A system for spatiotemporal coordination, planning, and optimization of supply chains based on ai models

Abstract

The application provides an AI model-based supply chain space-time coordination, planning and optimization system, based on data technology and data synchronization and ETL processing, analyzes the warehouse turnover time between supply chain nodes, the volume of warehouse storage type and historical warehouse-out data, reasonably distributes the warehouse-out materials to each storage type by using an AI model, and predicts the warehouse-out quantity in the future time; also splits the warehouse-in materials to the warehouse storage and configures the storage storage rules. The space optimization algorithm developed based on operational research and maximum optimization technology effectively completes the space optimization coordination and other tasks, predicts the early warning level and the warehouse-out proportion of the warehouse storage type, divides the soft warehouse-out and the hard warehouse-out according to the early warning level, and pushes the notification to the corresponding personnel, so as to provide reliable analysis and decision reference information for the corresponding personnel.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of supply chain, in particular to a supply chain space-time coordination, planning and optimization system based on an AI model. BACKGROUND

[0002] Warehouse inventory early warning technology is a core component of modern supply chain space-time coordination, planning and optimization, and its development background is closely related to the inventory management needs of enterprises, technological evolution and market competition environment. With the expansion of the scale of enterprises and the increase of market uncertainty, traditional inventory management methods cannot meet the real-time, accuracy and efficiency requirements of enterprises.

[0003] The inventory explosion early warning mechanism is a warehouse inventory risk prevention and control mechanism based on dynamic monitoring and intelligent analysis, and its core goal is to identify inventory backlog risks in advance and avoid excessive occupation of warehouses and waste of storage resources. When the inventory exceeds the preset safety threshold, an early warning signal is immediately sent to prompt the management personnel to take intervention measures. The multi-level threshold setting method of inventory explosion early warning is the key to the effective operation of the mechanism, and the threshold setting is too loose, which will lead to late warning and lose the prevention significance; the threshold setting is too strict, which will produce a large number of invalid alarms and cause "early warning fatigue". The existing explosion early warning threshold setting methods mainly include daily consumption method, ABC classification method, dynamic prediction method and supply chain oriented method. However, the above methods are by comparing the actual inventory of a certain type of material in the warehouse with the preset threshold, and when the inventory reaches the preset threshold, an alarm is triggered, but the warehouse space is not fully utilized, and in fact the overload of a certain type of material can share the storage space of other types of storage space to maximize the utilization of warehouse space. However, the existing inventory explosion early warning mechanism does not optimize and coordinate all storage space, and cannot fully utilize the warehouse space and effectively solve the explosion problem. SUMMARY

[0004] The purpose of the present application is to provide a supply chain space-time coordination, planning and optimization system based on an AI model, which combines company business, logistics methods between supply chain nodes and paths, data such as time efficiency, warehouse, capacity, etc., accurately splits the incoming materials to each type of storage space, and realizes fine management and control of the type of storage space; by adjusting the intelligent warehousing strategy, the materials are automatically selected to the optimal storage location according to the material volume and the remaining space of the storage space, the storage space of the warehouse is flexibly utilized, and the space utilization is maximized. A dual-mode early warning mechanism of soft explosion and hard explosion is also adopted, in the case of soft explosion, the materials in the explosion storage space are adjusted to other idle storage space; in the case of hard explosion, the subsequent work is immediately stopped and an alarm notification is sent, efficiently solving the problems of optimal configuration, coordination and operation of inventory space in the supply chain.

[0005] The present application is achieved by the following technical solutions:

[0006] The AI model-based supply chain space-time coordination, planning and optimization system comprises:

[0007] A data warehouse synchronization and cleaning module is configured to prepare supply chain business data, obtain warehouse location state data, warehouse historical outbound data, warehouse inbound data, and regularly clean and update data.

[0008] A location prediction module is configured to predict the outbound volume of a warehouse location at a future time based on the warehouse location state data and the warehouse historical outbound data.

[0009] A location storage rule setting module is configured to obtain predicted inbound time, inbound volume and storage type based on the warehouse inbound data, and set inbound material location storage rules based on the predicted inbound time, inbound volume and storage type.

[0010] A warehouse explosion prediction module is configured to predict a warehouse explosion event based on the outbound volume of a warehouse location at a future time and the inbound material location storage rules.

[0011] A warehouse explosion warning module is configured to perform a warehouse explosion warning operation based on the warehouse explosion event.

[0012] Optionally, the data warehouse synchronization and cleaning module is configured to prepare supply chain business data, comprising:

[0013] A data warehouse of a supply chain business system is subjected to data extraction, conversion and loading processing to obtain supply chain business data; wherein the data warehouse comprises business data related to materials, warehouses, logistics, transportation and procurement.

[0014] Optionally, the data warehouse synchronization and cleaning module is configured to obtain warehouse location state data, warehouse historical outbound data and warehouse inbound data, comprising:

[0015] The latest warehouse location type and area data are obtained from the supply chain business data to determine the total volume and used volume of the warehouse location type, which are used as the warehouse location state data.

[0016] The number of outbound goods of a warehouse location at a historical time interval is obtained from the supply chain business data, which is used as the warehouse historical outbound data.

[0017] Supply chain business node configurations are obtained from the supply chain business data to determine the turnover time of each business process under the supply chain; based on the turnover time, the arrival date of materials is determined to predict the number and volume of warehouse inbound goods on the arrival date, which are used as the warehouse inbound data.

[0018] Optionally, the data warehouse synchronization and cleaning module is configured to regularly clean and update data, comprising:

[0019] The warehouse location state data, the warehouse historical outbound data, and the warehouse inbound data are cleaned and updated in a timely manner, and the updated warehouse location state data, warehouse historical outbound data, and warehouse inbound data are stored in an OSS object storage specified directory and saved as a CSV file.

[0020] Optionally, the location prediction module is configured to predict, according to the warehouse location state data and the warehouse historical outbound data, an outbound volume of the warehouse location at a future time, including:

[0021] Invalid data is removed and repeated data is merged from the warehouse location state data and the warehouse historical outbound data.

[0022] According to the warehouse location state data, a usage volume ratio of the warehouse location is determined; and according to the usage volume ratio and the warehouse historical outbound data, a long short-term memory network model is used to predict an outbound volume of the warehouse location at a future time.

[0023] Optionally, the location storage rule setting module is configured to obtain, according to the warehouse inbound data, a predicted inbound time, an inbound volume, and a storage type, including:

[0024] According to historical inbound storage type information, data is completed for an inbound record in the warehouse inbound data that lacks storage type information.

[0025] The warehouse inbound data is grouped to obtain a predicted inbound time, an inbound volume, and a storage type of a material; and the warehouse inbound data of the material is sorted according to the predicted inbound time of the material.

[0026] Optionally, the location storage rule setting module is configured to set an inbound material location storage rule according to the predicted inbound time, the inbound volume, and the storage type, including:

[0027] According to the predicted inbound time, the inbound volume, and the storage type of the material, the material is adjusted for inbound according to volume priority, location space optimization, real-time dynamic allocation, and weight allocation, and the inbound material location storage rule is set.

[0028] Optionally, the warehouse explosion prediction module is configured to predict, according to an outbound volume of the warehouse location at a future time and an inbound material location storage rule, a warehouse explosion event, including:

[0029] According to the outbound volume of the warehouse location at a future time and the inbound material location storage rule, a soft warehouse explosion event and a hard warehouse explosion event of the warehouse location are predicted; wherein the soft warehouse explosion event refers to a single location predicted storage material volume exceeding its capacity; and the hard warehouse explosion event refers to all locations warning storage material volume exceeding the total capacity of the warehouse.

[0030] Optionally, the burst warning module is configured to perform a burst warning operation according to the burst event, including:

[0031] According to the burst event, a mail push notification, inventory monitoring, in-transit inventory trajectory tracking, and logistics trajectory map analysis are performed.

[0032] Optionally, the burst warning module performing a mail push notification includes calling a mail notification service through an API to push a warehouse capacity warning message.

[0033] The burst warning module performing inventory monitoring includes forming a warehouse inventory change curve every day in the future time to analyze the warehouse inventory change trend.

[0034] The burst warning module performing in-transit inventory trajectory tracking includes tracking the logistics trajectory route of the material in transit and needing to be warehoused on a map.

[0035] The burst warning module performing logistics trajectory map analysis includes analyzing and displaying the logistics transportation trajectory of the material on a world map.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] The AI model-based supply chain space-time coordination, planning and optimization system provided in the present application is based on data technology and data synchronization and ETL processing, analyzes the warehousing turnover time between supply chain nodes, the volume of warehouse space types and historical outbound data, uses an AI model to reasonably distribute warehouse outbound materials to various space types, and predicts the outbound quantity in the future time; the warehousing materials are also split to the warehouse spaces and configured with space storage rules. The space optimization algorithm developed based on operations research and maximum optimization technology effectively completes space optimization coordination and other tasks, predicts the warning level and burst proportion of the warehouse space type, divides the warning level into soft burst and hard burst, and pushes a notification to the corresponding personnel, providing reliable analysis and decision-making reference information for the corresponding personnel. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0039] Figure 1 is a structural schematic diagram of the AI model-based supply chain space-time coordination, planning and optimization system provided by the present application.

[0040] Figure 2is a data acquisition process of a data warehouse synchronization and cleaning module.

[0041] Figure 3 is a prediction process of a warehouse location prediction module.

[0042] Figure 4 is an early warning process of a warehouse blowout early warning module. DETAILED DESCRIPTION

[0043] In order to make the above objectives, features and advantages of the present application more apparent, a detailed description of the specific embodiments of the present application will be given below with reference to the accompanying drawings. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the purpose of description, only the parts related to the present application are shown in the drawings, rather than all the structures. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0044] The terms "comprising" and "having" and any variations thereof in the present application are intended to cover non-exclusive inclusion. For example, a process, system, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally further comprises steps or units not listed, or optionally further comprises other steps or units inherent to these processes, systems, products or devices.

[0045] In this document, reference to "embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood that the embodiments described herein are capable of combination.

[0046] Referring to Figure 1 An embodiment of the present application provides an AI model-based supply chain space-time coordination, planning and optimization system. The AI model-based supply chain space-time coordination, planning and optimization system comprises:

[0047] A data warehouse synchronization and cleaning module is used to prepare supply chain business data, thereby obtaining warehouse location state data, warehouse historical outbound data, warehouse inbound data, and regularly cleaning and updating data;

[0048] A warehouse location prediction module is used to predict the outbound volume of the warehouse location at a future time according to the warehouse location state data and the warehouse historical outbound data.

[0049] The warehouse storage rule setting module is configured to obtain a predicted storage time, a storage volume, and a storage type according to the warehouse storage data, and set a storage rule of the warehouse material according to the predicted storage time, the storage volume, and the storage type.

[0050] The warehouse burst prediction module is configured to predict a warehouse burst event according to the warehouse storage volume at a future time and the storage rule of the warehouse material.

[0051] The warehouse burst warning module is configured to perform a warehouse burst warning operation according to the warehouse burst event.

[0052] The above embodiments have the beneficial effects that the AI model-based supply chain space-time coordination, planning, and optimization system is based on data technology and data synchronization and ETL processing, analyzes the storage turnover time between supply chain nodes, the volume of warehouse storage types, and historical warehouse data, uses an AI model to reasonably distribute warehouse materials to various storage types, and performs warehouse volume prediction at a future time; the warehouse materials are also split into warehouse storage and configured with storage rules. The space optimization algorithm based on operations research and maximum optimization technology effectively completes space optimization coordination and other tasks, predicts the warning level and burst proportion of the warehouse storage type, divides the warning level into soft burst and hard burst, and pushes notifications to the corresponding personnel, providing reliable analysis and decision-making reference information for the corresponding personnel.

[0053] In another embodiment, the data warehouse synchronization and cleaning module is configured to prepare supply chain business data, including:

[0054] The data warehouse of the supply chain business system is subjected to data extraction, conversion, and loading processing to obtain supply chain business data; the data warehouse includes business data related to materials, warehouses, logistics, transportation, and procurement.

[0055] To ensure normal operation of the warehouse, a corresponding supply chain business system is constructed for the warehouse, and the data warehouse of the supply chain business system synchronously stores all relevant data of the warehouse and its supply chain during operation. Considering that the supply chain operation involves materials, warehouses, logistics, transportation, procurement, and other aspects, and the above aspects all affect the warehouse out and in, to comprehensively and accurately grasp the space usage state of different storage types in the warehouse, the business data related to materials, warehouses, logistics, transportation, and procurement in the data warehouse of the supply chain business system is subjected to data extraction, conversion, and loading processing (i.e., ETL processing) to obtain supply chain data, and realize accurate data acquisition of the warehouse supply chain.

[0056] In another embodiment, the data warehouse synchronization and cleaning module is configured to obtain warehouse storage state data, warehouse historical out data, and warehouse storage data, including:

[0057] Obtaining the latest warehouse location type and warehouse area data from the supply chain business data, so as to determine the total volume and used volume of the warehouse location type, and to use the same as the warehouse location state data;

[0058] Obtaining the warehouse location outbound quantity in the historical time interval from the supply chain business data, so as to use the same as the warehouse historical outbound data; wherein the warehouse location outbound quantity in the historical time interval can be, but is not limited to, the material outbound quantity of the warehouse location in the past one year;

[0059] Obtaining the supply chain business node configuration from the supply chain business data, so as to determine the turnover time of each business process under the supply chain; based on the turnover time, determining the arrival date of the material, so as to predict the warehouse inbound quantity and volume of the arrival date, and to use the same as the warehouse inbound data.

[0060] Please refer to Figure 2 , the warehouse is provided with multiple types of locations, and the capacity volume of different types of locations is different, and the occupied space volume of different types of locations is also different, which will affect the currently available space volume of different types of locations, so as to determine the quantity and volume of the subsequent inbound materials received and stored in the locations. In addition, the materials stored in different types of locations will be transferred out, and the more the quantity and volume of the materials transferred out in the locations, the larger the available space volume in the locations, so as to provide more storage space for the subsequent inbound materials. Different types of locations usually store specific types of materials, and the outbound of specific types of materials will present a certain rule, and the historical outbound data of different types of locations in the warehouse can reflect the future material outbound situation of the locations to a certain extent. Through the above analysis, it can be known that obtaining the warehouse location state data, the warehouse historical outbound data and the warehouse inbound data from the data warehouse can accurately calculate the space volume utilization rate of the locations in real time, and provide reliable data basis for predicting the space volume vacated after the locations perform material outbound. In addition, the corresponding supply chain of the warehouse includes multiple supply chain business nodes such as material supply points and material transportation and transfer points, and the configuration of these supply chain business nodes directly determines the turnover time required for each supply chain business node to run its own business process, and the above turnover time directly determines the date of the material arriving at the warehouse through the supply chain, so as to affect the time of the warehouse performing material inbound. Through the supply chain business node configuration, the turnover time of each business process is determined, so as to predict the warehouse inbound material quantity and volume of the arrival date, and accurately determine the space volume occupied by the warehouse inbound material in the future time.

[0061] In another embodiment, the data warehouse synchronization and cleaning module is used for periodically cleaning and updating data, including:

[0062] The warehouse location state data, warehouse historical outbound data and warehouse inbound data are cleaned and updated regularly, and the updated warehouse location state data, warehouse historical outbound data and warehouse inbound data are stored in the OSS object storage specified directory and saved as CSV files.

[0063] Considering that material outbound and inbound events occur in the warehouse at every moment, the warehouse location state data, warehouse historical outbound data and warehouse inbound data obtained at the current moment can only be valid within a certain time range. Once the above time range is exceeded, the above obtained data will not accurately reflect the actual situation of the warehouse. In order to ensure data validity, the warehouse location state data, warehouse historical outbound data and warehouse inbound data are cleaned and updated regularly. In addition, in order to comprehensively and stably save the data obtained from the data warehouse, the updated data is stored in the specified directory using the object storage service OSS and saved as a CSV file, which is convenient for reading and editing data at any time.

[0064] In another embodiment, the location prediction module is configured to predict the outbound volume of the warehouse location at a future time according to the warehouse location state data and the warehouse historical outbound data, comprising:

[0065] Invalid data is removed and duplicate data is merged from the warehouse location state data and the warehouse historical outbound data.

[0066] According to the warehouse location state data, the usage volume ratio of the warehouse location is determined; according to the usage volume ratio and the warehouse historical outbound data, the long short-term memory network model is used to predict the outbound volume of the warehouse location at a future time.

[0067] Please refer to Figure 3 , considering that most of the data in the supply chain business system is raw data uploaded by users, which has not been screened, edited and processed, resulting in errors or duplication in the raw data. In order to improve data accuracy, invalid data is removed and duplicate data is merged from the warehouse location state data and the warehouse historical outbound data to ensure correct data format and provide reliable data sources for subsequent AI model prediction and analysis. In addition, the warehouse historical outbound data is aggregated by month to form a monthly outbound trend; according to the usage volume ratio of each location type, the total outbound volume is allocated to specific location types, and the long short-term memory network model is used to predict the outbound volume of the warehouse location at a future time (such as the next few months), thereby accurately representing the future change trend of the outbound volume of all location types in the warehouse.

[0068] In another embodiment, the location storage rule setting module is configured to obtain the predicted inbound time, inbound volume and storage type according to the warehouse inbound data, comprising:

[0069] According to historical storage type information of warehouse storage, data completion is performed on warehouse storage data of missing storage type information.

[0070] The warehouse storage data is grouped to obtain the predicted storage time, storage volume, and storage type of the material; and the warehouse storage data of the material is sorted according to the predicted storage time of the material.

[0071] During the historical warehouse storage period, it is inevitable that the storage information missing record situation occurs, so that the storage type information (such as storage position information) of the material actually stored in the warehouse storage data is missing. In order to ensure that the storage data can be accurately split to the storage location, according to the historical storage type information of the warehouse storage, data completion is performed on the warehouse storage data of missing storage type information. In addition, according to the predicted storage time, the storage volume, and the storage type of the material, the warehouse storage data is grouped, and the mapping relationship between different brands of materials and storage locations is established; and the warehouse storage data of the material is sorted according to the predicted storage time of the material, so as to improve the order of the material storage arrangement of the warehouse.

[0072] In another embodiment, the storage location storage rule setting module is configured to set the storage location storage rule of the storage material according to the predicted storage time, the storage volume, and the storage type, including:

[0073] According to the predicted storage time, the storage volume, and the storage type of the material, the storage adjustment of the material is performed in terms of volume priority, storage space optimization, real-time dynamic allocation, and weight allocation, and the storage location storage rule of the storage material is set.

[0074] In actual operation, the AI model uses an intelligent placement algorithm (such as StackFaceFirst or LAFF) to determine the storage location of the storage material in the warehouse. Specifically, according to the predicted storage time, the storage volume, and the storage type of the material, the storage adjustment of the material is performed in terms of volume priority, storage space optimization, real-time dynamic allocation, and weight allocation, and the storage location storage rule of the storage material is set, so as to generate the storage location storage rule of the storage material according to the order from large to small in terms of material volume, select the appropriate storage location with the largest available space for each material, track the current usage of each storage location (considering the remaining space after the current predicted storage amount), calculate the weight distribution of the daily storage amount based on the past 30 days of storage mode, and maximize the utilization of the warehouse storage space and ensure that the storage material can be placed in the appropriate storage location.

[0075] In another embodiment, the warehouse explosion prediction module is configured to predict the warehouse explosion event according to the storage volume of the warehouse location at the future time and the storage location storage rule of the storage material, including:

[0076] According to the warehouse location out-of-warehouse volume at a future time and the warehouse location storage rules of the incoming material, the soft and hard warehouse explosion events of the warehouse location are predicted; wherein the soft warehouse explosion event refers to the volume of a single warehouse location exceeding its capacity; the hard warehouse explosion event refers to the total volume of all warehouse locations exceeding the total capacity of the warehouse.

[0077] In actual operation, the space optimal allocation algorithm based on operational research and maximum optimization technology is combined with the warehouse location out-of-warehouse volume at a future time and the warehouse location storage rules of the incoming material to predict the soft and hard warehouse explosion events of the warehouse location, and the soft and hard warehouse explosion events are used for early warning classification and quantitative calculation of the warehouse explosion ratio, thereby effectively reducing the warehouse explosion false alarm.

[0078] In another embodiment, the warehouse explosion early warning module is used to perform warehouse explosion early warning operation according to the warehouse explosion event, including:

[0079] According to the warehouse explosion event, mail push notification, inventory monitoring, in-transit inventory track tracking, and logistics track map analysis are performed.

[0080] Please refer to Figure 4 When it is determined that a warehouse explosion event occurs, a Python space-time planning warehouse explosion early warning notification service can be used to perform mail push notification, inventory monitoring, in-transit inventory track tracking, and logistics track map analysis, thereby providing multi-dimensional means for warehouse in-out monitoring and supply chain operation monitoring.

[0081] In another embodiment, the warehouse explosion early warning module performs mail push notification, including: calling a mail notification service through an API to push a warehouse capacity early warning message;

[0082] The warehouse explosion early warning module performs inventory monitoring, including: forming a warehouse inventory change curve every day in the future to analyze the warehouse inventory change trend;

[0083] The warehouse explosion early warning module performs in-transit inventory track tracking, including: tracking the logistics track route of the material in transit and needing to be stored in the warehouse;

[0084] The warehouse explosion early warning module performs logistics track map analysis, including: analyzing and displaying the logistics transportation track of the material on a world map.

[0085] In the above manner, the warehouse explosion event is early warned and tracked and analyzed by multiple independent means, thereby efficiently solving the problems of inventory space optimal allocation, coordination, and operation in the supply chain, and providing reliable analysis and decision-making reference information for the corresponding personnel.

[0086] Overall, the AI model-based supply chain space-time coordination, planning and optimization system is based on data technology and data synchronization and ETL processing, analyzes the warehouse turnover time between supply chain nodes, the volume of warehouse location type and historical outbound data, uses an AI model to reasonably distribute warehouse outbound materials to each location type, and predicts the outbound quantity in the future time; it also splits the inbound materials to the warehouse locations and configures the location storage rules. The space optimization algorithm developed based on operations research and maximum optimization technology effectively completes space optimization coordination and other tasks, predicts the early warning level and the warehouse location type of the warehouse location type, and according to the early warning level, it is divided into soft and hard warehouse explosion, and the corresponding personnel is pushed to provide reliable analysis and decision-making reference information for the corresponding personnel.

[0087] The above is only one specific embodiment of the present application, and any improvement made on the basis of the concept of the present application is considered to be within the scope of protection of the present application.

Claims

1. An AI model based supply chain space-time coordination, planning and optimization system, characterized in that, Comprise: A data warehouse synchronization and cleaning module for preparing supply chain business data to obtain warehouse location state data, warehouse historical outbound data, warehouse inbound data, and regularly clean and update the data; A location prediction module for predicting the outbound volume of the warehouse location at a future time based on the warehouse location state data and the warehouse historical outbound data; A location storage rule setting module for obtaining predicted inbound time, inbound volume, and storage type based on the warehouse inbound data, and setting inbound material location storage rules based on the predicted inbound time, inbound volume, and storage type; A warehouse explosion prediction module for predicting a warehouse explosion event based on the outbound volume of the warehouse location at the future time and the inbound material location storage rules; A warehouse explosion warning module for performing a warehouse explosion warning operation based on the warehouse explosion event; The location prediction module is configured to predict the outbound volume of the warehouse location at a future time based on the warehouse location state data and the warehouse historical outbound data, comprising: Invalid data elimination and duplicate data merging of the warehouse location state data and the warehouse historical outbound data; Determining the usage volume ratio of the warehouse location based on the warehouse location state data, and predicting the outbound volume of the warehouse location at a future time using a long short-term memory network model based on the usage volume ratio and the warehouse historical outbound data; The warehouse explosion prediction module is configured to predict a warehouse explosion event based on the outbound volume of the warehouse location at a future time and the inbound material location storage rules, comprising: Predicting soft warehouse explosion events and hard warehouse explosion events of the warehouse location based on the outbound volume of the warehouse location at a future time and the inbound material location storage rules; wherein the soft warehouse explosion event refers to the predicted storage material volume of a single location exceeding its capacity, and the hard warehouse explosion event refers to the predicted storage material volume of all locations exceeding the total capacity of the warehouse.

2. The AI model-based supply chain space-time coordination, planning, and optimization system of claim 1, wherein: The data warehouse synchronization and cleaning module is configured to prepare supply chain business data, comprising: Performing data extraction, transformation, and loading processing on the data warehouse of the supply chain business system to obtain supply chain business data; wherein the data warehouse comprises business data related to materials, warehouses, logistics, transportation, and procurement.

3. The AI model-based supply chain space-time coordination, planning, and optimization system of claim 1, wherein: The data warehouse synchronization and cleaning module is configured to obtain warehouse location state data, warehouse historical outbound data, and warehouse inbound data, comprising: Obtaining the latest warehouse location type and warehouse area data from the supply chain business data to determine the total volume and used volume of the warehouse location type, which are used as the warehouse location state data; Obtaining the number of outbound materials of the warehouse location at a historical time interval from the supply chain business data, which is used as the warehouse historical outbound data; Obtain supply chain business node configuration from the supply chain business data, so as to determine the turnover time of each business process under the supply chain; based on the turnover time, determine the material arrival date, so as to predict the warehouse storage quantity and volume of the arrival date as the warehouse storage data.

4. The AI model-based supply chain space-time coordination, planning and optimization system of claim 1, wherein: The data warehouse synchronization and cleaning module is used for regularly cleaning and updating data, including: The warehouse location state data, the warehouse historical outbound data, and the warehouse storage data are regularly cleaned and updated, and the updated warehouse location state data, warehouse historical outbound data, and warehouse storage data are stored in the OSS object storage specified directory and saved as CSV files.

5. The AI model-based supply chain space-time coordination, planning and optimization system of claim 1, In particular: The location storage rule setting module is used for obtaining predicted storage time, storage volume, and storage type according to the warehouse storage data, including: According to historical storage type information, data is completed for storage records in the warehouse storage data that lack storage type information; The warehouse storage data is grouped to obtain the predicted storage time, storage volume, and storage type of the material; and the warehouse storage data of the material is sorted according to the predicted storage time of the material.

6. The AI model-based supply chain space-time coordination, planning and optimization system of claim 5, wherein: wherein The location storage rule setting module is used for setting storage rules for the storage material according to the predicted storage time, storage volume, and storage type, including: According to the predicted storage time, storage volume, and storage type of the material, the material is adjusted for storage in terms of volume priority, location space optimization, real-time dynamic allocation, and weight allocation, and the storage rules for the storage material are set.

7. The AI model-based supply chain space-time coordination, planning and optimization system of claim 1, wherein: The warehouse explosion warning module is used for performing warehouse explosion warning operations according to the warehouse explosion events, including: According to the warehouse explosion events, email push notification, inventory monitoring, in-transit inventory tracking, and logistics trajectory map analysis are performed.

8. The AI model-based supply chain space-time coordination, planning and optimization system of claim 1, wherein: The warehouse explosion warning module performs email push notification, including: calling a mail notification service through an API to push a warehouse capacity warning message; The warehouse explosion warning module performs inventory monitoring, including: forming a warehouse inventory change curve every day in the future to analyze the warehouse inventory change trend; The warehouse explosion warning module performs in-transit inventory tracking, including: tracking the logistics trajectory route of the material in transit and requiring storage on the map; The warehouse explosion warning module performs logistics trajectory map analysis, including: analyzing and displaying the logistics transportation trajectory of the material on the world map.

Images