Ride-hailing dispatching methods, devices, computer equipment and storage media

Abstract

This application belongs to the field of transportation big data technology, and relates to a method, apparatus, computer equipment, and storage medium for dispatching ride-hailing orders. The method is applied to a comprehensive ride-hailing service platform and includes: acquiring ride-hailing orders received from various ride-hailing traffic platforms; determining dispatch parameters for each ride-hailing order, including the commission rate corresponding to the ride-hailing traffic platform receiving the order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set; determining a matching score between each candidate driver and the ride-hailing order based on the dispatch parameters; and determining a target driver from the candidate driver set based on the matching score of each candidate driver, and dispatching the ride-hailing order to the target driver. This application enables resource sharing and rational scheduling among multiple ride-hailing traffic platforms, thereby improving the utilization rate of ride-hailing resources.

Description

Technical Field

[0001] This application relates to the field of transportation big data technology, and in particular to a ride-hailing dispatching method, device, computer equipment and storage medium. Background Technology

[0002] With the development of the ride-hailing industry, numerous ride-hailing traffic platforms have emerged in the market. Each platform operates independently, using its own dispatching methods, resulting in a significant waste of ride-hailing resources. Therefore, how to achieve resource sharing and rational scheduling among multiple ride-hailing traffic platforms to improve the utilization rate of ride-hailing resources is a pressing technical problem that needs to be solved. Summary of the Invention

[0003] In order to achieve resource sharing and rational scheduling among multiple ride-hailing traffic platforms, thereby improving the utilization rate of ride-hailing resources, this application provides a ride-hailing dispatching method, device, computer equipment, and storage medium.

[0004] The above-mentioned objective of this application is achieved through the following technical solution:

[0005] Obtain ride-hailing orders received by various ride-hailing traffic platforms;

[0006] The dispatch parameters for the ride-hailing order are determined. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, as well as the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order.

[0007] Based on the dispatch parameters, determine the matching score between each candidate driver and the ride-hailing order;

[0008] Based on the matching score of each candidate driver, a target driver is determined from the set of candidate drivers, and the ride-hailing order is assigned to the target driver.

[0009] By adopting the above technical solutions, resource sharing and rational scheduling among multiple ride-hailing traffic platforms have been achieved, thereby improving the utilization rate of ride-hailing resources.

[0010] In one example, this application can be further configured as follows: determining the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters includes:

[0011] The matching score between each candidate driver and the ride-hailing order is determined using a trained score model based on the dispatch parameters.

[0012] By adopting the above technical solution, the matching score can be determined quickly and accurately based on the dispatch parameters.

[0013] In one example, this application can be further configured such that the trained score model includes a trained improved Transformer model.

[0014] By adopting the above technical solutions, the trained improved Transformer model has higher accuracy in matching score calculation applications.

[0015] In one example, this application can be further configured as follows: determining the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters using a trained score model includes:

[0016] The dispatch parameters are input into the trained improved Transformer model. Through each attention head of the trained improved Transformer model, the commission rate, the driver-passenger distance and the estimated fare per unit price corresponding to each candidate driver are weighted and adjusted respectively to obtain the first weight and first representation coefficient of the commission rate, the second weight and second representation coefficient of the driver-passenger distance corresponding to each candidate driver, and the third weight and third representation coefficient of the estimated fare per unit price corresponding to each candidate driver.

[0017] Based on the first weight and the first representation coefficient, the second weight and the second representation coefficient, and the third weight and the third representation coefficient, the commission rate, the driver-passenger distance, and the estimated fare per unit price corresponding to each candidate driver are weighted and summed to obtain the matching score between each candidate driver and the ride-hailing order.

[0018] By adopting the above technical solution, the dispatch parameters can be adjusted and weighted using the trained improved Transformer model. This allows the weights and representation coefficients of different indicators in the dispatch parameters to be adjusted to appropriate proportions, thereby improving the accuracy and reliability of the matching score.

[0019] In one example, this application can be further configured such that determining the target driver from the set of candidate drivers based on the matching score of each candidate driver includes:

[0020] The matching scores of each candidate driver are compared to obtain the comparison results;

[0021] Based on the comparison results, the target driver is determined from the candidate driver set.

[0022] By adopting the above technical solutions, the flexibility, fairness, and reliability of ride-hailing order dispatch can be improved.

[0023] In one example, this application can be further configured such that determining the dispatch parameters for the ride-hailing order includes:

[0024] The dispatch parameters for the ride-hailing order are determined based on the detailed information carried in the ride-hailing order.

[0025] By adopting the above technical solutions, comprehensive and accurate data can be provided for ride-hailing order dispatch.

[0026] In one example, this application can be further configured as follows: before obtaining the ride-hailing orders received by each ride-hailing traffic platform, it also includes:

[0027] An improved Transformer model is obtained by enhancing the attention mechanism of the preset Transformer model.

[0028] The improved Transformer model is trained based on the historical dispatch parameters of preset historical ride-hailing orders and their corresponding historical matching scores to obtain the trained improved Transformer model.

[0029] By adopting the above technical solutions, training speed and accuracy can be improved, thereby enhancing the performance and adaptability of the trained improved Transformer model in adjusting dispatch parameter weights.

[0030] The second objective of this invention is achieved through the following technical solution:

[0031] A ride-hailing dispatching device, the ride-hailing dispatching device comprising:

[0032] The acquisition module is used to acquire ride-hailing orders received by various ride-hailing traffic platforms;

[0033] The first determining module is used to determine the dispatch parameters of the ride-hailing order. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order.

[0034] The second determining module is used to determine the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters;

[0035] The dispatch module is used to determine the target driver from the set of candidate drivers based on the matching score of each candidate driver, and dispatch the ride-hailing order to the target driver.

[0036] The above-mentioned objective three of this application is achieved through the following technical solution:

[0037] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described ride-hailing dispatch method.

[0038] The fourth objective of this application is achieved through the following technical solution:

[0039] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described ride-hailing dispatch method.

[0040] In summary, this application includes the following beneficial technical effects:

[0041] By using dispatch parameters, the integrated ride-hailing service platform uniformly assigns suitable drivers to ride-hailing orders from multiple ride-hailing traffic platforms. This achieves efficient integration of ride-hailing resources from multiple platforms and rational allocation of ride-hailing orders, ensuring rapid response to orders. It improves the flexibility, fairness, reliability, and efficiency of dispatching ride-hailing orders from multiple platforms. This strengthens the sharing and rational scheduling of ride-hailing resources, thereby increasing their utilization rate. This not only helps optimize ride-hailing service quality to improve passenger and driver satisfaction but also enhances the operational level of the integrated ride-hailing service platform, ensuring its operational revenue. Attached Figure Description

[0042] Figure 1 A flowchart illustrating a ride-hailing order dispatching method provided in this application embodiment;

[0043] Figure 2 This is another flowchart illustrating a ride-hailing order dispatching method provided in an embodiment of this application;

[0044] Figure 3 An example diagram illustrating an application scenario of a ride-hailing order dispatching method provided in this application embodiment;

[0045] Figure 4 A schematic block diagram of a ride-hailing dispatching device provided in this application embodiment;

[0046] Figure 5 This is a schematic block diagram of the structure of a computer device according to an embodiment of this application.

[0047] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0050] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] This application provides a ride-hailing order dispatching method, apparatus, computer equipment, and storage medium. The ride-hailing order dispatching method involves a ride-hailing integrated service platform uniformly assigning suitable drivers to ride-hailing orders from multiple ride-hailing traffic platforms based on dispatching parameters. This achieves efficient integration of ride-hailing resources from multiple platforms and rational allocation of ride-hailing orders, ensuring rapid response to orders. It improves the flexibility, fairness, reliability, and efficiency of dispatching ride-hailing orders from multiple platforms. This strengthens the sharing and rational scheduling of ride-hailing resources, thereby increasing their utilization rate. This not only helps optimize ride-hailing service quality to improve passenger and driver satisfaction but also enhances the operational level of the ride-hailing integrated service platform, ensuring its operational revenue.

[0053] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0054] Please refer to Figure 1 , Figure 1This is a flowchart illustrating a ride-hailing dispatch method provided as an embodiment of this application. This ride-hailing dispatch method is primarily applied to computer equipment, such as PCs (Personal Computers) or servers, and other terminal devices with data processing capabilities.

[0055] The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and data analysis platforms.

[0056] like Figure 1 As shown, the ride-hailing dispatch method includes steps S101 to S104.

[0057] Step S101: Obtain ride-hailing orders received by various ride-hailing traffic platforms.

[0058] The computer equipment houses the integrated ride-hailing service platform. This platform integrates ride-hailing resources from multiple ride-hailing traffic platforms, enabling unified scheduling and monitoring of ride-hailing orders received from these platforms. These platforms can be ride-hailing apps (such as Didi Chuxing or Gaode Maps) or ride-hailing mini-programs (such as Meituan or WeChat).

[0059] Ride-hailing integrated service platforms can obtain ride-hailing orders received by various ride-hailing traffic platforms in real time through interfaces connected to ride-hailing traffic platforms.

[0060] Step S102: Determine the dispatch parameters for ride-hailing orders. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, as well as the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order.

[0061] For any ride-hailing order originating from various ride-hailing traffic platforms, the ride-hailing integrated service platform must first determine the order dispatch parameters. These parameters include, but are not limited to, the commission rate corresponding to the ride-hailing traffic platform receiving the order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set for the order. It can be understood that the commission rate refers to the percentage of profit that the ride-hailing integrated service platform can offer to the ride-hailing traffic platform receiving the order.

[0062] In one embodiment, the dispatch parameters for a ride-hailing order can be determined based on the detailed information carried in the ride-hailing order.

[0063] The detailed information carried by ride-hailing orders mainly includes the source identifier of the ride-hailing order, order number, passenger information, pick-up point and pick-up destination.

[0064] For example, the source identifier can be extracted from the details information, matched with a preset database, and a pre-stored ride-hailing traffic platform identifier that matches the source identifier can be found in the preset database. Based on the mapping relationship between the pre-stored ride-hailing traffic platform identifier and the pre-stored commission rate in the preset database, the pre-stored commission rate corresponding to the pre-stored ride-hailing traffic platform identifier that matches the source identifier can be determined, and the determined pre-stored commission rate can be used as the commission rate corresponding to the ride-hailing traffic platform for the ride-hailing order.

[0065] Understandably, the default database has good maintainability and scalability, and can be updated according to actual needs.

[0066] For example, the pick-up point can be extracted from the details information, and candidate drivers can be determined based on the distance between the pick-up point and the driver. For instance, all drivers within a 3-kilometer radius of the pick-up point who are not currently assigned a ride can be identified as candidate drivers, forming a candidate driver set. The actual distance between the location of each candidate driver in the candidate driver set and the pick-up point (defined as driver-passenger distance) can then be determined.

[0067] For example, the origin and destination can be extracted from the details of the ride, and the mileage of the ride-hailing order can be calculated based on the origin and destination. The estimated fare for each candidate driver in the candidate driver set can also be determined based on the driver-passenger distance for each candidate driver. Therefore, based on the estimated fare for each candidate driver and the mileage, the estimated fare per unit for each candidate driver in the candidate driver set can be determined.

[0068] This provides a comprehensive and accurate basis for the allocation of ride-hailing orders.

[0069] Step S103: Determine the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters.

[0070] Then, based on the dispatch parameters, the matching score between each candidate driver in the candidate driver set and the ride-hailing order is determined.

[0071] In one embodiment, in order to determine a more accurate matching score, step S103 may be to determine the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters using a trained score model.

[0072] By analyzing the dispatch parameters using a trained score model, the matching score between each candidate driver and a ride-hailing order in the candidate driver set can be quickly determined.

[0073] In one embodiment, the trained score model includes a trained improved Transformer model.

[0074] like Figure 2 As shown, before step S101, steps S105 to S106 are included.

[0075] Step S105: Enhance the attention mechanism of the preset Transformer model to obtain an improved Transformer model.

[0076] The Transformer model is an advanced neural network model for natural language processing tasks. The Transformer model includes multiple attention heads and multi-layer neural networks.

[0077] Since the Transformer model relies entirely on the attention mechanism of each attention head to compute the representation of its input and output, the original attention mechanism of each attention head of the Transformer model is enhanced to obtain an improved Transformer model.

[0078] Step S106: Based on the historical dispatch parameters of preset historical ride-hailing orders and their corresponding historical matching scores, train the improved Transformer model to obtain the trained improved Transformer model.

[0079] The improved Transformer model with enhanced attention can be trained based on the historical dispatch parameters of preset historical ride-hailing orders and their corresponding historical matching scores.

[0080] Specifically, historical dispatch parameters can be input into the improved Transformer model. This enhances the attention mechanism of each attention head in the improved Transformer model, allowing for weight adjustment and training of the historical dispatch parameters. This yields the importance of historical commission rates, historical driver-passenger distances, and historical fare rates among different attention heads. Based on this importance, weights and representation coefficients are generated for historical commission rates, historical driver-passenger distances, and historical fare rates. The weights for historical commission rates, historical driver-passenger distances, and historical fare rates are all normalized using a softmax function. In other words, historical commission rates... The higher the commission rate, the smaller the representation coefficient of the historical commission rate. The weights and representation coefficients corresponding to the historical commission rates are multiplied to obtain the weighted value corresponding to the historical commission rate; the weights and representation coefficients corresponding to the historical driver-passenger distance are multiplied to obtain the weighted value corresponding to the historical driver-passenger distance; and the weights and representation coefficients corresponding to the historical fare unit price are multiplied to obtain the weighted value corresponding to the historical fare unit price. The summation of these weighted values ​​yields the predicted comprehensive weight. The predicted comprehensive weight is then processed using the activation function (such as sigmoid or softmax) of the MLP (Multilayer Perceptron) of the Transformer model to obtain the predicted matching score for historical ride-hailing orders. Finally, based on the loss between the predicted matching score and the historical matching score, the parameters of the improved Transformer model are iteratively updated until the number of iterations reaches a preset threshold, resulting in a trained improved Transformer model.

[0081] It should be noted that the sum of the weights corresponding to the historical commission rate, the historical driver-passenger distance, and the historical fee unit price is equal to 1.

[0082] The enhanced attention mechanism of the improved Transformer model can effectively gather the attention of historical dispatch parameters and train them, thereby improving training speed and accuracy, and enhancing the performance and adaptability of the trained improved Transformer model in adjusting dispatch parameter weights.

[0083] Understandably, historical dispatch parameters can also include historical metrics such as driver ratings, order volume, and / or order completion volume. Therefore, when training the attention-enhanced improved Transformer model, corresponding weights and representation coefficients can be generated for these other historical metrics to obtain their weighted values. This weighted value is then added to the summation calculation, ensuring that the overall prediction weight encompasses the weighted values ​​of these historical metrics. Consequently, the predicted matching score considers the importance of these other historical metrics.

[0084] In this way, the weights of the dispatch parameters for ride-hailing orders can be adjusted and weighted summed using the trained improved Transformer model, thereby determining the matching score between each candidate driver and the ride-hailing order in the candidate driver set.

[0085] In one embodiment, determining the matching score between each candidate driver and a ride-hailing order based on dispatch parameters using a trained score model can be achieved by inputting the dispatch parameters into a trained improved Transformer model. Each attention head of the trained improved Transformer model is used to adjust the weights of the commission rate, the driver-passenger distance, and the estimated fare per unit for each candidate driver, resulting in a first weight and a first representation coefficient for the commission rate, a second weight and a second representation coefficient for the driver-passenger distance, and a third weight and a third representation coefficient for the estimated fare per unit for each candidate driver. Based on the first weight and the first representation coefficient, the second weight and the second representation coefficient, and the third weight and the third representation coefficient, a weighted sum is performed on the commission rate, the driver-passenger distance, and the estimated fare per unit for each candidate driver to obtain the matching score between each candidate driver and the ride-hailing order.

[0086] Specifically, the commission rate, the driver-passenger distance for each candidate driver, and the estimated fare per unit are input into the trained improved Transformer model. This allows the enhanced attention mechanism of each attention head in the improved Transformer model to adjust the weights of the dispatch parameters, resulting in the first weight and first representation coefficient of the commission rate, the second weight and second representation coefficient of the driver-passenger distance for each candidate driver, and the third weight and third representation coefficient of the estimated fare per unit for each candidate driver. All three weights are normalized using a softmax function. Multiplying the first weight and first representation coefficient of the commission rate yields the commission rate ratio... The first weighted value is obtained by multiplying the second weight and the second representation coefficient of the driver-passenger distance for each candidate driver, and the third weight and the third representation coefficient of the estimated fare per unit price for each candidate driver are multiplied to obtain the third weighted value of the estimated fare per unit price for each candidate driver. The first weighted value is then summed with the second weighted value of the driver-passenger distance and the third weighted value of the estimated fare per unit price for each candidate driver to obtain the comprehensive weighted value of each candidate driver. Finally, the comprehensive weighted value of each candidate driver is processed by the activation function of the MLP (Multilayer Perceptron) of the improved Transformer model to output the matching score of each candidate driver and the ride-hailing order.

[0087] For example, if the first weight of the commission rate is w1 and the first representation coefficient is R1, the second weight of the driver-passenger distance for any candidate driver is w2 and the second representation coefficient is R2, and the third weight of the estimated fare per unit price is w3 and the third representation coefficient is R3, then the overall weight R of the candidate driver is:

[0088] R = R1w1 + R2w2 + R3w3, where w1 + w2 + w3 = 1.

[0089] It should be noted that the higher the commission rate, the smaller the first representation coefficient corresponding to the commission rate.

[0090] Understandably, if the dispatch parameters for ride-hailing orders also include other indicators (such as the candidate driver's rating, order volume, etc.), then the candidate driver's overall weight R = R1w1 + R2w2 + R3w3 + ... + R n w n Among them, R1, R2, ..., R n This represents the coefficients corresponding to the n indicators in the dispatch parameters, w1, w2, ..., w n This represents the weights of the n indicators in the dispatch parameters, where w1 + w2 + ... + w n =1.

[0091] In this way, by adjusting and weighting the dispatch parameters using the trained improved Transformer model, the weights and representation coefficients of different indicators in the dispatch parameters are adjusted to an appropriate ratio, thereby improving the accuracy and reliability of the matching score.

[0092] Step S104: Based on the matching score of each candidate driver, determine the target driver from the candidate driver set and assign the ride-hailing order to the target driver.

[0093] Furthermore, the target driver is selected from the candidate driver set based on the matching score of each candidate driver in the candidate driver set.

[0094] In one embodiment, step S104 may be to compare the matching scores of each candidate driver to obtain the comparison results; and to determine the target driver from the candidate driver set based on the comparison results.

[0095] For example, the matching score of each candidate driver in the candidate driver set with the ride-hailing order can be compared, and the candidate driver with the highest matching score can be selected as the target driver. Alternatively, a candidate driver can be randomly selected from the top M candidate drivers with the highest matching scores, where the value of N can be flexibly set according to actual needs.

[0096] Ultimately, ride-hailing orders are assigned to target drivers. This improves the flexibility, fairness, and reliability of ride-hailing order dispatch.

[0097] like Figure 3 As shown, Figure 3 This is an example diagram illustrating an application scenario. To better understand the above embodiments, it is combined with... Figure 3 Examples of application scenarios are as follows:

[0098] The ride-hailing integrated service platform obtains ride-hailing orders received by platforms such as Didi Chuxing, Meituan Dache, and Gaode Dache in real time through interfaces connected to these platforms. Taking ride-hailing orders received by Didi Chuxing as an example, the platform determines the dispatch parameters for that order. These parameters include Didi Chuxing's commission rate, the driver-passenger distance, and the estimated fare per unit for each candidate driver in the candidate driver set. A trained, improved Transformer model is used to adjust and weight these dispatch parameters, resulting in a comprehensive weight for each candidate driver. Based on this comprehensive weight, a matching score is calculated for each candidate driver and the ride-hailing order. Finally, based on each candidate driver's matching score, a target driver is selected from the candidate driver set for the ride-hailing order, and the order is assigned to that driver. This achieves the rational scheduling of ride-hailing orders originating from Didi Chuxing.

[0099] The ride-hailing order dispatching method provided in the above embodiments involves the ride-hailing integrated service platform acquiring ride-hailing orders received by various ride-hailing traffic platforms; determining dispatching parameters for the ride-hailing orders, including the commission rate corresponding to the ride-hailing traffic platform receiving the ride-hailing order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order; determining a matching score between each candidate driver and the ride-hailing order based on the dispatching parameters; and determining a target driver from the candidate driver set based on the matching score of each candidate driver, and dispatching the ride-hailing order to the target driver. By using dispatch parameters, the integrated ride-hailing service platform uniformly assigns suitable drivers to ride-hailing orders from multiple ride-hailing traffic platforms. This achieves efficient integration of ride-hailing resources from multiple platforms and rational allocation of ride-hailing orders, ensuring rapid response to orders. It improves the flexibility, fairness, reliability, and efficiency of dispatching ride-hailing orders from multiple platforms. This strengthens the sharing and rational scheduling of ride-hailing resources, thereby increasing their utilization rate. This not only helps optimize ride-hailing service quality to improve passenger and driver satisfaction but also enhances the operational level of the integrated ride-hailing service platform, ensuring its operational revenue.

[0100] Please refer to point 4. Figure 4 This is a schematic block diagram of a ride-hailing dispatch device provided in an embodiment of this application.

[0101] like Figure 4 As shown, the ride-hailing dispatching device 400 includes: an acquisition module 401, a first determination module 402, a second determination module 403, and a dispatching module 404.

[0102] The acquisition module 401 is used to acquire ride-hailing orders received by various ride-hailing traffic platforms;

[0103] The first determining module 402 is used to determine the dispatch parameters of the ride-hailing order. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order.

[0104] The second determining module 403 is used to determine the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters;

[0105] The dispatch module 404 is used to determine the target driver from the set of candidate drivers based on the matching score of each candidate driver, and dispatch the ride-hailing order to the target driver.

[0106] The apparatus provided in the above embodiments can be implemented as a computer program, which can be used in, for example... Figure 5 It runs on the computer device shown.

[0107] Please see Figure 5 , Figure 5 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application.

[0108] like Figure 5 As shown, the computer device 500 includes a processor 502, a memory 503, and a communication interface 504 connected via a system bus 501. The memory may include a non-volatile storage medium and internal memory.

[0109] Non-volatile storage media can store operating systems and computer programs. These computer programs include program instructions that, when executed, cause the processor to perform any ride-hailing dispatch method.

[0110] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0111] Internal memory provides an environment for the execution of computer programs in non-volatile storage media. When the computer program is executed by the processor, it enables the processor to execute any ride-hailing dispatch method.

[0112] This communication interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0113] It should be understood that a processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a processor or any conventional processor.

[0114] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps:

[0115] Obtain ride-hailing orders received by various ride-hailing traffic platforms;

[0116] The dispatch parameters for the ride-hailing order are determined. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, as well as the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order.

[0117] Based on the dispatch parameters, determine the matching score between each candidate driver and the ride-hailing order;

[0118] Based on the matching score of each candidate driver, a target driver is determined from the set of candidate drivers, and the ride-hailing order is assigned to the target driver.

[0119] In one embodiment, when the processor implements the step of determining the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters, it is configured to:

[0120] The matching score between each candidate driver and the ride-hailing order is determined using a trained score model based on the dispatch parameters.

[0121] In one embodiment, the trained score model includes a trained improved Transformer model.

[0122] In one embodiment, when the processor implements the process of determining the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters using the trained score model, it is configured to:

[0123] The dispatch parameters are input into the trained improved Transformer model. Through each attention head of the trained improved Transformer model, the commission rate, the driver-passenger distance and the estimated fare per unit price corresponding to each candidate driver are weighted and adjusted respectively to obtain the first weight and first representation coefficient of the commission rate, the second weight and second representation coefficient of the driver-passenger distance corresponding to each candidate driver, and the third weight and third representation coefficient of the estimated fare per unit price corresponding to each candidate driver.

[0124] Based on the first weight and the first representation coefficient, the second weight and the second representation coefficient, and the third weight and the third representation coefficient, the commission rate, the driver-passenger distance, and the estimated fare per unit price corresponding to each candidate driver are weighted and summed to obtain the matching score between each candidate driver and the ride-hailing order.

[0125] In one embodiment, when the processor implements the step of determining a target driver from the set of candidate drivers based on the matching score of each candidate driver, it is configured to:

[0126] The matching scores of each candidate driver are compared to obtain the comparison results;

[0127] Based on the comparison results, the target driver is determined from the candidate driver set.

[0128] In one embodiment, when the processor implements the dispatch parameters for determining the ride-hailing order, it is configured to:

[0129] The dispatch parameters for the ride-hailing order are determined based on the detailed information carried in the ride-hailing order.

[0130] In one embodiment, before the processor implements the acquisition of ride-hailing orders received from various ride-hailing traffic platforms, it is further configured to implement:

[0131] An improved Transformer model is obtained by enhancing the attention mechanism of the preset Transformer model.

[0132] The improved Transformer model is trained based on the historical dispatch parameters of preset historical ride-hailing orders and their corresponding historical matching scores to obtain the trained improved Transformer model.

[0133] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can refer to various embodiments of the ride-hailing dispatch method of this application.

[0134] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0135] Furthermore, the computer-readable storage medium may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application required for a function, etc.; and the data storage area may store data created based on the use of blockchain nodes, etc.

[0136] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0137] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0138] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for dispatching ride-hailing orders, characterized in that, The method is applied to a ride-hailing integrated service platform, and the method includes: Obtain ride-hailing orders received by various ride-hailing traffic platforms; Before obtaining ride-hailing orders received from various ride-hailing traffic platforms, the process also includes: An improved Transformer model is obtained by enhancing the attention mechanism of the preset Transformer model. The improved Transformer model is trained based on the historical dispatch parameters of the preset historical ride-hailing orders and their corresponding historical matching scores to obtain the trained improved Transformer model. The dispatch parameters for the ride-hailing order are determined. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, as well as the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order. Based on the dispatch parameters, determine the matching score between each candidate driver and the ride-hailing order; Based on the matching score of each candidate driver, a target driver is determined from the set of candidate drivers, and the ride-hailing order is assigned to the target driver; Using the trained improved Transformer model, the matching score between each candidate driver and the ride-hailing order is determined based on the dispatch parameters, including: The dispatch parameters are input into the trained improved Transformer model. Through each attention head of the trained improved Transformer model, the commission rate, the driver-passenger distance and the estimated fare per unit price corresponding to each candidate driver are weighted and adjusted respectively to obtain the first weight and first representation coefficient of the commission rate, the second weight and second representation coefficient of the driver-passenger distance corresponding to each candidate driver, and the third weight and third representation coefficient of the estimated fare per unit price corresponding to each candidate driver. Based on the first weight and the first representation coefficient, the second weight and the second representation coefficient, and the third weight and the third representation coefficient, the commission rate, the driver-passenger distance, and the estimated fare per unit price corresponding to each candidate driver are weighted and summed to obtain the matching score between each candidate driver and the ride-hailing order.

2. The ride-hailing dispatching method according to claim 1, characterized in that, The step of determining the target driver from the set of candidate drivers based on the matching score of each candidate driver includes: The matching scores of each candidate driver are compared to obtain the comparison results; Based on the comparison results, the target driver is determined from the candidate driver set.

3. The ride-hailing dispatching method according to claim 1, characterized in that, The process of determining the dispatch parameters for the ride-hailing order includes: The dispatch parameters for the ride-hailing order are determined based on the detailed information carried in the ride-hailing order.

4. A ride-hailing dispatching device, characterized in that, The ride-hailing dispatching device includes: The acquisition module is used to acquire ride-hailing orders received by various ride-hailing traffic platforms; Prior to the acquisition module, it includes: An improved Transformer model is obtained by enhancing the attention mechanism of the preset Transformer model. The improved Transformer model is trained based on the historical dispatch parameters of the preset historical ride-hailing orders and their corresponding historical matching scores to obtain the trained improved Transformer model. The first determining module is used to determine the dispatch parameters of the ride-hailing order. The dispatch parameters include the commission rate corresponding to the ride-hailing traffic platform that receives the ride-hailing order, and the driver-passenger distance and estimated fare per unit for each candidate driver in the candidate driver set of the ride-hailing order. The second determining module is used to determine the matching score between each candidate driver and the ride-hailing order based on the dispatch parameters; The dispatch module is used to determine the target driver from the set of candidate drivers based on the matching score of each candidate driver, and dispatch the ride-hailing order to the target driver; The second determining module includes: The dispatch parameters are input into the trained improved Transformer model. Through each attention head of the trained improved Transformer model, the commission rate, the driver-passenger distance and the estimated fare per unit price corresponding to each candidate driver are weighted and adjusted respectively to obtain the first weight and first representation coefficient of the commission rate, the second weight and second representation coefficient of the driver-passenger distance corresponding to each candidate driver, and the third weight and third representation coefficient of the estimated fare per unit price corresponding to each candidate driver. Based on the first weight and the first representation coefficient, the second weight and the second representation coefficient, and the third weight and the third representation coefficient, the commission rate, the driver-passenger distance, and the estimated fare per unit price corresponding to each candidate driver are weighted and summed to obtain the matching score between each candidate driver and the ride-hailing order.

5. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the ride-hailing dispatch method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the ride-hailing dispatch method as described in any one of claims 1 to 3.

Images