Logistics transportation path planning method and device, computer equipment and storage medium

Abstract

The invention relates to a logistics transportation path planning method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring loading information of a target vehicle, and extracting vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information; according to the vehicle loading characteristics and the object loading and unloading characteristics, carrying out loading condition detection on the target vehicle to obtain a first loading detection result; and according to the first loading detection result and the transportation target information of X non-stop stations, a logistics transportation path of the target vehicle is planned, and X is a positive integer. By adopting the method, the accuracy of vehicle logistics transportation path planning can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method and apparatus for planning a logistics transportation route, a computer device, and a storage medium. Background Art

[0002] With the development of logistics transportation technology, in order to ensure the timeliness of goods transportation, it is necessary to rationally schedule the logistics transportation routes of vehicles. In traditional technologies, the loading status of vehicles is observed by transportation personnel with the naked eye, and then, based on the observed loading status, the logistics transportation routes of the vehicles are planned. The evaluation result of this loading status is limited by the subjective judgment of the transportation personnel, making the evaluation result of the loading status dependent on the observation ability and logistics transportation experience of the transportation personnel, resulting in inaccurate logistics transportation routes obtained based on the evaluation result of the loading status as the planning basis. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method and apparatus for planning a logistics transportation route, a computer device, a computer-readable storage medium, and a computer program product that can improve the accuracy of planning the logistics transportation route of a vehicle.

[0004] In a first aspect, this application provides a method for planning a logistics transportation route, including:

[0005] Obtain the loading information of a target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0006] Perform a loading status detection on the target vehicle according to the vehicle loading characteristics and object handling characteristics to obtain a first loading detection result;

[0007] Plan the logistics transportation route of the target vehicle according to the first loading detection result and the transportation target information of X unvisited stops, where X is a positive integer.

[0008] In a second aspect, this application further provides a device for planning a logistics transportation route, including:

[0009] An obtaining module, configured to obtain the loading information of a target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0010] A detection module, configured to perform a loading status detection on the target vehicle according to the vehicle loading characteristics and object handling characteristics to obtain a first loading detection result;

[0011] A planning module, configured to plan the logistics transportation route of the target vehicle according to the first loading detection result and the transportation target information of X unvisited stops, where X is a positive integer.

[0012] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0013] Obtain the loading information of the target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0014] According to the vehicle loading characteristics and object handling characteristics, perform a loading condition detection on the target vehicle to obtain a first loading detection result;

[0015] According to the first loading detection result and the transportation target information of X non-stop stations, plan the logistics transportation path of the target vehicle, where X is a positive integer.

[0016] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0017] Obtain the loading information of the target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0018] According to the vehicle loading characteristics and object handling characteristics, perform a loading condition detection on the target vehicle to obtain a first loading detection result;

[0019] According to the first loading detection result and the transportation target information of X non-stop stations, plan the logistics transportation path of the target vehicle, where X is a positive integer.

[0020] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0021] Obtain the loading information of the target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0022] According to the vehicle loading characteristics and object handling characteristics, perform a loading condition detection on the target vehicle to obtain a first loading detection result;

[0023] According to the first loading detection result and the transportation target information of X non-stop stations, plan the logistics transportation path of the target vehicle, where X is a positive integer.

[0024] The above-mentioned logistics transportation path planning method, device, computer equipment and storage medium obtain the loading information of the target vehicle, extract the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information, and then detect the loading status of the target vehicle according to the vehicle loading characteristics and object loading and unloading characteristics to obtain the first loading detection result. By using the objectively existing and multi-dimensional vehicle loading characteristics and object loading and unloading characteristics as the basis for loading status detection, the first loading detection result obtained by the detection can accurately reflect the loading status of the target vehicle. Furthermore, according to the first loading detection result and the transportation target information of X unvisited stations, where X is a positive integer, the logistics transportation path of the target vehicle can be planned. Since the logistics transportation path is planned based on the first loading detection result, the accuracy of vehicle logistics transportation path planning is improved. Description of the Drawings

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0026] Figure 1 It is an application environment diagram of the logistics transportation path planning method in an embodiment;

[0027] Figure 2 It is a flowchart of the logistics transportation path planning method in an embodiment;

[0028] Figure 3 It is a flowchart of obtaining the first loading detection result in a scenario in an embodiment;

[0029] Figure 4 It is a flowchart of training to obtain the first loading detection model (XGBoost model) in a scenario in an embodiment;

[0030] Figure 5 It is a flowchart of the step of extracting vehicle loading characteristics in an embodiment;

[0031] Figure 6 It is a flowchart of the step of planning the logistics transportation path of the target vehicle in an embodiment;

[0032] Figure 7 It is a structural block diagram of the logistics transportation path planning device in an embodiment;

[0033] Figure 8 It is an internal structure diagram of a computer device in an embodiment. Detailed Implementation Modes

[0034] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0035] In one embodiment, the logistics transportation path planning method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the loading information that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0036] In one embodiment, as Figure 2 shown, a logistics transportation path planning method is provided. In this embodiment, the method is applied to the terminal 102 in Figure 1 as an example, including steps 202 to 206:

[0037] Step 202, obtain the loading information of the target vehicle, and extract the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information.

[0038] Among them, the target vehicle in step 202 is the vehicle selected for logistics transportation path planning. The target vehicle can be single or multiple; when the loading information only includes the vehicle information of the target vehicle, the object loading and unloading characteristics extracted from the loading information can be blank, which can indicate that the target vehicle has not performed object loading and unloading at the current stop, or it can also indicate that the information on object loading and unloading of the target vehicle at the current stop has been characterized in the vehicle information.

[0039] Exemplarily, before obtaining the loading information of the target vehicle, it further includes: in response to a vehicle selection operation by a user (such as a logistics dispatcher), output the vehicle corresponding to the selection operation as the target vehicle; or, in response to a stop selection operation by the user, output the vehicle detected at the stop corresponding to the stop selection operation as the target vehicle.

[0040] Since the logistics personnel at the current stop where the vehicle has stopped may or may not perform object loading and unloading operations on the target vehicle, vehicle information is a necessary condition in the process of detecting the loading status of the target vehicle.

[0041] Exemplarily, obtaining the loading information of the target vehicle includes: obtaining the vehicle information sent by the target vehicle; or, obtaining the vehicle information sent by the target vehicle and the first object to be loaded and unloaded information of the current stop sent by the stop terminal corresponding to the current stop where the target vehicle is located.

[0042] Exemplarily, extracting the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information includes: obtaining a pre-trained feature extractor and mapping the loading information into the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle through the feature extractor; or, obtaining a pre-trained first loading detection model, where the first loading detection model includes a first feature extraction module and mapping the loading information into the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle through the first feature extraction module.

[0043] Step 204, detecting the loading status of the target vehicle according to the vehicle loading characteristics and object loading and unloading characteristics to obtain a first loading detection result.

[0044] Among them, the loading detection results involved in the full text (including but not limited to the first loading detection result, corrected loading detection result, and second loading detection result mentioned below) can be binary classification results. At this time, the loading detection result includes a full load result or an unfull load result; the loading detection result can also be a multi-classification result. At this time, the loading detection result is used to characterize the loading degree of the vehicle. For example, the loading detection result includes a first loading result (the range of the loading degree is 0%-25%), a second loading result (the range of the loading degree is 25%-50%), a third loading result (the range of the loading degree is 50%-75%), a fourth loading result (the range of the loading degree is 75%-100%), or a fifth loading result (the loading degree is greater than 100%).

[0045] As an embodiment, step 204 includes: obtaining a pre-trained first loading detection model, where the first loading detection model can be a neural network model such as an XGBoost (eXtreme Gradient Boosting) model. The first loading detection model includes a first loading detection classification module, fusing the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle to obtain a fused feature, and mapping the fused feature into the first loading detection result of the target vehicle through the first loading detection classification module.

[0046] Optionally, before obtaining the pre-trained first loading detection model, it further includes: obtaining a plurality of training samples, where a training sample includes a training fusion feature and a ground truth label, and mapping the training fusion feature to a training loading detection result through the first loading detection model to be trained; iteratively optimizing the first loading detection model to be trained according to the loss constructed based on the difference between the training loading detection result and the ground truth label to obtain the first loading detection model.

[0047] Exemplarily, obtaining a plurality of training samples includes: the training samples include a first sample and a second sample. The loading degree of the ground truth label in the first sample is less than or equal to a preset loading degree threshold, and the loading degree of the ground truth label in the second sample is greater than the preset loading degree threshold. Wherein, the preset loading degree threshold can be 100%. The training fusion feature of the second sample is aggregated from the training fusion features of the first samples, that is, the sum of the loading degrees of the ground truth labels in each aggregation object (selected from each first sample) is greater than the preset loading degree threshold. For example, the training fusion feature of the first sample with a ground truth label loading degree of 80% is aggregated with the training fusion feature of the first sample with a ground truth label loading degree of 30% to obtain the training fusion feature of the second sample.

[0048] As an embodiment, step 204 includes: obtaining a preset loading detection standard, where the preset loading detection standard includes a one-to-one correspondence between a preset feature group and a preset loading detection result, and the preset feature group includes a preset vehicle loading feature and a preset object loading and unloading feature; obtaining respective first similarities between the vehicle loading features corresponding to the target vehicle and each preset vehicle loading feature in the preset loading detection standard, and obtaining respective second similarities between the object loading and unloading features corresponding to the target vehicle and each preset object loading and unloading feature in the preset loading detection standard; selecting the first loading detection result corresponding to the target vehicle in the preset loading detection standard according to the respective first similarities and second similarities.

[0049] Exemplarily, selecting the first loading detection result corresponding to the target vehicle in the preset loading detection standard according to the respective first similarities and second similarities includes: selecting a target feature group in the preset loading detection standard whose corresponding first similarity satisfies a first preset similarity range and whose corresponding second similarity satisfies a second preset similarity range, and outputting the preset loading detection result corresponding to the target feature group as the first loading detection result; or, for each preset feature group in each preset feature group, aggregating the corresponding first similarity and second similarity to obtain a total similarity; selecting the target feature group with the highest corresponding total similarity in each preset feature group, and outputting the preset loading detection result corresponding to the target feature group as the first loading detection result.

[0050] Exemplarily, aggregating the first similarity and the second similarity corresponding to the preset feature group to obtain the total similarity includes: summing the first similarity and the second similarity corresponding to the preset feature group to obtain the total similarity; or, weighting the first similarity by a preset third weight to obtain a third similarity, weighting the second similarity by a preset fourth weight to obtain a fourth similarity, and summing the third similarity and the fourth similarity to obtain the total similarity.

[0051] Optionally, before all the loading status detections based on features involved in the full text, the features are normalized to ensure the unity of the feature dimensions and reduce the difficulty of feature processing for the loading status detection.

[0052] Optionally, as Figure 3 shown, the fused features are normalized, and then the normalized result is input into the XGBoost model, and the first loading detection result is output through the XGBoost model.

[0053] Optionally, as Figure 4 shown, the training fused features are normalized, and the XGBoost model is obtained through the normalized training fused features and the true labels.

[0054] Step 206, plan the logistics transportation path of the target vehicle according to the first loading detection result and the transportation target information of X non-stop stations, where X is a positive integer.

[0055] Among them, the logistics transportation path in step 206 is the path planned for the logistics transportation of the target vehicle from the current position of the target vehicle to at least one position; the unvisited station corresponds to the target vehicle. The unvisited station can be set by the user for the target vehicle, or the unvisited station can also be adapted to the objects already loaded in the target vehicle (for example, there are necessary stations corresponding to the objects already loaded in the target vehicle (for example, the necessary station is the transportation end point corresponding to the loaded object). When the first path and the second path are in opposite directions, the first path is the path planned for the target vehicle to move from the current position of the target vehicle to the unvisited station, and the second path is the path planned for the target vehicle to move between the current position of the target vehicle and the necessary station. There is a detour when the target vehicle moves to the unvisited station and the necessary station respectively. During the overall logistics transportation scheduling, there is a certain delay in logistics efficiency, affecting the timeliness of logistics transportation. Therefore, the unvisited station is the necessary station, or the unvisited station is the station where the corresponding first path and the second path are in the same direction), and the unvisited station can also be the station where the target vehicle has not stopped within the preset distance range. The preset distance range can be a circular range constructed with the target vehicle as the center and a preset radius, or the distance range between the unvisited station of the target vehicle and the current position of the target vehicle.

[0056] Exemplarily, step 206 includes: selecting at least one unvisited target station from the X unvisited stations according to the first loading detection result and the transportation target information of the X unvisited stations; planning the logistics transportation path of the target vehicle according to each unvisited target station.

[0057] As an embodiment, step 206 includes: selecting an unvisited target first station from the X unvisited stations according to the first loading detection result and the transportation target information of the X unvisited stations; removing the unvisited target first station from the X unvisited stations; and returning to the step of according to the first loading detection result and the transportation target information of the X unvisited stations. In this way, the overall path planning of the target vehicle can be realized.

[0058] In the case of the overall path planning of the target vehicle, during the logistics transportation process of the target vehicle with multiple stations, due to various force majeures (for example, the actual loading and unloading conditions of each station in the logistics transportation path of the target vehicle are unpredictable), there may be a large deviation between the first loading detection result of the target vehicle and the actual loading condition of the target vehicle, resulting in a situation where when the target vehicle passes through a certain station in the logistics transportation path for object loading, the target vehicle is already fully loaded and cannot perform object loading, resulting in a low planning accuracy of the logistics transportation path.

[0059] To overcome the above defects, as another embodiment, step 206 includes: determining the loading and unloading status of the target vehicle according to the first loading detection result and the transportation target information of X non-stop stations, where the loading and unloading status includes a loading status or an unloading status; selecting a non-stop target second station from the X non-stop stations according to the loading and unloading status of the target vehicle; planning the logistics transportation path of the target vehicle according to the non-stop target second station; when it is detected that the target vehicle arrives at the non-stop target second station, return to obtaining the loading information of the target vehicle. In this way, the logistics transportation path of the target vehicle is planned for each station one by one, reducing the risk of force majeure to a certain extent, avoiding the situation where the target vehicle is already fully loaded and unable to load objects when the target vehicle passes through a certain station in the logistics transportation path for object loading, and improving the planning accuracy of the logistics transportation path.

[0060] In the above logistics transportation path planning method, by obtaining the loading information of the target vehicle and extracting the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information, the loading status of the target vehicle is detected according to the vehicle loading characteristics and object loading and unloading characteristics, and the first loading detection result is obtained. The objectively existing and multi-dimensional vehicle loading characteristics and object loading and unloading characteristics are used as the basis for the loading status detection, so that the first loading detection result obtained by the detection can accurately reflect the loading status of the target vehicle. Furthermore, the logistics transportation path of the target vehicle can be planned according to the first loading detection result and the transportation target information of X non-stop stations, where X is a positive integer. Since the logistics transportation path is planned based on the first loading detection result, the planning accuracy of the vehicle logistics transportation path is improved.

[0061] To ensure the accuracy of the loading status detection of the target vehicle, that is, to ensure the planning accuracy of the vehicle logistics transportation path, a method for accurately extracting the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle is needed to achieve the accurate loading status detection of the target vehicle.

[0062] In an exemplary embodiment, as Figure 5 shown, the loading information includes the vehicle information of the target vehicle and the first object to be loaded and unloaded information corresponding to the current stop station of the target vehicle. The vehicle information includes vehicle shape information, vehicle capacity information, and vehicle loaded object information; extracting the vehicle loading capacity characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information includes steps 302 to 304:

[0063] Step 302, extracting the object loading and unloading characteristics of the object to be loaded and unloaded corresponding to the target vehicle at the current stop station from the first object to be loaded and unloaded information.

[0064] Among them, the first object to be loaded and unloaded information in step 302 includes the first object to be loaded information and / or the first object to be unloaded information. The first object to be loaded information is the information of the object to be loaded at the current stop station, and the first object to be unloaded information is the information of the object to be unloaded among the loaded objects of the target vehicle. That is, the transportation personnel load the object according to the first object to be loaded information at the current stop station of the target vehicle; or, the transportation personnel unload the loaded object from the target vehicle according to the first object to be unloaded information at the current stop station of the target vehicle; or, the transportation personnel load the object according to the first object to be loaded information at the current stop station of the target vehicle, and unload the loaded object from the target vehicle according to the first object to be unloaded information.

[0065] Exemplarily, step 302 includes: obtaining a pre-trained feature extractor, where the feature extractor includes an object feature extractor, and mapping the first object to be loaded and unloaded information to object loading and unloading features through the object feature extractor; or, obtaining a pre-trained first loading detection model, where the first loading detection model includes a first feature extraction module, and the first feature extraction module includes an object feature extraction module, and mapping the first object to be loaded and unloaded information to object loading and unloading features through the object feature extraction module.

[0066] Step 304, extract the vehicle loading feature of the target vehicle from the vehicle shape information, vehicle capacity information, and vehicle loaded object information, where the vehicle loading feature is used to characterize the remaining loading capacity of the target vehicle.

[0067] Among them, the object information involved throughout the text (including but not limited to the information of the first object to be loaded and unloaded, the information of the second object to be loaded and unloaded, and the information of the objects already loaded on the vehicle) includes various information of the object corresponding logistics packaging and / or the object itself. The various information includes but is not limited to material information, shape information, placement information, and size information. The material information is used to characterize the degree of easy deformation of the object or the logistics packaging, and the shape information is used to characterize the degree of easy movement of the object or the logistics packaging. Thus, when the object information includes material information and the material information in the object information characterizes a relatively high degree of easy deformation, during the process of loading and unloading or transporting objects in the target vehicle, due to the presence of objects to be loaded and unloaded or to be transported with a relatively high degree of easy deformation in the target vehicle, the objects are deformed, resulting in a large deviation between the detected loading condition without considering the material information and the actual loading condition. Therefore, taking the material information as the decision basis for detecting the loading condition and considering the influence of the material information on the detection of the loading condition, the accuracy of the detection of the loading condition is improved. When the object information includes shape information and the shape information in the object information characterizes a relatively high degree of easy movement, during the process of loading and unloading or transporting objects in the target vehicle, due to the presence of objects to be loaded and unloaded or to be transported with a relatively high degree of easy movement in the target vehicle, there is a large deviation between the detected loading condition without considering the shape information and the actual loading condition. Therefore, taking the shape information as the decision basis for detecting the loading condition and considering the influence of the shape information on the detection of the loading condition, the accuracy of the detection of the loading condition is improved. During the process of loading and unloading objects in the target vehicle, since the work quality of the transportation personnel performing the object loading and unloading is an unknown factor. For example, when the work quality of the transportation personnel performing the object loading and unloading is relatively high, the placement of the objects already loaded in the target vehicle is likely to be neat at this time, while when the work quality of the transportation personnel performing the object loading and unloading is relatively low, the placement of the objects already loaded in the target vehicle is likely to be untidy at this time, resulting in a large deviation between the detected loading condition without considering the placement information and the actual loading condition. Therefore, taking the placement information as the decision basis for detecting the loading condition and considering the influence of the placement information on the detection of the loading condition, the accuracy of the detection of the loading condition is improved. To ensure that the placement information can represent the placement condition of the objects already loaded in the target vehicle, usually before detecting the loading condition, after the object loading and unloading process has been completed at the current stop of the target vehicle, a vehicle loading image carrying the object characteristics in the target vehicle is obtained, and the placement information is obtained through image recognition of the vehicle loading image.

[0068] Among them, the vehicle shape information in step 304 is the shape information of the area in the target vehicle used to carry objects, and the area is usually the carriage.

[0069] Exemplarily, step 304 includes: the feature extractor includes a vehicle feature extractor, and the vehicle shape information, vehicle capacity information, and information on the objects already loaded in the vehicle are mapped into vehicle loading features through the vehicle feature extractor; or, the first feature extraction module includes a vehicle feature extraction module, and the vehicle shape information, vehicle capacity information, and information on the objects already loaded in the vehicle are mapped into vehicle loading features through the vehicle feature extraction module.

[0070] As an embodiment, step 304 includes: the vehicle feature extractor includes a vehicle shape feature extractor, a vehicle capacity feature extractor, and a loaded object feature extractor. The vehicle shape information is mapped into vehicle shape features through the vehicle shape feature extractor; the vehicle capacity information is mapped into vehicle capacity features through the vehicle capacity feature extractor; the information on the objects already loaded in the vehicle is mapped into vehicle loaded object features through the loaded object feature extractor; the vehicle shape features, vehicle capacity features, and vehicle loaded object features are concatenated into vehicle loading features.

[0071] As another embodiment, step 304 includes: the vehicle feature extraction module includes a vehicle shape feature extraction module, a vehicle capacity feature extraction module, and a loaded object feature extraction module. The vehicle shape information is mapped into vehicle shape features through the vehicle shape feature extraction module; the vehicle capacity information is mapped into vehicle capacity features through the vehicle capacity feature extraction module; the information on the objects already loaded in the vehicle is mapped into vehicle loaded object features through the loaded object feature extraction module; the vehicle shape features, vehicle capacity features, and vehicle loaded object features are concatenated into vehicle loading features.

[0072] Thus, since the vehicle shape information is used to characterize the shape information of the area in the target vehicle for carrying objects, when the vehicle shape information does not match the shape information of the object information in the target vehicle (including but not limited to the information on the objects already loaded in the vehicle, the information on the objects to be loaded in the first object to be loaded and unloaded information, and the information on the objects to be loaded in the second object to be loaded and unloaded information) (for example, the shape information of the object information is a rectangular body, and the vehicle shape information is a sphere), at this time, it is possible that the target vehicle is not fully loaded. However, due to the mismatch between the vehicle shape information and the shape information of the object information in the target vehicle, there is a lot of space waste in the target vehicle, resulting in a large deviation between the detected loading condition that does not consider the vehicle shape information and the actual loading condition. Therefore, using the vehicle shape information as a decision basis for detecting the loading condition and considering the influence of the vehicle shape information on the detection of the loading condition, the accuracy of the detection of the loading condition is improved.

[0073] Among them, according to the vehicle loading features and object loading and unloading features, the loading condition of the target vehicle is detected to obtain a first loading detection result, including:

[0074] Weight the vehicle loading characteristics according to a preset first weight to obtain a first weighted characteristic, and weight the object loading and unloading characteristics according to a preset second weight to obtain a second weighted characteristic.

[0075] Among them, the preset first weight and the preset second weight can be set by the user as needed. The preset first weight is used to represent the importance of the vehicle loading characteristics for the loading condition detection. The higher the importance of the vehicle loading characteristics for the loading condition detection, the larger the preset first weight; the preset second weight is used to represent the importance of the object loading and unloading characteristics for the loading condition detection. The higher the importance of the object loading and unloading characteristics for the loading condition detection, the larger the preset second weight.

[0076] Exemplarily, weighting the vehicle loading characteristics according to a preset first weight to obtain a first weighted characteristic, and weighting the object loading and unloading characteristics according to a preset second weight to obtain a second weighted characteristic includes: multiplying the preset first weight by the vehicle loading characteristics to obtain the first weighted characteristic; multiplying the preset second weight by the object loading and unloading characteristics to obtain the second weighted characteristic; or adding the preset first weight to the vehicle loading characteristics to obtain the first weighted characteristic, and adding the preset second weight to the object loading and unloading characteristics to obtain the second weighted characteristic.

[0077] Fuse the first weighted characteristic and the second weighted characteristic to obtain a fused characteristic.

[0078] Exemplarily, fusing the first weighted characteristic and the second weighted characteristic to obtain a fused characteristic includes: concatenating the first weighted characteristic and the second weighted characteristic to obtain the fused characteristic; or performing multiplication or addition processing on the first weighted characteristic and the second weighted characteristic to obtain the fused characteristic.

[0079] Detect the loading condition of the target vehicle according to the fused characteristic to obtain a first loading detection result.

[0080] Exemplarily, detecting the loading condition of the target vehicle according to the fused characteristic to obtain a first loading detection result includes: obtaining a pre-trained first loading detection model, where the first loading detection model includes a first loading detection classification module, and mapping the fused characteristic to the first loading detection result through the first loading detection classification module.

[0081] In this embodiment, by weighting the vehicle loading characteristics according to a preset first weight to obtain a first weighted characteristic, and weighting the object loading and unloading characteristics according to a preset second weight to obtain a second weighted characteristic, the first weighted characteristic and the second weighted characteristic can be fused to obtain a fused characteristic, and the loading condition of the target vehicle is detected according to the fused characteristic to obtain a first loading detection result. This fully considers the influence of various factors on the loading condition detection and provides more decision-making basis for the loading condition detection, thus improving the accuracy of the loading condition detection.

[0082] To ensure the accuracy of the vehicle logistics transportation path planning, an accurate path planning method is needed to achieve the accurate loading state detection of the target vehicle.

[0083] In an exemplary embodiment, as Figure 6 shown, the non-stop stations include loading stations and unloading stations, and the transportation target information of X non-stop stations includes the road conditions between each of the X non-stop stations and the current stop station; according to the first loading detection result and the transportation target information of the X non-stop stations, the logistics transportation path of the target vehicle is planned, including steps 402 to 406:

[0084] Step 402, according to the first loading detection result and the X road conditions, respectively predict the loading conditions of the target vehicle at the X non-stop stations to obtain X second loading detection results.

[0085] Among them, the road conditions in step 402 include distance information and / or driving road conditions, and the driving road conditions are used to characterize the flatness of the road surface.

[0086] Exemplarily, step 402 includes: for each of the X non-stop stations, obtain a second loading detection model, the second loading detection model includes a second loading feature extraction module and a second loading detection classification module, respectively extract features from the first loading detection result and the road conditions of the non-stop station through the second loading feature extraction module to obtain loading road condition features, and map the loading road condition features to the second loading detection results corresponding to the non-stop stations through the second loading detection classification module.

[0087] Among them, the loading information includes vehicle information; according to the first loading detection result and the X road conditions, respectively predict the loading conditions of the target vehicle at the X non-stop stations to obtain X second loading detection results, including:

[0088] According to the vehicle information and the X road conditions, respectively correct the first loading detection result to obtain X corrected loading detection results.

[0089] Exemplarily, according to the vehicle information and X road condition information, the first loading detection result is corrected respectively to obtain X corrected loading detection results, including: for each of the X non-stop stations, according to the road condition information and vehicle information of the non-stop station, a correction value corresponding to the non-stop station is calculated; the first loading detection result is corrected according to the correction value to obtain the corrected loading detection result corresponding to the non-stop station.

[0090] As an embodiment, calculating a correction value corresponding to a non-stop station according to the road condition information and vehicle information of the non-stop station includes: determining the influence degree of the road condition information and vehicle information of the non-stop station on the detection of the loading condition of the target vehicle, and calculating the correction value corresponding to the non-stop station based on the influence degree of the road condition information and vehicle information of the non-stop station on the detection of the loading condition of the target vehicle, wherein the greater the influence degree of the road condition information and vehicle information of the non-stop station on the detection of the loading condition of the target vehicle, the greater the corresponding correction value.

[0091] Wherein, the vehicle information includes vehicle shape information and vehicle loaded object information; according to the vehicle information and X road condition information, the first loading detection result is corrected respectively to obtain X corrected loading detection results, including:

[0092] According to the vehicle shape information, vehicle loaded object information and X road condition information, the scattering degree of the loaded object in the target vehicle during the target vehicle traveling to X non-stop stations is predicted respectively to obtain the predicted object scattering degree corresponding to X non-stop stations;

[0093] Exemplarily, according to the vehicle shape information, vehicle loaded object information and X road condition information, the scattering degree of the loaded object in the target vehicle during the target vehicle traveling to X non-stop stations is predicted respectively to obtain the predicted object scattering degree corresponding to X non-stop stations, including: for each of the X non-stop stations, a scattering degree prediction model is obtained, the scattering degree prediction model includes a scattering degree feature extractor and a scattering degree detection module, and the scattering degree feature extractor includes a vehicle shape feature extractor, an object feature extractor and a road condition feature extractor; the vehicle shape information is feature-extracted by the vehicle shape feature extractor to obtain vehicle shape features; the vehicle loaded object information is feature-extracted by the object feature extractor to obtain vehicle loaded object features; the road condition information of the non-stop station is feature-extracted by the road condition feature extractor to obtain road condition features; the vehicle shape features, vehicle loaded object features and road condition features are spliced into scattering degree features; the scattering degree features are mapped by the scattering degree detection module to the predicted object scattering degree corresponding to the non-stop station.

[0094] Thus, since the vehicle shape information is used to characterize the shape information of the area in the target vehicle for carrying objects, when the vehicle shape information does not match the shape information of the object information in the target vehicle, during the process of the target vehicle traveling to an unstopped station, the risk of the objects already loaded in the target vehicle being scattered is relatively high. Therefore, the vehicle shape information is used as the decision basis for predicting the object scatter degree, so the prediction accuracy of the scatter degree is improved.

[0095] Thus, when the road condition information includes the distance information and the distance information characterizes that the distance between the current stopped station and the unstopped station of the target vehicle is relatively long, due to the long distance, during the process of the target vehicle moving to the unstopped station, there may be various situations that lead to a relatively high risk of the objects already loaded in the target vehicle being scattered. Therefore, the distance information is used as the decision basis for predicting the object scatter degree, so the prediction accuracy of the scatter degree is improved.

[0096] Thus, when the road condition information includes the driving road condition information and the driving road condition information characterizes that the flatness of the road surface is relatively low (due to the rough road surface or the large road surface slope), during the process of the target vehicle moving to the unstopped station, there may be a situation where the target vehicle jolts frequently, resulting in a relatively high risk of the objects already loaded in the target vehicle being scattered. Therefore, the driving road condition information is used as the decision basis for predicting the object scatter degree, so the prediction accuracy of the scatter degree is improved.

[0097] According to the predicted object scatter degrees corresponding to X unstopped stations, the first loading detection results are respectively corrected to obtain X corrected loading detection results.

[0098] Exemplarily, according to the predicted object scatter degrees corresponding to X unstopped stations, the first loading detection results are respectively corrected to obtain X corrected loading detection results, including: for each of the X unstopped stations, according to the predicted object scatter degree corresponding to the unstopped station, calculate the correction value corresponding to the unstopped station; correct the first loading detection result according to the correction value to obtain the corrected loading detection result corresponding to the unstopped station.

[0099] Among them, according to the predicted object scatter degrees corresponding to X unstopped stations, the first loading detection results are respectively corrected to obtain X corrected loading detection results, including:

[0100] For each of the X unstopped stations, obtain the influence degree of the predicted object scatter degree corresponding to the unstopped station on the prediction of the loading condition of the target vehicle.

[0101] Among them, the greater the predicted object scatter degree, the greater the influence degree on the prediction of the loading condition of the target vehicle.

[0102] Exemplarily, obtaining the influence degree of the predicted object scatter degree corresponding to the non-stop stations on the loading condition prediction of the target vehicle includes: obtaining a first preset mapping relationship, where the first preset mapping relationship includes a one-to-one correspondence between a preset object scatter degree and a preset influence degree; mapping the predicted object scatter degree corresponding to the non-stop stations to the influence degree of the predicted object scatter degree on the loading condition prediction of the target vehicle through the first preset mapping relationship.

[0103] Generating a correction value according to the influence degree, where the greater the influence degree, the greater the corresponding correction value generated.

[0104] Exemplarily, generating a correction value according to the influence degree, where the greater the influence degree, the greater the corresponding correction value generated, includes: obtaining a second preset mapping relationship, where the second preset mapping relationship includes a one-to-one correspondence between a preset influence degree and a preset correction value; mapping the influence degree to a correction value through the second preset mapping relationship.

[0105] Performing weighted correction on the first loading detection result through the correction value to obtain a corrected loading detection result corresponding to the non-stop stations.

[0106] Exemplarily, performing weighted correction on the first loading detection result through the correction value to obtain a corrected loading detection result corresponding to the non-stop stations includes: obtaining the first loading degree corresponding to the first loading detection result, and summing the correction value and the first loading degree to obtain a corrected loading detection result corresponding to the non-stop stations; or multiplying the correction value and the first loading degree to obtain a corrected loading detection result corresponding to the non-stop stations.

[0107] Predicting the loading conditions of the target vehicle at X non-stop stations respectively according to the X corrected loading detection results and the second to-be-loaded / unloaded object information of the X non-stop stations to obtain X second loading detection results.

[0108] Exemplarily, predicting the loading conditions of the target vehicle at X non-stop stations respectively according to the X corrected loading detection results and the second to-be-loaded / unloaded object information of the X non-stop stations to obtain X second loading detection results includes: for each non-stop station among the X non-stop stations, the second loading detection model includes a second loading feature extraction module and a second loading detection classification module. Feature extraction is performed on the corrected loading detection result and the second to-be-loaded / unloaded object information corresponding to the non-stop station through the second loading feature extraction module to obtain corrected loading features; mapping the corrected loading features to a second loading detection result corresponding to the non-stop station through the second loading detection classification module.

[0109] Step 404, if all X second loading detection results meet the preset full-load detection conditions, select a unloading target site from the unloading sites of the X non-stop stations, and plan the logistics transportation route of the target vehicle according to the unloading target site.

[0110] Among them, the unloading site in step 404 is the site for unloading the loaded objects in the target vehicle; the preset full-load detection condition can be a preset loading degree range. For example, the preset full-load degree range is greater than 100%.

[0111] Exemplarily, before selecting the unloading target site from the unloading sites of the X non-stop stations, it further includes: selecting, from the X non-stop stations, the stations with the same unloading location corresponding to the loaded objects in the target vehicle as the unloading sites.

[0112] As an embodiment, selecting the unloading target site from the unloading sites of the X non-stop stations includes: selecting, from each unloading site, the site with the smallest loading degree corresponding to the second loading detection result as the unloading target site.

[0113] As another embodiment, selecting the unloading target site from the unloading sites of the X non-stop stations includes: selecting, from each unloading site, the site with the shortest distance corresponding to the route information as the unloading target site.

[0114] As yet another embodiment, selecting the unloading target site from the unloading sites of the X non-stop stations includes: selecting, from each unloading site, the site with the highest road surface flatness corresponding to the driving road condition information as the unloading target site.

[0115] Exemplarily, planning the logistics transportation route of the target vehicle according to the unloading target site includes: planning the logistics transportation route of the target vehicle according to the unloading target site and the current stop station of the target vehicle.

[0116] Step 406, if all X second loading detection results do not meet the preset full-load detection conditions, select a loading target site from the loading sites of the X non-stop stations, and plan the logistics transportation route of the target vehicle according to the loading target site.

[0117] Among them, the loading site in step 406 is the site for loading objects into the target vehicle.

[0118] Exemplarily, before selecting the loading target site from the loading sites of the X non-stop stations, it further includes: selecting, from the X non-stop stations, the stations corresponding to the existing loading tasks as the loading sites.

[0119] As an embodiment, selecting a loading target site from the loading sites of X non-stop sites includes: selecting, from each loading site, the site corresponding to the second loading detection result that is closest but does not meet the preset full-load detection condition as the loading target site.

[0120] As another embodiment, selecting a loading target site from the loading sites of X non-stop sites includes: selecting, from each loading site, the site corresponding to the shortest characterized journey information as the loading target site.

[0121] As yet another embodiment, selecting a loading target site from the loading sites of X non-stop sites includes: selecting, from each loading site, the site corresponding to the highest characterized road surface flatness in the driving road condition information as the loading target site.

[0122] Exemplarily, planning the logistics transportation path of the target vehicle according to the loading target site includes: planning the logistics transportation path of the target vehicle according to the loading target site and the current stop site of the target vehicle.

[0123] In this embodiment, by predicting the loading status of the target vehicle at X non-stop sites respectively according to the first loading detection result and X road condition information, X second loading detection results are obtained; if all X second loading detection results meet the preset full-load detection condition, then select an unloading target site from the unloading sites of X non-stop sites, and plan the logistics transportation path of the target vehicle according to the unloading target site, so as to realize that when the target vehicle is predicted to be in a full-load state at the corresponding X non-stop sites, timely plan to unload the loaded objects in the target vehicle. If not all X second loading detection results meet the preset full-load detection condition, then select a loading target site from the loading sites of X non-stop sites, and plan the logistics transportation path of the target vehicle according to the loading target site, so as to realize that when the target vehicle is not predicted to be in a full-load state at the corresponding X non-stop sites, it can plan to reload objects, maximizing the utilization of the target vehicle. In summary, the accuracy of the vehicle logistics transportation path planning is improved.

[0124] In a more detailed embodiment, first, object loading and unloading characteristics of the object to be loaded and unloaded corresponding to the current stopping station of the target vehicle are extracted from the first object information to be loaded and unloaded; vehicle loading characteristics of the target vehicle are extracted from the vehicle shape information, vehicle capacity information, and information on the objects already loaded in the vehicle, where the vehicle loading characteristics are used to characterize the remaining loading capacity of the target vehicle; according to a preset first weight, the vehicle loading characteristics are weighted to obtain a first weighted characteristic, and according to a preset second weight, the object loading and unloading characteristics are weighted to obtain a second weighted characteristic; the first weighted characteristic and the second weighted characteristic are fused to obtain a fused characteristic; the loading condition of the target vehicle is detected based on the fused characteristic to obtain a first loading detection result; according to the vehicle shape information, the information on the objects already loaded in the vehicle, and X road condition information, the degree of scattering of the objects already loaded in the target vehicle during the target vehicle's travel to X non-stopping stations is predicted respectively to obtain the predicted object scattering degrees corresponding to the X non-stopping stations.

[0125] Further, for each of the X non-stopping stations, the influence degree of the predicted object scattering degree corresponding to the non-stopping station on the prediction of the loading condition of the target vehicle is obtained; according to the influence degree, a correction value is generated, where the greater the influence degree, the greater the corresponding correction value generated; the first loading detection result is weighted and corrected by the correction value to obtain a corrected loading detection result corresponding to the non-stopping station; according to the X corrected loading detection results and the second object information to be loaded and unloaded at the X non-stopping stations, the loading conditions of the target vehicle at the X non-stopping stations are predicted respectively to obtain X second loading detection results; if all of the X second loading detection results meet the preset full-load detection conditions, an unloading target station is selected from the unloading stations at the X non-stopping stations, and based on the unloading target station, the logistics transportation path of the target vehicle is planned; if not all of the X second loading detection results meet the preset full-load detection conditions, a loading target station is selected from the loading stations at the X non-stopping stations, and based on the loading target station, the logistics transportation path of the target vehicle is planned.

[0126] In this way, the objectively existing and multi-dimensional vehicle loading characteristics and object loading and unloading characteristics are used as the basis for loading condition detection, so that the obtained first loading detection result can accurately reflect the loading condition of the target vehicle. Considering the influence of various factors on the scattering of the objects already loaded in the target vehicle during the transportation process of the target vehicle, the accuracy of loading condition prediction is improved, thereby improving the accuracy of the logistics transportation path planning of the vehicle.

[0127] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0128] Based on the same inventive concept, an embodiment of the present application further provides a logistics transportation path planning device for implementing the logistics transportation path planning method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the logistics transportation path planning device provided below can refer to the limitations on the logistics transportation path planning method in the above text, and will not be repeated here.

[0129] In an exemplary embodiment, as Figure 7 shown, a logistics transportation path planning device 700 is provided, including: an acquisition module 701, a generation module 702, and a selection module 703, where:

[0130] The acquisition module 701 is configured to acquire the loading information of the target vehicle, and extract the vehicle loading characteristics and object handling characteristics corresponding to the target vehicle from the loading information;

[0131] The detection module 702 is configured to detect the loading status of the target vehicle according to the vehicle loading characteristics and object handling characteristics, and obtain a first loading detection result;

[0132] The planning module 703 is configured to plan the logistics transportation path of the target vehicle according to the first loading detection result and the transportation target information of X unvisited stops, where X is a positive integer.

[0133] In one of the embodiments, the loading information includes the vehicle information of the target vehicle and the first object to be loaded and unloaded information corresponding to the current stop of the target vehicle. The vehicle information includes vehicle shape information, vehicle capacity information, and vehicle loaded object information; the detection module 702 is further configured to extract the object handling characteristics of the object to be loaded and unloaded corresponding to the target vehicle at the current stop from the first object to be loaded and unloaded information; and extract the vehicle loading characteristics of the target vehicle from the vehicle shape information, vehicle capacity information, and vehicle loaded object information, where the vehicle loading characteristics are used to characterize the remaining loading capacity of the target vehicle.

[0134] In one embodiment, the detection module 702 is further configured to weight the vehicle loading characteristics according to a preset first weight to obtain a first weighted characteristic, and weight the object loading and unloading characteristics according to a preset second weight to obtain a second weighted characteristic; fuse the first weighted characteristic and the second weighted characteristic to obtain a fused characteristic; and detect the loading condition of the target vehicle according to the fused characteristic to obtain a first loading detection result.

[0135] In one embodiment, the non-stop stations include loading stations and unloading stations, and the transportation target information of the X non-stop stations includes the road condition information between each of the X non-stop stations and the current stop station; the planning module 703 is further configured to predict the loading conditions of the target vehicle at the X non-stop stations respectively according to the first loading detection result and the X road condition information to obtain X second loading detection results; if all of the X second loading detection results meet the preset full-load detection condition, select an unloading target station from the unloading stations of the X non-stop stations, and plan the logistics transportation path of the target vehicle according to the unloading target station; if not all of the X second loading detection results meet the preset full-load detection condition, select a loading target station from the loading stations of the X non-stop stations, and plan the logistics transportation path of the target vehicle according to the loading target station.

[0136] In one embodiment, the loading information includes vehicle information; the planning module 703 is further configured to correct the first loading detection result respectively according to the vehicle information and the X road condition information to obtain X corrected loading detection results; and predict the loading conditions of the target vehicle at the X non-stop stations respectively according to the X corrected loading detection results and the second to-be-loaded / unloaded object information of the X non-stop stations to obtain X second loading detection results.

[0137] In one embodiment, the vehicle information includes vehicle shape information and the information of the objects already loaded on the vehicle; the planning module 703 is further configured to predict the scattering degree of the objects already loaded on the target vehicle during the target vehicle traveling to the X non-stop stations respectively according to the vehicle shape information, the information of the objects already loaded on the vehicle, and the X road condition information to obtain the predicted object scattering degrees corresponding to the X non-stop stations; and correct the first loading detection result respectively according to the predicted object scattering degrees corresponding to the X non-stop stations to obtain X corrected loading detection results.

[0138] In one embodiment, the planning module 703 is further configured to, for each of the X non-stop stations, obtain the influence degree of the predicted object scattering degree corresponding to the non-stop station on the prediction of the loading condition of the target vehicle; generate a correction value according to the influence degree, where the greater the influence degree, the greater the corresponding generated correction value; and perform weighted correction on the first loading detection result through the correction value to obtain the corrected loading detection result corresponding to the non-stop station.

[0139] Each module in the above-mentioned logistics transportation route planning device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0140] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a logistics transportation route planning method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0141] Those skilled in the art can understand that Figure 8 the structure shown in

[0142] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0144] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0145] It should be noted that the user information involved in this application (including but not limited to loading information, transportation target information, etc.) is all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0146] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0147] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0148] The above embodiments only express several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for planning a logistics transportation route, characterized in that, The method includes: Obtaining the loading information of the target vehicle, and extracting the vehicle loading characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information; Performing a loading condition detection on the target vehicle according to the vehicle loading characteristics and the object loading and unloading characteristics to obtain a first loading detection result; Planning the logistics transportation path of the target vehicle according to the first loading detection result and the transportation target information of X non-stop stations, where X is a positive integer.

2. The method according to claim 1, wherein The loading information includes the vehicle information of the target vehicle and the first object to be loaded and unloaded information corresponding to the current stop station of the target vehicle, and the vehicle information includes vehicle shape information, vehicle capacity information, and information on the objects already loaded on the vehicle; The extracting the vehicle loading capacity characteristics and object loading and unloading characteristics corresponding to the target vehicle from the loading information includes: Extracting the object loading and unloading characteristics of the object to be loaded and unloaded corresponding to the target vehicle at the current stop station from the first object to be loaded and unloaded information; Extracting the vehicle loading characteristics of the target vehicle from the vehicle shape information, the vehicle capacity information, and the information on the objects already loaded on the vehicle, where the vehicle loading characteristics are used to characterize the remaining loading capacity of the target vehicle.

3. The method according to claim 2, wherein The performing a loading condition detection on the target vehicle according to the vehicle loading characteristics and the object loading and unloading characteristics to obtain a first loading detection result includes: Weighting the vehicle loading characteristics according to a preset first weight to obtain a first weighted characteristic, and weighting the object loading and unloading characteristics according to a preset second weight to obtain a second weighted characteristic; Fusing the first weighted characteristic and the second weighted characteristic to obtain a fused characteristic; Performing a loading condition detection on the target vehicle according to the fused characteristic to obtain a first loading detection result.

4. The method according to claim 1, wherein, The non-stop stations include loading stations and unloading stations, and the transportation target information of the X non-stop stations includes the road conditions information between each of the X non-stop stations and the current stop station; The planning the logistics transportation path of the target vehicle according to the first loading detection result and the transportation target information of X non-stop stations includes: Predicting the loading conditions of the target vehicle at the X non-stop stations respectively according to the first loading detection result and the X road conditions information to obtain X second loading detection results; If all of the X second loading detection results meet the preset full-load detection conditions, selecting an unloading target station from the unloading stations of the X non-stop stations, and planning the logistics transportation path of the target vehicle according to the unloading target station; If all of the X second loading detection results do not meet the preset full-load detection conditions, selecting a loading target station from the loading stations of the X non-stop stations, and planning the logistics transportation path of the target vehicle according to the loading target station.

5. The method according to claim 4, characterized in that, The loading information includes vehicle information; the predicting the loading conditions of the target vehicle at the X non-stop stations respectively according to the first loading detection result and the X road conditions information to obtain X second loading detection results includes: According to the vehicle information and the X road condition information, respectively correct the first loading detection result to obtain X corrected loading detection results; According to the X corrected loading detection results and the second to-be-loaded / unloaded object information of the X non-stop stations, respectively predict the loading status of the target vehicle at the X non-stop stations to obtain the X second loading detection results.

6. The method according to claim 5, wherein The vehicle information includes vehicle shape information and vehicle loaded object information; the step of respectively correcting the first loading detection result according to the vehicle information and the X road condition information to obtain X corrected loading detection results includes: According to the vehicle shape information, the vehicle loaded object information and the X road condition information, respectively predict the scattering degree of the loaded objects in the target vehicle during the target vehicle driving to the X non-stop stations to obtain the predicted object scattering degrees corresponding to the X non-stop stations; According to the predicted object scattering degrees corresponding to the X non-stop stations, respectively correct the first loading detection result to obtain X corrected loading detection results.

7. The method according to claim 6, wherein The step of respectively correcting the first loading detection result according to the predicted object scattering degrees corresponding to the X non-stop stations to obtain X corrected loading detection results includes: For each non-stop station among the X non-stop stations, obtain the influence degree of the predicted object scattering degree corresponding to the non-stop station on the loading status prediction of the target vehicle; Generate a correction value according to the influence degree, wherein the greater the influence degree, the greater the corresponding correction value generated; Perform weighted correction on the first loading detection result through the correction value to obtain the corrected loading detection result corresponding to the non-stop station.

8. A logistics transportation route planning device, characterized in that, The logistics transportation path planning device includes: An acquisition module, configured to acquire the loading information of the target vehicle and extract the vehicle loading characteristics and object loading / unloading characteristics corresponding to the target vehicle from the loading information; A detection module, configured to detect the loading status of the target vehicle according to the vehicle loading characteristics and the object loading / unloading characteristics to obtain a first loading detection result; A planning module, configured to plan the logistics transportation path of the target vehicle according to the first loading detection result and the transportation target information of X non-stop stations, where X is a positive integer.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images