Industrial warehouse AI management method and system based on state data

Abstract

The invention relates to an AI management method and system for an industrial warehouse based on state data, and the method comprises the steps: obtaining the state data of each storage unit in the industrial warehouse in a first monitoring period, and generating a standardized state data set; based on the standardized state data set, evaluating the operation state of the industrial warehouse by using a preset data analysis model to obtain a detailed operation state evaluation result; generating an optimization management strategy table in the first monitoring period according to the operation state evaluation result, wherein the optimization management strategy table comprises a cargo scheduling plan, a regulation and control instruction, a personnel allocation scheme and the like; sending the optimization management strategy table to a management system of the industrial warehouse, and indicating the management system to execute corresponding management operation in a second monitoring period; according to the scheme, the operation state of the industrial warehouse can be accurately evaluated, a scientific and reasonable optimization management strategy is generated, and the management efficiency and the operation level of the industrial warehouse are improved.

Description

Technical Field

[0001] This application relates to the fields of industrial automation, big data and information technology, and in particular to an AI management method and system for industrial warehouses based on status data. Background Technology

[0002] As a crucial link in the logistics and supply chain, efficient and accurate industrial warehouse management is essential for a company's production and development. Traditional industrial warehouse management relies heavily on manual labor for tasks such as goods storage, inbound and outbound registration, and environmental monitoring. Manually recording the location of goods requires staff to manually fill in shelf and location numbers in paper ledgers or spreadsheets, while environmental monitoring involves regular manual inspections using simple thermometers, hygrometers, and light intensity meters to record relevant values.

[0003] To improve management efficiency and accuracy, some enterprises have introduced computer management systems, enabling the digital storage and retrieval of goods information, as well as the automatic collection and preliminary analysis of environmental parameters. These systems can collect data such as temperature, humidity, and light intensity within the warehouse in real time and electronically record the entry and exit operations of goods. However, these current computer management systems suffer from insufficient data processing capabilities. The systems can only perform simple data statistics and display, unable to conduct in-depth mining and analysis of large amounts of status data, making it difficult to generate scientific and reasonable management strategies. Consequently, warehouse operational efficiency still needs improvement. Summary of the Invention

[0004] The main purpose of this application is to provide an AI management method and system for industrial warehouses based on status data, which can accurately assess the operating status of industrial warehouses and generate scientific and reasonable optimization management strategies to improve the management efficiency and operational level of industrial warehouses.

[0005] To achieve the above objectives, embodiments of the present invention provide an AI management method for industrial warehouses based on status data, the method comprising the following steps: The status data of each storage unit in the industrial warehouse during the first monitoring period is obtained. The status data includes environmental parameters, goods storage location information and inbound / outbound operation records within the storage unit. The environmental parameters include temperature, humidity and light intensity values. The goods storage location information includes shelf number and storage location number. The inbound / outbound operation records include operation timestamp and operator identification. The state data is cleaned and classified to generate a standardized state dataset; Based on the standardized status dataset, the operating status of the industrial warehouse is evaluated through a preset data analysis model to obtain the operating status evaluation results. The operating status evaluation results include the occupancy rate of storage units, the abnormal distribution areas of environmental parameters, and the frequency distribution of inbound and outbound operations. Based on the operational status assessment results, an optimization management strategy table for the first monitoring period is generated. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies. The optimized management strategy table is sent to the industrial warehouse management system to instruct the management system to perform corresponding management operations based on the optimized management strategy table during the second monitoring cycle.

[0006] Accordingly, this application also provides an AI management system for industrial warehouses based on status data, the system comprising: The acquisition module is used to acquire the status data of each storage unit in the industrial warehouse during the first monitoring period. The status data includes environmental parameters, goods storage location information, and inbound / outbound operation records within the storage unit. The environmental parameters include temperature, humidity, and light intensity values. The goods storage location information includes shelf number and storage location number. The inbound / outbound operation records include operation timestamp and operator identification. The data processing module is used to clean and classify the state data to generate a standardized state dataset. The status assessment module is used to assess the operating status of the industrial warehouse based on the standardized status dataset and through a preset data analysis model to obtain the operating status assessment results, which include the occupancy rate of storage units, abnormal distribution areas of environmental parameters, and frequency distribution of inbound and outbound operations. The strategy generation module is used to generate an optimization management strategy table for the first monitoring period based on the operation status evaluation results. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies. The sending module is used to send the optimization management strategy table to the management system of the industrial warehouse, so as to instruct the management system to perform corresponding management operations according to the optimization management strategy table in the second monitoring cycle.

[0007] In summary, by adopting the technical solution of this application, the actual operating status of the industrial warehouse can be comprehensively and accurately grasped by acquiring the status data of each storage unit within the first monitoring period, including environmental parameters, goods storage location information, and inbound / outbound operation records. The status data is cleaned and classified to generate a standardized status dataset, providing a high-quality data foundation for subsequent data analysis. Based on the standardized status dataset, a preset data analysis model is used to evaluate the operating status of the industrial warehouse, obtaining detailed operational status evaluation results, including storage unit occupancy rate, abnormal distribution areas of environmental parameters, and distribution of inbound / outbound operation frequency. This helps to gain a deeper understanding of the warehouse's operational characteristics and existing problems. An optimized management strategy table for the first monitoring period is generated based on the operational status evaluation results, including goods scheduling plans, control instructions, and personnel allocation schemes, enabling targeted solutions to different problems. The optimized management strategy table is sent to the industrial warehouse management system, instructing it to execute corresponding management operations in the second monitoring period. This effectively improves warehouse management efficiency, rationally utilizes warehouse resources, ensures the stability of the goods storage environment, and enhances personnel work efficiency, thereby comprehensively improving the operational level of the industrial warehouse. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of a scenario for an AI management method for an industrial warehouse based on state data, as described in an embodiment of this application. Figure 2 A flowchart of an AI management method for industrial warehouses based on state data is provided for embodiments of this application; Figure 3 A schematic diagram of the warehouse status assessment process provided in this application embodiment; Figure 4 A flowchart illustrating the management strategy table generation process provided in this application embodiment; Figure 5 This is a schematic diagram of the process for generating a cargo scheduling plan provided in an embodiment of this application; Figure 6 A flowchart illustrating the personnel allocation scheme generation process provided in this application embodiment; Figure 7 A schematic diagram of the structure of an AI management system for an industrial warehouse based on state data, provided in an embodiment of this application; Figure 8A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0010] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0011] This application provides an AI management method and system for industrial warehouses based on status data, which will be described in detail below.

[0012] In this embodiment, the AI ​​(Artificial Intelligence) management method for industrial warehouses based on status data is a method that comprehensively utilizes artificial intelligence technology and data analysis to achieve efficient and precise management of industrial warehouses. This method collects status data from each storage unit within the industrial warehouse in real time, including environmental parameters within the storage units, goods storage location information, and inbound / outbound operation records. This data is then cleaned, classified, and analyzed to assess the operational status of the industrial warehouse, thereby generating targeted optimization management strategy tables. These strategy tables include goods scheduling plans, environmental control instructions, and personnel allocation schemes, which help industrial warehouses rationally arrange goods storage, optimize environmental conditions, and improve personnel work efficiency, achieving intelligent and automated management of industrial warehouses and enhancing their overall operational level and economic benefits.

[0013] like Figure 1 As shown, an AI management method scenario for an industrial warehouse based on status data is provided. The industrial warehouse management scenario mainly includes various sensors, data analysis platforms, and management systems installed in the industrial warehouse; the various sensors, data analysis platforms, and management systems are connected through wired or wireless networks.

[0014] Taking the industrial warehouse of a large manufacturing company as an example, this warehouse is mainly used to store raw materials, parts, and finished products required for production. The warehouse has a large area and is divided into multiple storage areas, each equipped with different types of shelves for storing goods of different specifications and uses.

[0015] Various sensors are installed in industrial warehouses to collect various types of data. For example, in a manufacturing enterprise's industrial warehouse, environmental sensors are installed in various storage units to monitor temperature, humidity, and light intensity in real time. For instance, in areas storing electronic components, where temperature and humidity requirements are strict, environmental sensors can accurately and promptly collect environmental parameter information. Goods location sensors are installed on shelves to record the storage location of goods, accurate to the shelf number and storage location number. When goods enter the warehouse, the sensors automatically identify the location and upload relevant information. Inbound / outbound operation sensors are installed at the warehouse entrances and exits to record the timestamps and operator identification of each operation, ensuring detailed records for every inbound / outbound transaction.

[0016] The data analysis platform receives and processes status data uploaded from various sensors. Specifically, it cleans and classifies the data, removing invalid and duplicate data, and organizing it into a standardized status dataset. Then, based on a pre-defined data analysis model, it assesses the operational status of the industrial warehouse. For example, by analyzing storage unit occupancy data, it identifies areas with excessively high occupancy rates, requiring cargo rescheduling; based on environmental parameter data, it identifies areas with abnormal environmental parameter distributions and issues timely control instructions; and it statistically analyzes inbound and outbound operation records to generate frequency distribution maps for rational personnel allocation.

[0017] Once the data analysis platform generates an optimization management strategy table, it sends it to the industrial warehouse management system. Based on the cargo scheduling plan in the strategy table, the management system arranges forklifts and other handling equipment to move goods from high-occupancy areas to vacant areas; for areas with abnormal environmental parameter distributions, it controls corresponding control equipment, such as air conditioners, humidifiers, and dehumidifiers, to regulate the environment; and based on the personnel allocation plan, it rationally schedules staff to perform inbound and outbound operations at different times to improve work efficiency.

[0018] In actual operation, the AI ​​management method for industrial warehouses based on status data in this application embodiment can accurately and in real time grasp the operational status of the warehouse, promptly identify problems, and take effective solutions. Through scientific and reasonable cargo scheduling, the utilization rate of warehouse space is improved; precise control of environmental parameters ensures the storage quality of goods; and a reasonable personnel allocation plan improves personnel work efficiency, thereby enhancing the overall operational level and economic benefits of the industrial warehouse.

[0019] refer to Figure 2 , Figure 2This is a flowchart illustrating an AI management method for an industrial warehouse based on state data, provided in an embodiment of this application. The execution entity of this method can be a computer device (which can be used as a data analysis platform), such as a server. The AI ​​management method for an industrial warehouse based on state data provided in this embodiment specifically includes: S10: Acquire status data of each storage unit in the industrial warehouse during the first monitoring period. The status data includes environmental parameters within the storage unit, goods storage location information, and inbound / outbound operation records. Environmental parameters include temperature, humidity, and light intensity values; goods storage location information includes shelf number and storage location number; and inbound / outbound operation records include operation timestamps and operator identification.

[0020] In this embodiment, an industrial warehouse is a location used for the centralized storage of raw materials, components, and finished products required for industrial production. It is a crucial link in the industrial production supply chain, undertaking functions such as storage, safekeeping, and turnover of goods. Industrial warehouses typically have a large space, internally divided into multiple different areas to meet the storage needs of different types of goods. For example, in an industrial warehouse of an automobile manufacturing company, there might be areas specifically for storing raw materials such as steel and plastics, areas for storing components such as engines and transmissions, and areas for storing finished automobiles.

[0021] In this embodiment, a storage unit is a basic unit used for storing goods in an industrial warehouse. It can be a shelf, a container, or a specific area. Each storage unit has its own unique identifier, such as a shelf number and a storage location number, to accurately record the storage location of the goods. For example, in a large warehouse, a shelf can be divided into multiple storage locations, and each storage location is a storage unit.

[0022] In this embodiment, the first monitoring period is a pre-defined time period used to collect and analyze the status data of each storage unit within the industrial warehouse. The duration of this period can be determined based on the actual operation and management needs of the warehouse, such as a day, a week, or a month. Within this period, the system continuously acquires the status data of the storage units to gain a comprehensive understanding of the warehouse's operational status during that time period.

[0023] In this embodiment, the status data is a set of key information reflecting the actual operating status of each storage unit in an industrial warehouse. The temperature value in the environmental parameters is a physical quantity that measures the degree of heat within the storage unit. For example, in a warehouse storing food or medicine, a suitable temperature can ensure the quality of the goods. The humidity value indicates the amount of water vapor in the air; excessively high or low humidity may damage goods; for example, metal products are prone to rusting in high humidity environments. The light intensity value reflects the degree of light exposure within the storage unit. Some light-sensitive goods, such as photosensitive materials, need to be stored under specific light intensities.

[0024] Information on the location of goods is crucial for accurately locating their whereabouts. Shelf numbers identify different shelves within the warehouse; each shelf has a unique number for quick location. Location numbers further specify the exact location of goods on the shelf. For example, a large shelf may be divided into multiple locations, each with its own unique number.

[0025] The inbound and outbound operation logs record the time of goods entering and leaving the warehouse and the personnel involved. The operation timestamp accurately records the specific time of each inbound and outbound operation, which helps in analyzing the flow patterns of goods. The personnel identification clearly identifies the responsible party for each operation, facilitating accountability and management.

[0026] In one embodiment, environmental parameters can be acquired by installing a temperature and humidity sensor and a light intensity sensor in each storage unit. The temperature and humidity sensor is a high-precision digital sensor that can measure the temperature and humidity values ​​within the storage unit in real time and accurately, and transmit the data to the management system via a wireless communication module. The light intensity sensor uses components such as photoresistors or photodiodes to convert light intensity into an electrical signal, which is then transmitted to the management system after analog-to-digital conversion.

[0027] For obtaining information on the location of goods, barcode or radio frequency identification (RFID) technology can be used. Barcode labels or RFID tags are installed on each shelf and storage location. When goods enter the warehouse, staff use barcode scanners or RFID readers to scan the labels on the goods and the labels on the shelves and storage locations. The system automatically records the storage location information of the goods.

[0028] To obtain inbound and outbound operation records, access control systems and operation recording devices can be installed at the warehouse entrances and exits. The access control system records the operator's identity information through methods such as card swiping or fingerprint recognition, while the operation recording device records the timestamp of each inbound and outbound operation, associates this information with the operator's identification, and uploads it to the management system.

[0029] S20: Perform data cleaning and classification on the state data to generate a standardized state dataset.

[0030] In this embodiment, data cleaning and classification are crucial preprocessing steps for raw state data. Data cleaning removes noise, errors, and duplicate information from the data to improve its quality. Because sensors may have measurement errors, or interference may occur during data transmission, the acquired state data may contain inaccurate or invalid information. For example, temperature and humidity sensors may occasionally show abnormal measurement values, requiring data cleaning.

[0031] Data classification involves categorizing cleaned data according to specific rules to facilitate subsequent analysis and processing. Environmental parameter data, goods storage location information, and inbound / outbound operation records are categorized separately to allow for targeted analysis of different data types.

[0032] A standardized state dataset is a collection of data that has been cleaned and classified, resulting in a unified format and standardized structure. This dataset facilitates data analysis and processing, improving the accuracy and reliability of the analysis results.

[0033] In one embodiment, data cleaning can employ statistical analysis and rule matching methods. Statistical analysis involves calculating statistical measures such as the mean and standard deviation of the data to identify data points deviating from the normal range and treating them as outliers. Rule matching, on the other hand, filters the data according to preset rules, such as a reasonable range for temperature values ​​or upper and lower limits for humidity values, removing data that does not conform to the rules.

[0034] For data classification and processing, a database table structure can be used for categorized storage. Environmental parameter data is stored in one table, including fields such as temperature, humidity, and light intensity; goods storage location information is stored in another table, including fields such as shelf number and storage location number; and inbound / outbound operation records are stored in a third table, including fields such as operation timestamp and operator identifier. This method achieves categorized management and storage of data.

[0035] S30: Based on the standardized status dataset, the operating status of the industrial warehouse is evaluated through a preset data analysis model to obtain the operating status evaluation results. The operating status evaluation results include the occupancy rate of storage units, the abnormal distribution areas of environmental parameters, and the frequency distribution of inbound and outbound operations.

[0036] In this embodiment, the preset data analysis model is a tool for in-depth analysis of standardized state datasets. This model, based on machine learning and statistical methods in the field of artificial intelligence, is capable of uncovering hidden information and patterns within the data.

[0037] Storage unit occupancy rate refers to the proportion of space occupied by goods within a storage unit to the total available space, reflecting the utilization of warehouse space. Abnormal distribution areas of environmental parameters refer to areas where environmental parameters exceed normal ranges, which may affect the storage of goods. The frequency distribution of inbound and outbound operations shows the frequency of these operations over different time periods, helping to rationally allocate personnel and resources.

[0038] In one embodiment, the preset data analysis model can employ a combination of cluster analysis and statistical analysis. For storage unit occupancy analysis, the occupancy rate is calculated by statistically analyzing the volume or weight of goods within each storage unit, and then clustered based on the occupancy rate, classifying storage units into three categories: high occupancy, medium occupancy, and low occupancy. For abnormal distribution area analysis of environmental parameters, statistical analysis is performed on environmental parameter data based on preset normal ranges to identify and mark areas exceeding the normal range. For frequency distribution analysis of inbound and outbound operations, the number of inbound and outbound operations within each time period is statistically analyzed, and a frequency distribution chart is plotted to visually demonstrate the frequency of these operations.

[0039] In one embodiment, the preset data analysis model can be an artificial intelligence-based model. Specifically, firstly, a large amount of historical state data from industrial warehouses is collected. This data can include historical information such as storage unit occupancy, environmental parameters, and inbound / outbound operation records, constructing a comprehensive and representative dataset. Next, the dataset is divided, with the majority of the data used as the training set to train the artificial intelligence model, and a smaller portion used as the validation and test sets for parameter tuning and performance evaluation, respectively. A suitable artificial intelligence model architecture, such as a deep neural network (DNN), is selected. During training, the model is iteratively trained using the training set data, continuously adjusting the model's weights and biases through backpropagation to minimize the error between the predicted results and the actual operational status evaluation results. Simultaneously, the validation set data is used to monitor the model's training progress to prevent overfitting. If overfitting is detected, regularization and other methods can be used for adjustment. After training, the test set data is used for final performance evaluation of the model to ensure high accuracy and generalization ability. By applying the trained artificial intelligence model to the actual operational status assessment of industrial warehouses, and inputting a standardized status dataset, the model can output accurate operational status assessment results, including the occupancy rate of storage units, abnormal distribution areas of environmental parameters, and frequency distribution of inbound and outbound operations.

[0040] S40: Based on the operational status assessment results, generate an optimization management strategy table for the first monitoring period. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies.

[0041] In this embodiment, the optimized management strategy table is a collection of management measures formulated based on the operational status assessment results. The cargo scheduling plan targets areas where storage unit occupancy exceeds a first threshold, reducing occupancy and improving warehouse space utilization by rationally arranging cargo transfer and storage. The control instructions target areas with abnormal environmental parameter distributions, adjusting environmental parameters to restore them to normal ranges by controlling corresponding control equipment. The personnel allocation plan rationally arranges staff working hours and tasks based on the frequency distribution of inbound and outbound operations, improving staff efficiency.

[0042] In one embodiment, a greedy algorithm can be used to generate the cargo scheduling plan. First, the cargo transfer priority value of each storage unit is calculated, and the cargo is sorted according to the priority value. Then, in descending order of priority, the cargo is transferred from areas with high occupancy to areas with low occupancy. For the generation of control instructions, based on the type and degree of environmental parameter anomalies, a preset control rule table is queried to determine the corresponding control equipment and control parameters, and control instructions are generated. For the generation of personnel allocation plans, based on the frequency distribution of inbound and outbound operations, peak and off-peak periods are determined. The number of staff is increased during peak periods and decreased during off-peak periods to achieve reasonable personnel allocation.

[0043] S50: Send the optimization management strategy table to the industrial warehouse management system to instruct the management system to perform corresponding management operations according to the optimization management strategy table during the second monitoring cycle.

[0044] In this embodiment, the industrial warehouse management system is the core system for executing the optimized management strategy table. After receiving the optimized management strategy table, the system can control the corresponding equipment and personnel to operate according to the cargo scheduling plan, control instructions, and personnel allocation scheme contained therein. During the second monitoring cycle, the management system can arrange forklifts and other handling equipment to transfer goods according to the cargo scheduling plan, control air conditioners, humidifiers, and other control equipment to adjust environmental parameters according to the control instructions, and assign work tasks to staff according to the personnel allocation scheme.

[0045] In this embodiment, the second monitoring period is a time interval following the first monitoring period, used to execute the optimized management strategy table generated based on the operational status assessment results of the first monitoring period. Its duration is typically the same as the first monitoring period or adjusted according to actual conditions, with the aim of verifying the effectiveness of the optimized management strategy and further optimizing the operational status of the industrial warehouse.

[0046] In this embodiment, sending the optimized management strategy table to the management system and executing corresponding management operations transforms the optimized management strategy into actual management actions, enabling dynamic management of the industrial warehouse. Technically, this continuously optimizes the operational status of the industrial warehouse, improving its overall operational level.

[0047] In one embodiment, the optimization management strategy table can be sent to the management system via a network communication protocol. Upon receiving the strategy table, the management system parses it into specific operation instructions and stores them in a database. During the second monitoring cycle, the management system executes operations such as cargo scheduling, environmental control, and personnel allocation sequentially according to a predetermined time order. Simultaneously, the management system monitors the execution status of these operations in real time, such as whether cargo transfer is complete and whether environmental parameters have returned to normal, and feeds back the execution results to relevant personnel for further adjustments and optimizations.

[0048] In one embodiment, reference Figure 3 Step S30 may include steps S31-S35, which will be described in detail below: Step S31: Extract storage unit occupancy data from the standardized state dataset and calculate the occupancy value for each storage unit.

[0049] In one embodiment, storage unit occupancy data measures the efficiency of storage unit utilization in an industrial warehouse. This data is extracted from a standardized status dataset, and information related to storage unit occupancy can be filtered using database queries. The occupancy rate for each storage unit can be calculated based on the volume or weight of the goods and the total capacity of the storage unit. For example, if a storage unit has a total capacity of 100 cubic meters and stores 60 cubic meters of goods, then the occupancy rate for that storage unit is 60%.

[0050] Step S32: Based on the storage cell occupancy rate data, determine the set of storage cells with an occupancy rate higher than the first threshold.

[0051] In one embodiment, the first threshold is a pre-set occupancy rate standard used to determine whether a storage unit is in a high-occupancy state. Based on the extracted storage unit occupancy rate data, the occupancy rate value of each storage unit is compared with the first threshold. If the occupancy rate value of a storage unit is higher than the first threshold, it is included in the set of storage units with occupancy rates higher than the first threshold. For example, if the first threshold is set to 80%, when the occupancy rate of a storage unit reaches 85%, that storage unit belongs to this set.

[0052] In one embodiment, a data filtering algorithm can be used to quickly filter storage unit occupancy data. The algorithm automatically identifies storage units with occupancy rates higher than a first threshold and organizes their information into a set. This approach improves filtering efficiency, ensuring timely detection of high-occupancy storage units so that appropriate measures can be taken.

[0053] Step S33: Extract environmental parameter data from the standardized state dataset, and perform anomaly detection on the environmental parameter data according to the preset normal range of environmental parameters to determine the abnormal distribution area of ​​environmental parameters.

[0054] In one embodiment, environmental parameter data may include temperature, humidity, and light intensity values. After extracting this data from a standardized state dataset, it needs to be compared with preset normal ranges for environmental parameters. These preset normal ranges can be set according to the storage requirements of the goods and the actual conditions of the warehouse. For example, for a warehouse storing electronic components, the temperature range is set to 20°C - 25°C, and the humidity range is set to 40% - 60%. When the environmental parameters of a certain area exceed these ranges, that area is determined to be an area with abnormal environmental parameter distribution.

[0055] In one embodiment, an environmental parameter anomaly detection model can be constructed. This model employs machine learning algorithms to monitor and analyze environmental parameter data in real time. Based on a preset normal range, the model automatically identifies abnormal data points and uses spatial analysis techniques to determine the distribution areas of abnormal environmental parameters. This approach improves the accuracy and timeliness of anomaly detection, ensuring the safety of the storage environment for goods.

[0056] Step S34: Extract inbound and outbound operation records from the standardized state dataset, count the number of inbound and outbound operations in each time period, and generate a frequency distribution map of inbound and outbound operations.

[0057] In this embodiment, the inbound / outbound operation records contain information such as operation timestamps and operator identifiers, serving as the foundational data for analyzing the frequency of inbound / outbound operations. After extracting these records from the standardized status dataset, they need to be processed according to the time dimension. The division of time periods can be based on actual needs, such as by hour, half-day, or day. By counting the inbound / outbound operation records within each time period, the number of inbound / outbound operations within that time period can be obtained.

[0058] A frequency distribution chart of inbound and outbound operations is a graphical representation of the frequency of these operations across different time periods. It helps managers clearly understand the patterns of warehouse inventory flow, such as peak and off-peak periods. This facilitates the rational allocation of personnel and resources, improving warehouse operational efficiency.

[0059] In one embodiment, data analysis software can be used to generate a frequency distribution chart of inbound and outbound operations. First, the extracted inbound and outbound operation records are imported into the software, and the data is grouped and counted according to time periods. Then, an appropriate chart type, such as a bar chart or line chart, is selected to visually display the number of inbound and outbound operations within each time period. The software can also beautify and adjust the charts as needed to make them clearer and easier to understand.

[0060] Step S35: Integrate storage unit occupancy data, abnormal distribution area data of environmental parameters, and distribution map of inbound and outbound operation frequency to generate the operational status assessment results of the industrial warehouse.

[0061] In this embodiment, integrating different types of data is for the purpose of comprehensively and holistically evaluating the operational status of the industrial warehouse. Storage unit occupancy data reflects the utilization of warehouse space, data on abnormal distribution areas of environmental parameters reflects the stability of the warehouse environment, and the distribution map of inbound and outbound operation frequencies shows the patterns of goods flow. Integrating these three types of data allows for the analysis and evaluation of the warehouse's operational status from multiple dimensions.

[0062] An industrial warehouse operational status assessment is a comprehensive set of information, which may include storage unit occupancy rates, areas of abnormal environmental parameter distribution, and the frequency distribution of inbound and outbound operations. This assessment helps managers gain a complete understanding of the warehouse's operational status, identify potential problems and risks, and develop corresponding management strategies.

[0063] In one embodiment, reference Figure 4 Step S40 may include steps S41-S44, which will be described in detail below: Step S41: For the set of storage units with an occupancy rate higher than the first threshold, calculate the cargo transfer priority value for each storage unit and generate a cargo scheduling plan based on the priority value.

[0064] In this embodiment, the cargo transfer priority value is an indicator that measures the urgency of cargo transfer in each storage unit. For a set of storage units with an occupancy rate higher than a first threshold, calculating the cargo transfer priority value requires comprehensive consideration of multiple factors, such as the difficulty of cargo handling, the remaining available space in the storage unit, and the importance of the cargo. Based on the calculated priority value, the order of cargo transfer can be determined, thereby generating a reasonable cargo scheduling plan.

[0065] In one embodiment, reference Figure 5 Step S41 may include steps S411-S414, which will be described in detail below: Step S411: For the set of storage units with an occupancy rate higher than the first threshold, obtain the cargo handling path information for each storage unit, and calculate the path complexity value of cargo handling based on the path information.

[0066] In this embodiment, the cargo handling path information refers to the specific path from the storage unit to the target storage location, including the starting point coordinates, the ending point coordinates, and the distribution of obstacles along the path. Calculating the path complexity value based on the path information quantifies the difficulty of cargo handling, providing an important basis for subsequent cargo transfer priority calculations.

[0067] In this embodiment of the application, calculating the path complexity value helps to accurately assess the difficulty of cargo handling, thereby arranging the cargo transfer sequence more reasonably.

[0068] In one embodiment, a 3D map of the warehouse and a path planning algorithm can be used to obtain goods handling path information. First, the location of each storage unit and the target storage location are marked on the 3D map of the warehouse. Then, the optimal handling path is calculated using a path planning algorithm. When calculating the path complexity value, factors such as path length, the number and type of obstacles can be considered. For example, if there are many obstacles on the path, or if the path is long, the path complexity value will be higher.

[0069] In one embodiment, step S411 can be implemented as follows: A1: For a set of storage units with an occupancy rate higher than the first threshold, extract the cargo handling path information corresponding to each storage unit from the layout diagram of the industrial warehouse. The cargo handling path information includes the starting point coordinates, the ending point coordinates, and the distribution of obstacles on the path.

[0070] In this embodiment, the layout map of the industrial warehouse is a graphic file that details the internal structure and facility locations of the warehouse. Extracting cargo handling path information from the layout map allows for accurate identification of the specific path from each storage unit to the target storage location. The start and end coordinates clearly define the starting and ending positions of cargo handling, while the distribution of obstacles along the path reflects potential obstacles encountered during the handling process.

[0071] In one embodiment, computer-aided design (CAD) software or geographic information system (GIS) can be used to process the layout map of the industrial warehouse. These software programs have powerful graphics processing and data analysis capabilities, enabling them to accurately extract information such as start-point coordinates, end-point coordinates, and obstacle distribution from the layout map. For example, in CAD software, a path between two points can be automatically generated by marking storage units and target storage locations, and obstacles along the path can be identified.

[0072] A2: Calculate the straight-line distance and actual path length based on the Euclidean distance and Manhattan distance between the starting and ending coordinates.

[0073] In this embodiment, Euclidean distance refers to the straight-line distance between two points in a Cartesian coordinate system, reflecting the shortest distance between the starting point and the ending point. Manhattan distance, on the other hand, refers to the distance traveled along the grid lines from one point to another in a city block grid, better reflecting the actual path length. By calculating these two distances, the length of the goods handling path can be evaluated from different perspectives.

[0074] In one embodiment, mathematical formulas can be used to calculate the Euclidean and Manhattan distances. Assuming the starting point coordinates are (x1, y1) and the ending point coordinates are (x2, y2), the Euclidean distance is calculated as: d_euclidean = √((x2 - x1)^2 + (y2 - y1)^2); the Manhattan distance is calculated as: d_manhattan = |x2 - x1| +|y2 - y1|. Based on the calculation results, reference values ​​for the straight-line distance and actual path length can be obtained.

[0075] A3: Count the number of obstacles on the path, and query the preset obstacle influence weight table according to the obstacle type to determine the influence weight value of each obstacle.

[0076] In this embodiment, obstacles along the path increase the difficulty and risk of goods handling. Counting the number of obstacles provides a clear understanding of the path's complexity, while determining the impact weight value based on obstacle type allows for a more accurate assessment of the impact of each obstacle on goods handling. The preset obstacle impact weight table is developed based on the characteristics of different obstacles and their degree of impact on handling.

[0077] In this embodiment, determining the impact weight value of each obstacle helps to more comprehensively and accurately assess path complexity. From a technical perspective, it provides more detailed parameters for path complexity calculation, improving the scientific rigor of cargo transfer priority assessment.

[0078] In one embodiment, obstacles along the path can be marked on the warehouse layout map and categorized statistically. Then, based on the type of obstacle, such as shelves, pillars, or equipment, a preset obstacle influence weight table is consulted to obtain the influence weight value for each type of obstacle. For example, large shelves may have a greater impact on handling, and their influence weight value may be higher; while small pillars have a relatively smaller impact, and their influence weight value may be lower.

[0079] A4: Calculate the path complexity value based on the actual path length, the number of obstacles, and the influence weight of each obstacle. The path complexity value is the weighted sum of the actual path length and the number of obstacles and their influence weights.

[0080] In this embodiment, the path complexity value comprehensively considers the path length and the impact of obstacles. By weighted summing the actual path length, the number of obstacles, and the impact weight of each obstacle, a value that accurately reflects the path complexity can be obtained. The higher this value, the greater the difficulty of goods handling.

[0081] In this embodiment, calculating the path complexity value helps to accurately assess the difficulty of cargo handling and provides an important basis for calculating cargo transfer priorities. From a technical perspective, this improves the rationality and efficiency of cargo scheduling and reduces time and cost consumption during the handling process.

[0082] In one embodiment, the path complexity value can be calculated using the following formula: Path complexity value = Actual path length + Number of obstacles × ∑(Influence weight of each obstacle). For example, assuming the actual path length is 50 meters and there are 3 obstacles on the path, namely a shelf (influence weight of 0.8), a pillar (influence weight of 0.3), and equipment (influence weight of 0.6), then the path complexity value = 50 + 3 × (0.8 + 0.3 + 0.6) = 50 + 3 × 1.7 = 55.1.

[0083] Step S412: Based on the path complexity value, remaining available space value, transfer difficulty coefficient, and cargo priority weight value, construct a cargo transfer priority optimization model with multi-dimensional constraints.

[0084] In this embodiment, the path complexity value reflects the ease or difficulty of goods handling, the remaining available space value reflects the idle status of the storage unit, the transfer difficulty coefficient considers the characteristics of the goods themselves and other factors during the handling process, and the goods priority weight value is set according to factors such as the importance and timeliness of the goods. By combining these factors, a multi-dimensional constraint-based goods transfer priority optimization model is constructed, which can more comprehensively and accurately evaluate the transfer priority of goods in each storage unit.

[0085] In this embodiment, constructing a cargo transfer priority optimization model can improve the scientific rigor and rationality of cargo transfer decisions. From a technical perspective, it helps optimize cargo scheduling schemes, improve warehouse space utilization efficiency, and increase cargo turnover speed.

[0086] In one embodiment, optimization algorithms such as linear programming or genetic algorithms can be used to construct the model. First, the weight coefficients of each factor are determined, and then a mathematical model is established based on these coefficients and their corresponding values. By solving this model, the cargo transfer priority value for each storage unit can be obtained. For example, in a genetic algorithm, the model parameters are continuously optimized by simulating the process of biological evolution until the optimal cargo transfer priority scheme is found.

[0087] Step S413: Using the cargo transfer priority optimization model, calculate the cargo transfer priority value of each storage unit. The priority value is a weighted sum of the path complexity value, the remaining available space value, the transfer difficulty coefficient, and the cargo priority weight value.

[0088] In this embodiment, the cargo transfer priority optimization model comprehensively considers multiple factors. By calculating the cargo transfer priority value for each storage unit using this model, the impact of these factors can be quantified into a specific numerical value. The weighted summation method can assign different weights based on the importance of each factor, making the priority value more accurately reflect the urgency of cargo transfer.

[0089] In this embodiment, calculating the cargo transfer priority value provides a clear order and basis for cargo scheduling. Technically, this helps improve the efficiency and accuracy of cargo scheduling, avoiding resource waste caused by blind scheduling.

[0090] In one embodiment, the path complexity value, remaining available space value, transfer difficulty coefficient, and cargo priority weight value can be input into the optimization model and weighted summed according to pre-set weight coefficients. For example, assuming the weight of the path complexity value is 0.3, the weight of the remaining available space value is 0.2, the weight of the transfer difficulty coefficient is 0.3, and the weight of the cargo priority weight value is 0.2, the cargo transfer priority value can be obtained by multiplying the values ​​of each factor by their respective weights and then summing them.

[0091] Step S414: Sort the goods in descending order of their transfer priority value to generate the final goods scheduling plan.

[0092] In this embodiment, goods are arranged in descending order of transfer priority value to determine the order of transfer. Goods in storage units with higher priority values ​​will be transferred first, ensuring that goods that need to be transferred more urgently are processed first within limited resources and time. Generating a final goods scheduling plan based on the arrangement result guarantees the rationality and effectiveness of goods scheduling.

[0093] In one embodiment, a sorting algorithm can be used to sort the cargo transfer priority values ​​in descending order. The sorting results are compiled into a table containing information such as the storage unit number, cargo information, and transfer order. Based on this table, a final cargo scheduling plan is generated, including information such as cargo handling routes, handling times, and handling personnel. For example, forklifts and other handling equipment can be arranged to transfer cargo in order of priority.

[0094] Step S42: For areas with abnormal distribution of environmental parameters, determine the type of environmental parameter corresponding to each abnormal distribution area, and generate control instructions according to preset control rules.

[0095] In this embodiment, the abnormal distribution areas of environmental parameters may involve different types of environmental parameter anomalies, such as excessively high temperature or excessively low humidity. Determining the type of environmental parameter corresponding to each abnormal distribution area is a prerequisite for generating control instructions. The preset control rules are a series of operating guidelines formulated based on different types and degrees of anomalies of environmental parameters. According to these rules, the corresponding control equipment and control parameters can be determined.

[0096] In this embodiment, the generated control commands can promptly correct abnormal environmental parameters, ensuring the safety of the storage environment for goods. From a technical perspective, this helps reduce damage to goods caused by environmental factors and improves the quality of goods storage.

[0097] In one embodiment, an environmental parameter control rule library can be established, storing control rules corresponding to various environmental parameter types and degrees of anomalies. Once the environmental parameter type corresponding to an abnormal distribution area is determined, the corresponding control device identifier and control parameter range are obtained by querying the control rule library. Then, control instructions are generated for each abnormal distribution area based on this information. For example, if the temperature in a certain area is too high, the control instruction might be to turn on the air conditioner and set the temperature to a suitable range.

[0098] In one embodiment, step S42 can be implemented in the following manner, which will be described in detail below: B1: For areas with abnormal distribution of environmental parameters, determine the type of environmental parameter that exceeds the preset normal range in each abnormal distribution area.

[0099] In this embodiment, the abnormal distribution area of ​​environmental parameters refers to the area in the warehouse where the environmental parameters do not conform to the preset normal range. Identifying the type of environmental parameter exceeding the normal range in each abnormal distribution area is crucial for developing targeted control measures. Different environmental parameter anomalies may require different control equipment and methods; therefore, accurately identifying the type of abnormal parameter is essential.

[0100] In one embodiment, the type of abnormal parameter can be determined by real-time monitoring and analysis of environmental parameter data. Environmental sensors are installed in each abnormal distribution area to continuously collect environmental parameter data such as temperature, humidity, and light intensity. The collected data is compared with preset normal range intervals to identify the types of parameters that exceed the range. For example, if the temperature data for a certain area exceeds the normal range, while the humidity and light intensity data are normal, then the abnormal environmental parameter type for that area can be determined to be temperature.

[0101] B2: Based on the environmental parameter type, query the preset control rule table to determine the control equipment identifier and control parameter range corresponding to the environmental parameter type.

[0102] In this embodiment, the preset control rule table is a series of operational guidelines developed based on different environmental parameter types and actual warehouse conditions. It details the control measures to be taken for each type of environmental parameter anomaly, including the control equipment used and the corresponding control parameter range. By querying this table, the control plan for a specific type of environmental parameter anomaly can be quickly and accurately determined.

[0103] In this embodiment, querying the control rule table to determine the control equipment identifier and parameter range provides a clear operational basis for environmental control. From a technical perspective, this helps standardize environmental control operations, improve control effectiveness, and reduce losses to goods caused by environmental anomalies.

[0104] In one embodiment, a preset control rule table can be stored in a database. Once the type of abnormal environmental parameter is determined, a database query is used to retrieve the corresponding control device identifier and control parameter range from the control rule table, based on the environmental parameter type as the query condition. For example, if the abnormal environmental parameter type is excessively high temperature, the query rule table might retrieve the control device identifier as an air conditioner, with a control parameter range of adjusting the temperature to 20°C - 25°C.

[0105] B3: Based on the control device identifier and control parameter range, generate control instructions for each abnormal distribution area.

[0106] In this embodiment, the control command is a specific instruction that guides the control equipment to operate. Based on the determined control equipment identifier and control parameter range, the generated control command ensures that the control equipment adjusts the abnormal environmental parameters as required. The control command for each abnormal distribution area is customized according to the specific abnormal situation and corresponding control scheme of that area.

[0107] For example, for the aforementioned abnormally high temperature distribution area, the generated control command might be "Turn on the air conditioner numbered ABC and set the temperature to 22℃". The generated control command will be sent to the corresponding control equipment control system to execute the environmental control operation.

[0108] Step S43: Based on the frequency distribution chart of inbound and outbound operations, calculate the peak time periods for inbound and outbound operations, determine the required number of personnel based on the number of operations during the peak time periods, and generate a personnel allocation plan.

[0109] In this embodiment, the frequency distribution chart of inbound and outbound operations can intuitively display the frequency of these operations within different time periods. By analyzing the frequency distribution chart, peak periods for inbound and outbound operations can be identified. Based on the number of operations during peak periods and preset individual operation efficiency parameters, the required number of personnel for that period can be calculated. The personnel allocation plan then rationally arranges the work tasks of staff in different time periods based on the calculated number of personnel.

[0110] In this embodiment, the personnel allocation scheme can optimize personnel configuration and improve personnel work efficiency. From a technical perspective, it helps avoid operational delays caused by insufficient personnel during peak periods, while preventing personnel idleness during off-peak periods, thus reducing labor costs.

[0111] In one embodiment, reference Figure 6 Step S43 may include steps S431-S434, which will be described in detail below. Step S431: Extract the number of operations in each time period from the frequency distribution map of inbound and outbound operations, and generate an operation number sorting table by sorting the operation number in descending order.

[0112] In this embodiment, the frequency distribution map of inbound and outbound operations visually displays the frequency of these operations within different time periods. Extracting the number of operations within each time period from this map provides specific operation data. Generating an operation frequency sorting table by descending order of operation frequency helps quickly identify peak and off-peak periods for inbound and outbound operations, providing data support for subsequent personnel allocation.

[0113] In one embodiment, data analysis software can be used to process the frequency distribution chart of inbound and outbound operations. The software can automatically identify and extract the number of operations corresponding to each time period in the chart. Then, a sorting algorithm is used to sort the number of operations in descending order, generating a sorted table of operation counts. For example, if a day is divided into 24 time periods, the software will extract the number of operations for each time period and arrange them in descending order to form a table containing the time periods and the number of operations.

[0114] Step S432: Determine the set of peak time periods for inbound and outbound operations according to the preset peak time period determination rules. The set of peak time periods includes all time periods in which the number of operations exceeds the second threshold.

[0115] In this embodiment, the preset peak period determination rule is formulated based on historical warehouse data and operational experience. The second threshold is a pre-set operation frequency standard used to determine whether a certain time period is a peak period. By comparing the operation frequency of each time period with the second threshold, the set of peak time periods for inbound and outbound operations can be determined.

[0116] In one embodiment, the second threshold is assumed to be set to 50 times. In the operation count sorting table, the number of operations for each time period is compared to 50. If the number of operations for a given time period exceeds 50, that time period is included in the peak time period set. For example, if the number of operations from 9:00 AM to 10:00 AM is 60, that time period will be identified as a peak time period.

[0117] Step S433: For each time period in the set of peak time periods, calculate the minimum number of personnel required for that time period. The minimum number of personnel is calculated based on the number of operations and a preset single-person operation efficiency parameter.

[0118] In this embodiment, the preset single-person operation efficiency parameter refers to the number of inbound and outbound operations that a worker can complete per unit of time. For each time period in the peak time period set, the minimum number of personnel required can be calculated based on the number of operations during that time period and the single-person operation efficiency parameter. This helps to rationally allocate personnel and ensure that there are sufficient manpower to complete inbound and outbound operations during peak periods.

[0119] In one embodiment, assuming the number of operations during a peak period is 80, and the preset single-person operation efficiency parameter is 20 operations / hour, then the minimum number of personnel required during this period is 80 ÷ 20 = 4 people.

[0120] In one embodiment, step S433 can be implemented as follows: D1: For each time period in the peak time period set, extract the number of operations within that time period from the inbound / outbound operation frequency distribution map, and query the preset single-person operation efficiency parameter table based on the number of operations to obtain the single-person operation efficiency value for that time period.

[0121] In this embodiment, the preset single-person operation efficiency parameter table is formulated based on different operation frequency ranges and the actual operation capabilities of the staff. Different operation frequencies may correspond to different single-person operation efficiency values ​​because when the number of operations is high, the staff may be affected by factors such as fatigue and stress, and the operation efficiency will change. Extracting the number of operations for each peak time period from the inbound and outbound operation frequency distribution map and querying the table to obtain the corresponding single-person operation efficiency value can more accurately calculate the required number of personnel.

[0122] In one embodiment, assuming a preset table of single-person operation efficiency parameters specifies that when the number of operations is between 30 and 50, the single-person operation efficiency value is 15 times / hour; when the number of operations is between 51 and 80, the single-person operation efficiency value is 12 times / hour. If the number of operations during a peak period is 60, the single-person operation efficiency value for that period can be obtained by querying the table, which is 12 times / hour.

[0123] D2: Based on the number of operations and the single-person operation efficiency value, calculate the theoretical number of personnel required in this time period. The theoretical number of personnel is the result of rounding up the ratio of the number of operations to the single-person operation efficiency value.

[0124] In this embodiment, rounding up is used to ensure that there are enough personnel to complete all inbound and outbound operations. Since the number of personnel must be an integer, and some personnel cannot complete all operations, the ratio of the number of operations to the efficiency of a single person is rounded up to obtain the theoretical number of personnel. This ensures that in actual operation, there will be no situation where operations cannot be completed on time due to insufficient personnel.

[0125] In one embodiment, if the number of operations during a peak period is 72, and the efficiency per person is 12 operations / hour, then the ratio of the number of operations to the efficiency per person is 72 ÷ 12 = 6. Since rounding up is not required, the theoretical number of personnel needed during this period is 6. If the number of operations is 75, the ratio is 75 ÷ 12 = 6.25, and after rounding up, the theoretical number of personnel is 7.

[0126] D3: Based on the actual number of available personnel in the industrial warehouse, determine the maximum number of personnel that can be allocated during this time period.

[0127] In this embodiment, the actual number of available personnel in the industrial warehouse is a limiting factor. Even if a larger number of personnel are theoretically needed, insufficient available personnel will prevent the demand from being met. Therefore, it is necessary to determine the maximum number of personnel that can be allocated in each time period based on the actual number of available personnel to ensure the feasibility of the personnel allocation plan.

[0128] In one embodiment, assuming that the theoretical number of personnel during a certain peak period is 8, but there are only 6 actually available personnel in the industrial warehouse, then the maximum number of personnel that can be allocated during that period is 6.

[0129] D4: Based on the theoretical number of personnel and the maximum number of personnel that can be allocated, determine the minimum number of personnel required for this time period. The minimum number of personnel is the smaller of the theoretical number of personnel and the maximum number of personnel that can be allocated.

[0130] In this embodiment, the minimum number of personnel is taken as the smaller of the theoretical number of personnel and the maximum number of personnel that can be allocated. This is to make the most rational use of personnel resources while meeting operational requirements. If the theoretical number of personnel is less than the maximum number of personnel that can be allocated, it means that there are enough personnel available, and allocation can be made according to the theoretical number of personnel. If the theoretical number of personnel is greater than the maximum number of personnel that can be allocated, then only the maximum number of personnel that can be allocated can be allocated.

[0131] In one embodiment, if the theoretical number of personnel during a peak period is 7 and the maximum number of personnel that can be allocated is 5, then the minimum number of personnel required during that period is 5. If the theoretical number of personnel is 4 and the maximum number of personnel that can be allocated is 6, then the minimum number of personnel is 4.

[0132] Step S434: Based on the minimum number of personnel in each time period in the peak time period set, and combined with the actual number of available personnel in the industrial warehouse, generate a personnel allocation scheme for the peak time period. The personnel allocation scheme includes specific personnel identifiers and their corresponding work time period arrangements.

[0133] In this embodiment, by combining the minimum number of personnel in each peak time period with the actual number of available personnel in the industrial warehouse, a personnel allocation plan that conforms to the actual situation can be formulated. The personnel allocation plan clarifies the work arrangements for specific personnel during different peak time periods, ensuring that personnel can be reasonably divided and efficiently complete inbound and outbound operations.

[0134] In one embodiment, a personnel scheduling algorithm can be used to generate a personnel allocation scheme. First, preliminary personnel allocation is performed based on the minimum number of personnel and the actual number of available personnel for each peak time period. Then, the allocation scheme is adjusted and optimized by considering factors such as personnel skill level, work experience, and work preferences. For example, experienced personnel are assigned to peak time periods with higher operational difficulty. The final generated personnel allocation scheme will clearly identify each personnel and their corresponding working time periods, such as "Zhang San, 9:00 AM - 11:00 AM; Li Si, 10:00 AM - 12:00 PM," etc.

[0135] In one embodiment, step 434 can be implemented as follows: E1: Determine the candidate personnel set for each time period based on the minimum number of personnel in each time period within the peak time period set, combined with the actual number of available personnel in the industrial warehouse.

[0136] In this embodiment, the candidate personnel set is determined by combining the minimum number of personnel in each time period during peak hours with the actual number of available personnel in the industrial warehouse. This is to select suitable personnel from the actual available personnel for each time period while meeting personnel needs. Different time periods may have different personnel requirements; filtering based on the minimum number of personnel ensures that there are enough personnel available for each time period.

[0137] In one embodiment, assuming the minimum number of personnel during a peak period is 3, and there are actually 10 available personnel in the industrial warehouse, 3-5 people can be selected from these 10 as a candidate set for that period based on factors such as skill level, work experience, and current work status. For example, priority can be given to personnel with skilled expertise and a relatively low recent workload.

[0138] E2: For each time period's set of candidates, calculate the comprehensive suitability value for each candidate based on their work efficiency level and fatigue recovery time.

[0139] In this embodiment, the work efficiency level reflects the candidate's work ability and operational proficiency, while the fatigue recovery time considers the employee's recovery ability after work. Calculating the overall fit score for each candidate by combining these two factors allows for a more comprehensive assessment of the candidate's suitability for the work during that time period. Employees with high work efficiency and short fatigue recovery times may have higher overall fit scores.

[0140] In one embodiment, weights can be assigned to work efficiency level and fatigue recovery time respectively. Assume the weight of work efficiency level is 0.6 and the weight of fatigue recovery time is 0.4. Work efficiency level is divided into three levels: high, medium, and low, corresponding to scores of 3, 2, and 1 respectively; fatigue recovery time is measured in hours, with shorter recovery times resulting in higher scores. For example, if a candidate has a high work efficiency level (3 points) and a fatigue recovery time of 2 hours (assuming a corresponding score of 4 points), their overall fit value is 3 × 0.6 + 4 × 0.4 = 3.4.

[0141] E3: Based on the candidates' overall fit value, generate a candidate ranking table by sorting the candidates in descending order of their overall fit value.

[0142] In this embodiment, a candidate ranking table is generated by sorting candidates in descending order of their overall suitability scores. This clearly demonstrates the order of suitability of each candidate for the work during that time period. Candidates ranked higher are more suitable for the work during that time period, providing a clear basis for subsequent personnel selection.

[0143] In one embodiment, a sorting algorithm can be used to sort the candidates' overall fitness values ​​in descending order. The sorting results are compiled into a table, which contains the candidate's identifier and overall fitness value. For example, if there are candidates A, B, and C with overall fitness values ​​of 3.4, 2.8, and 3.1 respectively, then the order in the sorting table would be A (3.4), C (3.1), and B (2.8).

[0144] E4: Select candidates from the candidate ranking list whose number matches the minimum number of personnel, assign them to the corresponding time slots, and record the specific personnel identification and their corresponding work time slot arrangements.

[0145] In this embodiment, selecting suitable candidates from the candidate ranking table based on the minimum number of personnel and assigning them to the corresponding time slots ensures that there are enough suitable personnel to work during those time slots. Recording specific personnel identifiers and their corresponding work time slots facilitates personnel management and scheduling, and also facilitates subsequent performance evaluation and accountability.

[0146] In one embodiment, if the minimum number of people during a certain peak time period is 2, and candidates A and C are ranked first and second in the candidate ranking list, then A and C are assigned to that time period. Record "Candidate A, 10:00 AM - 12:00 PM; Candidate C, 10:00 AM - 12:00 PM".

[0147] E5: Integrate the personnel allocation results of all time periods into a personnel allocation plan for peak time periods.

[0148] In this embodiment, the personnel allocation results for each peak time period are integrated into a complete personnel allocation scheme, providing warehouse managers with a comprehensive personnel arrangement plan. This scheme covers personnel allocation for all peak time periods, facilitating unified management and coordination of personnel work.

[0149] In one embodiment, the personnel allocation records for each peak time period are compiled into a table or document, including information such as time period, personnel identification, and work arrangement. For example, taking the peak time periods of a day as an example, the personnel allocation results for each time period, such as 9:00-11:00 AM and 2:00-4:00 PM, are integrated to form a complete peak time period personnel allocation scheme.

[0150] Step S44: Integrate the cargo scheduling plan, control instructions, and personnel allocation scheme into an optimized management strategy table.

[0151] In this embodiment, the optimized management strategy table is a comprehensive management solution that integrates cargo scheduling plans, control instructions, and personnel allocation schemes, providing comprehensive guidance for the management of industrial warehouses. By integrating these schemes, the coordination and consistency among various management measures can be ensured, thereby improving the overall management efficiency of the warehouse.

[0152] In this embodiment, generating an optimized management strategy table provides a unified operational guide for AI management of industrial warehouses based on status data. Technically, this helps to achieve more scientific, standardized, and refined warehouse management, thereby improving warehouse operational efficiency and economic benefits.

[0153] In one embodiment, spreadsheets or database management systems can be used to integrate these plans. Cargo scheduling plans, control instructions, and personnel allocation plans are organized into separate tables, and then merged into an optimization management strategy table. Different columns can be set in the table to distinguish different plan contents, and necessary explanations and annotations can be added for managers to view and implement.

[0154] Accordingly, to better implement the above methods, this application also provides an AI management system for industrial warehouses based on status data. For example... Figure 7 As shown, the AI ​​management system 80 for industrial warehouses based on status data includes: The acquisition module 801 is used to acquire the status data of each storage unit in the industrial warehouse during the first monitoring period. The status data includes environmental parameters, goods storage location information and inbound / outbound operation records within the storage unit. The environmental parameters include temperature, humidity and light intensity values. The goods storage location information includes shelf number and storage location number. The inbound / outbound operation records include operation timestamp and operator identification. Data processing module 802 is used to perform data cleaning and classification on the state data to generate a standardized state dataset; The status assessment module 803 is used to assess the operating status of the industrial warehouse based on the standardized status dataset and through a preset data analysis model to obtain the operating status assessment results. The operating status assessment results include the occupancy rate of storage units, the abnormal distribution areas of environmental parameters, and the frequency distribution of inbound and outbound operations. The strategy generation module 804 is used to generate an optimization management strategy table for the first monitoring period based on the operation status evaluation results. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies. The sending module 805 is used to send the optimization management strategy table to the management system of the industrial warehouse, so as to instruct the management system to perform corresponding management operations according to the optimization management strategy table in the second monitoring cycle.

[0155] The implementation details of each module are provided in the preceding method embodiments and will not be repeated here. The technical effects achieved by each module and device are described in the foregoing method embodiments.

[0156] like Figure 8 As shown, this application embodiment also provides a computer device 90, which includes a processor 901 and a memory 902, wherein the memory 902 stores a computer program, and when the computer program is executed by the processor 901, the processor 901 performs the steps of any of the methods described above.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or otherwise.

[0158] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application are still within the scope of this application.

Claims

1. An AI management method for industrial warehouses based on state data, characterized in that, Includes the following steps: The status data of each storage unit in the industrial warehouse during the first monitoring period is obtained. The status data includes environmental parameters, goods storage location information and inbound / outbound operation records within the storage unit. The environmental parameters include temperature, humidity and light intensity values. The goods storage location information includes shelf number and storage location number. The inbound / outbound operation records include operation timestamp and operator identification. The state data is cleaned and classified to generate a standardized state dataset; Based on the standardized status dataset, the operating status of the industrial warehouse is evaluated through a preset data analysis model to obtain the operating status evaluation results. The operating status evaluation results include the occupancy rate of storage units, the abnormal distribution areas of environmental parameters, and the frequency distribution of inbound and outbound operations. Based on the operational status assessment results, an optimization management strategy table for the first monitoring period is generated. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies. The optimized management strategy table is sent to the industrial warehouse management system to instruct the management system to perform corresponding management operations based on the optimized management strategy table during the second monitoring cycle.

2. The method according to claim 1, characterized in that, Based on the standardized status dataset, the operational status of the industrial warehouse is evaluated using a pre-defined data analysis model to obtain the operational status evaluation results, including the following steps: Extract storage unit occupancy data from the standardized state dataset and calculate the occupancy value for each storage unit; Based on storage cell occupancy data, determine the set of storage cells with an occupancy rate higher than the first threshold; Environmental parameter data is extracted from a standardized state dataset, and anomaly detection is performed on the environmental parameter data according to a preset normal range of environmental parameters to determine the abnormal distribution area of ​​environmental parameters. Extract inbound and outbound operation records from the standardized state dataset, count the number of inbound and outbound operations within each time period, and generate a frequency distribution map of inbound and outbound operations. By integrating storage unit occupancy data, abnormal distribution data of environmental parameters, and distribution maps of inbound and outbound operation frequencies, an operational status assessment result for the industrial warehouse is generated.

3. The method according to claim 2, characterized in that, Based on the operational status assessment results, an optimization management strategy table for the first monitoring period is generated, including the following steps: For a set of storage units with an occupancy rate higher than the first threshold, calculate the cargo transfer priority value for each storage unit and generate a cargo scheduling plan based on the priority value; For areas with abnormal distribution of environmental parameters, determine the type of environmental parameter corresponding to each abnormal distribution area, and generate control instructions according to preset control rules; Based on the frequency distribution chart of inbound and outbound operations, the peak time periods for inbound and outbound operations are statistically analyzed, and the required number of personnel is determined based on the number of operations during the peak time periods, generating a personnel allocation plan. The cargo scheduling plan, control instructions, and personnel allocation scheme are integrated into an optimized management strategy table.

4. The method according to claim 3, characterized in that, For a set of storage units with an occupancy rate exceeding a first threshold, calculate the cargo transfer priority value for each storage unit and generate a cargo scheduling plan based on the priority value, including the following steps: For a set of storage units with an occupancy rate higher than the first threshold, obtain the cargo handling path information for each storage unit, and calculate the path complexity value of cargo handling based on the path information; Based on path complexity, remaining available space, transfer difficulty coefficient, and cargo priority weight, a cargo transfer priority optimization model with multi-dimensional constraints is constructed. Using the aforementioned cargo transfer priority optimization model, the cargo transfer priority value of each storage unit is calculated. The priority value is a weighted sum of the path complexity value, the remaining available space value, the transfer difficulty coefficient, and the cargo priority weight value. The goods are sorted in descending order of transfer priority to generate the final cargo scheduling plan.

5. The method according to claim 4, characterized in that, For a set of storage units with an occupancy rate exceeding a first threshold, obtaining the goods handling path information for each storage unit and calculating the path complexity value for goods handling includes the following steps: For a set of storage units with an occupancy rate higher than a first threshold, the cargo handling path information corresponding to each storage unit is extracted from the layout diagram of the industrial warehouse. The cargo handling path information includes the starting point coordinates, the ending point coordinates, and the distribution of obstacles on the path. Calculate the straight-line distance and actual path length based on the Euclidean distance and Manhattan distance between the starting and ending coordinates. The system counts the number of obstacles on the path and queries a pre-defined obstacle influence weight table based on the obstacle type to determine the influence weight value of each obstacle. The path complexity value is calculated based on the actual path length, the number of obstacles, and the influence weight of each obstacle. The path complexity value is the weighted sum of the actual path length and the number of obstacles and their influence weights.

6. The method according to claim 3, characterized in that, For areas with abnormal distribution of environmental parameters, determine the type of environmental parameter corresponding to each abnormal distribution area, and generate control instructions according to preset control rules, including the following steps: For areas with abnormal distribution of environmental parameters, identify the types of environmental parameters that exceed the preset normal range in each abnormal distribution area; Based on the type of environmental parameter, query the preset control rule table to determine the control equipment identifier and control parameter range corresponding to the type of environmental parameter; Based on the control device identifier and control parameter range, control instructions are generated for each abnormal distribution area.

7. The method according to claim 3, characterized in that, Based on the frequency distribution chart of inbound and outbound operations, peak periods for these operations are identified. The required number of personnel is then determined according to the number of operations during these peak periods to generate a personnel allocation plan. This includes the following steps: Extract the number of operations within each time period from the frequency distribution map of inbound and outbound operations, and generate an operation number sorting table by sorting the operation number in descending order; According to the preset peak period determination rules, the set of peak time periods for inbound and outbound operations is determined, and the set of peak time periods includes all time periods in which the number of operations exceeds the second threshold. For each time period in the set of peak time periods, calculate the minimum number of personnel required for that time period. The minimum number of personnel is calculated based on the number of operations and a preset single-person operation efficiency parameter. Based on the minimum number of personnel in each time period of the peak time period set, and combined with the actual number of available personnel in the industrial warehouse, a personnel allocation scheme for the peak time period is generated. The personnel allocation scheme includes specific personnel identifiers and their corresponding work time period arrangements.

8. The method according to claim 7, characterized in that, For each time period in the set of peak time periods, calculate the minimum number of personnel required for that time period, including the following steps: For each time period in the peak time period set, extract the number of operations within that time period from the inbound and outbound operation frequency distribution map, and query the preset single-person operation efficiency parameter table based on the number of operations to obtain the single-person operation efficiency value for that time period. Based on the number of operations and the single-person operation efficiency value, calculate the theoretical number of personnel required in this time period. The theoretical number of personnel is the result of rounding up the ratio of the number of operations to the single-person operation efficiency value. Based on the actual number of available personnel in the industrial warehouse, determine the maximum number of personnel that can be allocated during this time period; Based on the theoretical number of personnel and the maximum number of personnel that can be allocated, determine the minimum number of personnel required for the time period. The minimum number of personnel is the smaller of the theoretical number of personnel and the maximum number of personnel that can be allocated.

9. The method according to claim 8, characterized in that, Based on the minimum number of personnel in each time period of the peak time period set, and combined with the actual number of available personnel in the industrial warehouse, the personnel allocation plan for peak time periods is generated, including the following steps: Based on the minimum number of personnel in each time period within the peak time period set, and combined with the actual number of available personnel in the industrial warehouse, determine the candidate personnel set for each time period. For each set of candidates in each time period, calculate the comprehensive suitability value for each candidate based on their work efficiency level and fatigue recovery time. Based on the candidates' overall fit value, a candidate ranking table is generated by sorting the candidates in descending order of their overall fit value. Select candidates from the candidate ranking list whose number matches the minimum number of personnel, assign them to the corresponding time slots, and record the specific personnel identification and their corresponding work time slot arrangements; The personnel allocation results for all time periods are integrated into a personnel allocation plan for peak time periods.

10. An AI management system for an industrial warehouse based on state data, characterized in that, The system includes: The acquisition module is used to acquire the status data of each storage unit in the industrial warehouse during the first monitoring period. The status data includes environmental parameters, goods storage location information, and inbound / outbound operation records within the storage unit. The environmental parameters include temperature, humidity, and light intensity values. The goods storage location information includes shelf number and storage location number. The inbound / outbound operation records include operation timestamp and operator identification. The data processing module is used to clean and classify the state data to generate a standardized state dataset. The status assessment module is used to assess the operating status of the industrial warehouse based on the standardized status dataset and through a preset data analysis model to obtain the operating status assessment results, which include the occupancy rate of storage units, abnormal distribution areas of environmental parameters, and frequency distribution of inbound and outbound operations. The strategy generation module is used to generate an optimization management strategy table for the first monitoring period based on the operation status evaluation results. The optimization management strategy table includes a cargo scheduling plan for areas where the storage unit occupancy rate is higher than a first threshold, control instructions for areas with abnormal distribution of environmental parameters, and personnel allocation schemes for the distribution of inbound and outbound operation frequencies. The sending module is used to send the optimization management strategy table to the management system of the industrial warehouse, so as to instruct the management system to perform corresponding management operations according to the optimization management strategy table in the second monitoring cycle.

Images