Goods in-out information management method and equipment under multi-warehouse cooperation and electronic medium

By building a collaborative warehousing network and penalty probability analysis, the problem of untimely and inaccurate cargo information in multi-warehouse collaborative operations is solved, real-time and accuracy of cargo entry and exit management is achieved, and the efficiency of warehousing resource allocation is improved.

CN119204957AActive Publication Date: 2024-12-27NANJING YUANWU TECH CO LTD

Patent Information

Application Number
CN202411707572.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-27
Publication Date
2024-12-27
Estimated Expiration
2044-11-27

AI Technical Summary

Technical Problem

In multi-warehouse collaborative operations, it is difficult to efficiently synchronize the information in and out of goods, resulting in lag or inaccurate information, reducing the utilization rate of warehousing resources and supply chain efficiency, and unable to meet the rapidly changing market demand.

Method used

By connecting the collaborative warehousing module, obtain the jurisdiction area and the incoming and outgoing goods database, build a collaborative warehousing network, perform warehousing status analysis and demand matching, and use punishment probability analysis and strategy optimization to achieve the formulation of cargo warehouse management strategies.

Benefits of technology

It improves the real-time and accuracy of cargo entry and exit management, improves the allocation and operation efficiency of warehousing resource, and meets complex market demands.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119204957A_ABST
    Figure CN119204957A_ABST
Patent Text Reader

Abstract

The invention discloses a cargo in-out information management method and device under multi-warehouse cooperation and an electronic medium, and relates to the technical field of cargo management. The method comprises the following steps: acquiring a jurisdiction area of collaborative warehousing and an in-out cargo database; carrying out storage state analysis, constructing a collaborative storage network according to a physical position relationship of collaborative storage, and fitting a storage state analysis result into the collaborative storage network; obtaining cargo storage demand characteristics; constructing a storage target configuration list; warehousing demand matching is carried out, and a warehousing matching relation is established; and strategy optimization is carried out by using the demand responsivity and the penalty probability coefficient in the storage matching relationship, and a cargo warehousing management strategy is obtained. The technical problem that in-out information of goods is not timely and inaccurate due to lack of collaborative management among multiple warehouses in the prior art is solved, warehouse demand matching and strategy optimization are carried out based on the collaborative warehouse network, and the technical effect of improving real-time performance and accuracy of goods in-out management is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of cargo management, and in particular to a method, device and electronic medium for managing cargo inlet and outlet information under multi-warehouse collaboration. Background Art

[0002] In modern warehousing and logistics management, with the increasing complexity of the supply chain and the diversification of market demands, warehousing management faces unprecedented challenges. Especially in multi-warehouse collaborative operations, it is difficult to synchronize the information flow and cargo flow between different warehouses efficiently, resulting in delayed or inaccurate information on the goods entering and leaving the warehouse. This not only reduces the utilization rate of warehousing resources, but may also affect the overall efficiency of the supply chain and cannot meet the rapidly changing market demands and the complexity of the warehousing environment. Therefore, how to achieve accurate management of goods entry and exit information under multi-warehouse collaboration and improve warehousing resource allocation and operational efficiency has become a technical problem that needs to be solved urgently in the field of warehousing management technology. Summary of the invention

[0003] The embodiments of the present application provide a method, device and electronic medium for managing cargo inlet and outlet information under multi-warehouse collaboration, which solves the technical problem in the prior art of lack of collaborative management between multiple warehouses, resulting in untimely and inaccurate cargo inlet and outlet information.

[0004] In view of the above problems, the embodiments of the present application provide a method, device and electronic medium for managing cargo inlet and outlet information under multi-warehouse collaboration.

[0005] A first aspect of an embodiment of the present application provides a method for managing cargo in-and-out information under multi-warehouse collaboration, the method comprising: Connect the collaborative warehousing module to obtain the jurisdiction area and inbound and outbound goods database of the collaborative warehousing; perform warehousing status analysis based on the jurisdiction area and inbound and outbound goods database of the collaborative warehousing, and build a collaborative warehousing network according to the physical location relationship of the collaborative warehousing, wherein the warehousing status analysis includes the existing inventory of goods, goods distribution, remaining storage intervals, and goods in-and-out timing characteristics, and fit the warehousing status analysis results to the collaborative warehousing network; obtain goods to be entered into the warehouse, perform warehousing demand analysis on the goods to be entered into the warehouse, and obtain goods warehousing demand characteristics, wherein the warehousing demand analysis includes demand characteristic analysis of warehousing cycle, warehousing environment, and warehousing occupied space; perform warehousing penalty probability analysis on the goods warehousing demand characteristics, sort them according to the penalty probability coefficient, and build a warehousing target configuration list; use the warehousing target configuration list as a management constraint, perform warehousing demand matching based on the collaborative warehousing network, and establish a warehousing matching relationship; use the demand responsiveness and penalty probability coefficient in the warehousing matching relationship to perform strategy optimization to obtain a goods entry management strategy.

[0006] The second aspect of an embodiment of the present application provides an electronic device, including: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement the method for managing cargo entry and exit information under multi-warehouse collaboration provided in the present application.

[0007] A third aspect of an embodiment of the present application provides a computer-readable electronic medium storing a computer program, which, when executed by a processor, implements the method for managing cargo entry and exit information under multi-warehouse collaboration provided in the present application.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, connect the collaborative warehousing module to obtain the jurisdiction area and inbound and outbound goods database of collaborative warehousing. Then, according to the jurisdiction area and inbound and outbound goods database of collaborative warehousing, perform warehousing status analysis, and build a collaborative warehousing network according to the physical location relationship of collaborative warehousing. The warehousing status analysis includes the existing inventory goods, goods distribution, remaining storage intervals, and goods in and out timing characteristics. The storage status analysis results are fitted to the collaborative warehousing network. Next, obtain the goods to be stored, analyze the storage demand of the goods to be stored, and obtain the storage demand characteristics of the goods. The storage demand analysis includes the demand characteristics of the storage cycle, storage environment, and storage space occupied. Further, perform storage penalty probability analysis on the storage demand characteristics of the goods, sort them according to the penalty probability coefficient, and build a storage target configuration list. Then, take the storage target configuration list as the management constraint, perform storage demand matching based on the collaborative warehousing network, and establish a storage matching relationship. Finally, use the demand responsiveness and penalty probability coefficient in the storage matching relationship to optimize the strategy and obtain the goods storage management strategy. It solves the technical problem of lack of collaborative management among multiple warehouses in the existing technology, which leads to untimely and inaccurate information on goods in and out. It matches storage needs and optimizes strategies based on a collaborative warehousing network, achieving the technical effect of improving the real-time and accuracy of goods in and out management. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flowchart of a method for managing cargo inbound and outbound information under multi-warehouse collaboration provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of performing storage penalty probability analysis in a method for managing cargo inlet and outlet information under multi-warehouse collaboration provided in an embodiment of the present application; Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0011] Description of the reference numerals: processor 31 , memory 32 , input device 33 , output device 34 . DETAILED DESCRIPTION

[0012] The embodiments of the present application solve the technical problem in the prior art of lack of collaborative management between multiple warehouses, resulting in untimely and inaccurate cargo in-and-out information, by providing a cargo in-and-out information management method, device and electronic medium under multi-warehouse collaboration.

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for managing cargo in-and-out information under multi-warehouse collaboration, wherein the method includes: Connect to the collaborative warehousing module to obtain the jurisdiction area and inbound and outbound cargo database of collaborative warehousing.

[0016] The collaborative warehousing module is used to realize information sharing and resource coordination among different warehouses. The collaborative warehousing module usually integrates data collection, communication interface and data processing functions, and can be connected with the management systems of multiple warehouses to obtain and synchronize warehousing information, such as jurisdiction areas, inventory status, goods in and out data, etc.

[0017] By connecting to the collaborative warehousing module, the jurisdiction information and inbound and outbound cargo database of each warehouse in the multi-warehousing system can be accessed and extracted. Specifically, by establishing a communication connection with the warehousing system, the physical coverage of the collaborative warehousing system and detailed cargo inbound and outbound records and inventory data can be obtained, providing basic data support for subsequent warehousing status analysis and network construction.

[0018] According to the jurisdiction area of ​​the collaborative warehousing and the in-and-out goods database, the warehousing status analysis is performed, and a collaborative warehousing network is constructed according to the physical location relationship of the collaborative warehousing, wherein the warehousing status analysis includes the existing inventory of goods, goods distribution, remaining storage intervals, and the timing characteristics of goods in and out, and the warehousing status analysis results are fitted into the collaborative warehousing network.

[0019] Based on the jurisdiction of collaborative warehousing and the in-and-out goods database, a detailed warehousing status analysis is carried out to build a comprehensive collaborative warehousing network. Specifically, by analyzing the acquired data, a comprehensive analysis is carried out on the existing inventory goods, goods distribution, remaining storage intervals, and the in-and-out timing characteristics of goods in each warehouse to identify the actual inventory status of each warehouse and its spatial and temporal distribution characteristics; based on the physical location relationship of each warehouse (such as geographical location, traffic conditions, distance between warehouses, etc.), a network structure reflecting the overall warehousing system is established, namely the collaborative warehousing network, which can intuitively display the association and collaboration relationship between warehouses; the storage status analysis results (existing inventory, goods distribution, remaining intervals, timing characteristics) are integrated into the collaborative warehousing network. In the network diagram, different colors or marks are used to represent the key information such as the inventory status and remaining space of different warehouses, so that the network can dynamically reflect the real-time status and characteristics of each warehouse.

[0020] Obtain goods to be stored, perform storage demand analysis on the goods to be stored, and obtain storage demand characteristics of the goods. The storage demand analysis includes demand characteristic analysis of storage cycle, storage environment, and storage space occupation.

[0021] Conduct in-depth analysis of incoming goods to determine their specific storage demand characteristics in order to achieve accurate matching in multi-warehouse collaborative management. Specifically, obtain data on goods to be stored, such as the type, quantity, and other relevant attributes of the goods; conduct detailed demand analysis on these goods and extract characteristics related to warehousing, including storage cycle (the length of time the goods are expected to be stored in the warehouse), storage environment (the requirements of the goods for storage conditions, such as temperature, humidity, ventilation and other special environmental parameters), storage space (the physical space required for the goods in the warehouse and the actual occupied volume); integrate the results of the above storage demand analysis into the storage demand characteristics of the goods, including storage cycle characteristics, storage environment characteristics, and storage space characteristics.

[0022] Perform storage penalty probability analysis on the cargo storage demand characteristics, sort them according to the penalty probability coefficients, and build a storage target configuration list.

[0023] According to the storage demand characteristics of each cargo (such as storage cycle, environmental requirements and space occupancy), analyze the restrictions or non-compliance that it may face when stored in the warehouse. The penalty probability coefficient is calculated through quantitative analysis. The penalty probability coefficient is used to indicate the penalty or unsuitability that may be caused when the cargo is stored in a warehouse. A higher penalty probability coefficient means that the cargo is stored at a higher risk or the storage conditions are not ideal. Sort the penalty probability coefficients of all cargoes from low to high to give priority to the configuration scheme with lower penalty probability. Based on the sorting results, generate a storage target configuration list, which lists the best storage options for each cargo in detail and indicates them by priority.

[0024] Furthermore, if Figure 2 As shown, a storage penalty probability analysis is performed on the cargo storage demand characteristics, including: Based on the storage cycle, a storage time penalty analysis is performed on the goods to be stored to obtain a time penalty coefficient; based on the storage environment, a storage environment penalty analysis is performed on the goods to be stored to obtain an environment penalty coefficient; based on the historical experience data of the goods to be stored, the time penalty probability and the environment penalty probability are fitted in view of the influence of storage characteristics on the quality of the goods; the penalty weight is determined using the time penalty probability and the environment penalty probability; the time penalty coefficient and the environment penalty coefficient are merged according to the penalty weight to obtain the penalty probability coefficient.

[0025] Specifically, based on the storage cycle, the time dimension of the incoming goods is analyzed to evaluate whether they will be affected within a specific storage time, such as the possible deterioration in quality or increase in storage costs due to exceeding the expected storage time; based on the storage cycle of the goods and its impact on quality, the storage time penalty coefficient is calculated based on the expert team and historical experience. The storage time penalty coefficient reflects the risk of quality loss of goods due to excessive storage time; based on the storage environment (such as temperature, humidity, ventilation, etc.), the adaptability of the incoming goods to the storage conditions is analyzed, and the potential damage or management risks when the environment deviates from the optimal value are evaluated; based on the degree of mismatch between warehouse environmental conditions and goods demand, the storage environment penalty coefficient is calculated based on the expert team and historical experience. The storage environment penalty coefficient reflects the risk of quality loss of goods due to improper environmental conditions. ; Collect historical experience data on goods to be stored, including changes in the quality of goods under different storage times and environmental conditions; use statistical methods to fit the relationship between storage characteristics (such as storage cycle, storage environment) and goods quality; based on the fitted relationship, calculate the time penalty probability and environmental penalty probability, which respectively reflect the possibility of loss of goods quality due to excessive storage time and improper environmental conditions; assign different weights to the time penalty probability and environmental penalty probability according to the characteristics of the goods and business needs, and the size of the weight reflects the importance of different penalty factors in the overall penalty; use the determined penalty weight to merge the time penalty coefficient and the environmental penalty coefficient to calculate the penalty probability coefficient, which reflects the risk of quality loss that the goods may suffer due to time and environmental factors during the storage process.

[0026] Furthermore, the storage target configuration list is constructed by sorting according to the penalty probability coefficient, including: According to the time penalty coefficient, the environment penalty coefficient and the penalty probability coefficient, they are sorted in descending order to establish a time penalty sequence, an environment penalty sequence and a penalty comprehensive coefficient sequence; identification labels of the time penalty sequence, the environment penalty sequence and the penalty comprehensive coefficient sequence are set to construct the warehouse target configuration list, wherein the penalty comprehensive coefficient sequence is configured with the first priority, and the time penalty sequence and the environment penalty sequence are configured with the second priority and the third priority respectively according to their size.

[0027] Preferably, the storage demand of each item of goods is sorted from large to small according to the calculated time penalty coefficient, environmental penalty coefficient and comprehensive penalty probability coefficient; three sorting sequences are established respectively: time penalty sequence (reflecting the adaptability sorting of goods storage time), environmental penalty sequence (reflecting the adaptability sorting of storage environment), and penalty comprehensive coefficient sequence (comprehensive sorting of time and environment); identification tags are set for each item in the three penalty sequences to identify the sorting position of the goods in different dimensions. A storage target configuration list is constructed, in which the penalty comprehensive coefficient sequence is set to the first priority, indicating that in the actual configuration, the overall risk of comprehensive consideration of time and environmental factors is the most important; the time penalty sequence is set to the second priority for detailed sorting when the comprehensive penalty coefficients are similar; the environmental penalty sequence is set to the third priority for providing further sorting basis when the time and comprehensive coefficients cannot be distinguished. Through this multi-dimensional sorting and priority configuration, the constructed storage target configuration list can provide a more reasonable storage solution for goods based on the comprehensive and single penalty coefficients, and realize the optimal configuration of storage resources and minimize risks.

[0028] Taking the storage target configuration list as a management constraint, storage demand matching is performed based on the collaborative storage network to establish a storage matching relationship.

[0029] Taking the storage target configuration list as the management constraint and combining it with the actual situation of the collaborative storage network, the storage demand of goods is matched to determine the best storage location for each type of goods. Specifically, taking the storage target configuration list as the management constraint, the configuration scheme with low penalty coefficient in the list is given priority to ensure that the goods can be matched with the storage environment and space with the lowest risk; in the collaborative storage network, the available resources (such as space, environment, time period, etc.) of each warehouse node are evaluated and matched one by one with the storage demand characteristics of each goods (including storage period, environmental requirements, space requirements, etc.); according to the matching results, a specific storage matching relationship is generated for each type of goods, and the matching situation between the goods and the warehouse nodes is recorded, including the warehouse location, storage period, environmental parameters, etc.

[0030] Furthermore, taking the storage target configuration list as a management constraint, performing storage demand matching based on the collaborative storage network and establishing a storage matching relationship include: According to the penalty probability coefficient in the warehousing target configuration list, an identification processing module is obtained, and the identification processing module has an identification matching model, and the identification matching model at least includes a warehousing cycle matching layer and a warehousing environment parameter matching layer; according to the time penalty coefficient and the environment penalty coefficient, the model weights of the warehousing cycle matching layer and the warehousing environment parameter matching layer are configured; using the identification matching model, identification and matching are performed with the collaborative warehousing network according to the goods warehousing demand characteristics to obtain the warehousing matching relationship.

[0031] Specifically, according to the penalty probability coefficient in the storage target configuration list, the identification processing module is called, and the identification processing module includes an identification matching model for automatic matching between storage demand and storage resources; the identification matching model is composed of multiple levels, including at least a storage cycle matching layer and a storage environment parameter matching layer, which are used for detailed matching in the two dimensions of time and environment respectively; according to the relative size of the time penalty coefficient and the environmental penalty coefficient, the weights of different levels in the matching model are configured, and the setting of the weights ensures that the needs of high penalty coefficient items are met first in the matching process, reducing potential risks in the storage process; the weight of the storage cycle matching layer is based on the time penalty coefficient. Adjustments are made to ensure that warehouse nodes with shorter storage cycles or better suitability are matched first. The weights of the storage environment parameter matching layer are adjusted according to the environmental penalty coefficient, so that goods with higher environmental requirements are matched to qualified warehouse nodes first. The configured identification and matching model is used to match the storage demand characteristics of each product with each warehouse node in the collaborative storage network one by one. Through the double-layer evaluation of the storage cycle matching layer and the environmental parameter matching layer, the optimal warehouse node is identified and the final storage matching relationship is determined. The storage matching relationship records the warehouse node information matched by the goods, as well as information such as the weights and penalty coefficients in the matching process, to ensure the optimization of the storage plan.

[0032] Further, obtaining the recognition processing module previously includes: A cargo in-and-out management database is obtained, which includes cargo attributes, cargo storage cycle requirements, cargo storage environment requirements, cargo storage location, cargo storage time period, cargo in-and-out management record information, and cargo storage quality impact results; based on the cargo in-and-out management database, multiple sets of training data sets are constructed, and the multiple sets of training data sets are obtained by randomly combining and constructing and re-constructing multiple sets of cycles based on the cargo in-and-out management database; the multiple sets of training data sets are used respectively to obtain identification sub-models through training convergence; each identification sub-model is tested and evaluated to obtain identification dimension parameters and precision evaluation values ​​of each identification sub-model; the identification dimension parameters and precision evaluation values ​​are used to cluster the identification sub-models to obtain a multi-category model library, and the multi-category model library includes a multi-dimensional parameter library and a multi-precision grade library.

[0033] Specifically, obtain the goods in-and-out management database, which records a wealth of goods-related information, including goods attributes (such as type, weight, size, etc.), goods storage cycle requirements (specified storage time requirements), goods storage environment requirements (such as temperature, humidity and other environmental conditions), goods storage location (identification of the current storage location), goods storage time cycle (actual storage time record), goods in-and-out management record information (detailed warehousing and out-of-warehouse time points, frequency, etc.), and goods storage quality impact results (the impact of storage conditions on goods quality, such as quality degradation caused by too long storage time or environmental deviation).

[0034] According to the cargo in-and-out management database, multiple sets of training data sets are constructed. Specifically, based on the multi-dimensional attribute information in the database, multiple sets of samples are created by random combination to enhance the diversity of the data; data sets are repeatedly generated by back-placement and reorganization to ensure the diversity and representativeness of the training data sets, thereby improving the generalization ability of the model. Use the constructed multiple sets of training data sets to train multiple recognition sub-models respectively. During the training process, the model parameters are optimized by repeated iterations until the convergence conditions are reached to obtain each recognition sub-model. These sub-models are trained on different storage demand feature dimensions, such as storage cycle, environmental requirements, etc., so as to be targeted in subsequent matching. Test each recognition sub-model to evaluate its recognition ability in each recognition dimension (such as time, environment), and then obtain the recognition dimension parameters (indicating the recognition dimension that the sub-model is good at) and its corresponding precision evaluation value (indicating the recognition accuracy of the sub-model in this dimension). According to the recognition dimension parameters and accuracy evaluation values, the recognition sub-models are clustered and classified according to different recognition dimensions and accuracy levels to form a multi-category model library. The multi-category model library includes a multi-dimensional parameter library (a parameter library for different sub-models on multiple recognition dimensions) and a multi-precision grade library (the sub-models are divided into multiple grades according to the recognition accuracy).

[0035] Furthermore, according to the penalty probability coefficient in the storage target configuration list, an identification processing module is obtained, and the identification processing module has an identification matching model, including: The penalty level and penalty parameter are analyzed according to the penalty probability coefficient, and the penalty analysis result is used to configure the recognition requirement accuracy and recognition dimension parameter ratio, wherein the recognition requirement accuracy is proportional to the penalty probability coefficient, and the recognition dimension parameter is the dimension parameter weight relationship determined according to the time penalty coefficient and the environment penalty coefficient; sub-model matching is performed from the multi-category model library according to the recognition requirement accuracy and the recognition dimension parameter ratio to determine the matching sub-model; the matching sub-model weights are allocated according to the recognition dimension parameter ratio, and the recognition matching model is obtained based on the matching sub-model through integrated training to construct the recognition processing module.

[0036] Specifically, the penalty level and penalty parameter analysis of the demand for goods are refined according to the penalty probability coefficient. The results of the penalty level and parameter analysis are used to measure the importance of different demand characteristics in the warehousing process to ensure that goods with high penalty risks are matched with higher accuracy; using the analysis results, configure the recognition demand accuracy and recognition dimension parameter ratio, where the recognition demand accuracy is proportional to the penalty probability coefficient, that is, the higher the penalty probability, the higher the recognition demand accuracy requirement, to ensure that the demand characteristics of the goods are highly matched with the warehousing conditions; the recognition dimension parameter ratio is the dimension parameter weight relationship determined according to the time penalty coefficient and the environment penalty coefficient, which is used to balance the weights of different demand dimensions (time, environment). Based on the configured recognition demand accuracy and recognition dimension parameter ratio, select the appropriate sub-model from the multi-category model library for matching; in the multi-category model library, the sub-models are classified according to different recognition dimensions (such as time, environment) and accuracy levels. According to the demand accuracy and dimensional parameter ratio, the sub-model that best matches the cargo demand is selected first to determine the matching sub-model to ensure the applicability and recognition accuracy of the model; according to the recognition dimensional parameter ratio, weights are assigned to the selected matching sub-model so that it has corresponding recognition weights in different dimensions; through integrated training, multiple matching sub-models are combined together so that the recognition model can take into account multi-dimensional features such as time and environment to form a comprehensive recognition matching model; through the integrated recognition matching model, the final recognition processing module is constructed, which can dynamically adapt to different penalty levels and parameter requirements, and flexibly and efficiently perform warehousing matching to ensure that the cargo demand is optimally configured.

[0037] The demand responsiveness and penalty probability coefficient in the warehousing matching relationship are used to perform strategy optimization to obtain a goods warehousing management strategy.

[0038] After obtaining the storage matching relationship, the warehousing strategy is optimized through demand responsiveness and penalty probability coefficient to formulate the best goods warehousing management strategy. Demand responsiveness indicates the responsiveness of the warehousing system to the demand for goods; according to the warehousing matching relationship, the degree of satisfaction of different warehouse nodes for goods demand (such as storage cycle, environmental requirements, etc.) is evaluated. The higher the demand responsiveness, the faster and more accurately the warehouse can meet the storage needs of goods. The penalty probability coefficient reflects the risk that may arise when the goods do not meet the demand. The higher the coefficient, the greater the possibility of unsatisfactory storage conditions; in the process of strategy optimization, the penalty probability coefficient is used as a constraint to avoid high-risk storage configuration and ensure that the goods are matched to a suitable storage environment.

[0039] Based on demand responsiveness and penalty probability coefficient, a strategy optimization model is established. The model should be able to comprehensively consider the storage demand of goods, the matching degree of warehouse resources and storage risks, and provide a scientific basis for the formulation of goods warehousing management strategies. In the strategy optimization model, set optimization goals, such as maximizing demand responsiveness and minimizing penalty probability coefficients; input data such as storage demand characteristics of goods, matching degree of warehouse resources and penalty probability coefficients into the strategy optimization model; run the strategy optimization model, and perform strategy optimization calculations based on the input data and optimization goals through optimization algorithms (such as genetic algorithms or particle swarm algorithms); evaluate the generated goods warehousing management strategies, and the evaluation indicators may include demand responsiveness, penalty probability coefficients, warehousing costs, warehousing efficiency, etc.; by comparing the evaluation results of different strategies, select the optimal goods warehousing management strategy, including designated warehousing storage nodes, recommended warehousing time, warehousing environment requirements, etc. The goods warehousing management strategy can dynamically adapt to changes in warehousing conditions to ensure that goods are stored in the best solution, while achieving efficient management under multi-warehouse collaboration.

[0040] Further, the goods incoming management strategy is obtained, which also includes: According to the goods in-and-out management database, the shipment timing is fitted for each cargo attribute, and the shipment cycle and shipment regret probability are constructed, wherein the shipment regret probability is the probability of shipment with abnormal deviation from the shipment cycle; the shipment cycle is used to predict the shipment spare storage timing of the collaborative warehousing network; the inbound storage demand timing is predicted according to the cargo attributes of the goods to be warehoused, and the timing demand is obtained; the shipment spare storage timing prediction result is matched with the timing demand to obtain the timing matching result; the comprehensive penalty probability is obtained according to the shipment regret probability and the penalty probability coefficient; the goods inbound management strategy is evaluated and verified using the timing matching result and the comprehensive penalty probability.

[0041] Preferably, historical shipment data of goods is obtained from the goods in-and-out management database, and the shipment time series is fitted for each cargo attribute to predict the shipment cycle and shipment regret probability of the goods. The shipment cycle represents the average time interval for goods to leave the warehouse, and the shipment regret probability is the probability that there is a significant deviation between the actual shipment cycle and the predicted shipment cycle, indicating that the shipment of goods may change due to various factors; using the shipment cycle data of the goods, the shipment vacancy storage time series prediction is performed for each warehouse node in the collaborative warehousing network. The shipment vacancy storage time series prediction is used to estimate the possible vacant capacity of the warehouse within a certain period of time in the future, and provide a dynamic vision of future storage space. Figure; Based on the properties of the goods to be stored, the storage demand time series forecast is carried out, and the storage demand in different time periods in the future is analyzed to form the time series demand; the delivery available storage time series forecast results are matched with the time series demand, and the storage demand in different time periods is analyzed whether the storage demand matches the storage space, so as to identify the possible shortage or surplus of storage space in the future, and then obtain the time series matching result; according to the probability of shipment regret (abnormal probability of shipment cycle) and the penalty probability coefficient of the warehousing stage, the comprehensive penalty probability is calculated, which quantifies the overall risk level in the warehousing process and is used to evaluate the stability and risk of storage decisions.

[0042] The existing goods warehousing management strategy is evaluated and verified using the timing matching results and the comprehensive penalty probability. Specifically, it is checked whether the warehousing timing requirements can be met under future warehousing conditions; it is evaluated whether the warehousing strategy can reduce the comprehensive penalty probability to the minimum, ensuring that the risk control in the warehousing process is within a reasonable range.

[0043] In summary, the embodiments of the present application have at least the following technical effects: First, connect the collaborative warehousing module to obtain the jurisdiction area and inbound and outbound goods database of collaborative warehousing. Then, according to the jurisdiction area and inbound and outbound goods database of collaborative warehousing, perform warehousing status analysis, and build a collaborative warehousing network according to the physical location relationship of collaborative warehousing. The warehousing status analysis includes the existing inventory goods, goods distribution, remaining storage intervals, and goods in and out timing characteristics. The storage status analysis results are fitted to the collaborative warehousing network. Next, obtain the goods to be stored, analyze the storage demand of the goods to be stored, and obtain the storage demand characteristics of the goods. The storage demand analysis includes the demand characteristics of the storage cycle, storage environment, and storage space occupied. Further, perform storage penalty probability analysis on the storage demand characteristics of the goods, sort them according to the penalty probability coefficient, and build a storage target configuration list. Then, take the storage target configuration list as the management constraint, perform storage demand matching based on the collaborative warehousing network, and establish a storage matching relationship. Finally, use the demand responsiveness and penalty probability coefficient in the storage matching relationship to optimize the strategy and obtain the goods storage management strategy. It solves the technical problem of lack of collaborative management among multiple warehouses in the existing technology, which leads to untimely and inaccurate information on goods in and out. It matches storage needs and optimizes strategies based on a collaborative warehousing network, achieving the technical effect of improving the real-time and accuracy of goods in and out management.

[0044] Embodiment 2: Figure 3 The schematic structural diagram of the electronic device provided in the second embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the electronic device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0045] Embodiment 3, based on the same inventive concept as the cargo in-and-out information management method under multi-warehouse collaboration in the above-mentioned embodiment, this embodiment provides a computer-readable electronic medium, which can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the cargo in-and-out information management method under multi-warehouse collaboration in the embodiment of the present application. The processor executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory, that is, realizing the above-mentioned cargo in-and-out information management method under multi-warehouse collaboration.

[0046] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0048] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for managing cargo in and out information under multi-warehouse collaboration, characterized in that: The method comprises: Connect to the collaborative warehousing module to obtain the jurisdiction area and inbound and outbound cargo database of collaborative warehousing; According to the jurisdiction area of ​​the collaborative warehousing and the in-and-out goods database, the warehousing status is analyzed, and the collaborative warehousing network is constructed according to the physical location relationship of the collaborative warehousing, wherein the warehousing status analysis includes the existing inventory goods, goods distribution, remaining warehousing intervals, and goods in-and-out time sequence characteristics, and the warehousing status analysis results are fitted into the collaborative warehousing network; Obtain goods to be stored, perform storage demand analysis on the goods to be stored, and obtain storage demand characteristics of the goods, wherein the storage demand analysis includes demand characteristic analysis of storage cycle, storage environment, and storage space occupation; Performing storage penalty probability analysis on the cargo storage demand characteristics, sorting them according to the penalty probability coefficients, and constructing a storage target configuration list; Taking the storage target configuration list as a management constraint, performing storage demand matching based on the collaborative storage network, and establishing a storage matching relationship; The demand responsiveness and penalty probability coefficient in the warehousing matching relationship are used to perform strategy optimization to obtain a goods warehousing management strategy.

2. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 1 is characterized in that: Performing storage penalty probability analysis on the storage demand characteristics of the goods, including: Based on the storage cycle, a storage time penalty analysis is performed on the goods to be stored to obtain a time penalty coefficient; Based on the storage environment, a storage environment penalty analysis is performed on the goods to be stored to obtain an environmental penalty coefficient; Based on the historical experience data of goods to be stored, the time penalty probability and environmental penalty probability are fitted according to the impact of storage characteristics on the quality of goods; Determine the penalty weight using the time penalty probability and the environment penalty probability; The time penalty coefficient and the environment penalty coefficient are integrated according to the penalty weight to obtain the penalty probability coefficient.

3. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 2 is characterized in that: Sort by penalty probability coefficient and build a storage target configuration list, including: According to the time penalty coefficient, the environment penalty coefficient and the penalty probability coefficient, they are sorted in descending order to establish a time penalty sequence, an environment penalty sequence and a penalty comprehensive coefficient sequence; Identification labels of the time penalty sequence, environmental penalty sequence, and comprehensive penalty coefficient sequence are set to construct the storage target configuration list, wherein the comprehensive penalty coefficient sequence is configured with a first priority, and the time penalty sequence and environmental penalty sequence are configured with a second priority and a third priority respectively according to their sizes.

4. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 3 is characterized in that: Taking the storage target configuration list as a management constraint, performing storage demand matching based on the collaborative storage network, and establishing a storage matching relationship include: According to the penalty probability coefficient in the storage target configuration list, an identification processing module is obtained, wherein the identification processing module has an identification matching model, and the identification matching model at least includes a storage period matching layer and a storage environment parameter matching layer; According to the time penalty coefficient and the environment penalty coefficient, the model weights of the storage cycle matching layer and the storage environment parameter matching layer are configured; The identification and matching model is used to perform identification and matching with the collaborative warehousing network according to the cargo warehousing demand characteristics to obtain the warehousing matching relationship.

5. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 4 is characterized in that: Get the recognition processing module, which previously included: Obtain a cargo in-and-out management database, which includes cargo attributes, cargo storage cycle requirements, cargo storage environment requirements, cargo storage location, cargo storage time cycle, cargo in-and-out management record information, and cargo storage quality impact results; According to the cargo in-and-out management database, multiple sets of training data sets are constructed, wherein the multiple sets of training data sets are obtained by randomly combining and constructing multiple sets of training data sets and then reconstructing multiple sets of training data sets according to the cargo in-and-out management database; Using the multiple sets of training data sets respectively, training and converging to obtain identification sub-models; Test and evaluate each recognition sub-model to obtain the recognition dimension parameters and accuracy evaluation values ​​of each recognition sub-model; The identification dimension parameters and their precision evaluation values ​​are used to perform identification sub-model clustering to obtain a multi-category model library, which includes a multi-dimensional parameter library and a multi-precision grade library.

6. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 5, characterized in that: According to the penalty probability coefficient in the storage target configuration list, an identification processing module is obtained, and the identification processing module has an identification matching model, including: According to the penalty probability coefficient, the penalty level and penalty parameter are analyzed, and the recognition requirement accuracy and recognition dimension parameter ratio are configured using the penalty analysis result, wherein the recognition requirement accuracy is proportional to the penalty probability coefficient, and the recognition dimension parameter is the dimension parameter weight relationship determined according to the time penalty coefficient and the environment penalty coefficient; According to the recognition requirement accuracy and recognition dimension parameter ratio, sub-model matching is performed from the multi-category model library to determine a matching sub-model; The weights of the matching sub-models are allocated according to the recognition dimension parameter ratio, and the recognition matching model is obtained based on the matching sub-models through integrated training to construct the recognition processing module.

7. The cargo in-and-out information management method under multi-warehouse coordination as claimed in claim 5, characterized in that: Obtain a goods inbound management strategy, which will also include: According to the goods in-and-out management database, the shipment time sequence of each cargo attribute is fitted to construct the shipment cycle and the shipment regret probability, wherein the shipment regret probability is the probability of shipment with abnormal deviation from the shipment cycle; Using the delivery cycle to predict the delivery vacant storage time sequence of the collaborative warehousing network; Performing a time series forecast of the incoming warehousing demand based on the properties of the goods to be incoming to obtain the time series demand; Perform time sequence matching based on the shipping free storage time sequence prediction result and the time sequence demand to obtain a time sequence matching result; Obtaining a comprehensive penalty probability according to the shipment regret probability and the penalty probability coefficient; The goods warehousing management strategy is evaluated and verified using the time series matching result and the comprehensive penalty probability.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; A processor is used to implement the cargo entry and exit information management method under multi-warehouse collaboration as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

9. A computer-readable electronic medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for managing cargo inlet and outlet information under multi-warehouse collaboration as described in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Agent unknown environment exploration method based on reinforcement learning

    CN111062491A

  • Vehicle dynamic scheduling method and device and terminal equipment

    CN111340318A

  • Warehouse collection list generation method and system

    CN111445172A

  • Main line transportation self-contained fleet scale optimization method

    CN115049314A

  • Warehouse inventory resource management method, device and equipment and storage medium

    CN117273603A

Cited By

  • Warehouse article management method, system and equipment based on industrial Internet of Things, and medium

    CN120198056A