Intelligent transport capacity scheduling method and system

Abstract

The invention discloses an intelligent transport capacity scheduling method and system, and belongs to the technical field of computers. The technical scheme provided by the embodiment of the invention provides a multi-dimensional and multi-step intelligent transport capacity scheduling method. According to the method, more accurate and flexible transport capacity distribution is realized by acquiring and comprehensively analyzing information of shops, commodities, areas, transport capacity, objects and the like. According to the method, the distribution distance and the transport capacity order receiving willingness are considered, and factors such as special requirements of orders, commodity characteristics, shop requirements, area conditions and transport capacity characteristics are taken into consideration, so that the flexibility and efficiency of transport capacity scheduling are greatly improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent transportation capacity scheduling method and system. Background Art

[0002] With the development of computer technology, take-out, carpooling, express delivery and other businesses have emerged, and business orders have continued to increase. Usually, after an order is generated, it is necessary to select a target transport capacity for the order, and the target transport capacity will complete the delivery of the goods corresponding to the order.

[0003] In the related technology, the delivery fee of the order is determined according to the delivery distance of the order, and the order is pushed to multiple delivery capacities. If any of the multiple delivery capacities accepts the order, the any delivery capacity is determined as the target capacity for the order, and after the target capacity completes the delivery of the order, the delivery fee of the order is transferred to the target capacity.

[0004] However, the above scheme can only allocate target capacity to orders based on the delivery distance of the orders and the delivery capacity's willingness to accept orders, and the flexibility of allocating target capacity is poor. Summary of the invention

[0005] The embodiment of the present application provides an intelligent capacity scheduling method and system, which can improve the flexibility and efficiency of capacity allocation. The technical solution is as follows:

[0006] On the one hand, a smart transportation capacity scheduling method is provided, the method comprising:

[0007] In response to a delivery request of a target store for a target product, store information of the target store, product information of the target product, area information of a target area, transportation capacity information of the target area, and object information of a target object are obtained, wherein the target area is a delivery area to which the target store belongs, and the target object is an object to which the target product needs to be delivered;

[0008] Determining a target delivery requirement for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object;

[0009] Based on the area information of the target area, the transportation capacity information of the target area and the target delivery demand, determine a target transportation capacity from a plurality of candidate transportation capacities of the target area, the target transportation capacity being the transportation capacity that matches the target delivery demand;

[0010] The target transportation capacity is summoned to deliver the target commodity to the target object.

[0011] In one aspect, an intelligent transportation capacity dispatching system is provided, the system comprising:

[0012] an acquisition module, configured to, in response to a delivery request of a target store for a target product, acquire store information of the target store, product information of the target product, area information of a target area, transportation capacity information of the target area, and object information of a target object, wherein the target area is a delivery area to which the target store belongs, and the target object is an object to which the target product needs to be delivered;

[0013] A demand determination module, configured to determine a target delivery demand for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object;

[0014] A transport capacity determination module, configured to determine a target transport capacity from a plurality of candidate transport capacities of the target area based on the area information of the target area, the transport capacity information of the target area, and the target delivery demand, wherein the target transport capacity is a transport capacity that matches the target delivery demand;

[0015] The summoning module is used to summon the target transportation capacity to deliver the target commodity to the target object.

[0016] On the one hand, a computer device is provided, which includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the intelligent capacity scheduling method.

[0017] On the one hand, a computer-readable storage medium is provided, in which at least one computer program is stored, and the computer program is loaded and executed by a processor to implement the intelligent capacity scheduling method.

[0018] On the one hand, a computer program product or a computer program is provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned intelligent capacity scheduling method.

[0019] The technical solution provided by the embodiment of the present application proposes a multi-dimensional, multi-step intelligent capacity scheduling method. This method achieves a more accurate and flexible capacity allocation by acquiring and comprehensively analyzing various information such as stores, goods, regions, capacity and objects. This method not only takes into account the delivery distance and the willingness of the capacity to accept orders, but also takes into account factors such as the special needs of the order, product characteristics, store requirements, regional conditions and capacity characteristics, thereby greatly improving the flexibility and efficiency of capacity scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a schematic diagram of an implementation environment of an intelligent transportation capacity scheduling method provided in an embodiment of the present application;

[0022] Figure 2 It is a flow chart of an intelligent transport capacity scheduling method provided by an embodiment of the present application;

[0023] Figure 3 is another flow chart of an intelligent transport capacity scheduling method provided by an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of an intelligent transport capacity dispatching device provided in an embodiment of the present application;

[0025] Figure 5 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0027] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with basically the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on quantity and execution order.

[0028] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain better results.

[0029] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.

[0030] Normalization: Mapping sequences with different value ranges to the interval (0, 1) facilitates data processing. In some cases, the normalized values ​​can be directly implemented as probabilities.

[0031] Embedded Coding: Embedded coding mathematically represents a correspondence, that is, mapping data in X space to Y space through a function F, where the function F is an injective function, and the mapping result is structural preservation. The injective function indicates that the data after mapping is uniquely corresponding to the data before mapping, and structural preservation indicates that the size relationship of the data before mapping is the same as the size relationship of the data after mapping. For example, there are data X1 and X2 before mapping, and after mapping, Y1 corresponding to X1 and Y2 corresponding to X2 are obtained. If the data X1 before mapping is greater than X2, then correspondingly, the data Y1 after mapping is greater than Y2. For words, it means mapping the words to another space to facilitate subsequent machine learning and processing.

[0032] Attention weight: It can indicate the importance of a certain data in the training or prediction process. Importance indicates the influence of input data on output data. Data with high importance has a higher corresponding attention weight value, and data with low importance has a lower corresponding attention weight value. In different scenarios, the importance of data is different. The process of training the attention weight of the model is also the process of determining the importance of data.

[0033] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0034] In related technologies, the order allocation process mainly depends on two factors: delivery distance and the willingness of transport capacity to accept orders. This simple allocation mechanism is not flexible enough when dealing with complex and changeable actual delivery scenarios. Specifically, the system cannot fully consider multi-dimensional factors such as the special needs of orders, the characteristics of goods, the requirements of stores, and the real-time status of the delivery area. This leads to inefficient capacity allocation and is unable to meet the growing demand for precise delivery. At the same time, due to the lack of in-depth analysis of capacity characteristics, it is difficult for the system to achieve optimal matching, affecting the overall delivery quality and efficiency.

[0035] For example, in a large city’s food delivery system, hundreds of thousands of orders need to be processed every day. The system uses a simple allocation algorithm based on distance and willingness to accept orders. However, this approach cannot cope with complex real-world situations. For example, some orders from high-end restaurants may require more specialized delivery services, some fresh goods require special insulation equipment, and during traffic congestion, allocating capacity based solely on distance may cause serious delays. In addition, the system cannot recognize and utilize the expertise and experience of different delivery personnel, such as delivery personnel who are familiar with a specific area or are good at handling special orders. These factors combined lead to inefficient delivery, reduced customer satisfaction, and increased operating costs.

[0036] If this technical problem cannot be effectively solved, it will have a serious negative impact on the entire intelligent transportation scheduling system. First, the delivery efficiency will not be substantially improved, causing the system to easily crash when faced with a surge in order volume. Secondly, due to the inability to accurately match order requirements and transportation characteristics, it may cause waste of resources, such as high-level transportation capacity being allocated to simple orders, while complex orders are not properly handled. Furthermore, this inflexible allocation mechanism is difficult to adapt to the rapid changes in the market and cannot meet users' growing demand for personalized and high-quality delivery. In the long run, this will seriously restrict the development of the platform and reduce market competitiveness. Therefore, it has become particularly important and urgent to develop a more intelligent and flexible transportation scheduling method.

[0037] Based on the analysis of relevant technical issues, this application proposes a new solution. Specifically, in order to solve the problem of poor flexibility in capacity allocation, this application considers collecting information from multiple dimensions and performing intelligent capacity scheduling based on this information.

[0038] First, the application recognizes that it is not enough to allocate capacity based on the delivery distance and the willingness of the capacity to accept orders. In order to improve the flexibility and accuracy of allocation, more factors need to be considered. Therefore, the application proposes the idea of ​​obtaining multi-dimensional information, including store information, product information, regional information, capacity information, and target object information.

[0039] Secondly, this application takes into account that different orders may have different delivery requirements. For example, some high-end restaurant orders may require more professional delivery services, and some fresh products require special insulation equipment. Therefore, this application proposes a method for determining target delivery requirements based on the multi-dimensional information obtained. This method can more accurately describe the special requirements of each order and provide a basis for subsequent capacity matching.

[0040] Thirdly, the present application recognizes that the selection of transport capacity should not be based solely on distance and willingness to accept orders, but should also consider whether the characteristics of the transport capacity match the needs of the order. For example, some couriers may be more familiar with a specific area or better at handling special orders. Therefore, the present application proposes a method for determining the target transport capacity based on the regional information of the target area, transport capacity information, and target delivery needs. This method can achieve a better order-capacity match.

[0041] Finally, the present application considers that after determining the optimal transport capacity, a mechanism is needed to actually dispatch the transport capacity. Therefore, the present application proposes a step of calling the target transport capacity to complete the entire intelligent transport capacity dispatching process.

[0042] Through this multi-step, multi-dimensional intelligent capacity scheduling method, this application can effectively solve the problem of poor flexibility in capacity allocation in related technologies. This method can better adapt to complex and changing distribution environments, improve distribution efficiency and quality, and also better meet the personalized needs of users.

[0043] Figure 1 This is a schematic diagram of an implementation environment of an intelligent transportation capacity scheduling method provided in an embodiment of the present application, see Figure 1 The implementation environment may include a store side 110, a customer side 120, a transportation side 130 and a server 140.

[0044] The store end 110 is connected to the server 140 via a wireless network or a wired network, and the store end 110 is a terminal used by the target store. Optionally, the store end 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The store end 110 is installed and runs an application that supports intelligent transportation scheduling.

[0045] The client terminal 120 is connected to the server 140 via a wireless network or a wired network, and is a terminal used by the target object. Optionally, the client terminal 120 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The client terminal 120 installs and runs an application that supports product delivery.

[0046] The transport terminal 130 is connected to the server 140 via a wireless network or a wired network, and is a terminal for transporting transport. Optionally, the transport terminal 130 is a smart phone, but is not limited thereto. The transport terminal 130 has an application installed and running that supports the delivery of goods.

[0047] The server 140 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, distribution networks (Content Delivery Network, CDN) and big data and artificial intelligence platforms. The server 140 can provide background services for applications running on the store end 110, the customer end 120, and the transportation end 130.

[0048] After introducing the implementation environment of the embodiment of the present application, the intelligent capacity scheduling method provided by the embodiment of the present application is described below. Figure 2 This is a flow chart of an intelligent transportation capacity scheduling method provided in an embodiment of the present application, see Figure 2 Taking the execution subject as a server as an example, the method includes the following steps.

[0049] 201. In response to the target store's delivery request for the target product, the server obtains the store information of the target store, the product information of the target product, the area information of the target area, the transportation capacity information of the target area, and the object information of the target object, where the target area is the delivery area to which the target store belongs, and the target object is the object to which the target product needs to be delivered.

[0050] Among them, store information refers to various data related to the target store, which can be specifically implemented by store description information, store delivery requirements and store attributes. Product information refers to various data related to the target product, which can be specifically implemented by product description information and product attributes. Regional information refers to various data related to the target area, which can be specifically implemented by regional delivery difficulty and regional delivery popularity. Capacity information refers to various data related to the available capacity in the target area, which can be specifically implemented by capacity distribution, capacity fatigue and proficiency of candidate capacity. Object information refers to various data related to the target object, which can be specifically implemented by object description information, object delivery requirements and object attributes. Among them, the target area is defined as the delivery area to which the target store belongs, and the target object is the object to which the target product needs to be delivered. This step provides comprehensive data support for subsequent decision-making.

[0051] 202. The server determines a target delivery requirement for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object.

[0052] Among them, based on the store information, product information and object information obtained in the previous step, the target delivery requirements of the delivery target products are determined. This step generates a more accurate description of the delivery requirements by comprehensively considering multiple factors. For example, the system may consider the special requirements of the store, the storage conditions of the products, and the delivery time preferences of the objects.

[0053] 203. The server determines a target transportation capacity from a plurality of candidate transportation capacities of the target area based on the area information of the target area, the transportation capacity information of the target area, and the target delivery demand. The target transportation capacity is a transportation capacity that matches the target delivery demand.

[0054] Among them, based on the regional information and capacity information of the target area and the target distribution demand determined in the previous step, the target capacity is determined from multiple candidate capacities in the target area. The target capacity is defined as the capacity that best matches the target distribution demand. This step selects the most suitable capacity by analyzing regional characteristics, capacity conditions and distribution demand, thereby improving the accuracy and efficiency of capacity allocation.

[0055] 204. The server summons the target transportation capacity to deliver the target product to the target object.

[0056] Among them, the determined target transport capacity is summoned to deliver the target goods to the target object. This step implements the decision results of the previous steps and completes the entire intelligent transport capacity scheduling process.

[0057] The following is an example to illustrate steps 201-204. This application can be implemented in a takeaway delivery system in a large city. Specifically, when the system receives a delivery request from a high-end Japanese food restaurant, it first obtains relevant information:

[0058] Store information may include the delivery requirements of the Japanese restaurant (such as special requirements for keeping food fresh), store description (such as high-end Japanese restaurant), and store attributes (such as located in a commercial district). Product information may include product description (such as sashimi platter) and product attributes (such as needing to be kept below 4°C). Area information may include the degree of traffic congestion in the commercial district and the current weather conditions. Transport capacity information may include the distribution of available delivery personnel in the current area, the working hours of each delivery personnel, and the familiarity with Japanese food delivery. Object information may include the customer's delivery address, expected delivery time, and whether there are special delivery requirements. Based on this information, the server determines the target delivery requirements, such as needing to deliver within 30 minutes, requiring an incubator, and the delivery personnel needing to have experience in Japanese food delivery. Then, the server selects the target transport capacity from multiple candidate transport capacities in the current area. The server may give priority to those delivery personnel who have experience in Japanese food delivery, are close to the current location, and have moderate working hours. Finally, the server may select a delivery personnel who is close to the distance, has experience in Japanese food delivery, and is equipped with an incubator as the target transport capacity. Finally, the server summons the delivery person, assigns the order to him, and provides the necessary delivery information and special requirements. In this way, the server can better meet the special needs of high-end Japanese food stores and customers and improve delivery quality and efficiency.

[0059] The technical solution provided by the embodiment of the present application proposes a multi-dimensional, multi-step intelligent capacity scheduling method. This method achieves a more accurate and flexible capacity allocation by acquiring and comprehensively analyzing various information such as stores, goods, regions, capacity and objects. This method not only takes into account the delivery distance and the willingness of the capacity to accept orders, but also takes into account factors such as the special needs of the order, product characteristics, store requirements, regional conditions and capacity characteristics, thereby greatly improving the flexibility and efficiency of capacity scheduling.

[0060] The above steps 201-204 are a brief introduction to the intelligent transport capacity scheduling method provided in the embodiment of the present application. The following will combine some examples to more clearly illustrate the intelligent transport capacity scheduling method provided in the embodiment of the present application. Figure 3 Taking the execution subject as a server as an example, the method includes the following steps.

[0061] 301. In response to the target store's delivery request for the target product, the server obtains the store information of the target store, the product information of the target product, the area information of the target area, the transportation capacity information of the target area, and the object information of the target object, where the target area is the delivery area to which the target store belongs, and the target object is the object to which the target product needs to be delivered.

[0062] Among them, the delivery request is sent by the target store to the server through the store end, and the target product is the product to be delivered to the target object. Store information refers to various data related to the target store, which can be specifically implemented by store description information, store delivery requirements and store attributes. Product information refers to various data related to the target product, which can be specifically implemented by product description information and product attributes. Regional information refers to various data related to the target area, which can be specifically implemented by regional delivery difficulty and regional delivery popularity. Capacity information refers to various data related to the available capacity in the target area, which can be specifically implemented by capacity distribution, capacity fatigue and proficiency of candidate capacity. Object information refers to various data related to the target object, which can be specifically implemented by object description information, object delivery requirements and object attributes. Among them, the target area is defined as the delivery area to which the target store belongs, and the target object is the object to which the target product needs to be delivered. This step provides comprehensive data support for subsequent decision-making.

[0063] In a possible implementation, in response to the target store's delivery request for the target product, the server uses the store ID of the target store to query and obtain the store information of the target store, the product information of the target product, and the target area to which the target store belongs. The server uses the area ID of the target area to query and obtain the area information of the target area and the transportation capacity information of the target area. The server queries based on the object ID of the target object and obtains the object information of the target object.

[0064] In this implementation mode, the above-mentioned various types of information can be obtained by using the store identification of the target store, the area identification of the target area, and the object identification of the target object, and the efficiency of obtaining the information is relatively high.

[0065] 302. The server determines a first delivery requirement for delivering the target product based on the store information of the target store and the product information of the target product.

[0066] Among them, store information may include the store's location, business hours, delivery range, etc., while product information may include product type, weight, volume, shelf life, etc. The combination of these two types of information can reflect the delivery requirements at the store and product levels. For example, for an ice cream shop, its store information may require that the delivery time does not exceed 30 minutes, while the product information requires that the temperature be kept low during the delivery process. These information combined can form a specific first delivery requirement.

[0067] In a possible implementation, the server determines the benchmark store delivery requirement of the target store based on the store delivery requirement. The server determines the reference store delivery requirement of the target store based on the store description information and store attributes. The server determines the product delivery requirement of the target product based on the product description information and product attributes. The server determines the first delivery requirement for delivering the target product based on the benchmark store delivery requirement, the reference store delivery requirement, and the product delivery requirement.

[0068] In this implementation, the acquired information is processed in different dimensions to obtain delivery demands in different dimensions, and the first delivery demand can be obtained by integrating the delivery demands in different dimensions.

[0069] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0070] Part 1: The server determines the benchmark store delivery requirements of the target store based on the store delivery requirements.

[0071] In a possible implementation, the store delivery requirement includes the store's required delivery time, the store's required delivery method, and the store's required transportation capacity description. The server determines the target store's delivery time requirement based on the store's required delivery time. The server determines the target store's delivery capacity requirement based on the store's required delivery method and the store's required transportation capacity description. The server determines the target store's benchmark store delivery requirement based on the delivery time requirement and the delivery capacity requirement.

[0072] For example, the server fills the store's required delivery time into the delivery demand template to obtain the target store's delivery time requirement. The server extracts features of the store's required delivery method and the store's required transportation capacity description to obtain the required delivery method features of the store's required delivery method and the required transportation capacity description features of the store's required transportation capacity description. The server fuses the required delivery method features with the required transportation capacity description features to obtain the target store's delivery capacity requirement features. Based on the attention mechanism, the server performs multiple rounds of iterative decoding on the delivery capacity requirement features to obtain the target store's delivery capacity requirement.

[0073] Among them, the delivery demand template is set by technical personnel according to actual conditions, and the embodiment of the present application does not limit this.

[0074] Part 2: The server determines the reference store delivery requirements of the target store based on the store description information and store attributes.

[0075] In a possible implementation, the server extracts semantic features from the store description information to obtain a first semantic feature of the store description information. The server extracts features from the store attributes to obtain store attribute features of the target store. The server determines the reference store delivery requirements of the target store based on the first semantic feature of the store description information and the store attribute features of the target store.

[0076] For example, the server encodes the store description information based on the attention mechanism to obtain the first semantic feature of the store description information. The server embeds the store attribute to obtain the store attribute feature of the target store. The server fuses the first semantic feature of the store description information with the store attribute feature of the target store to obtain the first fused feature. The server performs multiple rounds of iterative decoding on the first fused feature based on the attention mechanism to obtain the reference store delivery demand of the target store.

[0077] Part three: The server determines the product delivery requirements of the target product based on the product description information and product attributes.

[0078] In a possible implementation, the server performs semantic feature extraction on the product description information to obtain a second semantic feature of the product description information. The server performs feature extraction on the product attribute to obtain a product attribute feature of the target product. The server determines the product delivery demand of the target product based on the second semantic feature of the product description information and the product attribute feature of the target product.

[0079] For example, the server encodes the product description information based on the attention mechanism to obtain the second semantic feature of the product description information. The server embeds the product attribute to obtain the product attribute feature of the target product. The server fuses the second semantic feature of the product description information with the product attribute feature of the target product to obtain a second fused feature. The server performs multiple rounds of iterative decoding on the second fused feature based on the attention mechanism to obtain the product delivery demand of the target product.

[0080] Part 4: The server determines a first delivery requirement for delivering the target product based on the delivery requirement of the benchmark store, the delivery requirement of the reference store and the delivery requirement of the product.

[0081] In a possible implementation, the server merges the benchmark store delivery requirement with the reference store delivery requirement to obtain the store delivery requirement of the target store. The server merges the store delivery requirement of the target store with the product delivery requirement to obtain a first delivery requirement for delivering the target product.

[0082] The technical solution proposed in step 302 above realizes accurate determination of the first delivery demand by considering the information of stores and goods in multiple dimensions and levels. This solution not only considers the basic delivery requirements of stores, but also considers the description of stores and goods by transportation capacity, as well as the attribute characteristics of stores and goods. This comprehensive consideration can more accurately reflect the actual delivery demand, thereby providing a more reliable basis for subsequent transportation capacity scheduling.

[0083] The core invention of this solution is to break down the store information and product information into smaller parts and determine the first delivery requirement through a multi-step process. Compared with the traditional method of simply determining the delivery requirement based on the delivery distance, this method can more comprehensively consider various factors and improve the accuracy and flexibility of determining the delivery requirement.

[0084] In addition, the solution can adapt to different types of stores and products. By considering store description information, store attributes, product description information and product attributes, the solution can generate customized delivery requirements for stores and products with different characteristics, thereby improving the adaptability and versatility of the system.

[0085] In this application, the store information includes store description information, store delivery requirements, and store attributes. The store description information can be a subjective evaluation or objective description of the target store by the transport capacity, such as "this store has a wide variety of goods", "this store has a large order volume", etc. The store delivery requirements can include the delivery timeliness and delivery method of the store requirements. The store attributes can include objective data such as store type, business hours, average order volume, etc. The product information includes product description information and product attributes. The product description information can be a subjective evaluation or objective description of the target product by the transport capacity, such as "this product is fragile", "this product needs to be kept warm", etc. The product attributes can include objective data such as product type, weight, volume, etc. When determining the benchmark store delivery requirements of the target store based on the store delivery requirements, the delivery requirements clearly stated by the store can be directly used as the benchmark. For example, if the store requires delivery within 30 minutes, the benchmark store delivery requirements include this timeliness requirement. When determining the reference store delivery requirements of the target store based on the store description information and store attributes, a machine learning model can be used. The model can predict new stores by analyzing historical data and learning the relationship between store description information and attributes and actual delivery requirements. For example, if the store description mentions "large order volume" and the store attributes show that the average order volume is indeed high, the model may predict that the store needs more or more flexible delivery resources. Machine learning models can also be used to determine the product delivery requirements of the target product based on the product description information and product attributes. For example, if the product description mentions "fragile" and the product attributes show that it is a glass product, the model may predict that the product requires a more cautious delivery method. Finally, when determining the first delivery requirement for the delivery target product based on the benchmark store delivery requirement, the reference store delivery requirement, and the product delivery requirement, a weighted average or more complex fusion algorithm can be used. For example, a higher weight can be given to the benchmark store delivery requirement because it is a clear requirement put forward by the store; relatively lower weights can be given to the reference store delivery requirement and the product delivery requirement because these are the results of system predictions.

[0086] In this way, the application can comprehensively consider multiple factors and generate a more accurate and comprehensive first delivery demand. This not only improves delivery efficiency, but also better meets the needs of stores and customers, thereby improving the overall service quality.

[0087] 303. The server determines a second delivery requirement for delivering the target product based on the product information of the target product and the object information of the target object.

[0088] Among them, the object information may include the delivery address, time requirements, special needs, etc. The combination of these two types of information can reflect the delivery requirements at the product and delivery object levels. For example, for a birthday cake order that needs to be delivered before 3 pm, the product information requires that the cake be kept intact, while the object information requires it to be delivered on time. These information combined can form a specific second delivery requirement.

[0089] In a possible implementation, the server determines a description delivery requirement for delivering the target product to the target object based on the product description information and the object description information. The server determines an attribute delivery requirement for delivering the target product to the target object based on the product attribute and the object attribute. The server determines a second delivery requirement for delivering the target product based on the object delivery requirement, the description delivery requirement, and the attribute delivery requirement.

[0090] In this implementation, the acquired information is processed in different dimensions to obtain delivery demands in different dimensions, and these delivery demands in different dimensions are integrated to obtain a second delivery demand.

[0091] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0092] In the first part, the server determines a description and delivery requirement for delivering the target commodity to the target object based on the commodity description information and the object description information.

[0093] In a possible implementation, the server extracts semantic features from the product description information and the object description information to obtain a second semantic feature of the product description information and a third semantic feature of the object description information. The server determines the description delivery requirement based on the second semantic feature and the third semantic feature.

[0094] For example, the server encodes the product description information based on the attention mechanism to obtain the second semantic feature of the product description information. The server encodes the object description information based on the attention mechanism to obtain the third semantic feature of the product description information. The server fuses the second semantic feature and the third semantic feature to obtain a second fused feature. The server performs multiple rounds of iterative decoding on the second fused feature based on the attention mechanism to obtain the description of the delivery demand.

[0095] In the second part, the server determines the attribute delivery requirement of delivering the target commodity to the target object based on the attribute of the commodity and the attribute of the object.

[0096] In a possible implementation, the server extracts features of the commodity attribute and the object attribute to obtain commodity attribute features of the target commodity and object attribute features of the target object. The server determines attribute delivery requirements for delivering the target commodity to the target object based on the commodity attribute features of the target commodity and the object attribute features of the target object.

[0097] For example, the server extracts features of the commodity attribute and the object attribute to obtain the commodity attribute feature of the target commodity and the object attribute feature of the target object. The server fuses the commodity attribute feature of the target commodity and the object attribute feature of the target object to obtain a third fused feature. The server performs multiple rounds of iterative decoding on the third fused feature based on the attention mechanism to obtain the attribute delivery demand.

[0098] Part three: The server determines a second delivery requirement for delivering the target product based on the object delivery requirement, the description delivery requirement and the attribute delivery requirement.

[0099] In a possible implementation, the server determines a base object delivery requirement of the target object based on the object delivery requirement. The server determines a second delivery requirement of the target commodity based on the base object delivery requirement, the description delivery requirement, and the attribute delivery requirement.

[0100] For example, the server fills the object delivery requirement into the reference object delivery requirement template to obtain the reference object delivery requirement of the target object. The server merges the reference object delivery requirement, the description delivery requirement and the attribute delivery requirement to obtain the second delivery requirement of the target commodity.

[0101] Through the above step 303, multiple aspects of commodity information and object information are comprehensively considered to determine the description distribution requirements and attribute distribution requirements respectively, and then combined with the object distribution requirements to finally obtain the second distribution requirements. This method can more comprehensively and accurately reflect the distribution requirements, which is helpful for subsequent capacity matching and scheduling.

[0102] The main features of the technical solution include product information, object information, description of delivery requirements, attribute delivery requirements and second delivery requirements. The product description information in the product information can be a text description of the product by the transport capacity, such as "fragile goods", "fresh food", etc. The product attributes can include specific data such as the weight, volume, and shelf life of the product. The object description information in the object information can be a description of the delivery object by the transport capacity, such as "elderly people", "students", etc. Object delivery requirements can include expected delivery time, special delivery requirements, etc. Object attributes can include delivery address, contact information, etc.

[0103] The process of determining the descriptive delivery requirements can use natural language processing technology to perform semantic analysis on the product description information and object description information to extract key information. For example, when the product is described as "fragile" and the object is described as "elderly", the descriptive delivery requirements of "need to be handled with care and delivered to the door" can be obtained. The attribute delivery requirements can be determined by performing data analysis and matching on the product attributes and object attributes. For example, when the weight of the product is large and the delivery address is on a high floor without an elevator, the attribute delivery requirement of "requires additional manpower assistance" can be obtained. Finally, by comprehensively considering the object delivery requirements, descriptive delivery requirements, and attribute delivery requirements, a comprehensive second delivery requirement can be obtained. This process can use machine learning algorithms, such as decision trees or neural networks, to take various factors as input and output the final delivery requirements.

[0104] The advantage of this method is that it can more comprehensively consider various factors in the distribution process, including not only the characteristics of the goods themselves, but also the characteristics and requirements of the distribution objects. By processing the description information and attribute information separately, the qualitative and quantitative distribution requirements can be better captured. The final second distribution requirement can more accurately reflect the actual situation and help the system select the most appropriate transportation capacity for distribution.

[0105] 304. The server determines a target delivery requirement for delivering the target commodity based on the first delivery requirement and the second delivery requirement.

[0106] Among them, the target delivery requirement is determined based on the first delivery requirement and the second delivery requirement. This step comprehensively considers the information of the three dimensions of store, product and object, so as to obtain a comprehensive and accurate delivery requirement. For example, comprehensively considering the 30-minute delivery time limit and low temperature requirements of the ice cream shop, as well as the specific address and time requirements of the customer, finally determine a target delivery requirement that meets both the store and product requirements and the customer's needs.

[0107] In a possible implementation, the server uses a first weight and a second weight to merge the first delivery demand and the second delivery demand to obtain a target delivery demand for delivering the target product. The first weight corresponds to the first delivery demand, and the second weight corresponds to the second delivery demand. The first weight is determined based on the store attributes of the target store and the product attributes of the target product, and the second weight is determined based on the product attributes and the object attributes of the target object.

[0108] In order to explain the above implementation more clearly, the method for determining the first weight and the second weight in the above implementation is explained below.

[0109] First, the method of determining the first weight is described.

[0110] In a possible implementation, the server inputs the store attributes of the target store and the product attributes of the target product into a weight determination model, and extracts features of the store attributes of the target store and the product attributes of the target product through the weight determination model to obtain the store attribute features of the target store and the product attribute features of the target product. The server fuses the store attribute features and the product attribute features through the weight determination model to obtain a fourth fused feature. The server fully connects and normalizes the fourth fused feature through the weight determination model to obtain the first weight.

[0111] Among them, the weight determination model is a regression model.

[0112] The method for determining the second weight is described below.

[0113] In a possible implementation, the server inputs the object attribute of the target object and the commodity attribute of the target commodity into a weight determination model, and extracts features of the object attribute of the target object and the commodity attribute of the target commodity through the weight determination model to obtain the object attribute feature of the target object and the commodity attribute feature of the target commodity. The server fuses the object attribute feature and the commodity attribute feature through the weight determination model to obtain a fifth fused feature. The server fully connects and normalizes the fifth fused feature through the weight determination model to obtain the second weight.

[0114] Through the above steps 302-304, the target delivery demand is determined through comprehensive analysis of multi-dimensional information, which solves the problem that it is difficult to fully and accurately grasp the delivery demand by relying on single-dimensional information. The innovation of this method lies in the organic combination of information on stores, goods and delivery objects, and the determination of delivery demand at two levels, and finally a more comprehensive and accurate target delivery demand is obtained. This not only improves the accuracy of delivery demand determination, but also provides a more reliable basis for subsequent capacity matching and scheduling, which helps to improve overall delivery efficiency and service quality.

[0115] A specific implementation of steps 302-304 above may be as follows: Assume that a high-end restaurant in the city center (store information) needs to deliver a seafood meal set (product information) that needs to be kept warm to a customer in the suburbs (object information). The system will first generate a first delivery requirement based on the location of the restaurant and the characteristics of the seafood meal set, which requires delivery within 45 minutes and requires insulation equipment. Then, based on the characteristics of the seafood meal set and the location of the customer, the system will generate a second delivery requirement that requires long-distance transportation and keeps the food fresh. Finally, the system will combine these two requirements to generate a target delivery requirement that requires delivery within 1 hour, requires insulation equipment, and the delivery person needs to have long-distance delivery experience.

[0116] Compared with the method in the related art that determines the delivery requirements only based on the delivery distance of the order, the method of the present application takes into account more factors and can more accurately reflect the actual delivery requirements. For example, in the above embodiment, if only the delivery distance is considered, the requirements for food insulation and freshness may be ignored, resulting in customers receiving poor quality food. The method of the present application can better meet the needs of all parties and improve the quality and efficiency of delivery by comprehensively considering information from multiple dimensions.

[0117] 305. The server determines multiple reference transport capacities from the multiple candidate transport capacities based on the area information of the target area and the transport capacity information of the target area.

[0118] Among them, regional information refers to various data related to the target area, which can be specifically implemented by regional delivery difficulty and regional delivery popularity. Capacity information refers to various data related to available capacity in the target area, which can be specifically implemented by capacity distribution, capacity fatigue and proficiency of candidate capacity. Multiple candidate capacities are the capacity in the target area that has delivery capabilities, and multiple reference capacities are the capacity obtained by filtering the multiple candidate capacity using regional information and capacity information.

[0119] In a possible implementation, the server determines the delivery difficulty description information of the target area based on the delivery difficulty of the area and the capacity distribution. The server determines the delivery activity description information of the target area based on the delivery popularity of the area and the capacity distribution. The server determines the capacity status description information of each candidate capacity based on the capacity fatigue and proficiency of the multiple candidate capacities. The server determines multiple reference capacities from the multiple candidate capacities based on the delivery difficulty description information, the delivery activity description information, and the capacity status description information of each candidate capacity.

[0120] In this implementation, the regional information and capacity information can be used to screen multiple candidate capacities, thereby obtaining multiple reference capacities, which is helpful for subsequent determination of target capacity.

[0121] In order to explain the above implementation more clearly, the above implementation is explained in several parts below.

[0122] Part 1: The server determines the delivery difficulty description information of the target area based on the delivery difficulty of the area and the transportation capacity distribution.

[0123] In a possible implementation, the regional delivery difficulty includes the regional congestion level and the regional weather severity. The server determines the first delivery difficulty description information of the target area based on the regional congestion level and the regional weather severity. The server determines the second delivery difficulty description information of the target area based on the transportation capacity distribution. The server merges the first delivery difficulty description information and the second delivery difficulty description information of the target area to obtain the delivery difficulty description information of the target area.

[0124] For example, the server splices the congestion level of the area and the severity of the weather in the area with the first prompt text template to obtain the first prompt text. The server inputs the first prompt text into the target language model, processes the first prompt text through the target language model, and outputs the first delivery difficulty description information of the target area. The server splices the capacity distribution with the second prompt text template to obtain the second prompt text. The server inputs the second prompt text into the target language model, processes the second prompt text through the target language model, and outputs the second delivery difficulty description information of the target area. The server merges the first delivery difficulty description information and the second delivery difficulty description information of the target area to obtain the delivery difficulty description information of the target area.

[0125] The target language model is a large language model that has been pre-trained and fine-tuned, and the type and structure of the target language model are not limited in the embodiment of the present application. The first prompt text template and the second prompt text template are set by the technician according to the actual situation, and the embodiment of the present application does not limit this.

[0126] In the second part, the server determines the distribution activity description information of the target area based on the distribution popularity of the area and the distribution of the transportation capacity.

[0127] In a possible implementation, the server determines first delivery activity description information of the target area based on the delivery heat of the area, where the delivery heat of the area is used to indicate the activity level of ordering goods in the target area. The server determines second delivery activity description information of the target area based on the transportation capacity distribution. The server merges the first delivery activity description information and the second delivery activity description information to obtain the delivery activity description information of the target area.

[0128] For example, the server concatenates the distribution heat of the area with the third prompt text template to obtain the third prompt text. The server inputs the third prompt text into the target language model, processes the third prompt text through the target language model, and outputs the first distribution activity description information of the target area. The server concatenates the capacity distribution with the fourth prompt text template to obtain the fourth prompt text. The server inputs the fourth prompt text into the target language model, processes the fourth prompt text through the target language model, and outputs the second distribution activity description information of the target area. The server merges the first distribution activity description information with the second distribution activity description information to obtain the distribution activity description information of the target area.

[0129] Among them, the third prompt text template and the fourth prompt text template are set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.

[0130] Part 3: The server determines the capacity status description information of each candidate capacity based on the capacity fatigue level and proficiency level of the multiple candidate capacities.

[0131] In a possible implementation, the capacity fatigue degree includes the accumulated delivery time and physiological parameters, the proficiency includes the regional familiarity and delivery familiarity of the target area, and the server determines the fatigue state description information of each candidate capacity based on the accumulated delivery time and physiological parameters of each candidate capacity, and the physiological parameters include heart rate, blood pressure and body temperature. The server determines the delivery state description information of each candidate capacity based on the regional familiarity and delivery familiarity of each candidate capacity for the target area. The server determines the capacity state description information of each candidate capacity based on the fatigue state description information and delivery state description information of each candidate capacity.

[0132] For example, the server extracts features from the physiological parameters of each candidate capacity to obtain the physiological features of each candidate capacity. The server concatenates the cumulative delivery time and physiological features of each candidate capacity with the fifth prompt text template to obtain the fifth prompt text. The server inputs the fifth prompt text into the target language model, processes the fifth prompt text through the target language model, and outputs the fatigue status description information of each candidate capacity. The server concatenates the regional familiarity and delivery familiarity of each candidate capacity with the sixth prompt text template to obtain the sixth prompt text. The server inputs the sixth prompt text into the target language model, processes the sixth prompt text through the target language model, and outputs the delivery status description information of each candidate capacity. The server fuses the fatigue status description information and delivery status description information of each candidate capacity to obtain the capacity status description information of each candidate capacity.

[0133] Among them, the fifth prompt text template and the sixth prompt text template are set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.

[0134] Part 4: The server determines multiple reference transport capacities from the multiple candidate transport capacities based on the delivery difficulty description information, the delivery activity description information, and the capacity status description information of each candidate transport capacity.

[0135] In a possible implementation, the server determines the target area delivery difficulty coefficient of the target area based on the delivery difficulty description information and the delivery activity description information. The server determines the initial state score of each candidate transport capacity based on the capacity state description information of each candidate transport capacity. The server multiplies the initial state score of each candidate transport capacity by the target area delivery difficulty coefficient to obtain the target state score of each candidate transport capacity. The server determines the N candidate transport capacities with the highest target state scores among the multiple candidate transport capacities as the multiple reference transport capacities, where N is a positive integer.

[0136] For example, the server performs feature extraction on the delivery difficulty description information and the delivery activity description information to obtain the delivery difficulty feature of the delivery difficulty description information and the delivery activity feature of the delivery activity description information. The server fuses the delivery difficulty feature and the delivery activity feature to obtain the sixth fused feature. The server fully connects and normalizes the sixth fused feature to obtain the target area delivery difficulty coefficient of the target area. The server performs feature extraction on the capacity status description information of each candidate capacity to obtain the capacity status feature of each candidate capacity. The server fully connects and normalizes the capacity status feature of each candidate capacity to obtain the initial state score of each candidate capacity. The server multiplies the initial state score of each candidate capacity by the target area delivery difficulty coefficient to obtain the target state score of each candidate capacity. The server determines the N candidate capacities with the highest target state scores among the multiple candidate capacities as the multiple reference capacities, where N is a positive integer.

[0137] 306. The server determines the target transportation capacity from the multiple reference transportation capacities based on the target delivery demand and the transportation capacity information, and the target transportation capacity is the transportation capacity that matches the target delivery demand.

[0138] Among them, the target capacity is defined as the capacity that best matches the target distribution demand. This step selects the most suitable capacity by analyzing regional characteristics, capacity conditions and distribution needs, thereby improving the accuracy and efficiency of capacity allocation.

[0139] In a possible implementation, the transport capacity information includes the delivery styles, transport capacity description information, and transport capacity attributes of multiple reference transport capacities. The server determines the degree of match between each reference transport capacity and the target delivery demand based on the delivery styles, transport capacity description information, and transport capacity attributes of each reference transport capacity. The server determines the reference transport capacity with the highest degree of match between the multiple reference transport capacities and the target delivery demand as the target transport capacity.

[0140] In order to explain the above implementation more clearly, the method of determining the matching degree between each reference transport capacity and the target delivery demand in the above implementation is explained below.

[0141] In a possible implementation, the server determines the capacity profile of each reference transport capacity based on the delivery style, capacity description information, and capacity attributes of each reference transport capacity. The server extracts features from the capacity profile of each reference transport capacity to obtain the capacity profile features of each reference transport capacity. The server extracts features from the target delivery demand to obtain the target delivery demand features of the target delivery demand. The server determines the feature similarity between the capacity profile features of each reference transport capacity and the target delivery demand features as the degree of matching between each reference transport capacity and the target delivery demand.

[0142] 307. The server summons the target transportation capacity to deliver the target product to the target object.

[0143] Among them, the determined target transport capacity is summoned to deliver the target goods to the target object. This step implements the decision results of the previous steps and completes the entire intelligent transport capacity scheduling process.

[0144] In a possible implementation, the server pushes the target order to the transport capacity end of the target transport capacity so that the target transport capacity performs delivery based on the target order, and the target order is a delivery order for delivering the target commodity to the target object.

[0145] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0146] The technical solution provided by the embodiment of the present application proposes a multi-dimensional, multi-step intelligent capacity scheduling method. This method achieves a more accurate and flexible capacity allocation by acquiring and comprehensively analyzing various information such as stores, goods, regions, capacity and objects. This method not only takes into account the delivery distance and the willingness of the capacity to accept orders, but also takes into account factors such as the special needs of the order, product characteristics, store requirements, regional conditions and capacity characteristics, thereby greatly improving the flexibility and efficiency of capacity scheduling.

[0147] Figure 4This is a schematic diagram of the structure of an intelligent transportation capacity scheduling system provided in an embodiment of the present application, see Figure 4 The system includes: an acquisition module 401, a demand determination module 402, a capacity determination module 403 and a summoning module 404.

[0148] The acquisition module 401 is used to respond to the target store's delivery request for the target product, and obtain the store information of the target store, the product information of the target product, the area information of the target area, the transportation capacity information of the target area, and the object information of the target object. The target area is the delivery area to which the target store belongs, and the target object is the object to which the target product needs to be delivered.

[0149] The demand determination module 402 is used to determine the target delivery demand for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object.

[0150] The capacity determination module 403 is used to determine a target capacity from multiple candidate capacities of the target area based on the area information of the target area, the capacity information of the target area and the target delivery demand, and the target capacity is the capacity that matches the target delivery demand.

[0151] The summoning module 404 is used to summon the target transportation capacity to deliver the target commodity to the target object.

[0152] It should be noted that the intelligent transportation capacity dispatching system provided in the above embodiment only uses the division of the above functional modules as an example when performing transportation capacity dispatching. In actual applications, the above functional distribution can be completed by different functional modules as needed, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent transportation capacity dispatching system provided in the above embodiment and the intelligent transportation capacity dispatching method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0153] The technical solution provided by the embodiment of the present application proposes a multi-dimensional, multi-step intelligent capacity scheduling method. This method achieves a more accurate and flexible capacity allocation by acquiring and comprehensively analyzing various information such as stores, goods, regions, capacity and objects. This method not only takes into account the delivery distance and the willingness of the capacity to accept orders, but also takes into account factors such as the special needs of the order, product characteristics, store requirements, regional conditions and capacity characteristics, thereby greatly improving the flexibility and efficiency of capacity scheduling.

[0154] Figure 5This is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502, wherein at least one computer program is stored in the one or more memories 502, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the above-mentioned various method embodiments. Of course, the server 500 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server 500 may also include other components for implementing device functions, which will not be described in detail here.

[0155] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program, and the computer program can be executed by a processor to complete the intelligent transportation capacity scheduling method in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0156] In an exemplary embodiment, a computer program product or a computer program is also provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned intelligent capacity scheduling method.

[0157] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0158] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0159] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An intelligent transportation capacity scheduling method, characterized in that: The method comprises: In response to a delivery request of a target store for a target product, store information of the target store, product information of the target product, area information of a target area, transportation capacity information of the target area, and object information of a target object are obtained, wherein the target area is a delivery area to which the target store belongs, and the target object is an object to which the target product needs to be delivered; Determining a target delivery requirement for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object; Based on the area information of the target area, the transportation capacity information of the target area and the target delivery demand, determine a target transportation capacity from a plurality of candidate transportation capacities of the target area, the target transportation capacity being the transportation capacity that matches the target delivery demand; The target transportation capacity is summoned to deliver the target commodity to the target object.

2. The method according to claim 1, characterized in that The determining the target delivery requirement for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object includes: Determining a first delivery requirement for delivering the target product based on the store information of the target store and the product information of the target product; Determining a second delivery requirement for delivering the target product based on the product information of the target product and the object information of the target object; Based on the first delivery requirement and the second delivery requirement, a target delivery requirement for delivering the target commodity is determined.

3. The method according to claim 2, characterized in that The store information includes store description information, store delivery requirements, and store attributes, the store description information is description information of the target store by the transportation capacity, the product information includes product description information and product attributes, the product description information is description information of the target product by the transportation capacity, and determining the first delivery requirement for delivering the target product based on the store information of the target store and the product information of the target product includes: Determining a baseline store delivery requirement of the target store based on the store delivery requirement; Determining the reference store delivery requirements of the target store based on the store description information and store attributes; Determining the product delivery requirements of the target product based on the product description information and product attributes; Based on the benchmark store delivery requirement, the reference store delivery requirement, and the product delivery requirement, a first delivery requirement for delivering the target product is determined.

4. The method according to claim 3, characterized in that The store delivery requirements include the store delivery time, store delivery method and store transportation capacity description. The determining of the benchmark store delivery requirements of the target store based on the store delivery requirements includes: Based on the delivery time efficiency required by the store, determine the delivery time efficiency requirement of the target store; Determine the delivery capacity requirement of the target store based on the store's required delivery method and the store's required capacity description; Based on the delivery time requirement and the delivery transportation capacity requirement, a benchmark store delivery requirement of the target store is determined.

5. The method according to claim 2, characterized in that: The commodity information includes commodity description information and commodity attributes, the commodity description information is description information of the target commodity by the transport capacity, the object information includes object description information, object delivery requirements and object attributes, the object description information is description information of the target object by the transport capacity, and determining the second delivery requirement for delivering the target commodity based on the commodity information of the target commodity and the object information of the target object includes: Determining, based on the commodity description information and the object description information, a description delivery requirement for delivering the target commodity to the target object; Determining attribute delivery requirements for delivering the target commodity to the target object based on the commodity attributes and the object attributes; Based on the object delivery requirement, the description delivery requirement and the attribute delivery requirement, a second delivery requirement for delivering the target commodity is determined.

6. The method according to claim 5, characterized in that The determining the second delivery requirement for delivering the target commodity based on the object delivery requirement, the description delivery requirement and the attribute delivery requirement includes: Determining a baseline object delivery requirement for the target object based on the object delivery requirement; Based on the reference object delivery requirement, the description delivery requirement, and the attribute delivery requirement, a second delivery requirement of the target commodity is determined.

7. The method according to claim 2, characterized in that The determining, based on the first delivery requirement and the second delivery requirement, a target delivery requirement for delivering the target commodity includes: The first delivery demand and the second delivery demand are merged using a first weight and a second weight to obtain a target delivery demand for delivering the target product, the first weight corresponds to the first delivery demand, the second weight corresponds to the second delivery demand, the first weight is determined based on the store attributes of the target store and the product attributes of the target product, and the second weight is determined based on the product attributes and the object attributes of the target object.

8. The method according to claim 1, characterized in that: The determining the target transportation capacity from a plurality of candidate transportation capacities of the target area based on the area information of the target area, the transportation capacity information of the target area, and the target delivery demand includes: Determining a plurality of reference transport capacities from the plurality of candidate transport capacities based on the area information of the target area and the transport capacity information of the target area; Based on the target delivery demand and the transport capacity information, the target transport capacity is determined from the multiple reference transport capacities.

9. The method according to claim 8, characterized in that The regional information includes regional delivery difficulty and regional delivery popularity, the transport capacity information includes transport capacity distribution, transport capacity fatigue and proficiency of multiple candidate transport capacities, and determining multiple reference transport capacities from the multiple candidate transport capacities based on the regional information of the target area and the transport capacity information of the target area includes: Determine the delivery difficulty description information of the target area based on the regional delivery difficulty and the transportation capacity distribution; Determine the delivery activity description information of the target area based on the regional delivery popularity and the transportation capacity distribution; Determine the capacity status description information of each of the candidate transport capacities based on the transport fatigue degree and proficiency degree of the multiple candidate transport capacities; Based on the delivery difficulty description information, the delivery activity description information and the capacity status description information of each of the candidate capacities, multiple reference capacities are determined from the multiple candidate capacities.

10. An intelligent transport capacity dispatching system, characterized in that: The system comprises: an acquisition module, configured to, in response to a delivery request of a target store for a target product, acquire store information of the target store, product information of the target product, area information of a target area, transportation capacity information of the target area, and object information of a target object, wherein the target area is a delivery area to which the target store belongs, and the target object is an object to which the target product needs to be delivered; A demand determination module, configured to determine a target delivery demand for delivering the target product based on the store information of the target store, the product information of the target product, and the object information of the target object; A transport capacity determination module, configured to determine a target transport capacity from a plurality of candidate transport capacities of the target area based on the area information of the target area, the transport capacity information of the target area, and the target delivery demand, wherein the target transport capacity is a transport capacity that matches the target delivery demand; The summoning module is used to summon the target transportation capacity to deliver the target commodity to the target object.

Images