Intelligent warehouse storage and transfer scheduling system and application method thereof
By using an intelligent warehouse storage and transfer scheduling system, which utilizes machine learning algorithms and color coding technology to dynamically allocate storage space resources, the system solves the problems of low resource utilization and collaborative management among multiple courier companies in traditional warehouse systems, and achieves efficient resource sharing and delivery route planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-05
- Publication Date
- 2026-04-03
Smart Images
Figure CN121788024A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent warehousing and logistics technology, and in particular to an intelligent warehouse storage and transfer scheduling system and its application methods. Background Technology
[0002] With the rapid development of e-commerce and logistics, the application prospects of intelligent warehouse storage and transfer systems are becoming increasingly broad. Traditional warehouse systems need to handle a large number of express delivery storage and retrieval demands, especially in high-traffic areas and during peak periods.
[0003] However, existing technologies have many shortcomings and problems: First, traditional systems often adopt a static allocation strategy, which cannot dynamically adjust storage space resources according to real-time demand changes, resulting in low resource utilization and a tendency for insufficient or idle storage spaces during peak periods. Second, existing systems lack an effective mechanism for collaborative management of multiple courier companies, and cannot allocate resources fairly based on historical business proportions and real-time demands, easily leading to resource contention or inefficiency. Furthermore, handheld terminals have rudimentary functions and typically cannot provide real-time, visualized storage space status guidance, forcing couriers to rely on experience-based judgment, resulting in inefficient delivery route planning.
[0004] In response to the aforementioned technologies, a solution is proposed. Summary of the Invention
[0005] The purpose of this application is to provide an intelligent warehouse storage transfer scheduling system and its application method to solve the technical problems in the prior art, such as the inability to change storage locations in real time, uneven distribution, and rudimentary handheld terminals.
[0006] The intelligent warehouse storage and transfer scheduling system and its application method provided in this application adopt the following technical solution: The intelligent warehouse storage and transfer scheduling system includes a server module, a handheld terminal module, and a parcel storage and retrieval module:
[0007] Server module: Based on real-time demand and historical usage data, the number of storage slots in the express delivery storage module is dynamically allocated through machine learning algorithms, thereby prioritizing the allocation of storage slots in high-demand areas;
[0008] Handheld terminal module: Displays the storage location map generated by the server module to the courier through a push program, and displays the real-time available space of the courier storage box through color coding;
[0009] Express delivery storage and retrieval module: includes a virtual resource unit and a communication unit. The virtual resource unit creates an independent virtual storage space for cooperating express delivery companies. The communication unit obtains the real-time demand signals, historical business proportions and preset priorities of the express delivery companies through the server module and calculates and adjusts the virtual quota of the storage and retrieval box.
[0010] The virtual quota can be displayed on the handheld terminal module in real time.
[0011] By adopting the above technical solutions, the intelligent warehouse storage and transfer scheduling system achieves intelligent dynamic management of storage space resources through the coordinated operation of the server module, handheld terminal module, and express delivery storage and retrieval module.
[0012] Based on real-time demand and historical usage data, the server module uses machine learning algorithms for time-series prediction, analyzes the peak demand for storage spaces in different geographical regions, and dynamically allocates the number of storage spaces in the express delivery storage module, prioritizing high-demand areas. The algorithm model integrates seasonal, periodic, and trend components, and adjusts the influence of each component with weight coefficients to ensure prediction accuracy and adaptability. This effectively solves the problems of low resource utilization and response lag caused by traditional static allocation, and improves overall scheduling efficiency and resource elasticity.
[0013] The handheld terminal module receives the storage location map generated by the server module through the push program and displays the real-time available space of the storage box in a visually intuitive way using color coding, such as green indicating sufficient space, yellow indicating tight space, and red indicating insufficient space. At the same time, it allows couriers to input the size and quantity information of the packages to be delivered, and automatically generates the optimal delivery route. Based on visual guidance and real-time data mapping, it reduces the reliance on manual judgment and improves the convenience of operation and delivery accuracy.
[0014] The express delivery storage module creates independent virtual storage space for cooperating express delivery companies through virtual resource units. The communication unit calculates and adjusts the virtual quota of the storage box based on the real-time demand signals, historical business ratios, and preset priorities provided by the server module. The virtual quota is displayed on the handheld terminal module in real time. The use of dynamic weight values achieves fair resource sharing. The virtual quota, as the shared physical storage location corresponding to the logical quota, ensures the rationality and flexibility of resource allocation and reduces conflicts when multiple companies collaborate.
[0015] The machine learning algorithm employs a time-series prediction model, and its expression is as follows:
[0016]
[0017] in, This represents the predicted number of storage bits required for the access box b during time period t. The weighting coefficients representing the seasonal components; Indicates seasonal components; Indicates periodic components; The weighting coefficients representing the trend components; Indicates trend components; The weighting coefficients of the periodic components; Represents the random error term. The expression is used to predict the peak demand for storage space in different geographical areas during a specific future period based on historical usage data, thereby dynamically allocating the number of storage spaces.
[0018] The dynamic allocation employs a weighted allocation strategy, which assigns a set of dynamic weight values to each courier company. These dynamic weight values are calculated based on the real-time demand signal and the historical business proportion, and the calculation expression is as follows:
[0019]
[0020] in, This represents the dynamic weight value of the courier company; The weighting coefficients representing the real-time demand components; This indicates the real-time demand volume of the courier company. The weighting coefficients representing the historical business components; This indicates the historical business volume of the courier company; This represents the preset priority constant of the courier company. Furthermore, the number of storage spaces available to each of the aforementioned courier companies is proportional to the dynamic weight value, and the real-time demand signal includes:
[0021] The number of times the handheld terminal module connects to the server module;
[0022] The number of times the handheld terminal module is located within the preset geofence of the express delivery storage and retrieval module in the target storage location.
[0023] The number of storage spaces requested by the courier company through the handheld terminal module.
[0024] By adopting the above technical solution, and by introducing a machine learning algorithm based on a time-series prediction model and a weighted allocation strategy, accurate prediction of storage space demand and fair dynamic allocation of resources are achieved. The principle of this machine learning algorithm is to comprehensively consider the seasonal, cyclical and trend components in historical usage data, and adjust the influence of each component on the prediction results through weight coefficients, thereby scientifically predicting the peak storage space demand in different geographical areas in a specific future period and providing data support for dynamic allocation.
[0025] Based on this, the system adopts a weighted allocation strategy. The principle is to calculate a dynamic weight value for each cooperating courier company. This weight value is synthesized from real-time demand components and historical business components according to specific weight coefficients, and fine-tuned by introducing a preset priority constant. This ensures that the calculated dynamic weight value can reflect both immediate business pressure and long-term cooperative contributions, ultimately making the number of storage spaces available to each courier company proportional to its dynamic weight value. The real-time demand signals that this strategy relies on specifically include the number of handheld terminals accessing the server, the number of terminals entering the geofence of the target storage space, and the number of reservation requests. These multi-dimensional data together ensure the comprehensiveness and accuracy of real-time demand assessment.
[0026] The handheld terminal module also includes a map displaying the storage space. The map works in conjunction with the color coding to indicate that the storage space has sufficient available space in green, limited available space in yellow, and insufficient available space in red. The handheld terminal module can also input the size and quantity information of the package to be delivered and generate a delivery route based on the map according to the size and quantity information of the package.
[0027] By adopting the above technical solution, the storage location map is combined with the color coding system to realize an intuitive and visual display of the available space status of the storage box. The most intuitive visual element of color is used to map complex spatial status data, with green indicating sufficient available space, yellow indicating tight space, and red indicating insufficient space. This allows couriers to quickly and accurately grasp the overall resource status from the map without relying on experience or cumbersome text queries, thereby greatly improving the efficiency and accuracy of information acquisition.
[0028] Based on this, the handheld terminal module can also receive the size and quantity information of the packages to be delivered, input by the courier. The system automatically calculates and generates the optimal delivery route based on these specific physical space occupancy parameters, combined with real-time updated map data and color status. The principle of this route planning function is to match and optimize the input cargo information with the real-time capacity of the target storage location, ensuring that the recommended route is not only the shortest distance, but also effectively avoids storage locations that are in short supply or full, directly guiding the courier to the most suitable delivery point.
[0029] The independent virtual storage space created by the virtual resource unit is a logical quota. The storage bit corresponding to the quota is shared within the express delivery access module. The calculation formula for the virtual quota is:
[0030]
[0031] in, This refers to the virtual quota; This represents the total number of storage bits; This indicates the dynamic weight of the courier company; This represents the sum of the dynamic weights of all the aforementioned courier companies.
[0032] By adopting the above technical solution, the dynamic weight value is transformed into an executable virtual quota. The virtual resource unit creates an independent virtual storage space for each express delivery company, which is essentially a logical resource quota. This quota does not correspond to a specific physical storage location, but is realized by allocating usage rights proportionally in a shared physical storage resource pool.
[0033] The calculation formula for virtual quotas embodies this core idea. The total number of system storage bits, L, serves as the basis for the shared resource pool, while the dynamic weight ω_c of each company reflects its immediate resource demand priority. The formula determines the logical quota size a company should receive by calculating the proportion of its weight in the total weight. The principle behind this calculation method is to ensure that, under the premise of a constant total resource volume, quota allocation can respond in real-time to changes in the dynamic weights of each company, thereby achieving elastic scheduling and efficient sharing of physical resources among different companies.
[0034] The communication between the communication unit and the server module adopts an incremental synchronization protocol. The incremental synchronization protocol only sends status change data to the server module when the status of the storage bit changes. The server module is configured to send a rerouting suggestion notification to the handheld terminal module when it detects that the real-time available space of the storage box is lower than the virtual quota.
[0035] By adopting the above technical solution, the underlying data communication mechanism and proactive early warning function of the system are optimized. The communication unit and the server module use an incremental synchronization protocol for data interaction, changing the traditional continuous full synchronization method. Only when the actual state of the storage bit changes will the changed state data fragment be sent to the server module. This significantly reduces the amount of data transmitted in the network, reduces the occupation of communication bandwidth and processing latency, and ensures the efficiency and real-time performance of system state updates. Based on this efficient communication mechanism, the server module can continuously monitor the correspondence between the real-time available space of each storage box and its pre-allocated virtual quota.
[0036] The application method of an intelligent warehouse storage and transfer scheduling system includes the following steps:
[0037] S1. The server module collects the access status, number of active terminals within the geofence, and storage space reservation requests from the handheld terminal module in real time, and constructs a demand dataset by combining it with historical usage data.
[0038] S2. Based on the demand dataset, a machine learning algorithm is used to predict the peak demand for storage space in each geographical region in a time series, and a dynamic allocation strategy is generated.
[0039] S3. Adjust the virtual quota for the cooperating courier company according to the dynamic allocation strategy;
[0040] S4. The handheld terminal module receives the storage location status data and the virtual quota information sent by the server module in real time, maps the available space status of the storage box through color coding, and generates a visual guidance interface.
[0041] S5. When the real-time available space of a specific storage location is lower than the corresponding virtual quota, the server module automatically triggers a rerouting suggestion mechanism to push an alternative storage location allocation scheme to the handheld terminal module.
[0042] By adopting the above technical solution, the method begins with the server module collecting the access status of the handheld terminal module, the number of active terminals within the geofence, and storage space reservation requests in real time, and combining historical usage data to construct a comprehensive demand dataset. This step ensures the real-time nature and richness of the decision-making basis data.
[0043] Based on this dataset, the system uses machine learning algorithms to perform the core time-series prediction function, predicts the peak storage demand in different geographical areas during a specific future period, and generates a scientific dynamic allocation strategy accordingly. By analyzing the time-series patterns in the data through algorithm models, it provides a basis for decision-making for resource pre-allocation.
[0044] Subsequently, the system adjusts the virtual quotas of each cooperating express company according to the dynamic allocation strategy, thereby transforming the prediction results into actual resource scheduling instructions. The handheld terminal module receives and displays the storage location status and virtual quota information in real time, and generates a visual guidance interface through color coding mapping. The principle is to transform abstract quota and spatial data into intuitive visual signals, which greatly improves the efficiency of express delivery personnel in obtaining information and the convenience of operation.
[0045] By integrating discrete technical features into a collaborative and organic whole, the entire process from data acquisition, intelligent prediction, resource allocation, status visualization to proactive intervention is automated and intelligent, significantly improving the overall efficiency, response speed, and adaptive capability of warehouse storage transfer scheduling.
[0046] In step S4, the generation of the visual guidance interface includes: the handheld terminal module receiving the size and quantity information of the express delivery to be delivered input by the courier, combining the current storage location map data and color coding status, automatically planning the optimal delivery route, and highlighting the navigation mark of the target storage location in the interface.
[0047] By adopting the above technical solution, the size and quantity information of the packages to be delivered, actively input by the courier, are intelligently integrated and calculated with the current storage location map data and color coding status issued by the server module. The system accurately assesses the storage space requirements based on the input physical parameters of the goods, and at the same time obtains the space availability represented by the color status of each map point in real time. Through the built-in path planning algorithm, the system comprehensively considers the two key factors of optimal distance and resource availability, and automatically calculates an optimal delivery route that can effectively avoid areas with tight or insufficient space.
[0048] It has achieved an improvement from static information display to dynamic interactive planning, so that couriers no longer need to switch between multiple applications or interfaces to manually query and plan routes. The system generates intuitive and operable solutions with one click through intelligent calculation, which significantly reduces the complexity of operation and decision-making time.
[0049] In step S5, the triggering of the rerouting suggestion mechanism further includes: the server module continuously monitors the status changes of each group of storage bits based on the incremental synchronization protocol, and when it detects that multiple adjacent storage bits have insufficient available space at the same time, it recalculates the virtual quota distribution of the region and updates it to the handheld terminal module.
[0050] By adopting the above technical solution, the triggering logic and application scenarios of the rerouting suggestion mechanism are expanded. When the server module continuously monitors the changes in the storage bit status based on the incremental synchronization protocol, it not only responds to the situation of insufficient space in a single storage bit, but also identifies the regional resource tension situation where multiple adjacent storage bits are simultaneously experiencing insufficient available space.
[0051] The system identifies abnormal clustering patterns in space through real-time data monitoring. When multiple adjacent storage bits are detected to be below their virtual quotas at the same time, it determines that the overall resource load in the region is too high, thereby triggering a regional-level coordinated scheduling response. This elevates the system's response granularity from a single storage bit to the regional level, enabling early identification and coordinated resolution of regional resource bottlenecks. Through proactive quota reallocation, the system optimizes the overall resource layout within the region, preventing the spread and chain reactions of local congestion.
[0052] In summary, this application includes at least one of the following beneficial technical effects:
[0053] 1. By using machine learning algorithms and weighted allocation strategies in the server module, the number of storage bits is dynamically predicted and allocated based on real-time demand signals, historical usage data, and preset priorities. This solves the problems of low resource utilization and response lag caused by traditional static allocation, improving overall scheduling efficiency and resource adaptability;
[0054] 2. By using the virtual resource unit and communication unit of the express delivery storage module, an independent virtual storage space is created for the cooperating express delivery companies, and virtual quotas are calculated based on dynamic weight values to achieve fair and priority resource sharing. This overcomes the problem of the lack of a collaborative allocation mechanism in the existing system, ensures the rationality and flexibility of resource allocation, and reduces conflicts.
[0055] 3. The handheld terminal module intuitively displays the real-time available space of the storage box through color coding and generates delivery routes in combination with the map. The courier can input the size and quantity of the package to obtain the optimal navigation. This solves the shortcomings of traditional handheld terminals that have single functions and rely on manual judgment, and improves the convenience of operation and delivery accuracy.
[0056] 4. The communication unit employs an incremental synchronization protocol, sending data only when the storage bit state changes, reducing communication overhead. Simultaneously, the server module automatically triggers rerouting suggestions and pushes alternative solutions when the available space falls below the virtual quota. This avoids the bandwidth waste and response delays of full synchronization, enabling rapid early warning and path optimization, and reducing congestion risks. Attached Figure Description
[0057] Figure 1 This is a flowchart of the application method of the present invention.
[0058] Figure 2 This is the system architecture diagram of the present invention. Detailed Implementation
[0059] The following is in conjunction with the appendix Figure 1 - Appendix Figure 2 This application will be described in further detail below.
[0060] This application discloses an intelligent warehouse storage and transfer scheduling system and its application method.
[0061] The intelligent warehouse storage and transfer scheduling system includes a server module, a handheld terminal module, and a parcel storage and retrieval module.
[0062] Server module: Based on real-time demand and historical usage data, the number of storage slots in the express delivery storage module is dynamically allocated through machine learning algorithms, thereby prioritizing the allocation of storage slots in high-demand areas;
[0063] Handheld terminal module: Displays the storage location map generated by the server module to the courier through a push program, and displays the real-time available space of the courier storage box through color coding;
[0064] Express delivery storage and retrieval module: includes a virtual resource unit and a communication unit. The virtual resource unit creates an independent virtual storage space for cooperating express delivery companies. The communication unit obtains the real-time demand signals, historical business proportions and preset priorities of the express delivery companies through the server module and calculates and adjusts the virtual quota of the storage and retrieval box.
[0065] The virtual quota can be displayed on the handheld terminal module in real time.
[0066] Specifically, the algorithm runs periodically and outputs prediction results. Based on this, the server module instructs the access module to adjust the allocation of storage bits, prioritizing high-demand areas. This effectively solves the problems of low resource utilization and delayed response caused by traditional static allocation, and improves scheduling efficiency and resource adaptability.
[0067] The handheld terminal module receives storage location map data pushed by the server module through an application installed on a smartphone or dedicated device. This map displays the location of each storage location in a graphical interface and uses color coding to intuitively indicate the real-time available space of the storage boxes; for example, green indicates ample space, yellow indicates limited space, and red indicates insufficient space. The principle is to use visual signals to quickly convey complex spatial conditions, reducing the cognitive load on delivery personnel. In practice, the handheld terminal also allows delivery personnel to input the size and quantity of packages to be delivered. Based on these parameters and the map status, the system automatically plans the optimal delivery route and highlights navigation markers on the interface, thereby improving operational convenience and delivery accuracy.
[0068] The express delivery storage module physically consists of multiple storage boxes, each equipped with sensors and a communication unit. The virtual resource unit creates an independent virtual storage space for each cooperating express delivery company at the software level. Its principle is to share physical storage locations through logical quotas to achieve elastic resource allocation. The communication unit connects to the server module via a wireless network and adopts an incremental synchronization protocol, sending status change data only when the storage location status changes, reducing communication overhead. The communication unit calculates dynamic weight values based on real-time demand signals, historical business proportions, and preset priorities provided by the server, and then adjusts the virtual quotas. The virtual quotas are displayed in real time on the handheld terminal, enabling couriers to clearly understand resource allocation, ensuring fairness and reducing conflicts.
[0069] The machine learning algorithm employs a time-series prediction model, and its expression is as follows:
[0070]
[0071] in, This represents the predicted number of storage bits required for the access box b during time period t. The weighting coefficients representing the seasonal components; Indicates seasonal components; Indicates periodic components; The weighting coefficients representing the trend components; Indicates trend components; The weighting coefficients of the periodic components; Represents the random error term. The expression is used to predict the peak demand for storage space in different geographical areas during a specific future period based on historical usage data, thereby dynamically allocating the number of storage spaces.
[0072] The dynamic allocation employs a weighted allocation strategy, which assigns a set of dynamic weight values to each courier company. These dynamic weight values are calculated based on the real-time demand signal and the historical business proportion, and the calculation expression is as follows:
[0073]
[0074] in, This represents the dynamic weight value of the courier company; The weighting coefficients representing the real-time demand components; This indicates the real-time demand volume of the courier company. The weighting coefficients representing the historical business components; This indicates the historical business volume of the courier company; This represents the preset priority constant of the courier company. Furthermore, the number of storage spaces available to each of the aforementioned courier companies is proportional to the dynamic weight value, and the real-time demand signal includes:
[0075] The number of times the handheld terminal module connects to the server module;
[0076] The number of times the handheld terminal module is located within the preset geofence of the express delivery storage and retrieval module in the target storage location.
[0077] The number of storage spaces requested by the courier company through the handheld terminal module.
[0078] Specifically, The expression concretizes a classic time series prediction model, making it closely related to the business scenario of this invention, that is... This is the core output of the model. It's not a simple qualitative judgment of "whether it's busy," but a quantitative prediction. Based on this, the server can accurately determine that "tomorrow morning between 9 and 10 a.m., the storage box at the entrance of Community A is expected to need 15 medium-sized empty spaces," thus achieving truly accurate "dynamic allocation" and "priority allocation."
[0079] Capture recurring patterns on a weekly basis. For example, office building lockers always experience peak delivery times on weekday mornings (such as Monday at 9 a.m.), while weekends are very quiet.
[0080] It captures recent inertia or changes. It reflects the latest business dynamics. For example, if business volume suddenly surged at the same time yesterday, this information will be quickly transmitted to the current forecast through λ weights;
[0081] Focus on long-term (e.g., monthly) slow trends. For example, if the occupancy rate of a residential community increases year by year, its express delivery volume will also steadily increase;
[0082] These three weights are the model's "tuning knobs," determining which of the three factors—seasonality, recent cycles, and long-term trends—has a greater impact on the final prediction result. Their values are not preset by humans but are automatically optimized through machine learning training on a large amount of historical data. This allows the model to adapt to different scenarios.
[0083] The calculation formula transforms the calculation of dynamic weights from a conceptual level into an executable quantitative algorithm, clarifying the contribution mode and proportion of each factor. A benchmark for resource allocation among multiple courier companies. Companies with higher values will receive more virtual storage quotas, which changes the allocation decision from subjective judgment to objective calculation;
[0084] Mapping the demand signal strength of all companies to a range of 0 to 1 has the advantage of eliminating the influence of absolute values, making each company's demand signal strength more transparent. The values are comparable;
[0085] This ensures that important clients with large business volumes can obtain a stable basic weight, avoiding excessive reduction of quotas due to short-term demand fluctuations, and reflects the protection of strategic partners;
[0086] It is a moderating factor used to incorporate business strategy considerations. and This is the core strategy of the algorithm, determining the relative importance of the two principles, "responding to real-time needs" and "respecting historical contributions," in the final weighting:
[0087] if Set much larger than The system is highly sensitive and tends to prioritize the needs of companies with the most urgent immediate demands, which may harm the long-term interests of major clients; if Set much larger than If the system is stable, it can guarantee the basic quota for large customers, but it may not be able to flexibly cope with sudden peak demand.
[0088] The handheld terminal module also includes a map displaying the storage space. The map works in conjunction with the color coding to indicate that the storage space has sufficient available space in green, limited available space in yellow, and insufficient available space in red. The handheld terminal module can also input the size and quantity information of the package to be delivered and generate a delivery route based on the map according to the size and quantity information of the package.
[0089] Specifically, the handheld terminal module is implemented through an application installed on a smartphone or dedicated PDA device. This application continuously receives storage location map data and corresponding real-time available space status information pushed from the server module. The application interface combines a geographic information system map with a dynamic color coding system: each storage location icon on the map is rendered with a specific color according to the available space data sent by the server: a green icon indicates sufficient space, a yellow icon indicates limited space, and a red icon indicates insufficient space. This design utilizes human intuitive perception of color to quickly convey complex space capacity information, enabling couriers to grasp the overall resource status at a glance.
[0090] Meanwhile, the handheld terminal module provides an input interface, allowing couriers to manually input the size and quantity of the packages to be delivered. The system's built-in route planning algorithm then automatically calculates an optimal delivery route based on these cargo parameters, current map data, and the color status of each point. The algorithm prioritizes green icon locations, avoids red icon locations, and displays the planned route with highlighted lines on the interface map, while also highlighting the navigation marker of the target storage location.
[0091] The independent virtual storage space created by the virtual resource unit is a logical quota. The storage bit corresponding to the quota is shared within the express delivery access module. The calculation formula for the virtual quota is:
[0092]
[0093] in, This refers to the virtual quota; This represents the total number of storage bits; This indicates the dynamic weight of the courier company; This represents the sum of the dynamic weights of all the aforementioned courier companies.
[0094] Specifically, a separate virtual storage space is created for each cooperating courier company. This space is not a physically isolated storage area, but rather based on a calculation formula. Dynamically calculated logical quotas divide a fixed physical resource pool into logical quotas based on weight ratios, achieving both the sharing of physical resources and the independence of logical allocation.
[0095] During implementation, the server module periodically or based on real-time demand triggers weight calculations, and then uses this formula to redetermine the virtual quota C for each company. The calculated virtual quota information is sent to the handheld terminal module through the communication unit and clearly displayed on its interface, for example, under the corresponding company view, it is marked "Available Quota: X / Y storage bits".
[0096] The communication between the communication unit and the server module adopts an incremental synchronization protocol. The incremental synchronization protocol only sends status change data to the server module when the status of the storage bit changes. The server module is configured to send a rerouting suggestion notification to the handheld terminal module when it detects that the real-time available space of the storage box is lower than the virtual quota.
[0097] Specifically, the communication unit is implemented in the express delivery storage module by integrating a network communication chip and supporting firmware. The communication between the unit and the server module is implemented using an incremental synchronization protocol. Sensors installed on each storage box continuously monitor changes in the storage location status. However, the communication unit only generates a short message containing the change location identifier and the latest status data when it detects a change in the actual usage status of the storage location, such as when an express delivery is stored or retrieved, resulting in a change in space occupancy. This message is then sent to the server module via a wireless network.
[0098] After receiving this incremental data, the server module updates the system status view in real time and continuously compares the real-time available space of each storage box with its current virtual quota. When the monitoring logic determines that the real-time available space of a storage box is lower than its set virtual quota, the server module automatically triggers a rerouting suggestion mechanism. Specifically, this involves instantly generating a notification message containing an alternative storage location identifier, location, and route guidance, and sending it to the relevant courier's handheld terminal application interface via push service.
[0099] The application method of an intelligent warehouse storage and transfer scheduling system includes the following steps:
[0100] S1. The server module collects the access status, number of active terminals within the geofence, and storage space reservation requests from the handheld terminal module in real time, and constructs a demand dataset by combining it with historical usage data.
[0101] S2. Based on the demand dataset, a machine learning algorithm is used to predict the peak demand for storage space in each geographical region in a time series, and a dynamic allocation strategy is generated.
[0102] S3. Adjust the virtual quota for the cooperating courier company according to the dynamic allocation strategy;
[0103] S4. The handheld terminal module receives the storage location status data and the virtual quota information sent by the server module in real time, maps the available space status of the storage box through color coding, and generates a visual guidance interface.
[0104] S5. When the real-time available space of a specific storage location is lower than the corresponding virtual quota, the server module automatically triggers a rerouting suggestion mechanism to push an alternative storage location allocation scheme to the handheld terminal module.
[0105] Specifically, in step S1, the server module continuously receives access status heartbeat packets from all online handheld terminal modules through its data interface, and uses geofencing technology to count the number of active terminals within the preset range of the target storage location. At the same time, it records the storage location reservation requests submitted by each express delivery company through the terminal, and integrates these real-time data with historical usage records in the database to construct a demand dataset.
[0106] In step S2, the server calls a preset machine learning algorithm time series prediction model to process the dataset. The model calculates the weighted sum of seasonal, periodic and trend components, outputs the peak storage demand prediction for different geographical areas in a specific future period, and then generates a dynamic allocation strategy that specifies the number of storage spaces to be allocated to each area.
[0107] In step S3, the server recalculates the dynamic weight values of each cooperating courier company according to the strategy and adjusts their virtual quotas based on the virtual quota formula.
[0108] In step S4, the handheld terminal module receives the updated storage location status map and virtual quota data through the data push service, and visualizes the status of each storage box on its map interface with color coding: green indicates sufficient space, yellow indicates tight space, and red indicates insufficient space. At the same time, a visual guide interface integrating these status information is generated.
[0109] When the server detects that the real-time available space of a certain storage location is lower than its virtual quota during the S5 step, it immediately triggers the rerouting suggestion mechanism and automatically pushes a notification containing alternative storage location information to the relevant handheld terminal.
[0110] In step S4, the generation of the visual guidance interface includes: the handheld terminal module receiving the size and quantity information of the express delivery to be delivered input by the courier, combining the current storage location map data and color coding status, automatically planning the optimal delivery route, and highlighting the navigation mark of the target storage location in the interface.
[0111] Specifically, the application interface of the handheld terminal module provides a clear input area for couriers to manually input the size parameters and quantity information of the packages to be delivered. After the system receives this data, its built-in path planning algorithm is immediately activated. This algorithm can be referenced from Amazon's order sorting and guidance system. The principle of the algorithm is to comprehensively consider three core factors: the total volume of the input goods, the storage location map data currently obtained from the server, and the real-time available space status represented by the color coding of each storage location icon. The algorithm will automatically calculate and generate an optimal delivery route. This route is not only the shortest in distance, but also intelligently avoids storage locations with tight space displayed in red or yellow, and prioritizes the green icon representing the space with sufficient space.
[0112] In step S5, the triggering of the rerouting suggestion mechanism further includes: the server module continuously monitors the status changes of each group of storage bits based on the incremental synchronization protocol, and when it detects that multiple adjacent storage bits have insufficient available space at the same time, it recalculates the virtual quota distribution of the region and updates it to the handheld terminal module.
[0113] Specifically, the server will start the regional scheduling algorithm. The core logic of the regional scheduling algorithm draws on the idea of elastic load balancing in cloud computing. By monitoring the real-time load of each node in the region, the specific calculation process is as follows: First, based on the latest real-time demand signals such as the number of appointment requests and historical business ratio data, the dynamic weights of all cooperating express companies in the region are recalculated.
[0114] Subsequently, using a mapping mechanism similar to a consistent hashing algorithm, the recalculated virtual quotas are smoothly allocated to various specific storage locations within the region, generating a new virtual quota distribution scheme. The updated quota scheme is then distributed to all active handheld terminal modules within the relevant region via the communication unit, and the map color coding and quota display on the terminal interface are updated synchronously.
[0115] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Identical components are represented by the same reference numerals. Therefore, all equivalent changes made to the structure, shape, and principle of this application should be covered within the scope of protection of this application.
Claims
1. An intelligent warehouse storage and transfer scheduling system, comprising a server module, a handheld terminal module, and a parcel storage and retrieval module, characterized in that: Server module: Based on real-time demand and historical usage data, the number of storage slots in the express delivery storage module is dynamically allocated through machine learning algorithms, thereby prioritizing the allocation of storage slots in high-demand areas; Handheld terminal module: Displays the storage location map generated by the server module to the courier through a push program, and displays the real-time available space of the courier storage box through color coding; Express delivery storage and retrieval module: includes a virtual resource unit and a communication unit. The virtual resource unit creates an independent virtual storage space for cooperating express delivery companies. The communication unit obtains the real-time demand signals, historical business proportions and preset priorities of the express delivery companies through the server module and calculates and adjusts the virtual quota of the storage and retrieval box. The virtual quota can be displayed on the handheld terminal module in real time.
2. The intelligent warehouse storage and transfer scheduling system according to claim 1, characterized in that: The machine learning algorithm employs a time-series prediction model, and its expression is as follows: in, This represents the predicted number of storage bits required for the access box b during time period t; The weighting coefficients representing the seasonal components; Indicates seasonal components; Indicates periodic components; The weighting coefficients representing the trend components; Indicates trend components; The weighting coefficients of the periodic components; Represents the random error term. The expression predicts the peak demand for storage spaces in different geographical areas during a specific future period based on historical usage data, thereby dynamically allocating the number of storage spaces.
3. The intelligent warehouse storage and transfer scheduling system according to claim 2, characterized in that: The dynamic allocation employs a weighted allocation strategy, which assigns a set of dynamic weight values to each courier company. These dynamic weight values are calculated based on the real-time demand signal and the historical business proportion, and the calculation expression is as follows: in, This represents the dynamic weight value of the courier company; The weighting coefficients representing the real-time demand components; This indicates the real-time demand volume of the courier company. The weighting coefficients representing the historical business components; This indicates the historical business volume of the courier company; This represents the preset priority constant of the courier company. Furthermore, the number of storage spaces available to each of the express delivery companies is proportional to the dynamic weight value.
4. The intelligent warehouse storage and transfer scheduling system according to claim 3, characterized in that: The real-time demand signals include: The number of times the handheld terminal module connects to the server module; The number of times the handheld terminal module is located within the preset geofence of the express delivery storage and retrieval module in the target storage location. The number of storage spaces requested by the courier company through the handheld terminal module.
5. The intelligent warehouse storage and transfer scheduling system according to claim 1, characterized in that: The handheld terminal module also includes a map displaying the storage space. The map works in conjunction with the color coding to indicate that the storage space has sufficient available space in green, limited available space in yellow, and insufficient available space in red. The handheld terminal module can also input the size and quantity information of the package to be delivered and generate a delivery route based on the map according to the size and quantity information of the package.
6. The intelligent warehouse storage and transfer scheduling system according to claim 3, characterized in that: The independent virtual storage space created by the virtual resource unit is a logical quota. The storage bit corresponding to the quota is shared within the express delivery access module. The calculation formula for the virtual quota is: in, This refers to the virtual quota; This represents the total number of storage bits; This indicates the dynamic weight of the courier company; This represents the sum of the dynamic weights of all the aforementioned courier companies.
7. The intelligent warehouse storage and transfer scheduling system according to claim 1, characterized in that: The communication between the communication unit and the server module adopts an incremental synchronization protocol. The incremental synchronization protocol only sends status change data to the server module when the status of the storage bit changes. The server module is configured to send a rerouting suggestion notification to the handheld terminal module when it detects that the real-time available space of the storage box is lower than the virtual quota.
8. An application method for an intelligent warehouse storage and transfer scheduling system, applicable to the intelligent warehouse storage and transfer scheduling system as described in any one of claims 1-7, characterized in that, Includes the following steps: S1. The server module collects the access status, number of active terminals within the geofence, and storage space reservation requests from the handheld terminal module in real time, and constructs a demand dataset by combining it with historical usage data. S2. Based on the demand dataset, a machine learning algorithm is used to predict the peak demand for storage space in each geographical region in a time series, and a dynamic allocation strategy is generated. S3. Adjust the virtual quota for the cooperating courier company according to the dynamic allocation strategy; S4. The handheld terminal module receives the storage location status data and the virtual quota information sent by the server module in real time, maps the available space status of the storage box through color coding, and generates a visual guidance interface. S5. When the real-time available space of a specific storage location is lower than the corresponding virtual quota, the server module automatically triggers a rerouting suggestion mechanism to push an alternative storage location allocation scheme to the handheld terminal module.
9. The application method of the intelligent warehouse storage and transfer scheduling system according to claim 8, characterized in that: In step S4, the generation of the visual guidance interface includes: the handheld terminal module receiving the size and quantity information of the express delivery to be delivered input by the courier, combining the current storage location map data and color coding status, automatically planning the optimal delivery route, and highlighting the navigation mark of the target storage location in the interface.
10. The application method of the intelligent warehouse storage and transfer scheduling system according to claim 8, characterized in that: In step S5, the triggering of the rerouting suggestion mechanism further includes: the server module continuously monitors the status changes of each group of storage bits based on the incremental synchronization protocol, and when it detects that multiple adjacent storage bits have insufficient available space at the same time, it recalculates the virtual quota distribution of the region and updates it to the handheld terminal module.