A transport collaborative management system and method based on intelligent assisted dispatching

Abstract

The embodiment of the present invention provides a transportation collaborative management system and method based on intelligent auxiliary dispatching. The system includes a cluster analysis module that performs clustering according to target attribute information of target objects to obtain initial clustering results; a loading assessment module that performs loading assessment on the initial clustering results to obtain initial loading results; a distance calculation module that performs similarity calculation on target objects according to target attribute information to obtain target similarity; a loading adjustment module that adjusts the initial loading results according to target similarity to obtain target loading results; a data acquisition module that obtains the current transportation position and the target transportation position of the target loading result; a path determination module that determines the target transportation path according to the current transportation position and the target transportation position; an object determination module that obtains the target transportation result of the target transportation position and the object to be dispatched of the target transportation result; and an intelligent dispatching module that determines the target dispatching path according to the target transportation position and the target dispatching position of the object to be dispatched.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a transportation collaborative management system and method based on intelligent assisted dispatching. Background Art

[0002] In modern logistics and supply chain management, the efficient flow of goods is crucial to the success of an enterprise. However, the existing transportation collaborative management system still has many technical bottlenecks and problems when collaborating with multiple parties such as shippers, carriers, warehouses, and drivers. Traditional transportation collaborative management often relies on manual operations or fixed rules, which makes it difficult to flexibly respond to dynamic transportation needs and complex operating environments, resulting in low transportation efficiency and high transportation costs. Therefore, there is an urgent need for a transportation collaborative management system that can significantly reduce transportation costs and improve transportation efficiency. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a transport collaborative management system and method based on intelligent assisted dispatching, aiming to solve the problem that transport collaborative management in related technologies often relies on manual operations or fixed rules, and is difficult to flexibly respond to dynamic transport needs and complex operating environments, resulting in low transport efficiency and high transport costs.

[0004] In a first aspect, an embodiment of the present invention provides a transportation collaborative management system based on intelligent assisted dispatching, including:

[0005] A cluster analysis module, used to obtain target objects to be delivered and target attribute information corresponding to the target objects, and cluster the target objects according to the target attribute information to obtain an initial clustering result;

[0006] A loading evaluation module, used to perform loading evaluation on the initial clustering result to obtain an initial loading result corresponding to the initial clustering result;

[0007] A distance calculation module, used to calculate the similarity between the target objects according to the target attribute information to obtain the corresponding target similarity between the target objects;

[0008] A loading adjustment module, used to adjust the initial loading result according to the target similarity to obtain a target loading result corresponding to the target object;

[0009] A data acquisition module, used to obtain the current transportation position corresponding to the target object and the target transportation position corresponding to the target loading result;

[0010] A path determination module, configured to determine a target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target transportation path in accordance with the target loading result;

[0011] An object determination module is used to obtain a target transportation result corresponding to the target transportation location, and obtain an object to be delivered that needs to be delivered in the target transportation result;

[0012] The intelligent dispatching module is used to determine a target dispatching path according to the target transportation location and the target delivery location corresponding to the object to be delivered, so that the object to be delivered is delivered according to the target dispatching path.

[0013] In a second aspect, an embodiment of the present invention provides a transportation collaborative management method based on intelligent auxiliary dispatching, including:

[0014] Obtaining target objects to be delivered and target attribute information corresponding to the target objects, and clustering the target objects according to the target attribute information to obtain initial clustering results;

[0015] Performing loading evaluation on the initial clustering result to obtain an initial loading result corresponding to the initial clustering result;

[0016] Calculating the similarity between the target objects according to the target attribute information to obtain the corresponding target similarity between the target objects;

[0017] Adjusting the initial loading result according to the target similarity to obtain a target loading result corresponding to the target object;

[0018] Obtaining a current transport location corresponding to the target object and obtaining a target transport location corresponding to the target loading result;

[0019] Determining a target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target loading result along the target transportation path;

[0020] Obtaining a target transportation result corresponding to the target transportation location, and obtaining an object to be delivered that needs to be delivered in the target transportation result;

[0021] A target dispatch path is determined according to the target transportation location and the target dispatch location corresponding to the object to be dispatched, so that the object to be dispatched is dispatched according to the target dispatch path.

[0022] The embodiment of the present invention provides a transportation collaborative management system and method based on intelligent auxiliary dispatching, the system comprising: a cluster analysis module for obtaining target objects to be dispatched and their corresponding target attribute information. The target objects are clustered by analyzing the target attribute information to generate an initial clustering result. By clustering analysis, similar target objects are classified to facilitate subsequent loading and transportation, thereby providing solid support for the efficient operation of the entire logistics process. The loading evaluation module is responsible for evaluating the initial clustering results to generate an initial loading result. The module ensures that transportation resources (such as vehicle capacity, staffing, etc.) are optimized by analyzing the clustered target objects. Specific evaluation indicators include vehicle load, volume utilization rate, and personnel allocation. Through this evaluation process, empty loads and resource waste can be avoided, and the overall economic efficiency of transportation can be improved. The distance calculation module calculates the similarity between target objects based on the target attribute information of the target objects, generates target similarity, and then provides basic data support for subsequent loading adjustments. By calculating the similarity between target objects, it is possible to more accurately understand which target objects can be interchanged, thereby improving the efficiency and reliability of loading adjustments. The loading adjustment module further optimizes the initial loading result according to the target similarity and generates the final target loading result. Then, by adjusting the loading plan, it ensures the full utilization of transportation resources, avoids empty load and waste of resources, and further improves the economy of the overall transportation. The data acquisition module is used to obtain the current transportation position corresponding to the target object and the target transportation position corresponding to the target loading result; the path determination module determines the target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position of the target object, and then optimizes the target transportation path to ensure that the target object can be efficiently transported according to the target loading result, thereby improving transportation efficiency and customer satisfaction. The object determination module is used to obtain the target transportation result corresponding to the target transportation position and obtain the object to be delivered in the target transportation result; the intelligent dispatching module determines the target dispatching path according to the target transportation position and the target dispatching position corresponding to the object to be delivered, ensuring that the object to be delivered can be dispatched according to the target dispatching path to improve the accuracy and timeliness of the dispatch. Through the collaborative work of the above modules, the entire logistics and dispatching system can achieve a high degree of intelligence and optimization, significantly improve transportation efficiency, resource utilization and customer satisfaction, and provide strong support for the sustainable development of the logistics industry. The system uses the loading adjustment module to further optimize the initial loading results according to the target similarity and generate the final target loading results. Then, by adjusting the loading plan, it ensures the full utilization of transportation resources, avoids empty loads and waste of resources, and further improves the overall economic efficiency of transportation. It also solves the problem that transportation collaborative management in related technologies often relies on manual operations or fixed rules, which makes it difficult to flexibly respond to dynamic transportation needs and complex operating environments, resulting in low transportation efficiency and high transportation costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A schematic diagram of the module structure of a transport collaborative management system based on intelligent assisted dispatching provided by an embodiment of the present invention;

[0025] Figure 2 A flow chart of a transport collaborative management method based on intelligent assisted dispatching provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0028] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0029] The embodiment of the present invention provides a transport collaborative management system and method based on intelligent assisted dispatching. The transport collaborative management system based on intelligent assisted dispatching can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0030] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0031] Please refer to Figure 1 , Figure 1 A schematic diagram of the module structure of a transport collaborative management system based on intelligent assisted dispatching provided in an embodiment of the present invention.

[0032] like Figure 1 As shown, the transport collaborative management system 200 based on intelligent assisted dispatching includes a cluster analysis module 201, a loading evaluation module 202, a distance calculation module 203, a loading adjustment module 204, a data acquisition module 205, a path determination module 206, an object determination module 207, and an intelligent dispatching module 208, wherein the cluster analysis module 201 is used to obtain target objects to be dispatched and target attribute information corresponding to the target objects, and cluster the target objects according to the target attribute information to obtain initial clustering results; the loading evaluation module 202 is used to perform loading evaluation on the initial clustering results to obtain initial loading results corresponding to the initial clustering results; the distance calculation module 203 is used to calculate the similarity between the target objects according to the target attribute information to obtain the target similarity between the target objects; the loading adjustment module 204 is used to The target similarity adjusts the initial loading result to obtain the target loading result corresponding to the target object; the data acquisition module 205 is used to obtain the current transportation position corresponding to the target object and the target transportation position corresponding to the target loading result; the path determination module 206 is used to determine the target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target loading result according to the target transportation path; the object determination module 207 is used to obtain the target transportation result corresponding to the target transportation position, and obtain the to-be-delivered object that needs to be delivered in the target transportation result; the intelligent dispatching module 208 is used to determine the target dispatching path according to the target transportation position and the target dispatching position corresponding to the to-be-delivered object, so that the to-be-delivered object is dispatched according to the target dispatching path.

[0033] Exemplarily, the cluster analysis module 201 obtains all target objects that need to be delivered through the database. These target objects can be packages, goods, containers, etc. Each target object should have a unique identifier (such as an order number, package ID, etc.) to facilitate differentiation and tracking in subsequent operations. Obtain target attribute information for each target object, including but not limited to the place of shipment, destination, weight, volume, special transportation requirements (such as cold chain, expedited, etc.).

[0034] Exemplarily, the cluster analysis module 201 divides the target objects into K categories using K-means clustering algorithm, DBSCAN clustering algorithm, etc. according to the target attribute information such as geographic location, weight, volume, special transportation requirements, etc., to obtain the initial clustering result. The target objects in each category in the initial clustering result have high similarity in attributes.

[0035] Exemplarily, the loading assessment module 202 obtains the initial clustering results and parses the key attribute information of the target objects in each cluster, such as total weight, total volume, special transportation requirements, etc. This information will be used for subsequent loading assessment. The loading assessment module 202 sets the standards and indicators for loading assessment. The evaluation indicators include but are not limited to vehicle capacity utilization: measuring whether the total weight and total volume of the target objects loaded on the vehicle are close to the carrying capacity of the vehicle; loading stability: evaluating whether the loaded target objects are stable during transportation and whether there is a risk of overturning or damage; special requirements satisfaction: checking whether the special transportation requirements of each target object (such as cold chain, expedited, etc.) are met, and then setting a threshold for each evaluation representation. For example, the vehicle capacity utilization should be as close as possible to the maximum carrying capacity of the vehicle, and the loading stability should be above a certain standard to ensure transportation safety. Thus, the loading assessment module 202 simulates the process of loading the target objects in each cluster onto the vehicle. This process can be simulated by three-dimensional virtual software, so that the simulated loading results are calculated and evaluated according to the preset evaluation indicators. For example, the vehicle capacity utilization, loading stability score, etc. are calculated to form the initial loading result. The initial loading results include but are not limited to the loading effect corresponding to each cluster and the evaluation score corresponding to the loading effect.

[0036] Exemplarily, the target attribute information of the target object in the distance calculation module 203 includes but is not limited to geographical attributes (such as the latitude and longitude of the place of shipment and the place of receipt), physical attributes (such as weight, volume), time attributes (such as expected delivery time) and special attributes (such as whether cold chain transportation is required). Classification is performed according to the attribute type, for example, the attributes can be divided into numerical type (such as weight, volume) and category type (such as whether cold chain transportation is required). Since the dimensions and ranges of different attributes may be different, it is necessary to standardize the attribute data. Therefore, according to the attribute type and actual needs of the target object, a similarity measurement method such as Euclidean distance, Manhattan distance, etc. is selected to convert the target attribute information of each target object into an attribute vector, and then all target objects are calculated for pairwise similarity according to the similarity measurement method to obtain a similarity matrix. Each element in the matrix represents the target similarity between the corresponding two target objects. The target similarity is used to characterize the degree to which the two target objects can be replaced during the loading adjustment process. The greater the target similarity, the greater the degree to which the two target objects can be replaced during the loading adjustment process, and the smaller the target similarity, the smaller the degree to which the two target objects can be replaced during the loading adjustment process.

[0037] Exemplarily, the loading adjustment module 204 determines the loading status of the initial loading result. When there is loading overflow or insufficient loading in the initial loading result, the initial loading result is adjusted using the target similarity to obtain the target loading result corresponding to the target object.

[0038] Exemplarily, the target similarity is used to characterize the degree to which two target objects can be replaced during the loading adjustment process, but the target similarity does not include the similarity of the volume or weight of the target objects. If the target similarity between the two target objects is greater than a preset threshold, the target volume or target weight corresponding to the target object is obtained, so that the target object with a larger target volume is replaced from the target vehicle with overflowing load to another target vehicle with a smaller target volume that is not fully loaded, so that the target vehicle with overflowing load can load the remaining objects. Thus, the target loading result is obtained.

[0039] Exemplarily, the data acquisition module 205 acquires the current transportation location corresponding to the target object from the database and acquires the corresponding target transportation location from the database by querying the unique identifier of the target object included in each cluster in the target loading result.

[0040] Exemplarily, the path determination module 206 performs path planning based on the current transport location and the target transport location to determine the target transport path corresponding to each cluster in the target loading result, so that the target objects contained in each cluster in the target loading result are transported according to the target transport path and arrive at the target transport location corresponding to each cluster in the target loading result.

[0041] Exemplarily, the target objects contained in each cluster in the target loading result are transported according to the target transportation path. After arriving at the target transportation location corresponding to each cluster in the target loading result, the object determination module 207 obtains the target transportation result corresponding to the target transportation location. The target transportation result is the target transportation location in the cluster corresponding to the target loading result after arriving at the target transportation location. Thus, the to-be-delivered objects that need to be delivered from the target transportation result are the target objects corresponding to the corresponding target transportation location.

[0042] Exemplarily, the intelligent dispatching module 208 performs path planning based on the target transportation location and the target delivery location corresponding to the object to be delivered, thereby obtaining the target dispatching path corresponding to the object to be delivered when the dispatcher dispatches the object to be delivered, so that the object to be delivered is delivered according to the target dispatching path.

[0043] Specifically, through the collaborative work of the above modules, the entire logistics and dispatching system can achieve a high degree of intelligence and optimization, significantly improve transportation efficiency, resource utilization and customer satisfaction, and provide strong support for the sustainable development of the logistics industry. The system further optimizes the initial loading results according to the target similarity through the loading adjustment module to generate the final target loading results, and then adjusts the loading plan to ensure the full utilization of transportation resources, avoid empty loads and waste of resources, and further improve the overall economic efficiency of transportation. It also solves the problem that transportation collaborative management in related technologies often relies on manual operations or fixed rules, making it difficult to flexibly respond to dynamic transportation needs and complex operating environments, resulting in low transportation efficiency and high transportation costs.

[0044] In some embodiments, the cluster analysis module includes: a data determination module, used to determine the cargo delivery center and obtain the transportation destination corresponding to the target object from the target attribute information; a data calculation module, used to calculate the distance information between the cargo delivery center and the transportation destination, and obtain the distribution distance between the target object and the cargo delivery center; a result determination module, used to cluster the target objects according to the distribution distance to obtain the initial clustering result.

[0045] Exemplarily, the cluster analysis module includes a data determination module, a data calculation module, and a result determination module.

[0046] Exemplarily, the data determination module determines the cargo delivery center to which the target object can be sent according to the transportation destination corresponding to the target object, and obtains the transportation destination corresponding to the target object from the target attribute information. The cargo delivery center can be a logistics company warehouse, a distribution center, or a regional transfer station. The transportation destination is usually the cargo collection address.

[0047] For example, the data calculation module uses Manhattan distance to calculate the distance information between the cargo delivery center and the transportation destination to obtain the delivery distance between the transportation destination and the cargo delivery center of the target object. Then, the result determination module clusters the target object according to the delivery distance using a clustering algorithm such as K-means clustering, hierarchical clustering, etc. to obtain an initial clustering result.

[0048] In some embodiments, the loading assessment module includes: an attribute acquisition module, which is used to obtain cargo attribute information corresponding to the target cargo of each subclass cluster in the initial clustering result from the target attribute information; a target acquisition module, which is used to determine the target delivery center corresponding to each subclass cluster in the initial clustering result from the cargo delivery center, and determine the target vehicle corresponding to the target delivery center; a target determination module, which is used to determine the target function and target constraint corresponding to the subclass cluster based on the cargo attribute information and the target vehicle; and an assessment determination module, which is used to perform loading assessment on the subclass cluster based on the target function and the target constraint, and obtain the initial loading result corresponding to the subclass cluster in the initial clustering result.

[0049] Exemplarily, the loading assessment module includes an attribute acquisition module, a target acquisition module, a target determination module, and an assessment determination module.

[0050] Exemplarily, the attribute acquisition module obtains cargo attribute information corresponding to the target cargo of each sub-cluster in the initial clustering result from the target attribute information. The cargo attribute information may include weight, volume, whether cold chain transportation is required, destination address, priority, etc.

[0051] Exemplarily, the target acquisition module selects the most suitable one or more cargo delivery centers according to the destination and cargo attributes (such as cold chain requirements) of the cargo in each sub-cluster. When selecting, factors such as geographical location, capacity of the delivery center, and special facilities (such as cold chain capabilities) need to be considered. And according to the attributes of the target cargo (such as weight, volume, whether cold chain transportation is required) and the capabilities of the delivery center, the appropriate target vehicle type and quantity are selected. For example, for cold chain cargo, select a vehicle with cold chain facilities; for heavy cargo, select a vehicle with sufficient carrying capacity.

[0052] Exemplarily, the target determination module determines the objective function and objective constraints corresponding to the subclass cluster based on the cargo attribute information and the target vehicle. The objective function is a mathematical expression used to optimize the loading scheme, which is usually used to maximize or minimize a certain indicator. Objective functions include but are not limited to minimizing transportation costs (such as distance, time), maximizing vehicle utilization (such as loading rate), and minimizing loading instability (such as center of gravity offset). Objective constraints are restrictions to ensure the feasibility and rationality of the solution. Objective constraints include but are not limited to vehicle load and volume restrictions, cargo priority and delivery time windows, special cargo requirements (such as cold chain), and then set corresponding constraints based on the cargo attribute information and the target vehicle capabilities to ensure the feasibility and safety of the loading scheme.

[0053] Exemplarily, the evaluation and determination module performs loading evaluation on the subclass clusters according to the objective function and the objective constraint, and obtains the initial loading result corresponding to the subclass cluster in the initial clustering result. For example, for each subclass cluster, a loading evaluation is performed according to the set objective function and objective constraint. The purpose of the evaluation is to determine the optimal loading scheme so that the objective function is optimized while satisfying all constraints. The evaluation process may involve a trade-off of multiple factors, such as minimizing transportation costs or maximizing vehicle utilization while satisfying vehicle load and volume restrictions. The evaluated loading schemes are organized into initial loading results. The initial loading results of each subclass cluster should include: vehicle allocation information (vehicle type, quantity), loading order and loading method, and loading evaluation indicators (such as loading rate, transportation cost, and loading stability).

[0054] In some embodiments, the target determination module includes: an information acquisition module, which is used to obtain the first length information, first width information, first height information, first weight information and first volume information corresponding to the target cargo from the cargo attribute information; a vehicle information acquisition module, which is used to obtain the second length information, second width information, second height information, target capacity information and target weight information corresponding to the target vehicle; a center of gravity information acquisition module, which is used to obtain the first minimum value and the first maximum value corresponding to the horizontal axis center of gravity corresponding to the target vehicle, the second minimum value and the second maximum value corresponding to the longitudinal axis center of gravity corresponding to the target vehicle, and the third minimum value and the third maximum value corresponding to the vertical axis center of gravity corresponding to the target vehicle; a volume function determination module, which is used to determine the target volume function according to the first length information, the first width information, the first height information and the target capacity information; a weight function determination module, which is used to determine the target weight function according to the first weight information and the target weight information; a center of gravity function determination module, which is used to determine the target volume function according to the first weight information, the target weight information, the first maximum a first constraint determination module, for determining a target capacity constraint according to the first volume information and the target capacity information, and for determining a target weight constraint according to the target weight information and the first weight information; a second constraint determination module, for determining a target center of gravity constraint according to the first minimum value, the first maximum value, the second minimum value, the second maximum value, the third minimum value and the third maximum value; a third constraint determination module, for determining a target squeezing constraint according to the first position information corresponding to the target cargo in the target vehicle and the second position information corresponding to other cargoes in the subclass cluster except the target cargo; a target constraint determination module, for determining the target constraint by fusing the target capacity constraint, the target weight constraint, the target center of gravity constraint and the target squeezing constraint.

[0055] Exemplarily, the target determination module includes but is not limited to an information acquisition module, a vehicle information acquisition module, a center of gravity information acquisition module, a volume function determination module, a weight function determination module, a weight function determination module, a target function determination module, a first constraint determination module, a second constraint determination module, a third constraint determination module, and a target constraint determination module.

[0056] Exemplarily, the information acquisition module obtains first length information, first width information, first height information, first weight information and first volume information corresponding to the target cargo from the cargo attribute information, wherein the first length information is used to characterize the length information of the target cargo, the first width information is used to characterize the width information of the target cargo, the first height information is used to characterize the height information of the target cargo, the first weight information is used to characterize the weight information of the target cargo, and the first volume information is used to characterize the minimum occupied volume information of the target cargo, which is usually less than or equal to the length information × the width information × the height information.

[0057] Exemplarily, the vehicle information acquisition module obtains the second length information, second width information, second height information, target capacity information and target weight information corresponding to the target vehicle from the vehicle information database. The second length information is used to characterize the internal length of the target vehicle, the second width information is used to characterize the internal width of the target vehicle, the second height information is used to characterize the internal height of the target vehicle, the target capacity information is used to characterize the maximum loading volume of the target vehicle, and the target weight information is used to characterize the maximum carrying weight of the target vehicle.

[0058] Exemplarily, the center of gravity information acquisition module obtains the first minimum value and the first maximum value corresponding to the horizontal axis center of gravity of the target vehicle, the second minimum value and the second maximum value corresponding to the longitudinal axis center of gravity of the target vehicle, and the third minimum value and the third maximum value corresponding to the vertical axis center of gravity of the target vehicle from the vehicle design database. The center of gravity limit information is used to ensure that the target vehicle remains balanced and stable after loading the cargo.

[0059] Exemplarily, the volume function determination module determines the target volume function according to the first length information, the first width information, the first height information and the target capacity information. The target volume function is used to calculate or evaluate whether the volume of the target cargo meets the loading capacity of the target vehicle. The target volume function can be designed to calculate the maximum volume ratio of the target vehicle, for example, max (∑ (first length information × first width information × first height information) / target capacity information), ∑ means summing up and max means obtaining the maximum value. The target volume function ensures that the total volume of all cargoes does not exceed the loading capacity of the vehicle, and also guarantees the maximum volume ratio.

[0060] Exemplarily, the weight function determination module determines the target weight function according to the first weight information and the target weight information. The target weight function is used to calculate or evaluate whether the total weight of the goods meets the carrying weight of the vehicle. The target weight function can be represented by weight utilization: max (∑ (first weight information) / target weight information), ∑ means the sum meets, max means the maximum value is obtained, and the target weight function ensures that the total weight of all goods does not exceed the loading capacity of the target vehicle, and also guarantees the maximum weight utilization.

[0061] Exemplarily, the center of gravity function determination module determines the target center of gravity function according to the first weight information, the target weight information, the first minimum value, the first maximum value, the second minimum value, the second maximum value, the third minimum value and the third maximum value. The target center of gravity function is used to calculate or evaluate whether the center of gravity of the vehicle after loading the cargo is within the safe range. It is usually expressed as: the horizontal axis center of gravity function = ∑ (first weight information × cargo horizontal axis coordinate) / total weight is between the first minimum value and the first maximum value, the vertical axis center of gravity function = ∑ (first weight information × cargo vertical axis coordinate) / total weight is between the second minimum value and the second maximum value, the vertical axis center of gravity function = ∑ (first weight information × cargo vertical axis coordinate) / total weight is between the third minimum value and the third maximum value, the target center of gravity function includes the horizontal axis center of gravity function, the vertical axis center of gravity function and the vertical axis center of gravity function, and the target center of gravity function is used to ensure that the center of gravity of the target vehicle after loading the target cargo is within the safety range specified in the design.

[0062] Exemplarily, the objective function determination module sets the weights of the target volume function, the target weight function, and the target center of gravity function according to expert experience or historical needs, and then performs weighted summation of the target volume function, the target weight function, and the target center of gravity function according to the corresponding weights to obtain the objective function corresponding to the subclass cluster. The objective function ensures that the optimal loading solution is found under the premise of satisfying the volume, weight, and center of gravity constraints.

[0063] Exemplarily, the first constraint determination module determines the target capacity constraint according to the first volume information and the target capacity information, and determines the target weight constraint according to the target weight information and the first weight information. The target capacity constraint is used to ensure that the volume of all target goods does not exceed the loading volume of the target vehicle, and is generally expressed as: target capacity constraint: ∑(first volume information) ≤ target capacity information. The target weight constraint is used to ensure that the weight of all target goods does not exceed the carrying weight of the target vehicle, and is generally expressed as: target weight constraint: ∑(first weight information) ≤ target weight information.

[0064] Exemplarily, the second constraint determination module determines the target center of gravity constraint according to the first minimum value, the first maximum value, the second minimum value, the second maximum value, the third minimum value and the third maximum value. The target center of gravity constraint is used to ensure that the center of gravity of the target vehicle after loading the cargo is within a safe range, and the target center of gravity constraint includes the horizontal axis center of gravity being between the first minimum value and the first maximum value, the longitudinal axis center of gravity being between the second minimum value and the second maximum value, and the vertical axis center of gravity being between the third minimum value and the third maximum value. The target center of gravity constraint ensures that the center of gravity of the target vehicle after loading the target cargo will not cause the target vehicle to be unstable or overturn.

[0065] Exemplarily, the third constraint determination module determines the target squeeze constraint according to the first position information corresponding to the target cargo in the target vehicle and the second position information corresponding to other cargoes in the subclass cluster except the target cargo. The target squeeze constraint is used to ensure that the target cargo will not be damaged due to insufficient space or mutual squeezing in the target vehicle, and is generally expressed as: ∑(first position information of the target cargo) + ∑(second position information of other cargoes) ≤ available space of the target vehicle. The target squeeze constraint ensures that all target cargoes have enough space in the target vehicle and will not be squeezed or collided with each other to cause damage.

[0066] Exemplarily, the target constraint determination module jointly determines a target capacity constraint, a target weight constraint, a target center of gravity constraint, and a target squeeze constraint as the target constraints.

[0067] In some embodiments, the target object includes a first object and a second object, the target attribute information includes first attribute information corresponding to the first object and second attribute information corresponding to the second object, and the distance calculation module includes: a first splitting module, used to classify the first attribute information by type to obtain first quality attribute information and a first numerical attribute corresponding to the first object, the first quality attribute information is used to characterize the attribute affecting the transportation quality of the first object, and the first numerical attribute is used to characterize the inherent attribute corresponding to the first object; a second splitting module, used to classify the second attribute information by type to obtain second quality attribute information and a second numerical attribute corresponding to the second object, the second quality attribute information is used to characterize the attribute affecting the transportation quality of the second object, and the second numerical attribute is used to characterize the inherent attribute corresponding to the second object; a first calculation module, used to obtain a first influence relationship between the attributes contained in the first quality attribute information and the second quality attribute information, and determine the first similarity corresponding to the first object and the second object according to the first influence relationship combined with the first quality attribute information and the second quality attribute information; a second calculation module, used to determine the second similarity corresponding to the first object and the second object according to the first numerical attribute and the second numerical attribute; a similarity fusion module, used to fuse the first similarity and the second similarity to determine the target similarity corresponding to the first object and the second object.

[0068] Exemplarily, the distance calculation module includes a first splitting module, a second splitting module, a first calculation module, a second calculation module, and a similarity fusion module.

[0069] Exemplarily, the target object includes at least a first object and a second object, and the target attribute information includes at least first attribute information corresponding to the first object and second attribute information corresponding to the second object.

[0070] Exemplarily, the first splitting module classifies the first attribute information to obtain the first quality attribute information and the first numerical attribute of the first object. The factors affecting the transportation quality in the first attribute information are classified, for example, the attributes affecting the durability, fragility, flexibility and other characteristics of the first object in the first attribute information are determined as the first quality attribute information, and the first quality attribute information directly affects the safety and transportation quality of the first object during transportation. The first numerical attribute includes specific inherent attributes such as length, width, height, weight, etc., quantifies the specific characteristics of the first object, and is not affected by external factors such as transportation time and transportation mode.

[0071] Exemplarily, the second splitting module classifies the second attribute information to obtain the second quality attribute information and the second numerical attribute of the second object. The second attribute information is classified according to the factors affecting the transportation quality, and the attributes affecting the durability, fragility, flexibility and other characteristics of the second object in the second attribute information are determined as the second quality attribute information, and the second quality attribute information affects the state of the second object during transportation. The second numerical attribute includes specific weight, volume, appearance characteristics, etc., quantifies the specific characteristics of the second object, and is not affected by external factors such as transportation time and transportation mode.

[0072] Exemplarily, the first calculation module analyzes the first quality attribute information and the second quality attribute information of the first object and the second object, determines the first influence relationship between the quality attributes corresponding to the first quality attribute information and the second quality attribute information, and calculates the first similarity corresponding to the quality attributes of the first object and the second object based on the first influence relationship. For example, the weight of the first quality attribute information and the second quality attribute information in calculating the similarity is determined according to the first influence relationship, so that the first similarity can be obtained by multiplying the similarity between the first quality attribute information and the second quality attribute information according to a similarity metric (such as cosine similarity, Jaccard similarity, etc.) by the weight corresponding to the first influence relationship.

[0073] For example, the first calculation module uses a correlation analysis method (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.) to measure the correlation between different quality attributes according to the first quality attribute information and the second quality attribute information, so that when the correlation is greater than a preset value, it is determined that there is a first influence relationship between the corresponding two quality attributes. The first influence relationship can be a positive correlation relationship or a negative correlation relationship.

[0074] Exemplarily, the second calculation module determines the second similarity between the first object and the second object according to the first numerical attribute and the second numerical attribute. Considering that the target similarity is that the subsequent target object is replaced for support during loading, it is ensured that the larger the difference in inherent attributes such as weight and volume information between the first object and the second object, the more obvious the improvement in loading after subsequent replacement. Therefore, the smaller the difference between the first numerical attribute and the second numerical attribute, the greater the second similarity between the first object and the second object.

[0075] Exemplarily, the similarity fusion module uses weighted average method, logical addition or other algorithms to effectively combine the first similarity and the second similarity to obtain a more comprehensive target similarity. The greater the target similarity, the more obvious the loading effect after the first object and the second object are replaced and loaded.

[0076] In some embodiments, the first calculation module includes: a value determination module, which is used to determine the first attribute and the second attribute associated with the first influence relationship, obtain the first data corresponding to the first attribute and the second value corresponding to the second attribute from the first quality attribute information, and obtain the third data corresponding to the first attribute and the fourth value corresponding to the second attribute from the second quality attribute information; a first judgment module, which is used to obtain the first probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the first data and the second probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the third data when the first data and the third data are not equal; a first distribution calculation module, which is used to calculate the value corresponding to the second attribute according to the first probability distribution and the third data. a first attribute similarity between the first data and the second data determined by a second probability distribution; a second judgment module, used for obtaining, when the second data and the fourth data are not equal, a third probability distribution of the occurrence of the first attribute corresponding value under the condition corresponding to the second data and a fourth probability distribution of the occurrence of the first attribute corresponding value under the condition corresponding to the fourth data; a second distribution calculation module, used for determining the second attribute similarity between the third data and the fourth data according to the third probability distribution and the fourth probability distribution; a fusion calculation module, used for fusing the first attribute similarity and the second attribute similarity to determine the first similarity corresponding to the first object and the second object; wherein the first similarity is obtained according to the following formula:

[0077]

[0078] in, represents the first similarity, r represents the number of the first influence relationship, abs represents the absolute value, represents the maximum value corresponding to the second attribute, represents the maximum value corresponding to the first attribute, Indicates that the first attribute is the first data The corresponding probability value in the first probability distribution when the second attribute is the value w, Indicates that the first attribute is the third data The corresponding probability value in the second probability distribution when the second attribute is the value w, Indicates that the second attribute is the second data The corresponding probability value in the third probability distribution when the first attribute is a value h, Indicates that the second attribute is the second data The corresponding probability value in the fourth probability distribution when the first attribute is the numerical value h.

[0079] Exemplarily, the first calculation module includes a numerical determination module, a first judgment module, a first distribution calculation module, a second judgment module, a second distribution calculation module, and a fusion calculation module.

[0080] Exemplarily, the numerical determination module obtains the corresponding first attribute and second attribute from the first influence relationship, that is, there is a positive or negative correlation between the first attribute and the second attribute, and then obtains the first data corresponding to the first attribute in the first object and the second numerical value corresponding to the second attribute in the first object from the first quality attribute information, and obtains the third data corresponding to the first attribute in the second object and the fourth numerical value corresponding to the second attribute in the second object from the second quality attribute information.

[0081] Exemplarily, when the first data and the third data are not equal, the first judgment module obtains the first probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the first data and obtains the second probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the third data. That is, when the first attribute is the first data, the probability that each value corresponding to the second attribute may occur is obtained, thereby obtaining the first probability distribution. That is to say, when the first attribute is the first data, the probability that each value of each second attribute may occur is obtained. When the first attribute is the third data, the probability that each value corresponding to the second attribute may occur is obtained, thereby obtaining the second probability distribution. That is to say, when the first attribute is the third data, the probability that each value of each second attribute may occur is obtained.

[0082] Exemplarily, the first distribution calculation module determines the first attribute similarity between the first data and the second data according to the first probability distribution and the second probability distribution, that is, the similarity between the first data and the third data under the first attribute is not only related to the distance between the first data and the third data, but also related to the probability distribution corresponding to the value of the second attribute under the first attribute. For example, the first attribute similarity between the first data and the second data is calculated by using the first probability distribution and the second probability distribution using a similarity measurement method such as KL divergence, Jensen-Shannon divergence, etc. The first attribute similarity can also be obtained according to the following formula:

[0083]

[0084] in, Indicates the similarity of the first attribute, abs means taking the absolute value, represents the maximum value corresponding to the second attribute, Indicates that the first attribute is the first data When the second attribute is the value w, the corresponding probability value in the first probability distribution is, Indicates that the first attribute is the third data The corresponding probability value in the second probability distribution when the second attribute is the value w.

[0085] Exemplarily, when the second data and the fourth data are not equal, the second judgment module obtains the third probability distribution of the occurrence of the value corresponding to the first attribute under the condition corresponding to the second data and obtains the fourth probability distribution of the occurrence of the value corresponding to the first attribute under the condition corresponding to the fourth data. That is, when the second attribute is the second data, the probability that each value corresponding to the first attribute may occur is obtained, thereby obtaining the third probability distribution. That is to say, when the second attribute is the fourth data, the probability that each value corresponding to each first attribute may occur is obtained. When the second attribute is the fourth data, the probability that each value corresponding to the first attribute may occur is obtained, thereby obtaining the fourth probability distribution. That is to say, when the second attribute is the fourth data, the probability that each value corresponding to the first attribute may occur is obtained.

[0086] Exemplarily, the second distribution calculation module determines the second attribute similarity between the third data and the fourth data according to the third probability distribution and the fourth probability distribution; for example, the second attribute similarity between the first data and the second data is calculated by using the third probability distribution and the fourth probability distribution using a similarity measurement method such as KL divergence, Jensen-Shannon divergence, etc. The second attribute similarity can also be obtained according to the following formula:

[0087]

[0088] in, Indicates the similarity of the second attribute, abs means taking the absolute value, Indicates the maximum value corresponding to the first attribute, Indicates that the second attribute is the second data The corresponding probability value in the third probability distribution when the first attribute is a value h, Indicates that the second attribute is the second data The corresponding probability value in the fourth probability distribution when the first attribute is the numerical value h.

[0089] Exemplarily, the fusion calculation module sums the first attribute similarities and the second attribute similarities under all first influence relationships to determine the first similarity corresponding to the first object and the second object; wherein the first similarity is obtained according to the following formula:

[0090]

[0091] in, represents the first similarity, r represents the number of corresponding first influence relations, and abs represents the absolute value. Indicates the maximum value corresponding to the second attribute. Indicates the maximum value corresponding to the first attribute, Indicates that the first attribute is the first data When the second attribute is the value w, the corresponding probability value in the first probability distribution is, Indicates that the first attribute is the third data The corresponding probability value in the second probability distribution when the second attribute is the value w, Indicates that the second attribute is the second data When the first attribute is the value h, the corresponding probability value in the third probability distribution is, Indicates that the second attribute is the second data The corresponding probability value in the fourth probability distribution when the first attribute is the numerical value h.

[0092] Exemplarily, when calculating the first similarity between the first object and the second object, the present application not only considers the direct difference in values ​​between the first attribute and the second attribute through a multi-dimensional comprehensive consideration strategy, but also deeply analyzes their probability distribution under different conditions. This comprehensive analysis method can more comprehensively capture the similarity between the first object and the second object, thereby providing a more accurate similarity evaluation result. This process takes into account both the direct numerical differences of the attributes and their potential relationships under complex conditions, and comprehensively evaluates the degree of similarity from multiple dimensions, greatly improving the accuracy and reliability of the similarity calculation.

[0093] In some embodiments, the loading adjustment module includes: a state screening module, used to obtain a first cluster corresponding to a loading overflow state and a second cluster corresponding to an underload state from the initial loading result; an object acquisition module, used to obtain a first associated object corresponding to the first cluster and a second associated object corresponding to the second cluster according to the target similarity when the distance between the first destination center corresponding to the first cluster and the second destination center corresponding to the second cluster is less than a preset distance; an information determination module, used to obtain the second volume information corresponding to the first associated object and the third volume information corresponding to the second associated object; a loading replacement module, used to swap the loading positions of the first associated object and the second associated object when the second volume information is greater than the third volume information, to obtain the target loading result.

[0094] Exemplarily, the loading adjustment module includes a state screening module, an object acquisition module, an information determination module, and a loading replacement module.

[0095] For example, the state screening module screens out the first cluster corresponding to the loading effect of overflow and the second cluster corresponding to the loading effect of under-loading from the initial loading results. Thus, by screening out the clusters of overflow and under-loading, the target vehicle that needs to be optimized can be quickly located, which helps to make subsequent adjustments and optimizations more accurately.

[0096] Exemplarily, the object acquisition module processes and calculates the distance information between the first destination center of the first cluster and the second destination center of the second cluster, and when the distance information is less than a preset distance, the first associated object corresponding to the first cluster and the second associated object corresponding to the second cluster are obtained from the first cluster and the second cluster when the target similarity between any two target objects is greater than the preset similarity.

[0097] For example, if the target similarity between the target object a in the first cluster and the target object b in the second cluster is greater than a preset similarity, the target object a in the first cluster is determined as the first associated object, and the target object b in the second cluster is determined as the second associated object.

[0098] Exemplarily, the information determination module obtains the third volume information corresponding to the first associated object and the third volume information corresponding to the second associated object from the target attribute information. Thus, when the loading replacement module obtains that the second volume information is greater than the third volume information, the loading positions of the first associated object and the second associated object are swapped, so that more space is freed in the first cluster and more space is occupied in the second cluster, thereby obtaining the target loading result.

[0099] Exemplarily, when the distance information is greater than or equal to the preset distance, or the second volume information is less than or equal to the third volume information, any two target objects obtained from the first cluster and the second cluster cannot be replaced.

[0100] Specifically, the present application can significantly improve the accuracy and efficiency of loading, reduce space waste and loading overflow problems, and ultimately obtain better target loading results by screening problem clusters, reasonably matching related objects, accurately obtaining volume information, and effectively performing loading replacement.

[0101] In some embodiments, the system further includes: a vehicle tracking module, used to obtain a target vehicle corresponding to the target loading result, and to track the target vehicle in real time according to an Internet of Things device to obtain a position of the target vehicle; and a path adjustment module, used to adjust the target transportation path in real time according to the position of the target vehicle to obtain the adjusted target transportation path.

[0102] Exemplarily, the transport collaborative management system based on intelligent assisted dispatching also includes: a vehicle tracking module and a path adjustment module.

[0103] Exemplarily, the vehicle tracking module obtains the target vehicle corresponding to the target loading result, and performs real-time tracking through IoT devices such as GPS, RFID, sensors, etc. to obtain the target vehicle position of the target vehicle.

[0104] For example, the path adjustment module analyzes the driving status of the target vehicle and then evaluates the effectiveness and applicability of the current path in combination with the target vehicle position and the preset path planning algorithm. If problems are found in the current path (such as traffic jams, weather effects, etc.), the target transportation path is adjusted in real time according to the target vehicle position and real-time traffic information, and then a new target transportation path is generated according to the adjusted path planning.

[0105] Specifically, by tracking the target vehicle in real time, obtaining accurate location information, and then dynamically adjusting the transportation route according to real-time traffic and environmental changes, the flexibility and efficiency of transportation can be significantly improved, ensuring that the target vehicle travels on the optimal route, and ultimately obtaining the adjusted target transportation vehicle, achieving efficient management and optimization of the transportation process.

[0106] In some embodiments, the path adjustment module includes: an environmental information acquisition module, used to obtain target environmental information and abnormal event information corresponding to the target vehicle position; a detailed path adjustment module, used to adjust the target transportation path in real time according to the target vehicle position combined with the target environmental information and the abnormal event information to obtain the adjusted target transportation path.

[0107] Exemplarily, the path adjustment module includes an environment information acquisition module and a detailed path adjustment module.

[0108] Exemplarily, the environmental information acquisition module obtains the environmental information of the target vehicle at the target vehicle location through various sensors, Internet of Things devices, traffic management systems, etc. Environmental information may include weather conditions (such as rain, snow, fog, etc.), road conditions (such as slippery, icy, etc.), road types (such as highways, urban roads, etc.), and other surrounding environmental factors (such as construction areas, school areas, etc.). At the same time, real-time monitoring and acquisition of abnormal event information related to the target vehicle location. These abnormal events may include traffic accidents, road closures, traffic jams, temporary traffic control, natural disasters, etc.

[0109] Exemplarily, the detailed path adjustment module evaluates the suitability of the current target transport path in combination with the target vehicle position, environmental information (such as weather, road conditions, etc.) and abnormal event information (such as traffic accidents, road closures, etc.) of the target vehicle. If it is found that the current target transport path is affected by abnormal events (such as traffic accidents) or adverse environmental conditions (such as heavy fog, road icing, etc.), the target transport path is adjusted based on real-time data. When adjusting the target transport path, the system may consider a variety of factors, such as avoiding accident areas, avoiding bad weather, detouring closed sections, etc., while ensuring that the new target transport path is still optimal or suboptimal to ensure transportation efficiency. Thus, a new target transport path is generated based on the adjusted target transport path, and the navigation information of the target transport vehicle is updated in real time to ensure that the target vehicle can continue to travel along the new target transport path.

[0110] Specifically, the environmental information acquisition module provides data support for the detailed path adjustment module by collecting the environment and abnormal event information of the target vehicle location. The detailed path adjustment module analyzes and adjusts the transportation path in real time based on this data to ensure that the target vehicle can complete the transportation task safely and efficiently. Through this dynamic adjustment mechanism, the system can significantly improve transportation efficiency, enhance safety, and effectively respond to various emergencies during transportation.

[0111] See also Figure 2 , Figure 2 A transport collaborative management method based on intelligent assisted dispatching is provided in an embodiment of the present application, and the transport collaborative management method based on intelligent assisted dispatching includes steps S101 to S108.

[0112] Step S101: obtaining target objects to be delivered and target attribute information corresponding to the target objects, and clustering the target objects according to the target attribute information to obtain initial clustering results;

[0113] Step S102: performing loading evaluation on the initial clustering result to obtain an initial loading result corresponding to the initial clustering result;

[0114] Step S103: calculating the similarity between the target objects according to the target attribute information to obtain the target similarity between the target objects;

[0115] Step S104: adjusting the initial loading result according to the target similarity to obtain a target loading result corresponding to the target object;

[0116] Step S105, obtaining the current transport position corresponding to the target object and obtaining the target transport position corresponding to the target loading result;

[0117] Step S106: determining a target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target loading result along the target transportation path;

[0118] Step S107: obtaining a target transportation result corresponding to the target transportation location, and obtaining an object to be delivered that needs to be delivered in the target transportation result;

[0119] Step S108: determining a target dispatch path according to the target transportation location and the target delivery location corresponding to the object to be delivered, so that the object to be delivered is delivered according to the target dispatch path.

[0120] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the transport collaborative management method based on intelligent assisted dispatching described above can refer to the corresponding process in the aforementioned transport collaborative management system based on intelligent assisted dispatching embodiment, and will not be repeated here.

[0121] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of a transport collaborative management system based on intelligent assisted dispatching as provided in the description of the embodiment of the present invention.

[0122] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0123] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0124] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0125] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A transportation collaborative management system based on intelligent assisted dispatching, characterized in that: The system comprises: A cluster analysis module is used to obtain target objects to be delivered and target attribute information corresponding to the target objects, determine a cargo delivery center, and obtain a transportation destination corresponding to the target object from the target attribute information; calculate the distance information between the cargo delivery center and the transportation destination, and obtain the delivery distance between the target object and the cargo delivery center; cluster the target objects according to the delivery distance to obtain an initial clustering result; An attribute acquisition module, used to obtain cargo attribute information corresponding to the target cargo of each sub-cluster in the initial clustering result from the target attribute information; A target acquisition module, used to determine a target delivery center corresponding to each of the sub-cluster in the initial clustering result from the cargo delivery center, and determine a target vehicle corresponding to the target delivery center; A target determination module, used for determining the target function and target constraint corresponding to the subclass cluster according to the cargo attribute information and the target vehicle; An evaluation and determination module, configured to perform a loading evaluation on the subclass cluster according to the objective function and the objective constraint, and obtain an initial loading result corresponding to the subclass cluster in the initial clustering result; A distance calculation module, used to calculate the similarity between the target objects according to the target attribute information to obtain the corresponding target similarity between the target objects; A loading adjustment module, used to obtain, from the initial loading result, a first cluster corresponding to a loading overflow state and a second cluster corresponding to an under-loading state; when the distance between a first destination center corresponding to the first cluster and a second destination center corresponding to the second cluster is less than a preset distance, obtain a first associated object corresponding to the first cluster and a second associated object corresponding to the second cluster according to the target similarity; obtain second volume information corresponding to the first associated object and third volume information corresponding to the second associated object; when the second volume information is greater than the third volume information, swap the loading positions of the first associated object and the second associated object to obtain a target loading result; A data acquisition module, used to obtain the current transportation position corresponding to the target object and the target transportation position corresponding to the target loading result; A path determination module, configured to determine a target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target transportation path in accordance with the target loading result; An object determination module is used to obtain a target transportation result corresponding to the target transportation location, and obtain an object to be delivered that needs to be delivered in the target transportation result; An intelligent dispatching module, used to determine a target dispatching path according to the target transportation location and the target delivery location corresponding to the object to be delivered, so that the object to be delivered is delivered according to the target dispatching path; The target object includes a first object and a second object, the target attribute information includes first attribute information corresponding to the first object and second attribute information corresponding to the second object, and the distance calculation module includes: A first splitting module is used to classify the first attribute information by type to obtain first quality attribute information and a first numerical attribute corresponding to the first object, wherein the first quality attribute information is used to characterize an attribute that affects the transportation quality of the first object, and the first numerical attribute is used to characterize an inherent attribute corresponding to the first object; A second splitting module is used to classify the second attribute information by type to obtain second quality attribute information and a second numerical attribute corresponding to the second object, wherein the second quality attribute information is used to characterize an attribute that affects the transportation quality of the second object, and the second numerical attribute is used to characterize an inherent attribute corresponding to the second object; a first calculation module, configured to obtain a first influence relationship between attributes included in the first quality attribute information and the second quality attribute information, and determine a first similarity corresponding to the first object and the second object according to the first influence relationship in combination with the first quality attribute information and the second quality attribute information; A second calculation module, configured to determine a corresponding second similarity between the first object and the second object according to the first numerical attribute and the second numerical attribute; A similarity fusion module is used to fuse the first similarity and the second similarity to determine the corresponding target similarity between the first object and the second object.

2. The system according to claim 1, characterized in that The target determination module comprises: An information acquisition module, used to obtain first length information, first width information, first height information, first weight information and first volume information corresponding to the target cargo from the cargo attribute information; A vehicle information acquisition module, used to obtain second length information, second width information, second height information, target capacity information and target weight information corresponding to the target vehicle; A center of gravity information acquisition module, used to obtain a first minimum value and a first maximum value corresponding to the horizontal axis center of gravity of the target vehicle, a second minimum value and a second maximum value corresponding to the longitudinal axis center of gravity of the target vehicle, and a third minimum value and a third maximum value corresponding to the vertical axis center of gravity of the target vehicle; a volume function determination module, configured to determine a target volume function according to the first length information, the first width information, the first height information and the target capacity information; a weight function determination module, configured to determine a target weight function according to the first weight information and the target weight information; a center of gravity function determination module, configured to determine a target center of gravity function according to the first weight information, the target weight information, the first minimum value, the first maximum value, the second minimum value, the second maximum value, the third minimum value, and the third maximum value; An objective function determination module, used for fusing the objective volume function, the objective weight function and the objective center of gravity function to determine the objective function corresponding to the subclass cluster; a first constraint determination module, configured to determine a target capacity constraint according to the first volume information and the target capacity information, and to determine a target weight constraint according to the target weight information and the first weight information; a second constraint determination module, configured to determine a target center of gravity constraint according to the first minimum value, the first maximum value, the second minimum value, the second maximum value, the third minimum value, and the third maximum value; A third constraint determination module is used to determine a target squeezing constraint according to first position information corresponding to the target cargo on the target vehicle and second position information corresponding to other cargoes in the subclass cluster except the target cargo; The target constraint determination module determines the target constraint by integrating the target capacity constraint, the target weight constraint, the target center of gravity constraint and the target squeezing constraint.

3. The system according to claim 1, characterized in that The first calculation module includes: a value determination module, configured to determine a first attribute and a second attribute associated with the first influence relationship, obtain first data corresponding to the first attribute and second data corresponding to the second attribute from the first quality attribute information, and obtain third data corresponding to the first attribute and fourth data corresponding to the second attribute from the second quality attribute information; A first judgment module, configured to obtain, when the first data and the third data are not equal, a first probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the first data and a second probability distribution of the occurrence of the value corresponding to the second attribute under the condition corresponding to the third data; A first distribution calculation module, configured to determine a first attribute similarity between the first data and the third data according to the first probability distribution and the second probability distribution; A second judgment module is used for obtaining a third probability distribution of the occurrence of the value corresponding to the first attribute under the condition corresponding to the second data and a fourth probability distribution of the occurrence of the value corresponding to the first attribute under the condition corresponding to the fourth data when the second data and the fourth data are not equal; A second distribution calculation module, used to determine a second attribute similarity between the second data and the fourth data according to the third probability distribution and the fourth probability distribution; a fusion calculation module, configured to fuse the first attribute similarity and the second attribute similarity to determine the first similarity corresponding to the first object and the second object; The first similarity is obtained according to the following formula: ; ; in, represents the first similarity, r represents the number of the first influence relationship, abs represents the absolute value, represents the maximum value corresponding to the second attribute, represents the maximum value corresponding to the first attribute, Indicates that the first attribute is the first data The corresponding probability value in the first probability distribution when the second attribute is the value w, Indicates that the first attribute is the third data The corresponding probability value in the second probability distribution when the second attribute is the value w, Indicates that the second attribute is the second data The corresponding probability value in the third probability distribution when the first attribute is a value h, Indicates that the second attribute is the fourth data The corresponding probability value in the fourth probability distribution when the first attribute is the numerical value h.

4. The system according to any one of claims 1 to 3, characterized in that: The system further comprises: A vehicle tracking module is used to obtain a target vehicle corresponding to the target loading result, and to track the target vehicle in real time according to an Internet of Things device to obtain the position of the target vehicle; The path adjustment module is used to adjust the target transportation path in real time according to the position of the target vehicle to obtain the adjusted target transportation path.

5. The system according to claim 4, characterized in that The path adjustment module includes: An environmental information acquisition module, used to obtain target environmental information and abnormal event information corresponding to the target vehicle position; The detailed path adjustment module is used to adjust the target transportation path in real time according to the target vehicle position combined with the target environment information and the abnormal event information to obtain the adjusted target transportation path.

6. A transportation collaborative management method based on intelligent assisted dispatching, characterized in that: The method comprises: Obtaining a target object to be delivered and target attribute information corresponding to the target object, determining a cargo delivery center, and obtaining a transportation destination corresponding to the target object from the target attribute information; calculating distance information between the cargo delivery center and the transportation destination, and obtaining a delivery distance between the target object and the cargo delivery center; clustering the target objects according to the delivery distance to obtain an initial clustering result; Obtain cargo attribute information corresponding to the target cargo of each sub-cluster in the initial clustering result from the target attribute information; determine the target delivery center corresponding to each sub-cluster in the initial clustering result from the cargo delivery center, and determine the target vehicle corresponding to the target delivery center; determine the objective function and objective constraint corresponding to the sub-cluster according to the cargo attribute information and the target vehicle; perform loading evaluation on the sub-cluster according to the objective function and the objective constraint, and obtain the initial loading result corresponding to the sub-cluster in the initial clustering result; Calculating the similarity between the target objects according to the target attribute information to obtain the corresponding target similarity between the target objects; A first cluster corresponding to a loading overflow state and a second cluster corresponding to an under-loading state are obtained from the initial loading result; when a distance between a first destination center corresponding to the first cluster and a second destination center corresponding to the second cluster is less than a preset distance, a first associated object corresponding to the first cluster and a second associated object corresponding to the second cluster are obtained according to the target similarity; second volume information corresponding to the first associated object and third volume information corresponding to the second associated object are obtained; when the second volume information is greater than the third volume information, the loading positions of the first associated object and the second associated object are swapped to obtain a target loading result; Obtaining a current transport location corresponding to the target object and obtaining a target transport location corresponding to the target loading result; Determining a target transportation path corresponding to the target loading result according to the current transportation position and the target transportation position, so that the target object is transported according to the target loading result along the target transportation path; Obtaining a target transportation result corresponding to the target transportation location, and obtaining an object to be delivered that needs to be delivered in the target transportation result; Determining a target dispatch path according to the target transportation location and the target dispatch location corresponding to the object to be dispatched, so that the object to be dispatched is dispatched according to the target dispatch path; The target object includes a first object and a second object, the target attribute information includes first attribute information corresponding to the first object and second attribute information corresponding to the second object, and the similarity between the target objects is calculated according to the target attribute information to obtain the target similarity between the target objects, including: Classifying the first attribute information by type to obtain first quality attribute information and a first numerical attribute corresponding to the first object, wherein the first quality attribute information is used to characterize an attribute that affects the transport quality of the first object, and the first numerical attribute is used to characterize an inherent attribute corresponding to the first object; Classifying the second attribute information by type to obtain second quality attribute information and a second numerical attribute corresponding to the second object, wherein the second quality attribute information is used to characterize an attribute affecting the transport quality of the second object, and the second numerical attribute is used to characterize an inherent attribute corresponding to the second object; Obtaining a first influence relationship between the attributes included in the first quality attribute information and the second quality attribute information, and determining a corresponding first similarity between the first object and the second object according to the first influence relationship in combination with the first quality attribute information and the second quality attribute information; Determine a corresponding second similarity between the first object and the second object according to the first numerical attribute and the second numerical attribute; The first similarity and the second similarity are combined to determine the target similarity corresponding to the first object and the second object.

Images