Methods, devices, equipment, media and procedures for recommending return cargo sources and return routes

Abstract

A method, device, equipment, medium and program for recommending return cargo sources and return routes, belonging to the field of computer technology. The method includes: in response to the determination that the target freight vehicle has a return intention, obtaining the vehicle information and the target freight vehicle status of the target freight vehicle; determining the target freight vehicle's transportable cargo source from the cargo source pool according to the vehicle information and the target freight vehicle status; in response to detecting the target freight vehicle user's selection operation for the target cargo source from the transportable cargo sources, generating the target freight vehicle's return route according to the cargo source information and vehicle information corresponding to the target cargo source; sending the return route and cargo source information to the target freight vehicle user. The present application establishes a return cargo source matching mechanism, which can accurately match reverse cargo sources for drivers, shorten the matching cycle, realize vehicle scheduling and cargo source allocation, and reduce the overall cargo transportation cost and driver return cost.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular to a method, apparatus, device, computer-readable medium, and computer program product for recommending return cargo sources and return routes. Background Art

[0002] After a freight vehicle transports a load of goods to a destination, if it returns empty-handed, it not only wastes vehicle resources, but also has to bear fixed costs such as fuel and tolls. However, carrying return cargo can effectively share these costs, improve transportation efficiency, and reduce transportation costs.

[0003] In the prior art, when a freight vehicle driver searches for cargo sources on an online freight platform, the online freight platform will calculate the driver's preferences based on the customer's historical orders, browsing history, vehicle model and other information, and then recommend cargo sources. The cargo push method is mostly through recommendations based on the customer's previous records or the driver's own search.

[0004] However, when the above method is used to recommend return cargo sources and return routes, the following technical problems often occur:

[0005] First, the existing online freight method only considers the cargo source for one trip, and there is no recommendation logic specifically for the return cargo source scenario. The return cargo source can generally only be searched by the driver himself. There are many types of cargo sources and they are distributed in a messy manner. Different types of transport vehicles can carry different cargoes, which greatly increases the difficulty of searching. It is difficult to find high-quality cargo sources that match the return route, resulting in empty trips for freight vehicles on the return trip, high return costs, and low efficiency.

[0006] Second, existing cargo recommendation methods often only recommend matching cargo based on the routes of freight vehicles, which often results in the cargo being unable to be transported because the cargo does not match the vehicle model, or the cargo is damaged after transportation.

[0007] Third, the existing route recommendation methods often ignore freight demand and only support route recommendations for points A and B. There is a lack of route recommendation methods that can take into account both return routes and return freight routes. In addition, the existing route recommendation methods often take a long time and the results are not accurate enough.

[0008] The prior art has disclosed a variety of methods to solve the above problems. For example, the Chinese patent application with publication number CN114548881A discloses a freight order matching method, system, device and storage medium to provide freight orders for return freight vehicles to improve the efficiency of freight order processing and reduce the costs of logistics companies, cargo owners and manufacturing companies.

[0009] Although the existing technology represented by the above patents has improved the efficiency of freight order processing, it still cannot solve the three technical problems mentioned above. Therefore, it is urgent to develop a new method for recommending return cargo sources and return routes to solve the current defects and shortcomings. Summary of the invention

[0010] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0011] Some embodiments of the present application propose a method, apparatus, device, computer-readable medium and program product for recommending return cargo sources and return routes to at least partially solve the technical problems mentioned in the above background technology section.

[0012] In a first aspect, some embodiments of the present application provide a method for recommending return cargo sources and return routes, the method comprising: in response to determining that a target freight vehicle has a return intention, obtaining vehicle information and a status of the target freight vehicle; determining the cargo that the target freight vehicle can transport from a cargo pool based on the vehicle information and the status of the target freight vehicle; in response to detecting a selection operation of a target freight vehicle user for the target cargo from the cargo that can be transported, generating a return route for the target freight vehicle based on the cargo information and the vehicle information corresponding to the target cargo; and sending the return route and the cargo information to the target freight vehicle user.

[0013] In a second aspect, some embodiments of the present application provide a device for recommending a return cargo source and a return route, the device comprising: an acquisition unit, configured to acquire vehicle information and a status of the target freight vehicle in response to determining that the target freight vehicle has a return intention; a determination unit, configured to determine the transportable cargo source of the target freight vehicle from a cargo source pool based on the vehicle information and the status of the target freight vehicle; a generation unit, configured to generate a return route for the target freight vehicle based on the cargo source information and the vehicle information corresponding to the target cargo source in response to detecting a selection operation of the target freight vehicle user for the target cargo source from the transportable cargo sources; and a sending unit, configured to send the return route and the cargo source information to the target freight vehicle user.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by one or more processors, the one or more processors implement a method as described in any implementation method in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0016] In a fifth aspect, some embodiments of the present application provide a computer program product, including a computer program, which implements the method described in any implementation manner in the above-mentioned first aspect when executed by a processor.

[0017] One of the above-mentioned embodiments of the present application has the following beneficial effects: when it is determined that the target freight vehicle has the intention to return, the vehicle information and the status of the target freight vehicle are obtained, and then the transportable cargo source is determined according to the above-mentioned vehicle information and the above-mentioned status of the target freight vehicle. After that, when the target freight vehicle user selects the target cargo source, the return route of the above-mentioned target freight vehicle is generated. Finally, the above-mentioned return route and the above-mentioned cargo source information are sent to the above-mentioned target freight vehicle user, thereby establishing a return cargo source matching mechanism, which can accurately match the reverse cargo source for the driver, shorten the matching cycle, realize vehicle scheduling and cargo source allocation, and reduce the overall cargo transportation cost and the driver's return cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0019] Figure 1 is a flow chart of some embodiments of the method for recommending return cargo sources and return routes according to the present application;

[0020] Figure 2 It is a schematic diagram of the structure of some embodiments of the return cargo source and return route recommendation device according to the present application;

[0021] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0022] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0023] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0028] refer to Figure 1 , shows a process 100 of some embodiments of the method for recommending return cargo sources and return routes according to the present application. The method for recommending return cargo sources and return routes includes the following steps:

[0029] Step 101, in response to determining that a target freight vehicle has a return intention, obtaining vehicle information and a target freight vehicle status of the target freight vehicle.

[0030] In some embodiments, in response to determining that the target freight vehicle has a return intention, the execution entity of the return cargo source and return route recommendation method (such as an electronic device) can obtain the vehicle information and status of the above-mentioned target freight vehicle.

[0031] It should be noted that the above-mentioned electronic device can be hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0032] It should be pointed out that the vehicle information and the status of the target freight vehicle can be transmitted to the above-mentioned execution entity through wired or wireless connection. For some freight vehicles equipped with GPS signal collection and vehicle loading status monitoring, the corresponding status information can be automatically collected and transmitted to the above-mentioned electronic equipment. For ordinary freight vehicles that do not have corresponding collection equipment, the status input device can also be input through keyboard, mouse, voice or touch screen, and then transmitted to the above-mentioned electronic equipment through wired or wireless connection. The above-mentioned wired connection method includes, for example, wired interconnection of devices, or vehicle bus system, etc. The above-mentioned wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0033] As an example, the execution subject may obtain the state of the target freight vehicle through a detection device pre-installed in the target freight vehicle. As another example, the execution subject may also monitor the state of the target freight vehicle through an electronic device of a user of the target freight vehicle.

[0034] Here, the above-mentioned vehicle information generally refers to vehicle-related information, which may include the following: vehicle model, cargo preference, route preference, order acceptance habits, vehicle fuel consumption, route closure rate, number of orders accepted, GPS online rate, evaluation score, current freight route, pick-up time, estimated return time, whether return cargo is needed, whether return cargo is available, return starting point, return end point, etc.

[0035] The above-mentioned target freight vehicle status generally refers to the status information of the above-mentioned target freight vehicle, which may include the following contents: vehicle position, vehicle speed, vehicle direction, vehicle acceleration, vehicle maximum speed, vehicle traveled distance, vehicle driving stability, etc.

[0036] Specifically, the execution entity may interact with the user of the target freight vehicle to determine whether the target freight vehicle has the intention to return.

[0037] Step 102, determining the cargo source that can be transported by the target freight vehicle from a cargo source pool according to the vehicle information and the status of the target freight vehicle.

[0038] In some embodiments, the execution entity (eg, an electronic device) may determine the available cargo source of the target freight vehicle from a cargo source pool based on the vehicle information and the status of the target freight vehicle.

[0039] Specifically, the cargo pool generally refers to a data list that summarizes the cargo sources that need to be entrusted for transportation. The cargo pool may be obtained by collecting cargo source information. Each cargo source information stored in the cargo pool includes cargo information, the starting point of the freight, and the destination of the freight. The transportable cargo sources generally refer to the cargo sources that match the target freight vehicles.

[0040] As an example, the above-mentioned execution entity can pre-establish a relationship table between cargo types and vehicle models, and obtain the cargo types that match the target freight vehicle by consulting the relationship table between cargo types and vehicle models, and filter out all cargo sources that match the vehicle model of the target freight vehicle from the cargo source pool as transportable cargo sources.

[0041] As another example, the execution entity may also select, according to the status of the target freight vehicle, cargo sources whose distance from the departure point and / or destination of the target freight vehicle does not exceed a preset threshold from the cargo source pool as transportable cargo sources.

[0042] Step 103, in response to detecting that the user of the target freight vehicle has selected the target source of cargo from the above-mentioned transportable sources of cargo, a return route of the above-mentioned target freight vehicle is generated according to the source of cargo information corresponding to the above-mentioned target source of cargo and the above-mentioned vehicle information.

[0043] In some embodiments, in response to detecting a selection operation of a target freight vehicle user on a target source of cargo from the above-mentioned transportable sources of cargo, the above-mentioned execution entity may generate a return route for the above-mentioned target freight vehicle based on the source of cargo information corresponding to the above-mentioned target source of cargo and the above-mentioned vehicle information.

[0044] Here, the target cargo source generally refers to the cargo source selected by the user of the target freight vehicle. As an example, the target cargo source may be the cargo source selected by the user to browse, or the cargo source selected by the user to transport.

[0045] Specifically, the execution entity may display the transportable cargo sources on an electronic device of a target freight vehicle user, and the target freight vehicle user may select a target cargo source from the transportable cargo sources displayed on the electronic device.

[0046] As an example, the above-mentioned execution entity can generate a return route for the target freight vehicle based on the freight starting point and freight end point in the above-mentioned cargo information and the return starting point and return end point in the vehicle information, so that when the above-mentioned target freight vehicle returns along the above-mentioned return route, it can complete the transportation task of the above-mentioned target cargo.

[0047] In some optional implementation methods of some embodiments, the above-mentioned execution entity can determine the freight starting point and the freight end point based on the above-mentioned cargo source information; determine the return starting point and the return end point of the above-mentioned target freight vehicle based on the above-mentioned vehicle information; input the above-mentioned freight starting point, freight end point, return starting point and return end point as input vectors into a pre-trained route planning model to obtain the return route of the above-mentioned target freight vehicle, wherein the above-mentioned return route includes the freight starting point, freight end point, return starting point and return end point.

[0048] Here, the route planning model is usually used to characterize the correspondence between the input vector and the return route. As an example, the route planning model can be a correspondence table prepared by researchers based on a large amount of data. As another example, the route planning model can also be a neural network model trained with a sample input vector as input and a sample return route corresponding to the sample input vector as the expected output, such as a graph neural network.

[0049] In some optional implementations of some embodiments, the route planning model is obtained by training the initial model using a graph neural network as an initial model, a sample input vector as an input, and a sample return route corresponding to the sample input vector as an output, wherein the route planning model is composed of an input layer, a neighborhood feature aggregation module, a hidden layer, a feature fusion layer, and an output layer, and the neighborhood feature aggregation module adopts the following function:

[0050] ,in, represents the node representation of the l+1th layer, represents the j-node representation of the l-th layer; represents the neighbor set of node i; represents the weight matrix of the lth layer; represents the bias term of the lth layer; represents the activation function; represents the distance between neighbor nodes j; Indicates the distance between node i and neighbor node j The weighting function for the calculation is determined according to the following formula:

[0051] ,in, and Represents a hyperparameter.

[0052] Here, the neighborhood feature aggregation module is used to integrate the information of neighboring nodes of the current node. The neighborhood feature aggregation module adopts a custom distance weighting function: .

[0053] Taking the historical vehicle dispatch data of the inventor's unit as a sample, the above route planning model and the ordinary graph neural network model were trained respectively. It was found that after adding the above neighborhood feature aggregation module, the route planning model has the following improvements compared with the ordinary graph neural network:

[0054] Enhanced feature richness: By aggregating information from neighboring nodes, the model can obtain more comprehensive features, significantly improving the ability to express features, and improving accuracy by 10%-15%.

[0055] Improved robustness: Reduced reliance on a single node, reduced the impact of noise and outliers, and made the model more robust to changes in input data. The accuracy of the validation set increased by 5%-10%.

[0056] Improved adaptability: This module enables the model to dynamically adjust feature weights based on different input data, thereby performing better under diverse input conditions. Improved adaptability by 3%-8%.

[0057] Improved convergence speed: Since the aggregation process improves the effectiveness of features, the model learns important features faster during training, thereby accelerating convergence. The number of training iterations is reduced by about 20%-30%.

[0058] After the neighborhood feature aggregation module adopts the above custom distance weighting function, the route planning model achieves the following results:

[0059] Distance sensitivity: The custom distance weighting function can dynamically adjust the weights according to the distance between nodes, so that close neighbors have a greater impact on feature aggregation and distant neighbors have less impact. This dynamic adjustment improves the model's sensitivity to local information.

[0060] Improve learning efficiency: By focusing on nodes that are closer, the network can focus on important features more quickly, improving learning efficiency. The convergence speed of the model during training can be increased by 10%-20%.

[0061] Enhanced model performance: More accurate distance weighting can improve the performance of the model on complex data sets, especially in non-uniformly distributed data, and the output accuracy is expected to increase by 5%-15%.

[0062] Optimize aggregation results: By using a custom distance weighting function to strengthen the focus on neighboring nodes, the aggregation results are more representative, the overall model performance stability is enhanced, and the accuracy of the validation set may increase by 3%-10%.

[0063] In some optional implementations of some embodiments, the route planning model includes at least two hidden layers, a memory update formula is set between the at least two hidden layers, and the at least two hidden layers retain and transmit information through the memory update formula, and the memory update formula is set to: , where γ represents the memory weight, ranging from 0<γ<1; represents the node representation of the lth layer; Represents the node representation of the l+1th layer.

[0064] By adding the memory update formula, the model can retain historical information and help the model capture long-term dependencies.

[0065] In some optional implementations of some embodiments, an attention weight formula is provided in the neighborhood feature aggregation module, and the attention weight formula is used to adjust the influence of neighboring nodes. The attention weight formula is set to: ,in, represents the representation of node j at layer l; represents the node representation of the l+1th layer; Represents the importance score of the neighbor node, which is determined by the following formula:

[0066] , represents the representation of node i; represents the representation of neighbor node j; represents the neighbor set of node i; represents the similarity measure between node i and its neighbor node j; represents the similarity measure between node i and its neighbor node k; represents the representation of neighbor node k.

[0067] By adding the attention weight formula, the model can focus on the important parts of the input features and enhance the expressiveness of the model.

[0068] Specifically, the structure of the route planning model can be set as follows:

[0069] The number of nodes in the input layer: 8 (corresponding to the x-coordinate and y-coordinate of the return starting point, the x-coordinate and y-coordinate of the return destination, the x-coordinate and y-coordinate of the freight starting point, and the x-coordinate and y-coordinate of the freight destination); the number of hidden layers: 3 layers, the first layer: 128 nodes; the second layer: 64 nodes; the third layer: 32 nodes, the hidden layer can use ReLU as the activation function, and the connection relationship between the layers can be set as follows:

[0070] Input layer to the first hidden layer: The 8 nodes of the input layer are fully connected to the 128 nodes of the first hidden layer. By weight Passed to each first hidden layer node .

[0071] From the first hidden layer to the second hidden layer: The 128 nodes of the first hidden layer are fully connected to the 64 nodes of the second hidden layer. By weight Passed to each second hidden layer node .

[0072] From the second hidden layer to the third hidden layer: The 64 nodes in the second hidden layer are fully connected to the 32 nodes in the third hidden layer. By weight Passed to each third hidden layer node .

[0073] From the third hidden layer to the output layer: The 32 nodes in the third hidden layer are fully connected to the n nodes in the output layer. By weight Passed to each output layer node .

[0074] Neighborhood feature aggregation module: set in each hidden layer, using the following custom distance weighted function for aggregation: For each node in layer l+1, its feature representation is obtained by aggregating its neighbor nodes information to be updated.

[0075] Feature fusion layer: Connected after each hidden layer, the following formula is used to combine the outputs of different layers for weighted fusion:

[0076] ,in, represents the fusion weight, represents the node representation after fusion, Represents the node representation of the kth layer.

[0077] Memory update formula: A memory update formula is set between each hidden layer to retain and transfer information through the memory update formula:

[0078] ,γ: memory weight, the range is 0<γ<1, : The node representation of the lth layer, : Node representation of the l+1th layer.

[0079] Attention mechanism: In the neighborhood aggregation module, attention weights are used to adjust the influence of neighbor nodes:

[0080] ,in, represents the representation of node i, represents the representation of neighbor node j, represents the neighbor set of node i, Represents the similarity measure between node i and its neighbor node j (such as dot product); represents the similarity measure between node i and its neighbor node k (such as dot product); represents the representation of neighbor node k.

[0081] Output layer: Number of nodes: n (output key points or coordinates of the planned route), a linear activation function can be used.

[0082] The route planning model with the above structure has the following effects: Improved accuracy and adaptability of path planning, especially in complex and dynamic environments. Enhanced model stability, improved training and convergence efficiency. Optimized feature learning and expression capabilities, making the model perform better in different situations. Reduced overfitting risk, improved model generalization ability.

[0083] Step 104, sending the return route and the cargo source information to the target freight vehicle user.

[0084] In some embodiments, the execution entity may send the return route and the cargo source information to the target freight vehicle user.

[0085] In some optional implementations of some embodiments, the execution entity may determine the cargo source score in the cargo source pool according to the vehicle information, the target freight vehicle status and the following formula:

[0086] ,

[0087] in, represents the matching degree between vehicle i and cargo source j; Represents the distance between the starting point of vehicle i and the starting point of cargo source j, based on the state of the target freight vehicle Sure; Indicates the maximum distance between the vehicle departure point and the cargo source departure point, used for normalization; represents the customer ratings of vehicle i and source j; Represents the maximum value of all customer ratings, used for normalization; represents the time sensitivity of source j; Indicates the state of the target freight vehicle Determined vehicle condition score; Represents the velocity component of the vehicle on the X-axis; Represents the velocity component of the vehicle on the Y axis; represents the distance between the destination of vehicle i and the destination of cargo source j; Indicates the maximum distance between the vehicle destination and the cargo source destination; The weight of the starting point distance is used to measure the impact of the starting point distance on the matching degree; Indicates the weight of the customer rating, which is used to consider the customer's satisfaction with the source of goods; A weight indicating time sensitivity, used to indicate the urgency of the supply; The weight of the vehicle status is used to indicate the impact of the importance of the vehicle status on the cargo; The weights of the direction angle and distance adjustment are used to represent the impact of the vehicle's directionality on the cargo; The weight of the destination distance is used to measure the impact of the destination distance on the matching degree;

[0088] It indicates the influence of vehicle status score and vehicle speed on matching degree, which is determined by the following formula:

[0089] ,

[0090] in, Represents the adjustment factor, which is used to emphasize the effect of speed on matching; Indicates the vehicle status score; Represents the adjustment function related to direction angle and distance, determined according to the following formula:

[0091] ,

[0092] in, represents the ideal direction of cargo source j from the starting point to the destination; the state of the target freight vehicle , determined according to the following formula:

[0093] ,in, Indicates the position coordinate of the vehicle on the X-axis; Indicates the position coordinate of the vehicle on the Y axis; Indicates the direction angle of the vehicle;

[0094] The cargo corresponding to the cargo score that meets the preset conditions will be regarded as the transportable cargo.

[0095] Here, the vehicle status score Can be based on the target freight vehicle status Determine, as an example, the vehicle status score above It can be determined based on a preset correspondence table between the target freight vehicle state and the vehicle state score. As another example, the vehicle state score It can also be determined based on a functional relationship between the preset target freight vehicle state and the vehicle state score. For example, assuming that the distance between vehicle i and cargo source j is relatively close, and the vehicle speed is relatively fast and the direction angle is relatively close to the direction of the cargo source, then the vehicle state score A higher rating may be given.

[0096] Specifically, the weights in the above formula , The matching evaluation criteria can be flexibly adjusted according to different scenarios to meet different needs.

[0097] Specifically, some parameters in the above formula can be obtained from the Internet by crawling a web crawler, etc. Some parameters in the above formula can also be predetermined by researchers or business review organizations based on a large amount of sample data.

[0098] The above formula takes into account multiple dimensions, including distance, customer rating, time sensitivity, vehicle status, etc., to more comprehensively reflect the matching degree between vehicles and cargo sources. The impact of vehicle status on matching is added to enhance the perception of transportation requirements of different cargo sources.

[0099] By adopting the above formula, the matching results between vehicles and cargo sources have been significantly optimized. The use of multi-dimensional comprehensive scoring not only improves accuracy and flexibility, but also enhances response speed and vehicle status perception. Considering the distance between the starting point and the end point makes the matching more comprehensive and goal-oriented, making freight scheduling more efficient, and better meeting freight demand and freight vehicle transportation needs. It also makes the matching degree between the carrier cargo source and the freight vehicle higher, reducing the occurrence of detours, empty driving, mismatch between cargo source and vehicle type, and damage caused by fragile transported goods.

[0100] Different from the overall (multi-vehicle) scheduling solution in the prior art, the present application adopts the above-mentioned method to realize the scheduling of a single vehicle and the allocation of cargo for a single vehicle, which is more flexible and applicable to more extreme scenarios.

[0101] One of the above-mentioned embodiments of the present application has the following beneficial effects: when it is determined that the target freight vehicle has the intention to return, the vehicle information and the status of the target freight vehicle are obtained, and then the transportable cargo source is determined according to the above-mentioned vehicle information and the above-mentioned status of the target freight vehicle. After that, when the target freight vehicle user selects the target cargo source, the return route of the above-mentioned target freight vehicle is generated. Finally, the above-mentioned return route and the above-mentioned cargo source information are sent to the above-mentioned target freight vehicle user, thereby establishing a return cargo source matching mechanism, which can accurately match the reverse cargo source for the driver, shorten the matching cycle, realize the scheduling of a single vehicle and the cargo source allocation for a single vehicle, and reduce the overall cargo transportation cost and the driver's return cost.

[0102] Further references Figure 2 As an implementation of the methods shown in the above figures, the present application provides some embodiments of a return cargo source and return route recommendation device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0103] like Figure 2 As shown, some embodiments of the return cargo source and return route recommendation device 200 include: an acquisition unit 201, a determination unit 202, a generation unit 203 and a sending unit 204. The acquisition unit 201 is configured to acquire the vehicle information and the target freight vehicle status of the target freight vehicle in response to the determination that the target freight vehicle has a return intention; the determination unit 202 is configured to determine the cargo source that can be carried by the target freight vehicle from the cargo source pool according to the vehicle information and the target freight vehicle status, specifically including the following steps: determining the cargo source score in the cargo source pool according to the vehicle information, the target freight vehicle status and the following formula:

[0104] ,

[0105] in, Indicates the matching degree between vehicle i and cargo source j; Represents the distance between the starting point of vehicle i and the starting point of cargo source j, based on the state of the target freight vehicle Sure; Indicates the maximum distance between the vehicle departure point and the cargo source departure point, used for normalization; represents the customer ratings of vehicle i and source j; Represents the maximum value of all customer ratings, used for normalization; represents the time sensitivity of source j; Indicates the state of the target freight vehicle Determined vehicle condition score; Represents the velocity component of the vehicle on the X-axis; Represents the velocity component of the vehicle on the Y axis; represents the distance between the destination of vehicle i and the destination of cargo source j; Indicates the maximum distance between the vehicle destination and the cargo source destination; The weight of the starting point distance is used to measure the impact of the starting point distance on the matching degree; Indicates the weight of the customer rating, which is used to consider the customer's satisfaction with the source of goods; A weight indicating time sensitivity, used to indicate the urgency of the supply; The weight of the vehicle status is used to indicate the impact of the importance of the vehicle status on the cargo; The weights of the direction angle and distance adjustment are used to represent the impact of the vehicle's directionality on the cargo; The weight of the destination distance is used to measure the impact of the destination distance on the matching degree; It indicates the influence of vehicle status score and vehicle speed on matching degree, which is determined by the following formula: ,in, Represents the adjustment factor, which is used to emphasize the effect of speed on matching; Indicates the vehicle status score; Represents the adjustment function related to direction angle and distance, determined according to the following formula: ,in, represents the ideal direction of cargo source j from the starting point to the destination; the state of the target freight vehicle , determined according to the following formula: ,in, Indicates the position coordinate of the vehicle on the X-axis; Indicates the position coordinate of the vehicle on the Y axis; Indicates the direction angle of the vehicle; the cargo corresponding to the cargo score that meets the preset conditions is used as the transportable cargo source; the generating unit 203 is configured to respond to detecting the target cargo vehicle user's selection operation for the target cargo from the above-mentioned transportable cargo sources, and generate a return route for the above-mentioned target cargo vehicle according to the cargo source information corresponding to the above-mentioned target cargo source and the above-mentioned vehicle information; the sending unit 204 is configured to send the above-mentioned return route and the above-mentioned cargo source information to the above-mentioned target cargo vehicle user.

[0106] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.

[0107] One of the above-mentioned embodiments of the present application has the following beneficial effects: when it is determined that the target freight vehicle has the intention to return, the vehicle information and the status of the target freight vehicle are obtained, and then the transportable cargo source is determined according to the above-mentioned vehicle information and the above-mentioned status of the target freight vehicle. After that, when the target freight vehicle user selects the target cargo source, the return route of the above-mentioned target freight vehicle is generated. Finally, the above-mentioned return route and the above-mentioned cargo source information are sent to the above-mentioned target freight vehicle user, thereby establishing a return cargo source matching mechanism, which can accurately match the reverse cargo source for the driver, shorten the matching cycle, realize vehicle scheduling and cargo source allocation, and reduce the overall cargo transportation cost and the driver's return cost.

[0108] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device that executes the method for recommending return cargo sources and return routes) 300 that is suitable for implementing some embodiments of the present application. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0109] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0110] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0111] In particular, according to some embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present application are executed.

[0112] It should be noted that the computer-readable medium described above in some embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0113] In some embodiments of the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0114] Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0115] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0116] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to the determination that the target freight vehicle has a return intention, obtain the vehicle information and the target freight vehicle status of the target freight vehicle; determine the cargo source that the target freight vehicle can transport from the cargo source pool according to the vehicle information and the target freight vehicle status; in response to detecting the target freight vehicle user's selection operation for the target cargo source from the cargo source that can be transported, generate the return route of the target freight vehicle according to the cargo source information corresponding to the target cargo source and the vehicle information; send the return route and the cargo source information to the target freight vehicle user.

[0117] Computer program code for performing the operations of some embodiments of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0118] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] The units described in some embodiments of the present application may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a determination unit, a generation unit, and a sending unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the acquisition unit may also be described as "a unit for acquiring vehicle information and target freight vehicle status of the target freight vehicle in response to a determination that the target freight vehicle has a return intention".

[0120] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0121] Some embodiments of the present application also provide a computer program product, including a computer program, which implements any of the above-mentioned return cargo source and return route recommendation methods when executed by a processor.

[0122] The above description is only some preferred embodiments of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present application is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present application to form a technical solution.

Claims

1. A method for recommending return cargo sources and return routes, characterized in that: include: In response to determining that the target freight vehicle has a return intention, acquiring vehicle information of the target freight vehicle and a state of the target freight vehicle; Determine the cargo source that can be carried by the target freight vehicle from the cargo source pool according to the vehicle information and the status of the target freight vehicle, specifically including the following steps: The cargo source score in the cargo source pool is determined based on the vehicle information, the target freight vehicle status, and the following formula: ， in, Indicates the matching degree between vehicle i and cargo source j; Represents the distance between the starting point of vehicle i and the starting point of cargo source j, based on the state of the target freight vehicle Sure; Indicates the maximum distance between the vehicle departure point and the cargo source departure point, used for normalization; represents the customer ratings of vehicle i and source j; Represents the maximum value of all customer ratings, used for normalization; represents the time sensitivity of source j; Indicates the state of the target freight vehicle Determined vehicle condition score; Represents the velocity component of the vehicle on the X-axis; Represents the velocity component of the vehicle on the Y axis; represents the distance between the destination of vehicle i and the destination of cargo source j; Indicates the maximum distance between the vehicle destination and the cargo source destination; The weight of the starting point distance is used to measure the impact of the starting point distance on the matching degree; Indicates the weight of the customer rating, which is used to consider the customer's satisfaction with the source of goods; A weight indicating time sensitivity, used to indicate the urgency of the supply; The weight of the vehicle status is used to indicate the impact of the importance of the vehicle status on the cargo; The weights of the direction angle and distance adjustment are used to represent the impact of the vehicle's directionality on the cargo; The weight of the destination distance is used to measure the impact of the destination distance on the matching degree; It indicates the influence of vehicle status score and vehicle speed on matching degree, which is determined by the following formula: ， in, Represents the adjustment factor, which is used to emphasize the effect of speed on matching; Indicates the vehicle status score; Represents the adjustment function related to direction angle and distance, determined according to the following formula: ， Where β represents the adjustment coefficient of the adjustment function related to the direction angle and distance; Indicates the direction angle of the vehicle; represents the ideal direction of cargo source j from the starting point to the destination; the state of the target freight vehicle , determined according to the following formula: ,in, Indicates the position coordinate of the vehicle on the X-axis; Indicates the position coordinate of the vehicle on the Y axis; The cargo sources corresponding to the cargo source scores that meet the preset conditions are regarded as the transportable cargo sources; In response to detecting a selection operation of a target freight vehicle user for a target source of cargo from available sources of cargo, generating a return route of the target freight vehicle according to cargo source information and vehicle information corresponding to the target source of cargo; The return route and cargo source information are sent to the target freight vehicle users.

2. The method for recommending return cargo sources and return routes according to claim 1, characterized in that: Generate a return route for the target freight vehicle based on the cargo source information and vehicle information corresponding to the target cargo source, including: Determine the freight starting point and freight destination based on the cargo source information; Determine the return starting point and return destination of the target freight vehicle according to the vehicle information; The freight starting point, the freight destination, the return starting point and the return destination are input as input vectors into a pre-trained route planning model to obtain a return route of the target freight vehicle, wherein the return route includes the freight starting point, the freight destination, the return starting point and the return destination.

3. The method for recommending return cargo sources and return routes according to claim 2, characterized in that: The route planning model is obtained by training the initial model with a graph neural network as the initial model, a sample input vector as the input, and a sample return route corresponding to the sample input vector as the output. The route planning model consists of an input layer, a neighborhood feature aggregation module, a hidden layer, a feature fusion layer, and an output layer. The neighborhood feature aggregation module is set in the hidden layer, and the neighborhood feature aggregation module uses the following function: ,in, represents the node representation of the l+1th layer; represents the neighbor set of node i; represents the representation of node j at layer l; represents the weight matrix of the lth layer; represents the bias term of the lth layer; represents the activation function; Represents the distance between node i and its neighbor node j; Indicates the distance between node i and neighbor node j The weighting function for the calculation.

4. The method for recommending return cargo sources and return routes according to claim 3, characterized in that: The route planning model includes at least two hidden layers, a memory update formula is set between at least two hidden layers, and at least two hidden layers retain and transmit information through the memory update formula. The memory update formula is set as: , where γ represents the memory weight, ranging from 0<γ<1; represents the node representation of the lth layer; Represents the node representation of the l+1th layer.

5. The method for recommending return cargo sources and return routes according to claim 3, characterized in that: The attention weight formula is set in the neighborhood feature aggregation module. The attention weight formula is used to adjust the influence of neighbor nodes. The attention weight formula is set as: ,in, represents the representation of node j at layer l; represents the node representation of the l+1th layer; Represents neighbor nodes The importance score is determined according to the following formula: , represents the representation of node i; represents the representation of neighbor node j; represents the neighbor set of node i; represents the similarity measure between node i and its neighbor node j; represents the similarity measure between node i and its neighbor node k; represents the representation of neighbor node k.

6. A device for recommending return cargo sources and return routes, characterized in that: The return cargo source and return route recommendation device comprises: an acquisition unit configured to acquire vehicle information of the target freight vehicle and a state of the target freight vehicle in response to a determination that the target freight vehicle has a return trip intention; The determination unit is configured to determine the available cargo source of the target freight vehicle from the cargo source pool according to the vehicle information and the state of the target freight vehicle, and specifically includes the following steps: The cargo source score in the cargo source pool is determined based on the vehicle information, the target freight vehicle status, and the following formula: ， in, represents the matching degree between vehicle i and cargo source j; Represents the distance between the starting point of vehicle i and the starting point of cargo source j, based on the state of the target freight vehicle Sure; Indicates the maximum distance between the vehicle departure point and the cargo source departure point, used for normalization; represents the customer ratings of vehicle i and source j; Represents the maximum value of all customer ratings, used for normalization; represents the time sensitivity of source j; Indicates the state of the target freight vehicle Determined vehicle condition score; Represents the velocity component of the vehicle on the X-axis; Represents the velocity component of the vehicle on the Y axis; represents the distance between the destination of vehicle i and the destination of cargo source j; Indicates the maximum distance between the vehicle destination and the cargo source destination; The weight of the starting point distance is used to measure the impact of the starting point distance on the matching degree; Indicates the weight of the customer rating, which is used to consider the customer's satisfaction with the source of goods; A weight indicating time sensitivity, used to indicate the urgency of the supply; The weight of the vehicle status is used to indicate the impact of the importance of the vehicle status on the cargo; The weights of the direction angle and distance adjustment are used to represent the impact of the vehicle's directionality on the cargo; The weight of the destination distance is used to measure the impact of the destination distance on the matching degree; It indicates the influence of vehicle status score and vehicle speed on matching degree, which is determined by the following formula: ， in, Represents the adjustment factor, which is used to emphasize the effect of speed on matching; Indicates the vehicle status score; Represents the adjustment function related to direction angle and distance, determined according to the following formula: ， Where β represents the adjustment coefficient of the adjustment function related to the direction angle and distance; Indicates the direction angle of the vehicle; represents the ideal direction of cargo source j from the starting point to the destination; the state of the target freight vehicle , determined according to the following formula: ,in, Indicates the position coordinate of the vehicle on the X-axis; Indicates the position coordinate of the vehicle on the Y axis; The cargo sources corresponding to the cargo source scores that meet the preset conditions are regarded as the transportable cargo sources; A generating unit is configured to generate a return route of the target freight vehicle according to the cargo source information and vehicle information corresponding to the target cargo source in response to detecting a selection operation of the target freight vehicle user for the target cargo source from the transportable cargo sources; The sending unit is configured to send the return route and cargo source information to the target freight vehicle user.

7. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for recommending return cargo sources and return routes as described in any one of claims 1-5.

8. A computer-readable medium, characterized in that The computer-readable medium stores a computer program, wherein the computer program, when executed by a processor, implements the method for recommending return cargo sources and return routes as described in any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed, the method for recommending a return cargo source and a return route according to any one of claims 1 to 5 is implemented.

Images