Intelligent transportation capacity scheduling method and system

Abstract

This application discloses an intelligent transportation capacity scheduling method and system, belonging to the field of computer technology. The embodiments of this application provide a multi-dimensional, multi-step intelligent transportation capacity scheduling method. This method achieves more accurate and flexible transportation capacity allocation by acquiring and comprehensively analyzing information from multiple aspects such as stores, products, regions, transportation capacity, and recipients. This method not only considers delivery distance and the willingness of transportation capacity to accept orders, but also incorporates factors such as special order requirements, product characteristics, store requirements, regional conditions, and transportation capacity characteristics, thereby greatly improving the flexibility and efficiency of transportation capacity scheduling.

Description

Technical Field

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

[0002] With the development of computer technology, services such as food delivery, ride-sharing, and express delivery have emerged, and the number of orders has continued to increase. Typically, after an order is generated, a target delivery capacity needs to be selected for that order, and the target delivery capacity will then be responsible for delivering the goods corresponding to that order.

[0003] In related technologies, the delivery cost of an order is determined based on the delivery distance, and the order is pushed to multiple delivery capabilities. If any of the multiple delivery capabilities accepts the order, that delivery capability is designated as the target capability for the order. After the target capability completes the delivery of the order, the delivery cost of the order is transferred to the target capability.

[0004] However, the above scheme can only allocate target capacity to orders based on the delivery distance of the order and the willingness of delivery capacity to accept the order, which is not very flexible in allocating target capacity. Summary of the Invention

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

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

[0007] In response to a delivery request from a target store for a target product, the system obtains the store information of the target store, the product information of the target product, the regional 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.

[0008] Based on the store information of the target store, the product information of the target product, and the object information of the target object, the target delivery demand for the target product is determined;

[0009] Based on the regional information of the target area, the transportation capacity information of the target area, and the target delivery demand, a target transportation capacity is determined from multiple candidate transportation capacities in the target area, wherein the target transportation capacity is the transportation capacity that matches the target delivery demand;

[0010] The target delivery capacity is summoned to deliver the target goods to the target object.

[0011] On the one hand, an intelligent transportation capacity scheduling system is provided, the system comprising:

[0012] The acquisition module is used to respond to the target store's delivery request for the target product, and acquire 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.

[0013] The demand determination module is used to determine the target delivery demand for 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] The capacity determination module is used to determine a target capacity from multiple candidate capacity in the target area based on the area information of the target area, the capacity information of the target area, and the target delivery demand. The target capacity is the capacity that matches the target delivery demand.

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

[0016] On one hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one computer program, the computer program being 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, wherein at least one computer program is stored in the computer-readable storage medium, the computer program being loaded and executed by a processor to implement the intelligent capacity scheduling method.

[0018] On the one hand, a computer program product or computer program is provided, which includes program code stored in a computer-readable storage medium. The processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform the above-described intelligent transportation capacity scheduling method.

[0019] This application provides a multi-dimensional, multi-step intelligent transportation capacity scheduling method. This method acquires and comprehensively analyzes information from multiple aspects, including stores, products, regions, transportation capacity, and recipients, to achieve more accurate and flexible transportation capacity allocation. This method not only considers delivery distance and the willingness of transportation capacity to accept orders, but also incorporates factors such as special order requirements, product characteristics, store requirements, regional conditions, and transportation capacity characteristics, thereby greatly improving the flexibility and efficiency of transportation capacity scheduling. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

[0022] Figure 2 This is a flowchart of an intelligent transportation capacity scheduling method provided in an embodiment of this application;

[0023] Figure 3 This is a flowchart of another intelligent transportation capacity scheduling method provided in the embodiments of this application;

[0024] Figure 4 This is a schematic diagram of the structure of an intelligent transportation capacity scheduling device provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further 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 essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or 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 multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can 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 endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and instruction-based learning.

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

[0031] Embedded coding, mathematically speaking, represents a correspondence, that is, mapping data in space X to space Y using a function F. This function F is injective, and the mapping result preserves the structure. An injective function means that the mapped data uniquely corresponds to the original data, and preserving the structure means that the size relationship between the original and mapped data is the same. For example, if there are data X1 and X2 before mapping, after mapping we get Y1 corresponding to X1 and Y2 corresponding to X2. If the original data X1 > X2, then correspondingly, the mapped data Y1 > Y2. For words, this means mapping words to another space to facilitate subsequent machine learning and processing.

[0032] Attention weights represent the importance of a piece of data during training or prediction. Importance indicates the magnitude of the influence of input data on output data. Data with high importance corresponds to higher attention weights, while data with low importance corresponds to lower attention weights. The importance of data varies in different scenarios, and training the model to assign attention weights is essentially the process of determining data importance.

[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, data stored, data displayed, 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 related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0034] In related technologies, the order allocation process mainly relies on two factors: delivery distance and the willingness of delivery personnel to accept orders. This simple allocation mechanism is not flexible enough when dealing with complex and ever-changing real-world delivery scenarios. Specifically, the system cannot fully consider multi-dimensional factors such as the specific needs of orders, the characteristics of goods, store requirements, and the real-time status of delivery areas. This leads to inefficient delivery capacity allocation, failing to meet the growing demand for precise delivery. Furthermore, due to the lack of in-depth analysis of delivery capacity characteristics, the system struggles to achieve optimal matching, impacting overall delivery quality and efficiency.

[0035] For example, a food delivery system in a large city handles hundreds of thousands of orders daily. The system uses a simple allocation algorithm based on distance and order willingness. However, this method cannot cope with complex real-world situations. For instance, orders from certain high-end restaurants may require more specialized delivery services, some fresh produce requires special temperature control equipment, and during peak traffic hours, relying solely on distance to allocate delivery capacity can lead to severe delays. Furthermore, the system cannot identify and utilize the expertise and experience of different delivery personnel, such as those familiar with specific areas or skilled at handling special orders. These factors combined result in low delivery efficiency, decreased 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 capacity scheduling system. First, delivery efficiency will not be substantially improved, making the system prone to crashing when faced with a surge in orders. Second, the inability to accurately match order demand with capacity characteristics may lead to resource waste; for example, high-level capacity may be allocated to simple orders, while complex orders will not be properly processed. Furthermore, this inflexible allocation mechanism will struggle to adapt to rapid market changes and fail to meet users' growing demands for personalized and high-quality delivery. In the long run, this will severely restrict the platform's development and reduce its market competitiveness. Therefore, developing a more intelligent and flexible capacity scheduling method is particularly important and urgent.

[0037] Based on an analysis of relevant technical problems, this application proposes a novel solution. Specifically, to address the issue of poor flexibility in capacity allocation, this application considers collecting information from multiple dimensions and using this information for intelligent capacity scheduling.

[0038] First, this application recognizes that relying solely on delivery distance and the willingness of delivery personnel to accept orders is insufficient for capacity allocation. To improve the flexibility and accuracy of allocation, more factors need to be considered. Therefore, this application proposes an approach to obtaining multi-dimensional information, including store information, product information, regional information, delivery capacity information, and target audience information.

[0039] Secondly, this application considers that different orders may have different delivery requirements. For example, orders from certain high-end restaurants may require more specialized delivery services, and some fresh produce requires special insulation equipment. Therefore, this application proposes a method for determining target delivery needs based on acquired multi-dimensional information. This method can more accurately describe the specific requirements of each order, providing a foundation for subsequent capacity matching.

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

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

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

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

[0044] The store terminal 110 is connected to the server 140 via a wireless or wired network. The store terminal 110 is the terminal used by the target store. Optionally, the store terminal 110 can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The store terminal 110 has an application that supports intelligent capacity scheduling installed and running.

[0045] Client 120 is connected to server 140 via a wireless or wired network. Client 120 is a terminal used by the target user. Optionally, client 120 can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. Client 120 has an application installed and running that supports product delivery.

[0046] Delivery terminal 130 is connected to server 140 via wireless or wired network, and is the terminal used for delivery. Optionally, delivery terminal 130 is a smartphone, but is not limited to this. Delivery terminal 130 has an application installed and running that supports goods delivery.

[0047] Server 140 is a standalone physical server, 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 communication, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. Server 140 can provide backend services for applications running on the store side 110, customer side 120, and delivery side 130.

[0048] After introducing the implementation environment of the embodiments of this application, the intelligent transportation capacity scheduling method provided by the embodiments of this application will be described below. Figure 2 This is a flowchart of an intelligent transportation capacity scheduling method provided in an embodiment of this application. See also... Figure 2 Taking the server as the executing entity 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. 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] The data includes: Store information (which can be represented by store descriptions, delivery requirements, and store attributes); Product information (which can be represented by product descriptions and attributes); Regional information (which can be represented by regional delivery difficulty and popularity); Capacity information (which can be represented by available capacity within the target region, including capacity distribution, fatigue levels, and proficiency of candidate delivery personnel); and Object information (which can be represented by object descriptions, delivery requirements, and attributes). The target region is defined as the delivery area of ​​the target store, 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. Based on the store information of the target store, the product information of the target product, and the object information of the target object, the server determines the target delivery requirement for the target product.

[0052] Based on the store, product, and customer information obtained in the previous step, the target delivery demand for the desired product is determined. This step generates a more accurate description of the delivery demand by comprehensively considering multiple factors. For example, the system may consider the store's specific requirements, the product's storage conditions, and the customer's preferred delivery time.

[0053] 203. Based on the regional information of the target area, the transportation capacity information of the target area, and the target delivery demand, the server determines the target transportation capacity from multiple candidate transportation capacities in the target area. The target transportation capacity is the transportation capacity that matches the target delivery demand.

[0054] In this process, based on regional information, capacity information, and the target delivery demand determined in the previous step, target capacity is selected from multiple candidate capacities within the target area. Target capacity is defined as the capacity that best matches the target delivery demand. This step improves the accuracy and efficiency of capacity allocation by analyzing regional characteristics, capacity availability, and delivery needs to select the most suitable capacity.

[0055] 204. The server summons the target delivery capacity to deliver the target goods to the target object.

[0056] In this process, the designated target capacity is used to deliver the target goods to the target recipient. This step puts the decisions made in the previous steps into practice, completing the entire intelligent capacity scheduling process.

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

[0058] Store information may include the Japanese restaurant's delivery requirements (such as special requirements for maintaining food freshness), store description (e.g., high-end Japanese restaurant), and store attributes (e.g., located in a commercial area). Product information may include product descriptions (e.g., sashimi platter) and product attributes (e.g., needing to be kept below 4°C). Area information may include the traffic congestion level and current weather conditions in the commercial area. Delivery capacity information may include the distribution of available delivery personnel in the current area, each delivery person's working hours, and their familiarity with Japanese food delivery. Target information may include the customer's delivery address, expected delivery time, and whether there are any special delivery requirements. Based on this information, the server determines the target delivery needs, such as delivery within 30 minutes, the need for an insulated box, and the delivery person needing experience in Japanese food delivery. Then, the server selects the target delivery person from multiple candidate delivery personnel in the current area. The server may prioritize delivery personnel with Japanese food delivery experience, a nearby location, and suitable working hours. Ultimately, the server may select a delivery person who is nearby, has Japanese food delivery experience, and is equipped with an insulated box as the target delivery person. Finally, the server summons the delivery person, assigns the order, and provides the necessary delivery information and special requests. In this way, the server can better meet the specific needs of high-end Japanese restaurants and their customers, improving delivery quality and efficiency.

[0059] This application provides a multi-dimensional, multi-step intelligent transportation capacity scheduling method. This method acquires and comprehensively analyzes information from multiple aspects, including stores, products, regions, transportation capacity, and recipients, to achieve more accurate and flexible transportation capacity allocation. This method not only considers delivery distance and the willingness of transportation capacity to accept orders, but also incorporates factors such as special order requirements, product characteristics, store requirements, regional conditions, and transportation capacity characteristics, thereby greatly improving the flexibility and efficiency of transportation capacity scheduling.

[0060] Steps 201-204 above are a brief introduction to the intelligent capacity scheduling method provided in the embodiments of this application. The following will provide a clearer explanation of the intelligent capacity scheduling method provided in the embodiments of this application, using some examples. See [link to relevant documentation]. Figure 3 Taking the server as the executing entity 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 regional 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.

[0062] In this process, the delivery request is sent from the target store to the server, and the target product is the item to be delivered to the target recipient. Store information refers to various data related to the target store, specifically including store descriptions, delivery requirements, and store attributes. Product information refers to various data related to the target product, specifically including product descriptions and attributes. Regional information refers to various data related to the target region, specifically including regional delivery difficulty and delivery popularity. Transportation capacity information refers to various data related to available transportation capacity within the target region, specifically including capacity distribution, the fatigue level of candidate transportation vehicles, and their proficiency. Target information refers to various data related to the target object, specifically including object descriptions, delivery requirements, and attributes. The target region is defined as the delivery area of ​​the target store, 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 one possible implementation, in response to a delivery request from a target store for a target product, the server queries the store's identifier to obtain the store information, the product information, and the target area to which the store belongs. The server then queries the area identifier of the target area to obtain the area information and delivery capacity information for that area. Finally, the server queries the object identifier of the target object to obtain its object information.

[0064] In this implementation, the above-mentioned information can be obtained by using the store identifier of the target store, the area identifier of the target area, and the object identifier of the target object, resulting in high information acquisition efficiency.

[0065] 302. Based on the store information of the target store and the product information of the target product, the server determines the first delivery request for the target product.

[0066] Store information might include its location, opening hours, and delivery area, while product information might include the product type, weight, volume, and shelf life. Combining these two types of information reflects the delivery needs at both the store and product levels. For example, an ice cream shop might require delivery within 30 minutes, while its product information might require maintaining a low temperature during delivery. This information, taken together, forms a specific primary delivery requirement.

[0067] In one possible implementation, the server determines the baseline store delivery requirement for the target store based on the store's delivery request. The server determines the reference store delivery requirement for the target store based on the store description information and store attributes. The server determines the product delivery requirement for the target product based on the product description information and product attributes. Based on the baseline store delivery requirement, the reference store delivery requirement, and the product delivery requirement, the server determines the first delivery requirement for delivering the target product.

[0068] In this implementation, the acquired information is processed in different dimensions to obtain delivery needs in different dimensions. By integrating these different dimensions of delivery needs, the first delivery need can be obtained.

[0069] To provide a clearer explanation of the above embodiments, the following description is divided into several parts.

[0070] Part 1: Based on the store's delivery requirements, the server determines the baseline store delivery needs for the target store.

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

[0072] For example, the server fills the store's required delivery time into the delivery requirement template to obtain the target store's delivery time requirement. The server extracts features from the store's required delivery method and required capacity description to obtain the required delivery method feature and required capacity description feature, respectively. The server then fuses these two features to obtain the target store's delivery capacity requirement feature. Finally, based on an attention mechanism, the server iteratively decodes this delivery capacity requirement feature multiple times to obtain the target store's actual delivery capacity requirement.

[0073] The delivery demand template is set by technical personnel according to the actual situation, and this application embodiment does not limit this.

[0074] Part Two: Based on the store description information and store attributes, the server determines the reference store delivery requirements for the target store.

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

[0076] For example, the server encodes the store description information using an attention mechanism to obtain the first semantic feature of the store description information. The server embeds and encodes the store attributes to obtain the store attribute features of the target store. The server fuses the first semantic feature of the store description information and the store attribute features of the target store to obtain the first fused feature. The server then performs multiple rounds of iterative decoding on the first fused feature using an attention mechanism to obtain the reference store delivery requirements of the target store.

[0077] Part Three: Based on the product description and attributes, the server determines the product delivery requirements for the target product.

[0078] In one possible implementation, the server extracts semantic features from the product description information to obtain a second semantic feature. The server then extracts features from the product attributes to obtain the product attribute features of the target product. Based on the second semantic feature of the product description information and the product attribute features of the target product, the server determines the delivery requirement for the target product.

[0079] For example, the server encodes the product description information using an attention mechanism to obtain the second semantic feature of the product description information. The server embeds and encodes the product attributes to obtain the product attribute features of the target product. The server fuses the second semantic feature of the product description information and the product attribute features of the target product to obtain the second fused feature. The server then performs multiple rounds of iterative decoding on the second fused feature using an attention mechanism to obtain the product delivery requirements of the target product.

[0080] Part Four: Based on the baseline store delivery demand, the reference store delivery demand, and the product delivery demand, the server determines the first delivery demand for the target product.

[0081] In one possible implementation, the server merges the baseline store delivery demand and the reference store delivery demand to obtain the target store's store delivery demand. The server then merges the target store's store delivery demand with the product delivery demand to obtain a first delivery demand for the target product.

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

[0083] The core innovation of this solution lies in its detailed breakdown of store and product information, and its multi-step processing to determine the primary delivery demand. Compared to the traditional method of simply determining delivery demand based on delivery distance, this approach considers various factors more comprehensively, improving the accuracy and flexibility of delivery demand determination.

[0084] Furthermore, this 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 system's adaptability and versatility.

[0085] In this application, store information includes store description information, store delivery requirements, and store attributes. Store description information can be a subjective evaluation or objective description of the target store by the delivery personnel, such as "this store has a wide variety of products" or "this store has a large order volume." Store delivery requirements can include the store's required delivery time and delivery method. Store attributes can include objective data such as store type, business hours, and average order volume. Product information includes product description information and product attributes. Product description information can be a subjective evaluation or objective description of the target product by the delivery personnel, such as "this product is fragile" or "this product needs to be kept warm." Product attributes can include objective data such as product type, weight, and volume. When determining the baseline store delivery requirements for the target store based on the store delivery requirements, the store's explicitly stated delivery requirements can be directly used as the baseline. For example, if the store requires delivery within 30 minutes, then the baseline store delivery requirements include this timeliness requirement. When determining the reference store delivery requirements for the target store based on the store description information and store attributes, a machine learning model can be used. This model can analyze historical data to learn the relationship between store description information and attributes and actual delivery requirements, thereby predicting new stores. For example, if a store description mentions "high order volume," and the store attributes show a indeed high average order volume, the model might predict that the store needs more or more flexible delivery resources. Machine learning models can also be used when determining the delivery needs of a target product based on product description information and product attributes. For example, if a product description mentions "fragile," and the product attributes show it's a glass item, the model might predict that the product requires a more cautious delivery method. Finally, when determining the primary delivery need for a target product based on baseline store delivery needs, reference store delivery needs, and product delivery needs, weighted averages or more complex fusion algorithms can be used. For example, the baseline store delivery needs can be given a higher weight because they are explicitly stated by the store; the reference store delivery needs and product delivery needs can be given relatively lower weights because these are predictions from the system.

[0086] In this way, the application can comprehensively consider multiple factors to 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 enhancing overall service quality.

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

[0088] The recipient information may include delivery address, time requirements, and special needs. The combination of these two types of information reflects the delivery needs at both the product and recipient levels. For example, for a birthday cake order that needs to be delivered before 3 PM, product information requires the cake to be intact, while recipient information requires on-time delivery. This information, taken together, forms a specific second delivery requirement.

[0089] In one 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 then determines an attribute delivery requirement for delivering the target product to the target object based on the product attributes and the object attributes. Finally, 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 needs in different dimensions. By integrating these different dimensions of delivery needs, a second delivery need can be obtained.

[0091] To provide a clearer explanation of the above embodiments, the following description is divided into several parts.

[0092] Part 1: Based on the product description information and the object description information, the server determines the description delivery requirement for delivering the target product to the target object.

[0093] In one 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. Based on the second and third semantic features, the server determines the delivery requirement for the description.

[0094] For example, the server encodes the product description information using an attention mechanism to obtain the second semantic feature of the product description information. The server then encodes the object description information using the attention mechanism to obtain the third semantic feature of the product description information. The server fuses the second and third semantic features to obtain the second fused feature. The server then performs multiple rounds of iterative decoding on the second fused feature using an attention mechanism to obtain the delivery requirement described.

[0095] Part Two: Based on the product attributes and the object attributes, the server determines the attribute delivery requirements for delivering the target product to the target object.

[0096] In one possible implementation, the server performs feature extraction on the product attributes and the object attributes to obtain the product attribute features of the target product and the object attribute features of the target object. Based on the product attribute features of the target product and the object attribute features of the target object, the server determines the attribute delivery requirement for delivering the target product to the target object.

[0097] For example, the server extracts features from the product attributes and the object attributes to obtain the product attribute features of the target product and the object attribute features of the target object. The server then fuses the product attribute features of the target product and the object attribute features of the target object to obtain a third fused feature. The server uses an attention mechanism to iteratively decode this third fused feature multiple times to obtain the delivery requirement for that attribute.

[0098] Part Three: Based on the object's delivery requirements, the description of delivery needs, and the attribute of delivery needs, the server determines the second delivery requirement for delivering the target product.

[0099] In one possible implementation, the server determines a baseline object delivery requirement for the target object based on the object delivery request. The server then determines a second delivery requirement for the target product based on the baseline object delivery requirement, the description delivery requirement, and the attribute delivery requirement.

[0100] For example, the server fills the object's delivery requirement into the baseline object delivery requirement template to obtain the baseline object delivery requirement for the target object. The server then merges the baseline object delivery requirement, the description delivery requirement, and the attribute delivery requirement to obtain the second delivery requirement for the target product.

[0101] Through step 303 above, by comprehensively considering multiple aspects of product information and object information, the descriptive delivery requirements and attribute delivery requirements are determined separately. Combined with the object delivery requirements, the second delivery requirement is finally derived. This method can more comprehensively and accurately reflect delivery needs, which is helpful for subsequent capacity matching and scheduling.

[0102] The main features of this technical solution include product information, object information, description of delivery requirements, attribute-based delivery requirements, and secondary delivery requirements. Product information includes a textual description of the product, such as "fragile" or "fresh food." Product attributes can include specific data such as weight, volume, and shelf life. Object information includes a description of the recipient, such as "elderly" or "student." Delivery requirements can include expected delivery time and special delivery requests. Object attributes can include delivery address and contact information.

[0103] The process of determining delivery requirements can employ natural language processing (NLP) techniques to perform semantic analysis on product and object descriptions, extracting key information. For example, when a product is described as "fragile" and an object is described as "elderly," the delivery requirement could be "handle with care, delivered to the door." Determining attribute-based delivery requirements involves data analysis and matching of product and object attributes. For instance, when a product is heavy and the delivery address is on a high floor without an elevator, the attribute-based delivery requirement could be "requires additional human assistance." Finally, by comprehensively considering the object delivery requirements, description-based delivery requirements, and attribute-based delivery requirements, a comprehensive second delivery requirement can be obtained. This process can utilize machine learning algorithms, such as decision trees or neural networks, taking various factors as input and outputting the final delivery requirement.

[0104] The advantage of this method lies in its ability to more comprehensively consider various factors in the delivery process, including not only the characteristics of the goods themselves but also the features and requirements of the recipients. By processing descriptive and attribute information separately, qualitative and quantitative delivery needs can be better captured. The final secondary delivery demand more accurately reflects the actual situation, helping the system select the most suitable transportation capacity for delivery.

[0105] 304. Based on the first delivery demand and the second delivery demand, the server determines the target delivery demand for the target product.

[0106] The first step involves determining the target delivery demand based on the primary and secondary delivery needs. This step comprehensively considers information from three dimensions: the store, the product, and the customer, resulting in a comprehensive and accurate delivery demand. For example, by comprehensively considering the ice cream shop's 30-minute delivery time limit and low-temperature requirements, as well as the customer's specific address and time requirements, a target delivery demand is ultimately determined that satisfies both the store and product requirements and the customer's needs.

[0107] In one possible implementation, the server merges the first delivery request and the second delivery request using a first weight and a second weight to obtain the target delivery request for the target product. The first weight corresponds to the first delivery request, and the second weight corresponds to the second delivery request. 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] To provide a clearer explanation of the above implementation methods, the determination method of the first weight and the second weight in the above implementation methods will be explained below.

[0109] First, let's explain how the first weight is determined.

[0110] In one possible implementation, the server inputs the store attributes of the target store and the product attributes of the target product into a weighted determination model. The model extracts features from these attributes to obtain store attribute features and product attribute features. The server then fuses these features using the weighted determination model to obtain a fourth fused feature. Finally, the model performs a fully connected and normalized operation on this fourth fused feature to obtain the first weight.

[0111] The weighting model is a regression model.

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

[0113] In one possible implementation, the server inputs the object attributes of the target object and the product attributes of the target product into a weighted determination model. The model extracts features from these attributes to obtain object attribute features and product attribute features. The server then fuses these object attribute features and product attribute features using the weighted determination model to obtain a fifth fused feature. Finally, the model performs a fully connected and normalized operation on this fifth fused feature to obtain the second weight.

[0114] Through steps 302-304 above, the target delivery demand is determined through comprehensive analysis of multi-dimensional information, solving the problem that relying solely on single-dimensional information makes it difficult to fully and accurately grasp delivery demand. The innovation of this method lies in the organic combination of information from stores, products, and delivery recipients. By determining delivery demand at two levels, a more comprehensive and accurate target delivery demand is ultimately derived. This not only improves the accuracy of delivery demand determination but also provides a more reliable basis for subsequent capacity matching and scheduling, contributing to improved overall delivery efficiency and service quality.

[0115] A specific implementation of steps 302-304 above might be as follows: Suppose a high-end restaurant in the city center (store information) needs to deliver a seafood set meal that requires insulation (product information) to a customer in the suburbs (customer information). First, the system will generate a first delivery request based on the restaurant's location and the characteristics of the seafood set meal, requiring delivery within 45 minutes and requiring insulation equipment. Then, based on the characteristics of the seafood set meal and the customer's location, the system will generate a second delivery request that requires long-distance transportation and maintaining food freshness. Finally, the system will combine these two requests to generate a target delivery request that requires delivery within one hour, requires insulation equipment, and the delivery person needs to have long-distance delivery experience.

[0116] Compared to related technologies that determine delivery needs solely based on order delivery distance, the method in this application considers more factors and can more accurately reflect actual delivery demands. For example, in the above embodiments, considering only delivery distance might overlook the requirements for food insulation and freshness, resulting in customers receiving poor-quality food. The method in this application, by comprehensively considering information from multiple dimensions, can better meet various needs and improve delivery quality and efficiency.

[0117] 305. Based on the regional information of the target area and the capacity information of the target area, the server determines multiple reference capacities from the multiple candidate capacities.

[0118] Among them, regional information refers to various data related to the target area, which can be specifically implemented using regional delivery difficulty and regional delivery popularity. Capacity information refers to various data related to the available capacity within the target area, which can be specifically implemented using capacity distribution, the fatigue level of candidate capacity, and their proficiency. Multiple candidate capacity refers to capacity with delivery capabilities in the target area, while multiple reference capacity refers to capacity obtained after filtering these multiple candidate capacity using regional and capacity information.

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

[0120] In this implementation, multiple candidate capacities can be screened using regional and capacity information to obtain multiple reference capacities, which helps in the subsequent determination of target capacities.

[0121] To provide a clearer explanation of the above embodiments, the following description is divided into several parts.

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

[0123] In one possible implementation, the delivery difficulty of the area includes the degree of regional congestion and the severity of regional weather. The server determines first delivery difficulty description information for the target area based on the degree of regional congestion and the severity of regional weather. The server then determines second delivery difficulty description information for the target area based on the capacity distribution. Finally, the server merges the first and second delivery difficulty description information for the target area to obtain the final delivery difficulty description information for the target area.

[0124] For example, the server concatenates the congestion level and weather severity of the area with a first prompt text template to obtain the first prompt text. The server inputs this first prompt text into a target language model, processes it, and outputs the first delivery difficulty description information for the target area. The server then concatenates the transportation capacity distribution with a second prompt text template to obtain the second prompt text. The server inputs this second prompt text into the target language model, processes it, and outputs the second delivery difficulty description information for the target area. Finally, the server merges the first and second delivery difficulty description information for the target area to obtain the final delivery difficulty description information for the target area.

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

[0126] Part Two: The server determines the delivery activity description information for the target area based on the delivery popularity and the distribution of delivery capacity in that area.

[0127] In one possible implementation, the server determines first delivery activity description information for the target area based on the delivery popularity of the area, whereby the delivery popularity indicates the activity level of ordered goods within the target area. The server then determines second delivery activity description information for the target area based on the delivery capacity distribution. Finally, the server merges the first and second delivery activity description information to obtain the final delivery activity description information for the target area.

[0128] For example, the server concatenates the delivery popularity data for the region with a third prompt text template to obtain the third prompt text. The server inputs this third prompt text into a target language model, processes it, and outputs the first delivery activity description information for the target region. The server then concatenates the delivery capacity distribution data with a fourth prompt text template to obtain the fourth prompt text. The server inputs this fourth prompt text into the target language model, processes it, and outputs the second delivery activity description information for the target region. Finally, the server merges the first and second delivery activity description information to obtain the final delivery activity description information for the target region.

[0129] The third and fourth prompt text templates are set by technicians according to the actual situation, and this application embodiment does not limit them.

[0130] Part Three: Based on the capacity fatigue level and proficiency level of the multiple candidate transport capacities, the server determines the capacity status description information of each candidate transport capacity.

[0131] In one possible implementation, the fatigue level of the transport capacity includes cumulative delivery time and physiological parameters. The proficiency level includes familiarity with the target area and delivery procedures. Based on the cumulative delivery time and physiological parameters of each candidate transport capacity, the server determines the fatigue state description information for each candidate transport capacity. The physiological parameters include heart rate, blood pressure, and body temperature. Based on the familiarity with the target area and delivery procedures of each candidate transport capacity, the server determines the delivery state description information for each candidate transport capacity. Based on the fatigue state description information and delivery state description information of each candidate transport capacity, the server determines the transport capacity state description information for each candidate transport capacity.

[0132] For example, the server extracts features from the physiological parameters of each candidate transport capacity to obtain its physiological characteristics. The server concatenates the cumulative delivery time and physiological characteristics of each candidate transport capacity with a fifth prompt text template to obtain the fifth prompt text. The server inputs this fifth prompt text into a target language model, processes it, and outputs a description of the fatigue state of each candidate transport capacity. The server then concatenates the regional familiarity and delivery familiarity of each candidate transport capacity with a sixth prompt text template to obtain the sixth prompt text. The server inputs this sixth prompt text into a target language model, processes it, and outputs a description of the delivery status of each candidate transport capacity. Finally, the server fuses the fatigue state descriptions and delivery status descriptions of each candidate transport capacity to obtain a description of its overall transport capacity status.

[0133] The fifth and sixth prompt text templates are set by technicians according to the actual situation, and this application embodiment does not limit them.

[0134] Part Four: Based on the delivery difficulty description information, the delivery activity description information, and the capacity status description information of each candidate capacity, the server determines multiple reference capacity from the multiple candidate capacity.

[0135] In one possible implementation, the server determines the target area delivery difficulty coefficient 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 its capacity status description information. 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 then identifies the N candidate transport capacities with the highest target state scores among these candidate transport capacities as the reference transport capacities, where N is a positive integer.

[0136] For example, the server extracts features from the delivery difficulty description and the delivery activity description to obtain the delivery difficulty feature and delivery activity feature, respectively. The server then fuses these two features to obtain a sixth fused feature. The server performs a fully connected operation and normalization on this sixth fused feature to obtain the target area delivery difficulty coefficient. The server extracts features from the capacity status description of each candidate capacity to obtain the capacity status feature of each candidate capacity. The server performs a fully connected operation and normalization on 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 then identifies the N candidate capacities with the highest target state scores among these candidate capacities as the reference capacities, where N is a positive integer.

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

[0138] The target capacity is defined as the capacity that best matches the target delivery demand. This step, by analyzing regional characteristics, capacity status, and delivery needs, selects the most suitable capacity, improving the accuracy and efficiency of capacity allocation.

[0139] In one possible implementation, the capacity information includes delivery styles, capacity descriptions, and capacity attributes of multiple reference capacity services. The server determines the degree of matching between each reference capacity and the target delivery demand based on these attributes. The server then identifies the reference capacity with the highest degree of matching to the target delivery demand among the multiple reference capacity services as the target capacity.

[0140] To provide a clearer explanation of the above implementation methods, the method for determining the degree of matching between each reference capacity and the target delivery demand in the above implementation methods will be described below.

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

[0142] 307. The server summons the target delivery capacity to deliver the target goods to the target object.

[0143] In this process, the designated target capacity is used to deliver the target goods to the target recipient. This step puts the decisions made in the previous steps into practice, completing the entire intelligent capacity scheduling process.

[0144] In one possible implementation, the server pushes the target order to the delivery terminal of the target delivery capacity, so that the target delivery capacity can make delivery based on the target order, which is a delivery order for delivering the target goods to the target object.

[0145] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0146] This application provides a multi-dimensional, multi-step intelligent transportation capacity scheduling method. This method acquires and comprehensively analyzes information from multiple aspects, including stores, products, regions, transportation capacity, and recipients, to achieve more accurate and flexible transportation capacity allocation. This method not only considers delivery distance and the willingness of transportation capacity to accept orders, but also incorporates factors such as special order requirements, product characteristics, store requirements, regional conditions, and transportation capacity characteristics, thereby greatly improving the flexibility and efficiency of transportation capacity scheduling.

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

[0148] The acquisition module 401 is used to respond to the target store's delivery request for the target product, and acquire 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 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 the target capacity from multiple candidate capacity in the target area based on the area information of the target area, the capacity information of the target area and the target delivery demand. 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 goods to the target object.

[0152] It should be noted that the intelligent transportation capacity scheduling system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent transportation capacity scheduling system and the intelligent transportation capacity scheduling method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0153] This application provides a multi-dimensional, multi-step intelligent transportation capacity scheduling method. This method acquires and comprehensively analyzes information from multiple aspects, including stores, products, regions, transportation capacity, and recipients, to achieve more accurate and flexible transportation capacity allocation. This method not only considers delivery distance and the willingness of transportation capacity to accept orders, but also incorporates factors such as special order requirements, product characteristics, store requirements, regional conditions, and transportation capacity characteristics, thereby greatly improving the flexibility and efficiency of transportation capacity scheduling.

[0154] Figure 5This is a schematic diagram of a server structure provided in an embodiment of this application. The server 500 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 501 and one or more memories 502. The one or more memories 502 store at least one computer program, which is loaded and executed by the one or more processors 501 to implement the methods provided in the various method embodiments described above. Of course, the server 500 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 500 may also include other components for implementing device functions, which will not be elaborated upon here.

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

[0156] In an exemplary embodiment, a computer program product or computer program is also provided, which includes program code stored in a computer-readable storage medium. The processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform the above-described intelligent transportation capacity scheduling method.

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

[0158] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

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

Claims

1. An intelligent transportation capacity scheduling method, characterized in that, The method includes: In response to a delivery request from a target store for a target product, the system acquires the store information of the target store, the product information of the target product, the regional 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. The regional information includes regional delivery difficulty and regional delivery popularity. The transportation capacity information includes transportation capacity distribution, the fatigue level and proficiency level of multiple candidate transportation companies, the store information includes store description information, store delivery requirements, and store attributes. The store description information is the transportation company's description of the target store. The product information includes product description information and product attributes. The product description information is the transportation company's description of the target product. The object information includes object description information, object delivery requirements, and object attributes. The object description information is the transportation company's description of the target object. Based on the store delivery requirements, determine the baseline store delivery requirements for the target store; based on the store description information and store attributes, determine the reference store delivery requirements for the target store; based on the product description information and product attributes, determine the product delivery requirements for the target product; based on the baseline store delivery requirements, the reference store delivery requirements, and the product delivery requirements, determine the first delivery requirement for delivering the target product. Based on the product description information and the object description information, a description delivery requirement for delivering the target product to the target object is determined; based on the product attributes and the object attributes, an attribute delivery requirement for delivering the target product to the target object is determined; based on the object delivery requirements, the description delivery requirement, and the attribute delivery requirement, a second delivery requirement for delivering the target product is determined. The first delivery demand and the second delivery demand are merged using a first weight and a second weight to obtain the target delivery demand for 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. Based on the regional delivery difficulty and the capacity distribution, the following steps are taken: Determine the delivery difficulty description information for the target region; determine the delivery activity description information for the target region based on the regional delivery popularity and the capacity distribution; determine the capacity status description information for each candidate capacity based on the capacity fatigue and proficiency of the multiple candidate capacity providers; determine the target region delivery difficulty coefficient based on the delivery difficulty description information and the delivery activity description information; determine the initial status score for each candidate capacity based on its capacity status description information; multiply the initial status score of each candidate capacity by the target region delivery difficulty coefficient to obtain the target status score for each candidate capacity; determine the N candidate capacity providers with the highest target status scores among the multiple candidate capacity providers as multiple reference capacity providers, where N is a positive integer; and determine the target capacity from the multiple reference capacity providers based on the target delivery demand and the capacity information, where the target capacity is the capacity matching the target delivery demand. The target delivery personnel are summoned to deliver the target goods to the target object.

2. The method according to claim 1, characterized in that, The store delivery requirements include the store's required delivery time, required delivery method, and required delivery capacity. Determining the baseline store delivery requirements for the target store based on these requirements includes: Based on the delivery time requirements of the stores, determine the delivery time requirements of the target stores; Based on the store's required delivery method and the store's required delivery capacity description, the delivery capacity requirement of the target store is determined; Based on the delivery timeliness requirements and the delivery capacity requirements, the baseline store delivery requirements for the target store are determined.

3. The method according to claim 1, characterized in that, The step of determining the second delivery requirement for the target product based on the object delivery requirements, the description delivery requirements, and the attribute delivery requirements includes: Based on the object delivery requirements, determine the baseline object delivery needs for the target object; Based on the baseline object delivery requirements, the description delivery requirements, and the attribute delivery requirements, the second delivery requirements for the target product are determined.

4. An intelligent transportation capacity scheduling system, characterized in that, The system includes: The acquisition module is used to respond to a delivery request from a target store for a target product by acquiring the store information of the target store, the product information of the target product, the regional 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. The regional information includes regional delivery difficulty and regional delivery popularity. The transportation capacity information includes transportation capacity distribution, the fatigue level and proficiency level of multiple candidate transportation companies, the store information includes store description information, store delivery requirements, and store attributes. The store description information is the transportation capacity's description of the target store. The product information includes product description information and product attributes. The product description information is the transportation capacity's description of the target product. The object information includes object description information, object delivery requirements, and object attributes. The object description information is the transportation capacity's description of the target object. The demand determination module is used to: determine the baseline store delivery demand of the target store based on the store delivery requirements; determine the reference store delivery demand of the target store based on the store description information and store attributes; determine the product delivery demand of the target product based on the product description information and product attributes; determine the first delivery demand for the target product based on the baseline store delivery demand, the reference store delivery demand, and the product delivery demand; determine the description delivery demand for the target product to be delivered to the target object based on the product description information and the object description information; determine the attribute delivery demand for the target product to be delivered to the target object based on the product attributes and the object attributes; determine the second delivery demand for the target product based on the object delivery requirements, the description delivery demand, and the attribute delivery demand; and fuse the first delivery demand and the second delivery demand using a first weight and a second weight to obtain the target delivery demand for 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. The capacity determination module is used to: determine delivery difficulty description information for the target area based on the regional delivery difficulty and the capacity distribution; determine delivery activity description information for the target area based on the regional delivery popularity and the capacity distribution; determine capacity status description information for each candidate capacity based on the capacity fatigue level and proficiency level of the multiple candidate capacity providers; determine the target area delivery difficulty coefficient for the target area based on the delivery difficulty description information and the delivery activity description information; determine the initial status score for each candidate capacity based on the capacity status description information of each candidate capacity; multiply the initial status score of each candidate capacity by the target area delivery difficulty coefficient to obtain the target status score of each candidate capacity; determine the N candidate capacity providers with the highest target status scores among the multiple candidate capacity providers as multiple reference capacity providers, where N is a positive integer; and determine the target capacity from the multiple reference capacity providers based on the target delivery demand and the capacity information, wherein the target capacity is the capacity matching the target delivery demand. The summoning module is used to summon the target delivery capacity to deliver the target goods to the target object, wherein the target delivery capacity is the selected delivery person.

Images