the prediction results are sent to the analysis module.

[0045] The analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the paths according to the weight values ​​of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the smallest analysis value to the service publishing module; the analysis module combines the prediction results generated by the ARIMA model with the road network structure information, calculates the weight values ​​of different road sections, and evaluates the cost of each possible path. By comparing the analysis values ​​of each path, the path with the lowest cost is selected as the recommended route and passed to the service publishing module.

[0046] The service publishing module is used to provide real-time route planning to online car-hailing drivers through the SaaS platform, and to transmit online car-hailing order service information to the road network module through the SaaS platform. The optimal path output by the analysis module is provided to the online car-hailing drivers in real time through the SaaS platform. Drivers can obtain the system-recommended route planning information through mobile applications or web interfaces, thereby improving driving efficiency and reducing passenger waiting time and driving costs.

[0047] The service publishing module transmits the online car-hailing order service information to the road network module through the SaaS platform, which includes the pick-up order information and the drop-off order information. The pick-up order information includes the current online car-hailing location information and the passenger boarding location information, and the drop-off order information includes the passenger alighting destination location information.

[0048] The road network module is used to store road network structure information, and processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtains the road network map and transmits it to the information collection module and the monitoring module, which means: the road network module stores the road network structure information that integrates the road network data from different sources into a unified format, and then processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, respectively obtains the pick-up map and the drop-off map, the pick-up map and the drop-off map together constitute the road network map, and then the pick-up map and the drop-off map are respectively transmitted to the information collection module and the monitoring module, and processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, which means: according to the order service information provided by the service publishing module, such as the passenger boarding location and destination, the road network module needs to dynamically filter out relevant road network information, which may include selecting the road network of a specific area, pre-excluding sections that do not meet the vehicle type or driving rules, etc., and constructs a map specifically for pick-up and drop-off order services based on the screening and calculation results. These maps will highlight recommended routes and may contain additional information, such as traffic light signal timing, recommended driving speed, etc. If a traffic accident, road closure or severe congestion occurs, the preset processing strategy should be able to quickly adjust the road network map and provide new routes for selection. Subsequent information collection modules and monitoring modules can exclude data collection and real-time monitoring of excluded sections, such as sections where traffic accidents, road closures or severe congestion occur, thereby reducing the complexity of the data and processing time.

[0049] The information collection module is used to collect historical road condition information based on the received road network map, and obtain a road condition historical information set after summarizing and transmitting it to the preprocessing module, which means: the information collection module collects the historical information of the car pick-up map based on the car pick-up map, and collects the historical information of the send-off map based on the send-off map. The car pick-up map historical information and the send-off map historical information together constitute the road condition historical information, and obtain a road condition historical information set after summarizing and transmitting it to the preprocessing module; the monitoring module is used to collect real-time road condition information based on the received road network map, and obtain a real-time road condition information set after summarizing and transmitting it to the preprocessing module, which means: the monitoring module collects the real-time car pick-up map information based on the car pick-up map, and collects the real-time send-off map information based on the send-off map. The car pick-up map real-time information and the send-off map real-time information together constitute the real-time road condition information, and obtain a real-time road condition information set after summarizing and transmitting it to the preprocessing module.

[0050] The model building module is used to build the ARIMA model according to the historical information processing set, establish a time series prediction model, and then input the real-time information processing set into the constructed model. The obtained prediction results are summarized and sent to the analysis module, which means: select the data and data acquisition time of the preset input items in the historical information processing set as the input data for model training. These input data may include historical traffic flow, speed, accident reports, etc., use the data of the preset output items in the historical information processing set as the output data for model training, and select the data of the preset output items as the target output for model training. This is usually a road condition indicator in a certain period of time in the future, such as the degree of traffic congestion, the average speed of the road section, etc. When the prediction performance of the model meets the preset requirements, until the performance indicators of the model such as mean square error, absolute percentage error, etc. meet the service standards, then ARI After the MA model is built, the real-time information processing set is input into the built model, and the prediction results are summarized and sent to the analysis module. These data will be input into the trained model to generate predictions for future road conditions. The model building module provides a reliable time series prediction tool for the online car-hailing path planning system. The tool can use historical data to predict future road conditions, thereby helping drivers avoid congestion and improve driving efficiency.

[0051] The analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the smallest analysis value of the path to the service publishing module.

[0052] The analysis module receives the summarized prediction results from the model building module. These results include the possible road conditions of each section in the road network in the future, such as traffic flow, congestion level, etc. The target section number in the road network map is set to i, and the output data of the prediction result is marked as SCi, and then the weight value of the target section is calculated: Qi is the weight value of the target road section, Zi is the preset standard threshold value of the target road section. If the predicted traffic flow of a road section exceeds its standard threshold value, the weight value of the road section will increase, indicating that the road section is more likely to be congested. After the real-time traffic information set of the target road section is processed, the preset traffic item data is marked as Li, and the traffic value of the target road section is: Ki is the road condition value, which is usually based on the processed road condition item data Li and the corresponding preset ratio value fi. This road condition value reflects the actual driving conditions of the current road section. The smaller the road condition value, the greater the satisfaction of the actual driving conditions for the online car-hailing vehicle, which means that the online car-hailing vehicle can pass faster and better. m is the total number of road condition items, and fi is the preset ratio value corresponding to the road condition item. Calculate the passing value of the target road section, TGi=Qi*Ki, TGi is the passing value, and the passing value TGi is an indicator reflecting the traffic efficiency of the road section. It may be a function based on the weight value Qi and the road condition value Ki. The lower the passing value, the higher the traffic efficiency of the road section, and vice versa.

[0053] The paths in the pick-up map are enumerated, and then the analysis values ​​of the enumerated paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all the road sections on the path. Then the path corresponding to the minimum analysis value is used as the pick-up path and transmitted to the service publishing module; the paths in the delivery map are enumerated, and then the analysis values ​​of the enumerated paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all the road sections on the path. Then the path corresponding to the minimum analysis value is used as the delivery path and transmitted to the service publishing module; for each path in the pick-up map and the delivery map, the module will calculate the analysis value of the path, that is, the passing value TGi of all the road sections on the path. The sum of i, this analysis value represents the traffic efficiency of the entire path. The analysis module transmits the optimal pick-up path and drop-off path to the service publishing module, which then provides these path information to the online car-hailing drivers to help them choose the best driving route, thereby improving service quality and efficiency. Among all possible paths, the analysis module will select the path with the smallest analysis value as the optimal path. For the pick-up service, the module will select the path corresponding to the smallest pick-up path analysis value; for the drop-off service, the module will also select the path corresponding to the smallest drop-off path analysis value. The analysis module not only utilizes the predictive ability of the ARI MA model, but also converts these predictions into actually available path planning suggestions, providing powerful navigation support for online car-hailing drivers. The optimal path released to the online car-hailing drivers by the service publishing module is displayed on the road network map.

[0054] Example 2

[0055] The online car-hailing route planning method based on the ARI MA model and SaaS includes the following steps:

[0056] Step 1: Process the road network structure information according to the service information and the preset processing strategy to obtain a road network map;

[0057] Step 2: Collect historical traffic information and real-time traffic information according to the road network map to obtain a historical traffic information set and a real-time traffic information set respectively;

[0058] Step 3: Preprocess the historical traffic information set and the real-time traffic information set respectively, and construct the ARIMA model to establish a time series prediction model. Then, the preprocessed real-time information processing set is input into the constructed model to obtain the prediction result.

[0059] Step 4: Calculate the weight value of each road section in the road network map according to the prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path. Finally, provide the real-time path planning to the online car-hailing driver for the path corresponding to the smallest analysis value.

[0060] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0061] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0062] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0063] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0064] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The online car-hailing route planning system based on ARIMA model and SaaS is characterized by: It includes road network module, information collection module, preprocessing module, model building module, monitoring module, analysis module and service publishing module; The road network module is used to store the road network structure information, and process the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtain the road network map and transmit it to the information collection module and the monitoring module; The information collection module is used to collect the historical information of road conditions according to the received road network map, and obtain the historical information set of road conditions after aggregation and transmit it to the preprocessing module; The monitoring module is used to collect real-time information on road conditions based on the received road network map, summarize the real-time information set on road conditions and transmit it to the preprocessing module; The preprocessing module is used to preprocess the road condition historical information set, obtain the historical information processing set and transmit it to the model building module; Preprocess the real-time traffic information set to obtain a real-time information processing set and transmit it to the model building module; The model building module is used to build the ARIMA model based on the historical information processing set, establish a time series forecasting model, and then input the real-time information processing set into the built model, and summarize the obtained forecast results and send them to the analysis module; The analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the paths according to the weight value of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the smallest analysis value of the path to the service publishing module; The analysis module is used to calculate the weight value of each road section in the road network map according to the summarized prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path, and then transmit the path corresponding to the smallest analysis value of the path to the service publishing module. Set the target road segment number in the road network map to i, then mark the output data of the prediction result as SCi, and then calculate the weight value of the target road segment: , Qi is the weight value of the target road section, Zi is the preset standard threshold value of the target road section, and the preset road condition item data of the real-time traffic information set of the target road section after processing is marked as Li, then the traffic value of the target road section is: , Ki is the road condition value, m is the total number of road condition items, fi is the preset ratio value corresponding to the road condition item; calculate the passing value of the target road section, , TGi is the passing value; The paths in the pick-up map are listed, and then the analysis values ​​of the listed paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all sections on the path. Then the path corresponding to the minimum analysis value is used as the pick-up path and transmitted to the service publishing module; The paths in the delivery map are listed, and then the analysis values ​​of the listed paths are calculated. The analysis value of the path refers to the sum of the passing values ​​TGi of all sections on the path. Then the path corresponding to the minimum analysis value is used as the delivery path and transmitted to the service publishing module; The service publishing module is used to provide real-time route planning to online car-hailing drivers through the SaaS platform, and to transmit online car-hailing order service information to the road network module through the SaaS platform.

2. The online car-hailing route planning system based on ARIMA model and SaaS according to claim 1 is characterized in that: The service publishing module transmits the online car-hailing order service information to the road network module through the SaaS platform, which includes the pick-up order information and the drop-off order information. The pick-up order information includes the current online car-hailing location information and the passenger boarding location information, and the drop-off order information includes the passenger alighting destination location information.

3. The online car-hailing route planning system based on ARIMA model and SaaS according to claim 2 is characterized in that: The road network module is used to store the road network structure information, and processes the road network structure information according to the service information of the service publishing module and the preset processing strategy, obtains the road network map and transmits it to the information collection module and the monitoring module. The road network module stores road network structure information that integrates road network data from different sources into a unified format. The road network structure information is then processed according to the service information of the service publishing module and the preset processing strategy to obtain a pick-up map and a drop-off map, which together constitute a road network map. The pick-up map and the drop-off map are then sent to the information collection module and the monitoring module, respectively.

4. The online car-hailing route planning system based on ARIMA model and SaaS according to claim 3 is characterized in that: The information collection module is used to collect historical road condition information based on the received road network map, summarize the historical road condition information set and transmit it to the preprocessing module. The information collection module collects the historical information of the car pick-up map according to the car pick-up map, and collects the historical information of the send-off map according to the send-off map. The historical information of the car pick-up map and the historical information of the send-off map together constitute the historical information of the road condition. After aggregation, the historical information set of the road condition is obtained and transmitted to the preprocessing module.

5. The online car-hailing route planning system based on ARIMA model and SaaS according to claim 4 is characterized in that: The monitoring module is used to collect real-time traffic information based on the received road network map, summarize the real-time traffic information set and transmit it to the preprocessing module. The monitoring module collects real-time information of the car pick-up map based on the car pick-up map, and collects real-time information of the send-off map based on the send-off map. The real-time information of the car pick-up map and the real-time information of the send-off map together constitute the real-time information of the road condition. After aggregation, the real-time information set of the road condition is obtained and transmitted to the preprocessing module.

6. The online car-hailing route planning system based on ARIMA model and SaaS according to claim 5 is characterized in that: The model building module is used to build the ARIMA model based on the historical information processing set, establish a time series forecasting model, and then input the real-time information processing set into the built model. The forecast results are summarized and sent to the analysis module. The data and data acquisition time of the preset input items in the historical information processing set are selected as the input data for model training, and the data of the preset output items in the historical information processing set are used as the output data for model training. When the prediction performance of the model meets the preset requirements, the ARIMA model is built, and then the real-time information processing set is input into the constructed model, and the obtained prediction results are summarized and sent to the analysis module.

7. A method for an online car-hailing route planning system based on an ARIMA model and SaaS according to any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: Process the road network structure information according to the service information and the preset processing strategy to obtain a road network map; Step 2: Collect historical traffic information and real-time traffic information according to the road network map to obtain a historical traffic information set and a real-time traffic information set respectively; Step 3: Preprocess the historical traffic information set and the real-time traffic information set respectively, and construct the ARIMA model to establish a time series prediction model. Then, the preprocessed real-time information processing set is input into the constructed model to obtain the prediction result. Step 4: Calculate the weight value of each road section in the road network map according to the prediction results, and then analyze the path according to the weight value of each road section in the road network map to obtain the analysis value of each path. Finally, provide the real-time path planning to the online car-hailing driver for the path corresponding to the smallest analysis value.

Images