Multi-tenant online car-hailing order processing method based on passenger preference
By using the decision tree model and three-wheel matching mechanism in the online ride-hailing platform, the problem of difficult to meet the needs of special scenarios in the existing technology is solved, the accuracy and efficiency of matching are improved, and the improvement of the accuracy and efficiency of matching is improved. User experience and cost-effectiveness.
Patent Information
- Application Number
- CN202410949829.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-08
AI Technical Summary
The existing online ride-hailing platform is difficult to meet the personalized needs of passengers in special scenarios, such as elderly people or unwell passengers need comfortable drivers, children need child seats, female passengers need safe drivers in the middle of the night, etc., resulting in the inability to accurately match and meet passengers. Customized requirements.
In the multi-tenant online ride-hailing driver and passenger matching system, passengers enter travel demand information, evaluate the order safety level through the decision tree model, and use the three-wheel matching mechanism to screen out drivers that meet the needs, including based on travel time, location and environment, and driver history Match behaviors and passenger preferences.
Improve user satisfaction and experience, and reduce labor costs and management costs by accurately matching passenger needs and available drivers, ensuring that passengers' personalized needs are met.
Smart Images

Figure CN118917912A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent matching technology, and more specifically, to a method for processing multi-tenant online car-hailing orders based on passenger preferences. Background Art
[0002] With the popularization of mobile Internet and the rise of the sharing economy, under the conditions of market supervision and government policy support, the scale of online car-hailing has developed rapidly, solving various problems in the traditional taxi industry and meeting people's needs for convenient, economical and high-quality travel.
[0003] When passengers use the online ride-hailing platform software to hail a taxi, they can usually only set the departure place, destination, payment method, time of use and other information. However, in some special scenarios, for example, the elderly or passengers in poor health need a more comfortable and stable driver, children need child seats, passengers need to bring pets, and female passengers need to consider their own safety in late night scenarios and hope that the system can match drivers of the same gender. These invisible needs cannot be informed to the online ride-hailing platform, resulting in the inability to meet the personalized needs of passengers. Summary of the invention
[0004] In view of the technical problems existing in the prior art, the present invention provides a multi-tenant online car-hailing order processing method based on passenger preferences to solve the problems raised in the above background technology.
[0005] The technical solution of the present invention to solve the above technical problems is as follows: a multi-tenant online car-hailing order processing method based on passenger preferences, specifically comprising the following steps:
[0006] Step 101: In the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs travel demand information, collects basic demand and customized demand information, and transmits the collected information to the matching module;
[0007] Step 102: In the matching module, the order information transmitted by the order module is received, the safety level of the order is determined by using a decision tree, matching is performed among available drivers according to passenger requirements, and the matching result is returned to the order module;
[0008] Step 103: After receiving the matching result, the order module generates an order and notifies the passenger and driver to determine the final driver-passenger matching relationship.
[0009] In a preferred embodiment, in step 101, in the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs the travel demand information, collects the basic demand and customized demand information, and transmits the collected information to the matching module. The specific steps are as follows:
[0010] Step A1, passenger demand information collection: an order module is set up in the multi-tenant online car-hailing driver-passenger matching system, and passengers use the order module interface to input travel demand information, including basic demand and customized demand information;
[0011] Step A2, information transmission: Generate an order and assign a unique order number based on the demand information entered by the passenger, and push the order information to the matching module.
[0012] In a preferred embodiment, in the information transmission of step A2, the order information is pushed to the matching module, further comprising the following steps:
[0013] Step A201, establishing a data transmission channel: the order module packages the collected information and converts it into a transmittable data structure, and establishes a connection with the matching module through the HTTP protocol for data transmission;
[0014] Step A202: The order module transmits the packaged passenger demand information to the matching module through the established communication channel, uses encryption algorithm technology to protect the data, and stores the data in the database.
[0015] In a preferred embodiment, in step 102, in the matching module, the order information transmitted by the order module is received, a decision tree is used to determine the safety level of the order, a match is performed among available drivers according to the passenger's needs, and the matching result is returned to the order module. The specific steps are as follows:
[0016] Step B1, building a decision tree model: receiving order information transmitted by the order module, including basic and customized needs of passengers, building a decision tree model based on the travel time, order location and surrounding environment of the destination in the order information, and classifying the orders into three safety levels: high, medium and low;
[0017] Step B2: Build a passenger profile based on the passenger's historical order behavior and complaint behavior, and calculate the passenger's preference for different driver services;
[0018] Step B3, matching drivers: matching among available drivers according to the needs of passengers, and finding drivers that meet the needs through a three-round matching mechanism;
[0019] Step B4, generating matching results: the matching results including the selected driver information and estimated arrival time are fed back to the order module through the communication channel of the order module.
[0020] In a preferred embodiment, in the step B1, a decision tree model is constructed according to the travel time, the order location and the surrounding environment of the destination in the order information, and the orders are divided into three safety levels of high, medium and low, further comprising the following steps:
[0021] Step B101, organize the order information transmitted by the order module into a data set, including features and corresponding security level labels; select travel time, order location and surrounding environment of the destination as features from the order information, divide the data set into a training set and a test set, use the training set data to build a decision tree model, adopt the information gain-based division criterion, divide at each node until the stop condition is met, and divide the order into corresponding high, medium and low security levels through the branches of the decision tree. The specific calculation formula is as follows:
[0022]
[0023] Among them, IG is the information gain, S is the data set of the parent node before partitioning, and S i is the data set of the child node after the i-th partition, |S| is the number of samples of the parent node, |S i | is the number of samples of the i-th child node, E(S) is the entropy of the parent node S, E(S i ) is the i-th child node S i Entropy of
[0024] Step B102: Apply the constructed decision tree model to new order data, predict the safety level of the order based on the order information, and return the prediction result to the matching module as one of the bases for matching drivers.
[0025] In a preferred embodiment, in the step B3, matching drivers is performed among available drivers according to the needs of passengers, and a driver who meets the needs is found through a three-round matching mechanism, further comprising the following steps:
[0026] Step B301, first round of matching: according to the passenger demand transmitted by the order module, find the area around the order location, perform the first round of matching according to the driver registration information, filter out the drivers and vehicles that cannot meet the passenger's demands, and select the drivers who meet the passenger's demands as the candidate drivers for the second round of matching;
[0027] Step B302, second round of matching: using the driver's past driving behavior data, define indicators to evaluate the driver's driving level and safety, including average speed, emergency braking frequency, acceleration control, and vehicle stability indicators, normalize these indicators and assign them respective weights, use the weighted sum method to calculate each driver's driving score, and sort each driver's driving score by score as a reference for the third round of matching. The specific calculation formula is as follows:
[0028] Q=ω1×P+ω2×S+ω3×T+ω4×D
[0029] Among them, (ω1, ω2, ω3, ω4) are the weights of each index, satisfying ω1+ω2+ω3+ω4=1, Q is the driving score, P is the average speed index, S is the emergency braking frequency index, T is the acceleration control index, and D is the vehicle stability index;
[0030] Step B303, the third round of matching: A comprehensive evaluation is conducted on the remaining drivers after the second round of matching. Based on the passengers' past preferences for different online car-hailing tenants, the online car-hailing tenant with the strongest passenger preference is selected as the target tenant for this service. Under the target tenant, the driver with the closest pick-up distance is selected from the remaining drivers as the final matching result.
[0031] In a preferred embodiment, in step 103, after receiving the matching result, the order module generates an order and notifies the passenger and the driver to determine the final driver-passenger matching relationship. The specific steps are as follows:
[0032] Step D1, order generation: after receiving the matching result, the order module generates an order according to the matching result, and the order includes the passenger's travel information, the driver's information and the estimated fare;
[0033] Step D2, order information is notified to the passenger: the order module sends a notification to the passenger via SMS or App push. After receiving the notification, the passenger confirms the order and contacts the driver;
[0034] Step D3: Notify the driver of the order information: The order module sends a notification to the successfully matched driver, and the driver can view the order details through the driver-passenger platform;
[0035] Step D4: After receiving the notification, the driver goes to the departure location designated by the passenger to wait for the passenger. After the passenger arrives at the departure location at the scheduled time, he / she contacts the driver and completes the ride. After the driver delivers the passenger to the destination, the order module updates the order status to completed and sends a notification of order completion to the passenger.
[0036] The beneficial effects of the present invention are as follows: in the order module of a multi-tenant online car-hailing driver-passenger matching system, the passenger inputs travel demand information, collects basic demand and customized demand information, and passes the collected information to the matching module; in the matching module, the order information passed by the order module is received, a decision tree is used to determine the safety level of the order, and matching is performed among available drivers according to passenger demand, and the matching result is returned to the order module; after receiving the matching result, the order module generates an order and notifies the passenger and the driver, and determines the final driver-passenger matching relationship. This is a multi-tenant online car-hailing order processing method based on passenger preferences, which improves user satisfaction and experience by matching according to the personalized needs of passengers, and uses intelligent matching algorithms to more accurately match passenger needs and available drivers, improves matching accuracy and efficiency, and reduces labor costs and management costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 is a flow chart of the method of the present invention;
[0038] Figure 2 The order information of the present invention is a data set. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0040] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.
[0041] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.
[0042] Example 1
[0043] This embodiment provides Figure 1 A multi-tenant online car-hailing order processing method based on passenger preferences is shown, which specifically includes the following steps:
[0044] Step 101: In the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs travel demand information, collects basic demand and customized demand information, and transmits the collected information to the matching module;
[0045] Step 102: In the matching module, the order information transmitted by the order module is received, the safety level of the order is determined by using a decision tree, matching is performed among available drivers according to passenger requirements, and the matching result is returned to the order module;
[0046] Step 103: After receiving the matching result, the order module generates an order and notifies the passenger and driver to determine the final driver-passenger matching relationship.
[0047] Preferably, in step 101, in the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs the travel demand information, collects the basic demand and customized demand information, and transmits the collected information to the matching module. The specific steps are as follows:
[0048] Step A1, passenger demand information collection: An order module is set up in the multi-tenant online car-hailing driver-passenger matching system. Passengers use the order module interface to enter travel demand information, including the passenger's starting and ending points, payment method, basic time requirements for the car, whether a child seat is needed, whether to bring pets, and customized demand information on the driver's driving preferences;
[0049] Step A2, information transmission: The preference information entered by the passenger is stored in the database for subsequent use. Based on the demand information entered by the passenger, an order is generated and a unique order number is assigned. The order information is pushed to the matching module, including the order number, passenger travel demand information of departure place, destination, travel time, passenger personal information, and passenger customized demand information.
[0050] Preferably, in the information transmission of step A2, the order information is pushed to the matching module, further comprising the following steps:
[0051] Step A201, establishing a data transmission channel: the order module packages the collected information and converts it into a transmittable data structure, and establishes a connection with the matching module through the HTTP protocol for data transmission;
[0052] Step A202: The order module transmits the packaged passenger demand information to the matching module through the established communication channel, uses encryption algorithms and other technologies to protect the data, and stores the data in the database.
[0053] Preferably, in step 102, in the matching module, the order information transmitted by the order module is received, a decision tree is used to determine the safety level of the order, matching is performed among available drivers according to passenger requirements, and the matching result is returned to the order module. The specific steps are as follows:
[0054] Step B1, building a decision tree model: receiving order information transmitted by the order module, including basic and customized needs of passengers, building a decision tree model based on the travel time, order location and surrounding environment of the destination in the order information, and classifying the orders into three safety levels: high, medium and low;
[0055] Step B2: Passenger profile capability: Build a passenger profile based on the passenger’s historical order behavior and complaint behavior, and obtain the passenger’s preference for different driver services;
[0056] Step B3, matching drivers: matching among available drivers according to the needs of passengers, and finding drivers that meet the needs through a three-round matching mechanism;
[0057] Step B4, generating matching results: the matching results including the selected driver information and estimated arrival time are fed back to the order module through the communication channel of the order module.
[0058] Preferably, in the step B1, a decision tree model is constructed according to the travel time, the order location and the surrounding environment of the destination in the order information, and the orders are divided into three safety levels of high, medium and low, further comprising the following steps:
[0059] Step B101: Figure 2 As shown, the order information passed by the order module is organized into a data set, including features and corresponding safety level labels, the features including whether the travel time is morning, afternoon, or evening; whether the surrounding environment of the order location and the destination is a densely populated area or a remote area; the corresponding safety level labels are high, medium, and low; the travel time, the surrounding environment of the order location, and the destination are selected as features from the order information, the data set is divided into a training set and a test set, the training set data is used to build a decision tree model, and the division criterion based on information gain is adopted to divide each node until the stopping condition is met, and the orders are divided into corresponding high, medium, and low safety levels through the branches of the decision tree;
[0060] Step B102: Apply the constructed decision tree model to new order data, predict the safety level of the order based on the order information, and return the prediction result to the matching module as one of the bases for matching drivers.
[0061] Preferably, in the step B3 of matching drivers, matching is performed among available drivers according to the needs of the passengers, and a driver who meets the needs is found through a three-round matching mechanism, further comprising the following steps:
[0062] Step B301, first round matching: according to the passenger needs transmitted by the order module, find the area around the ordering location, perform the first round matching according to the driver registration information, screen out the drivers and vehicles that cannot meet the passenger's needs, and select the drivers who meet the passenger's needs as the candidate drivers for the second round matching. When the passenger needs a safety seat, only select the driver who can provide a safety seat; if the order is placed by a female passenger in a remote location late at night, screen out the male driver;
[0063] Step B302, second round of matching: using the driver's past driving behavior data, defining indicators to evaluate the driver's driving level and safety, including average speed, emergency braking frequency, acceleration control, and vehicle stability indicators, normalizing these indicators and assigning them respective weights, and using the weighted sum method to calculate each driver's driving score. The higher the score, the more the driver's driving behavior meets the passenger's requirements. The driving score of each driver is sorted according to the score, which serves as a reference for the third round of matching.
[0064] Step B303, the third round of matching: A comprehensive evaluation is conducted on the remaining drivers after the second round of matching. Based on the passengers' past preferences for different online car-hailing tenants, the online car-hailing tenant with the strongest passenger preference is selected as the target tenant for this service. Under the target tenant, the driver with the closest pick-up distance is selected from the remaining drivers as the final matching result.
[0065] Preferably, in step 103, after receiving the matching result, the order module generates an order and notifies the passenger and the driver to determine the final driver-passenger matching relationship. The specific steps are as follows:
[0066] Step D1, order generation: after receiving the matching result, the order module generates an order according to the matching result, and the order includes the passenger's travel information, the driver's information and the estimated fare; the passenger's travel information includes the departure place, destination and travel time; the driver's information includes the driver's name and vehicle information;
[0067] Step D2, order information is notified to the passenger: the order module sends a notification to the passenger via SMS or App push, including the driver's name, license plate number, estimated arrival time, and estimated fare. After receiving the notification, the passenger confirms the order and contacts the driver;
[0068] Step D3, order information notification to the driver: The order module sends a notification to the successfully matched driver, including the passenger's departure location, destination, and estimated arrival time information. The driver can view the order details through the driver-passenger platform;
[0069] Step D4: After receiving the notification, the driver goes to the departure location designated by the passenger to wait for the passenger. After the passenger arrives at the departure location at the scheduled time, he / she contacts the driver and completes the ride. After the driver delivers the passenger to the destination, the order module updates the order status to completed and sends a notification of order completion to the passenger.
[0070] In this embodiment, it should be specifically explained that the driving score of each driver is calculated using the weighted sum method, and the specific calculation formula is as follows:
[0071] Q=ω1×P+ω2×S+ω3×T+ω4×D
[0072] Among them, (ω1, ω2, ω3, ω4) are the weights of each indicator, satisfying ω1+ω2+ω3+ω4=1, Q is the driving score, P is the average speed indicator, S is the emergency braking frequency indicator, T is the acceleration control indicator, and D is the vehicle stability indicator. The weights are selected by experiments and model tuning to obtain the best weight combination.
[0073] In this embodiment, it should be specifically explained that the division criterion based on information gain is adopted to perform division on each node, and the specific calculation formula is as follows: IG is the information gain, which indicates the change in entropy before and after the data set is divided. The greater the information gain, the greater the purity of the data set after the division. S is the data set of the parent node before the division. i is the data set of the child node after the i-th partition, |S| is the number of samples of the parent node, |S i | is the number of samples of the i-th child node, E(S) is the entropy of the parent node S, E(S i ) is the i-th child node S i The entropy of .
[0074] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
[0075] 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.
[0076] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0077] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0079] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0081] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0082] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A multi-tenant online car-hailing order processing method based on passenger preferences, characterized in that: The specific steps include: Step 101: In the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs travel demand information, collects basic demand and customized demand information, and transmits the collected information to the matching module; Step 102: In the matching module, the order information transmitted by the order module is received, the safety level of the order is determined by using a decision tree, matching is performed among available drivers according to passenger requirements, and the matching result is returned to the order module; Step 103: After receiving the matching result, the order module generates an order and notifies the passenger and driver to determine the final driver-passenger matching relationship.
2. A multi-tenant online car-hailing order processing method based on passenger preferences according to claim 1, characterized in that: In step 101, in the order module of the multi-tenant online car-hailing driver-passenger matching system, the passenger inputs the travel demand information, collects the basic demand and customized demand information, and transmits the collected information to the matching module. The specific steps are as follows: Step A1, passenger demand information collection: an order module is set up in the multi-tenant online car-hailing driver-passenger matching system, and passengers use the order module interface to input travel demand information, including basic demand and customized demand information; Step A2, information transmission: Generate an order and assign a unique order number based on the demand information entered by the passenger, and push the order information to the matching module.
3. A multi-tenant online car-hailing order processing method based on passenger preferences according to claim 2, characterized in that: In the information transmission of step A2, the order information is pushed to the matching module, which further includes the following steps: Step A201, establishing a data transmission channel: the order module packages the collected information and converts it into a transmittable data structure, and establishes a connection with the matching module through the HTTP protocol for data transmission; Step A202: The order module transmits the packaged passenger demand information to the matching module through the established communication channel, uses encryption algorithm technology to protect the data, and stores the data in the database.
4. A multi-tenant online car-hailing order processing method based on passenger preference according to claim 1, characterized in that: In step 102, the matching module receives the order information transmitted by the order module, uses a decision tree to determine the safety level of the order, matches the available drivers according to the passenger's needs, and returns the matching result to the order module. The specific steps are as follows: Step B1, building a decision tree model: receiving order information transmitted by the order module, including basic and customized needs of passengers, building a decision tree model based on the travel time, order location and surrounding environment of the destination in the order information, and classifying the orders into three safety levels: high, medium and low; Step B2: Build a passenger profile based on the passenger's historical order behavior and complaint behavior, and calculate the passenger's preference for different driver services; Step B3, matching drivers: matching among available drivers according to the needs of passengers, and finding drivers that meet the needs through a three-round matching mechanism; Step B4, generating matching results: the matching results including the selected driver information and estimated arrival time are fed back to the order module through the communication channel of the order module.
5. A multi-tenant online car-hailing order processing method based on passenger preference according to claim 4, characterized in that: In the step B1, the decision tree model is constructed according to the travel time, the order location and the surrounding environment of the destination in the order information, and the order is divided into three safety levels: high, medium and low. The steps further include: Step B101, organize the order information transmitted by the order module into a data set, including features and corresponding security level labels; select travel time, order location and surrounding environment of the destination as features from the order information, divide the data set into a training set and a test set, use the training set data to build a decision tree model, adopt the information gain-based division criterion, divide at each node until the stop condition is met, and divide the order into corresponding high, medium and low security levels through the branches of the decision tree. The specific calculation formula is as follows: Among them, IG is the information gain, S is the data set of the parent node before partitioning, and S i is the data set of the child node after the i-th partition, |S| is the number of samples of the parent node, |S i | is the number of samples of the i-th child node, E(S) is the entropy of the parent node S, E(S i ) is the i-th child node S i Entropy of Step B102: Apply the constructed decision tree model to new order data, predict the safety level of the order based on the order information, and return the prediction result to the matching module as one of the bases for matching drivers.
6. A multi-tenant online car-hailing order processing method based on passenger preference according to claim 4, characterized in that: In the step B3 of matching drivers, a driver who meets the requirements is found through a three-round matching mechanism, further comprising the following steps: Step B301, first round of matching: according to the passenger demand transmitted by the order module, find the area around the order location, perform the first round of matching according to the driver registration information, filter out the drivers and vehicles that cannot meet the passenger's demands, and select the drivers who meet the passenger's demands as the candidate drivers for the second round of matching; Step B302, second round of matching: using the driver's past driving behavior data, define indicators to evaluate the driver's driving level and safety, including average speed, emergency braking frequency, acceleration control, and vehicle stability indicators, normalize these indicators and assign them respective weights, use the weighted sum method to calculate each driver's driving score, and sort each driver's driving score by score as a reference for the third round of matching. The specific calculation formula is as follows: Q=ω1×P+ω2×S+ω3×T+ω4×D Among them, (ω1, ω2, ω3, ω4) are the weights of each index, satisfying ω1+ω2+ω3+ω4=1, Q is the driving score, P is the average speed index, S is the emergency braking frequency index, T is the acceleration control index, and D is the vehicle stability index; Step B303, the third round of matching: A comprehensive evaluation is conducted on the remaining drivers after the second round of matching. Based on the passengers' past preferences for different online car-hailing tenants, the online car-hailing tenant with the strongest passenger preference is selected as the target tenant for this service. Under the target tenant, the driver with the closest pick-up distance is selected from the remaining drivers as the final matching result.
7. A multi-tenant online car-hailing order processing method based on passenger preference according to claim 1, characterized in that: In step 103, after receiving the matching result, the order module generates an order and notifies the passenger and the driver to determine the final driver-passenger matching relationship. The specific steps are as follows: Step D1, order generation: after receiving the matching result, the order module generates an order according to the matching result, and the order includes the passenger's travel information, the driver's information and the estimated fare; Step D2, order information is notified to the passenger: the order module sends a notification to the passenger via SMS or App push. After receiving the notification, the passenger confirms the order and contacts the driver; Step D3: Notify the driver of the order information: The order module sends a notification to the successfully matched driver, and the driver can view the order details through the driver-passenger platform; Step D4: After receiving the notification, the driver goes to the departure location designated by the passenger to wait for the passenger. After the passenger arrives at the departure location at the scheduled time, he / she contacts the driver and completes the ride. After the driver delivers the passenger to the destination, the order module updates the order status to completed and sends a notification of order completion to the passenger.
