Visualization-based warehouse management method, device and system

Abstract

The invention is suitable for the technical field of warehouse management, and provides a visualization-based warehouse management method, device and system, and the method comprises the steps: obtaining first warehouse data collected based on a sensor, enabling the first warehouse data to comprise environment parameters and cargo state information, carrying out the analysis of the first warehouse data, and obtaining a warehouse management result; and generating a data analysis result, and adjusting the objects in the warehouse according to the data analysis result, thereby maximizing space utilization. Besides, based on the first storage data and the data analysis result, a preset visual warehouse three-dimensional model is updated, a visual user interface is provided for warehouse management personnel, and the inventory state and the like can be easily checked.

Description

Technical Field

[0001] This application belongs to the technical field of warehouse management, and particularly relates to a visualization-based warehouse management method, device, and system. Background Art

[0002] Existing warehouse management systems often rely on shelves with fixed structures. In the face of seasonal goods or large fluctuations in inventory levels, this may lead to low space utilization. Summary of the Invention

[0003] Embodiments of this application provide a visualization-based warehouse management method, device, and system, which can adjust objects in the warehouse in real time to maximize space utilization, and provide an intuitive warehouse management user interface for warehouse managers to easily view inventory status, etc.

[0004] In a first aspect, embodiments of this application provide a visualization-based warehouse management method, including:

[0005] Obtain first warehouse data collected based on sensors; wherein, the first warehouse data includes environmental parameters and goods status information;

[0006] Analyze the first warehouse data to generate a data analysis result;

[0007] Adjust objects in the warehouse according to the data analysis result;

[0008] Update a preset visualized three-dimensional model of the warehouse based on the first warehouse data and the data analysis result.

[0009] In a possible implementation manner of the first aspect, the analyzing the first warehouse data to generate a data analysis result includes:

[0010] Predict the first warehouse data to generate second warehouse data;

[0011] Analyze the second warehouse data to generate the data analysis result.

[0012] In a possible implementation manner of the first aspect, before predicting the first warehouse data to generate second warehouse data, it further includes:

[0013] Pack the first warehouse data; wherein, the packed first warehouse data includes the first warehouse data and identification information corresponding to the first warehouse data; the identification information includes at least one of the following: sensor ID, timestamp;

[0014] Store the packed first warehouse data in a server.

[0015] In a possible implementation of the first aspect, the method further includes:

[0016] Create a three-dimensional model of the warehouse; wherein, the objects of the three-dimensional model of the warehouse include the warehouse, shelves, goods, and temperature;

[0017] Set attribute fields and identifiers for the objects of the three-dimensional model of the warehouse; wherein, the identifier matches the identification information;

[0018] Export the three-dimensional model of the warehouse as a model file and load the model file;

[0019] After establishing a connection between the client and the server, obtain the first warehousing data from the server;

[0020] Associate the obtained first warehousing data with the attribute fields in the three-dimensional model of the warehouse after loading the model file;

[0021] According to the associated first warehousing data, update the display of the three-dimensional model of the warehouse in real time;

[0022] Render the three-dimensional model of the warehouse and visualize the status of the warehouse on the client.

[0023] In a possible implementation of the first aspect, the method further includes:

[0024] Interact with the real-time updated three-dimensional model of the warehouse through the interface of the client.

[0025] In a possible implementation of the first aspect, the adjusting the objects in the warehouse according to the data analysis result includes:

[0026] According to the data analysis result, adjust at least one of the following: shelf height, shelf layout, temperature, humidity, transportation path, air conditioning parameters, replenishment strategy.

[0027] In a second aspect, an embodiment of the present application provides a warehousing management device based on visualization, including:

[0028] An acquisition module, configured to acquire first warehousing data collected based on sensors; wherein, the first warehousing data includes environmental parameters and goods status information;

[0029] A generation module, configured to analyze the first warehousing data and generate a data analysis result;

[0030] An adjustment module, configured to adjust the objects in the warehouse according to the data analysis result;

[0031] A display module, configured to update a preset visual three-dimensional model of a warehouse based on the first warehousing data and the data analysis result.

[0032] In a third aspect, an embodiment of the present application provides a visualization-based warehousing management system, including: a sensor, a data processing unit, a visualization modeling unit, a client, a server, and a central processing unit;

[0033] The sensor is configured to collect first warehousing data and send the first warehousing data to the data processing unit;

[0034] The data processing unit is configured to analyze the first warehousing data to generate a data analysis result, and generate an adjustment instruction based on the data analysis result; wherein, the adjustment instruction is used to adjust objects in the warehouse;

[0035] The server is configured to store the first warehousing data and the data analysis result;

[0036] The visualization modeling unit is configured to update a preset visual three-dimensional model of a warehouse based on the first warehousing data and the data analysis result;

[0037] The client is configured to visualize the state of the warehouse, and interact with the real-time updated three-dimensional model of the warehouse through the interface of the client;

[0038] The central processing unit is configured to coordinate the work of the data processing unit, the visualization modeling unit, the client, and the server.

[0039] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the visualization-based warehousing management method described in any item of the first aspect above is implemented.

[0040] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the visualization-based warehousing management method described in any item of the first aspect above is implemented.

[0041] In a sixth aspect, an embodiment of the present application provides a computer program product, and when the computer program product runs on a computer device, the computer device is enabled to execute the visualization-based warehousing management method described in any item of the first aspect above.

[0042] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: obtaining first warehousing data collected based on sensors, where the first warehousing data includes environmental parameters and cargo status information, analyzing the first warehousing data to generate a data analysis result, and adjusting objects in the warehouse according to the data analysis result, so as to maximize space utilization. In addition, based on the first warehousing data and the data analysis result, update a preset visual three-dimensional model of the warehouse to provide an intuitive user interface for warehouse managers, and they can easily view the inventory status, etc.

[0043] It can be understood that the beneficial effects of the second to sixth aspects above can refer to the relevant descriptions in the first aspect above, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 is a schematic flowchart of a visualization-based warehousing management method provided by an embodiment of the present application;

[0046] Figure 2 is a schematic flowchart of a visualization-based warehousing management method provided by another embodiment of the present application;

[0047] Figure 3 is a schematic structural diagram of a visualization-based warehousing management device provided by an embodiment of the present application;

[0048] Figure 4 is a schematic system diagram of a visualization-based warehousing management device provided by an embodiment of the present application;

[0049] Figure 5 is a schematic structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0051] It should be understood that when used in the specification and the appended claims of this application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0052] It should also be understood that the term "and / or" used in the specification and the appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0053] As used in the specification and the appended claims of this application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0054] In addition, in the description of the specification and the appended claims of this application, the terms "first", "second", "third", etc. are only used for differentiating descriptions and cannot be understood as indicating or implying relative importance.

[0055] The reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0056] In recent years, with the development of Internet of Things (IoT) technology, data analysis, cloud computing, and 3D visualization technology, new possibilities have been provided for realizing the intelligentization of warehousing logistics. By deploying various sensors inside the warehouse and using modern information technology to process this data, a comprehensive perception of the warehousing environment and the status of goods can be achieved, and then the warehousing management process can be optimized.

[0057] Currently, there are already some solutions on the market that attempt to use IoT technology and data analysis technology to improve warehousing management. These solutions generally include the following aspects:

[0058] Data collection: By deploying devices such as temperature sensors, humidity sensors, and Radio Frequency Identification (RFID) tags inside the warehouse, the warehousing environment and the status of goods are monitored in real time.

[0059] Data processing: Using database technology and cloud computing platforms, the collected data is stored and preliminarily processed.

[0060] Decision support: Based on simple statistical analysis, some basic reports and charts are provided to assist management in making decisions.

[0061] Although these technologies have improved the efficiency of warehousing management to a certain extent, there are still the following deficiencies:

[0062] Existing warehousing management systems can achieve simple device control, but they usually do not have the ability to dynamically adjust according to complex environmental changes. For example, in the face of sudden changes in climatic conditions, they often cannot respond quickly.

[0063] Most warehousing management systems provide a relatively simple user interface, lacking intuitive visualization tools, which makes it difficult for users to quickly understand the meaning behind complex data and is not convenient for remote monitoring and management.

[0064] To solve the above problems, Figure 1 Fig. shows a schematic flowchart of a visualization-based warehousing management method provided by this application.

[0065] S101, obtain first warehousing data collected based on sensors; wherein, the first warehousing data includes environmental parameters and goods status information.

[0066] Among them, various IoT sensors (such as temperature sensors, humidity sensors, pressure sensors, etc.) are deployed at appropriate positions inside the warehouse to collect warehousing environmental parameters and goods status information in real time.

[0067] Among them, the appropriate positions can be the following positions:

[0068] Goods storage area: Deploy sensors on the shelves or in the storage area to monitor the temperature and humidity conditions of the goods and ensure that the storage environment meets the requirements of the goods.

[0069] Passages and entrances: Deploy sensors at the passages and entrances of the warehouse to monitor environmental changes during the flow of people and goods, such as temperature fluctuations and humidity changes.

[0070] Near air conditioners and ventilation systems: Deploy sensors near air conditioning and ventilation equipment to monitor and adjust the working status of these systems in real time to maintain a suitable warehouse environment.

[0071] Near high-value or sensitive goods: For goods that require special attention to environmental conditions, such as perishable foods or electronic products, sensors should be deployed near these goods.

[0072] Corners and edges of the warehouse: These areas may have dead zones of temperature and humidity. Deploying sensors can help monitor the environmental conditions in these areas.

[0073] Goods picking and packing areas: Deploying sensors in these areas can monitor environmental changes during operations to ensure the environmental conditions of goods during handling.

[0074] Security and monitoring areas: In addition to environmental parameters, sensors can also be deployed in key areas to monitor security conditions, such as fires or intrusions.

[0075] Goods transportation path areas: Deploying sensors on the goods transportation path can monitor the environmental conditions of goods during movement to ensure the safety of goods during transportation.

[0076] Top and bottom of the warehouse: Since hot air rises, the top of the warehouse may be hotter and the bottom may be colder. Therefore, sensors at these locations can help monitor temperature stratification.

[0077] By deploying sensors in these appropriate locations, the warehouse management system can more effectively monitor and control the warehouse environment, ensure the safety and quality of goods, and improve the operational efficiency of the warehouse at the same time.

[0078] Among them, the environmental parameters include: temperature, humidity, light, ventilation conditions, air quality, etc.

[0079] Among them, the goods status information includes: location, quantity, status (such as intact, damaged, awaiting inspection, etc.), batch information, expiration date, weight, dimensions, etc.

[0080] S102. Analyze the first warehouse data to generate a data analysis result.

[0081] S103. Adjust the objects in the warehouse according to the data analysis result.

[0082] Among them, the first warehouse data can be predicted first to generate second warehouse data, and then the second warehouse data can be analyzed to generate a data analysis result.

[0083] Most of the existing solutions stay at the level of data aggregation, lacking in-depth data mining and prediction capabilities. They can only provide information on the current state and cannot accurately predict future demand trends, so they cannot achieve true intelligent optimization.

[0084] In the embodiments of the present application, environmental parameters and cargo status information of the warehouse are collected in real time by sensors deployed at different positions in the warehouse. Subsequently, the collected data is preprocessed, such as cleaning and sorting, to ensure the quality and consistency of the data. Then, machine learning algorithms (such as Support Vector Machine, SVM) are applied to analyze the preprocessed data, predict future trends, and generate second warehouse data. These predictions may include cargo demand, inventory level, environmental changes, etc. The generated second warehouse data reflects the expected future state of the warehouse, such as the expected arrival time of goods, storage requirements, and outbound requirements. Combining with path optimization algorithms (such as the shortest path algorithm, genetic algorithm, particle swarm optimization algorithm), the optimal cargo transportation path and storage location are calculated to improve logistics efficiency.

[0085] Among them, the generated data analysis results include but are not limited to the above-mentioned cargo demand, inventory level, environmental changes, expected arrival time of goods, storage requirements, outbound requirements, optimal cargo transportation path, and storage location, etc.

[0086] Among them, the data analysis results are used to guide the dynamic adjustment of the warehouse, such as adjusting at least one of the following: shelf height, shelf layout, temperature, humidity, transportation path, air conditioning parameters, replenishment strategy.

[0087] For example, to dynamically adjust the shelf height, through the rail system installed on the ceiling, the shelf can dynamically adjust its height and position according to real-time inventory data. This can ensure that high-demand goods are more accessible, while low-demand goods can be stored in more remote locations.

[0088] In the embodiments of the present application, control instructions are generated according to the data analysis results, and these instructions are executed through the warehouse management system to realize the automation and intelligence of warehouse operations.

[0089] S104, based on the first warehouse data and the data analysis results, update the preset visual three-dimensional model of the warehouse.

[0090] In an optional embodiment, the construction process of the three-dimensional model of the warehouse is as follows:

[0091] Step a, create a three-dimensional model of the warehouse; among them, the objects of the three-dimensional model of the warehouse include the warehouse, shelves, goods, and temperature.

[0092] Step b, set attribute fields and identifiers for the objects of the three-dimensional model of the warehouse; among them, the identifier matches the identification information.

[0093] Step c, export the three-dimensional model of the warehouse as a model file and load the model file.

[0094] Step d, after establishing the connection between the client and the server, obtain the first warehouse data from the server.

[0095] Step e: Associate the obtained first warehousing data with the attribute fields in the 3D warehouse model after loading the model file.

[0096] Among them, a mapping relationship is formed between the attribute fields in the 3D warehouse model and the data collected by IoT sensors. When the IoT sensors upload data, the client matches the corresponding real-time data through the identifier and updates the attribute fields of the objects in the 3D warehouse model. In this way, the display of the 3D warehouse model will reflect the current state of the warehouse in real time.

[0097] Step f: According to the associated first warehousing data, update the display of the 3D warehouse model in real time.

[0098] Step g: Render the 3D warehouse model to visualize the state of the warehouse on the client side. Intuitively display information such as the internal structure of the warehouse, the location of goods, and environmental parameters in the form of 3D graphics.

[0099] In the embodiment of the present application, 3D modeling tools such as Revit and 3ds Max can be used to create a 3D warehouse model including objects such as warehouses, shelves, and goods. Then, define attribute fields for each object (such as shelves and goods) that need to display information in the 3D warehouse model to store information related to the data collected by IoT sensors (such as, goods identification codes, Universally Unique Identifiers UUIDs, etc.). Assign a unique identifier (such as UUID) to each object and match it with the identification information in the warehousing data packet. This identifier will be used to establish a connection between the real-world data and the digital model. Export the 3D warehouse model as a WebGL-compatible model file (such as FBX, GLTF). This model file supports storing the geometric information and attribute fields of the 3D warehouse model while retaining the mapping information. Then load the 3D warehouse model and establish a real-time communication connection. Specifically: select a front-end framework and use Three.js or other libraries that support WebGL to process and render the 3D warehouse model. In the front-end framework, first initialize a renderer. Use the loader provided by the front-end framework to load the above model file. Once the model file is loaded, it needs to be added to the scene. The client (front-end) establishes a connection with the server through WebSocket or other real-time communication technologies (such as polling, long polling, Server-Sent Events, etc.) to obtain the data uploaded by IoT sensors or the data uploaded by the server in real time.

[0100] After the path optimization algorithm calculates the optimal path, a series of coordinate points and their order will be generated. This information needs to be converted into a form that can be parsed by the front-end (such as JSON format) and sent to the front-end through the RESTful API interface. Among them, for the convenience of understanding the coordinate points and their order, an example is given here.

[0101] Suppose the path optimization algorithm outputs a set of coordinate points and their order,

[0102] Coordinate points: [(x1,y1),(x2,y2),(x3,y3),...]

[0103] Order: [1,3,2,...] (indicating starting from the first point, then jumping to the third point, then to the second point, and so on).

[0104] The data collected by the sensor, after being pre - processed, is transmitted to the front - end through real - time communication technologies such as WebSocket, and mapped to the corresponding 3D model object according to a pre - set unique identifier (such as UUID). Among them, the front - end associates the data with the corresponding 3D model object according to the UUID carried in the data. The front - end needs to maintain a mapping relationship between UUID and 3D model objects for quick data lookup and update.

[0105] To facilitate the fusion between the two, objects with timestamps are used to record the time point of each update and the corresponding values. For example, it can include timestamps, sensor data (such as temperature, humidity, pressure, etc.) and path data (such as the current coordinate point and the next coordinate point, etc.). Synchronization mechanism: Ensure the synchronization of the path optimization result and sensor data in the time dimension. Different scenarios maintain time consistency between the front - end and the back - end by introducing heartbeat packets or periodic polling. For example, when receiving a heartbeat packet, the front - end checks the timestamp, updates the local time, and adjusts the synchronization strategy with sensor data and path optimization results as needed. When sending a heartbeat packet, the back - end can carry the latest sensor data and path optimization results to ensure timely data update and synchronization.

[0106] Conflict resolution strategy: When there are differences in the information provided by the two data sources (such as the predicted path does not match the actual position of the goods), the latest sensor data is preferentially considered as a reflection of the real state. The order of priority for result execution is: taking the actual position data as the benchmark - the manager makes a judgment and operation - according to the predicted operation. Among them, sensor data can usually provide the latest real - time information. Therefore, when a conflict occurs, preferentially considering the latest sensor data as a reflection of the real state can timely reflect the current actual situation. Optionally, taking the actual position data provided by the sensor as the benchmark to initially judge the real state and position of the goods, so as to quickly identify the difference between the predicted path and the actual position. Then, according to the actual position data, adjust the original predicted path to ensure that subsequent operations and decisions can be based on correct information.

[0107] If the path optimization algorithm is based on idealized assumptions (such as ignoring the existence of certain temporary obstacles), then its results cannot be directly applied to the current environment. At this time, the warehouse management system automatically switches back to the manual mode based on sensor feedback and issues a warning to prompt the management to intervene. For factors that are known but not taken into account (such as newly added shelves), the map model is updated in a timely manner; for unforeseeable changes (such as sudden equipment failures), manual judgment is relied on for correction.

[0108] The output of the prediction model generates some information for assisting decision-making, such as the expected inventory level, recommended replenishment quantity, etc., after predicting the demand trend for a period of time in the future. Such data can also be formatted according to the methods mentioned above and transmitted to the front end through the API. In long-term planning for those plans involving the next few weeks or even months (such as seasonal activity preparations), more attention is paid to the overall trend rather than specific details, and the prediction data needs to be updated regularly. In anomaly warnings, when detecting potential risk events (such as an area about to have excessive goods accumulation), that is, when there is no actual change currently, but the prediction data is updated to remind relevant personnel to take measures in advance.

[0109] In an actual case, in a large warehouse, stock preparation work is underway:

[0110] Real-time monitoring: Through sensors deployed everywhere, the specific location, quantity of goods, and environmental conditions can be mastered at any time, and this information is updated to the 3D model in real time.

[0111] Path optimization: The warehouse management system calculates the best handling route for the current day based on the actual operation situation of the previous day and maps it to the model for the operator to refer to and choose whether to execute. For certain fixed scenarios, only one judgment is required, and then it is executed according to the predicted path.

[0112] Prediction support: Using a prediction model trained with historical data, the approximate demand for each category of goods is given one week in advance for the management to judge, and this data can be referred to for deciding whether to adjust the storage location of the products.

[0113] In an optional embodiment, before predicting the first warehouse data to generate the second warehouse data, it further includes: packing the first warehouse data and storing the packed first warehouse data in the server.

[0114] In the embodiment of the present application, the first warehouse data is packed to generate the packed first warehouse data. Among them, the packed first warehouse data includes the first warehouse data and the identification information corresponding to the first warehouse data; the identification information includes at least one of the following: sensor ID, timestamp.

[0115] Among them, the first warehouse data can be sent to the server through wireless communication technology.

[0116] Among them, the wireless communication protocols adopted by the wireless communication technology include but are not limited to LoRaWAN and MQTT protocols. Among them, LoRaWAN uses LoRa technology to achieve long-distance transmission and is suitable for Internet of Things applications with wide-area coverage. The MQTT protocol is a lightweight message queuing telemetry transport protocol and is suitable for communication between Internet of Things devices and cloud platforms.

[0117] In an optional embodiment, the method further includes: interacting with a real-time updated three-dimensional model of the warehouse through the interface of the client.

[0118] Among them, the interaction generally includes the following aspects:

[0119] Users can view the three-dimensional model of the warehouse in real time through the client interface, including the positions of goods, the states of shelves, and environmental parameters (such as temperature and humidity).

[0120] The three-dimensional model of the warehouse will be updated according to the real-time data obtained from the server or IoT sensors, enabling users to intuitively see the dynamic changes inside the warehouse, such as the movement of goods or changes in environmental conditions.

[0121] Users can operate through the client interface, such as clicking, dragging, or zooming, to view different areas of the warehouse or detailed information of goods.

[0122] Users can issue instructions through the interface, such as adjusting the height of the shelf, changing the storage position of goods, or controlling the air conditioning system. These instructions will be sent to the server through the client and then passed by the server to the corresponding automation devices for execution.

[0123] If certain parameters in the warehouse exceed the preset range, an alarm or notification can be sent to the user through the client interface to remind the user to pay attention.

[0124] For the sake of easy understanding, an example is given here. For example, assume that the temperature in a specific area of the warehouse exceeds the safety threshold. The IoT sensor will detect this change and send the data to the server. After processing these data, the server sends the update to the client through WebSocket or other real-time communication technologies. The three-dimensional model of the warehouse on the client will be updated in real time to show the abnormal temperature in that area. Users can see this change through the client interface and may adjust the air conditioning system through the control panel on the interface to lower the temperature in that area. At the same time, the system may send an alarm notification to the user through the client interface to prompt the user to take action. This interaction method not only improves the efficiency of warehouse management but also enhances the control of the warehouse environment, ensuring the safety and quality of goods.

[0125] Optionally, when predicting the first warehouse data in the intelligent warehouse management system, feature selection, feature construction, and feature transformation in feature engineering are required. Specifically:

[0126] Feature selection: Select the most influential features for the prediction target from the original data to improve the performance and accuracy of the model. Statistical tests, model-based methods, or heuristic methods can be used to select features.

[0127] In warehouse operations, the features that may be selected include: environmental parameters such as temperature, humidity, and light; goods status including inventory level, goods location, and goods type; time features such as time of day, season, and holidays; external factors such as weather, traffic conditions, and changes in market demand.

[0128] Feature engineering: Create new features from the original data to improve the performance of the model.

[0129] Feature construction: Create new features according to the data characteristics, which may more directly reflect the requirements or improve the prediction ability of the model. For example, calculate the average temperature in different time periods in the warehouse, the average level or fluctuation range of humidity, or construct features of the goods turnover speed based on historical data.

[0130] Feature transformation: Transform the original features to improve the performance of the model and make the model easier to learn and predict. Commonly used transformation methods include logarithmic transformation, standardization, normalization, etc. For example, perform logarithmic transformation on the inventory quantity to reduce the skewness of the data, or standardize the temperature data for easy model processing.

[0131] After feature selection and feature engineering, predict the first warehouse data to obtain the second warehouse data.

[0132] Optionally, when analyzing the second warehouse data and generating data analysis results in the intelligent warehouse management system, a suitable data analysis algorithm needs to be selected. The selection of the data analysis algorithm depends on the target and data characteristics. The following is a detailed description of the selection of various algorithms:

[0133] Classification algorithm:

[0134] Objective: Predict the category of goods or determine whether a specific event occurs. Application scenarios: For example, predict which category of product a good belongs to, or predict whether a certain good will be delivered late. Algorithm selection: Logistic regression, decision tree, random forest.

[0135] Regression algorithm:

[0136] Objective: Predict numerical variables, such as future demand, price changes, etc. Application scenarios: Predict the demand for goods within a specific time period, or predict changes in warehouse environmental parameters. Algorithm selection: Linear regression, Ridge regression, Support vector regression.

[0137] Clustering algorithm:

[0138] Objective: Group goods for more effective management and optimization. Application scenarios: Group goods according to their characteristics, demand patterns, or storage conditions. Algorithm selection: K-means clustering.

[0139] Deep learning algorithms:

[0140] Objective: Handle complex non-linear relationships, such as image recognition, natural language processing, or complex time series prediction. Application scenarios: In intelligent warehousing, deep learning can be used to predict the risk of goods damage, optimize warehouse layout, or predict equipment failures. Algorithm selection: Convolutional neural network, Recurrent neural network, Long short-term memory network.

[0141] In an intelligent warehousing management system, selecting appropriate data analysis algorithms can improve the accuracy of predictions, optimize the operational efficiency of the warehouse, and provide data support for decision-making.

[0142] In an intelligent warehousing management system, model training and evaluation, as well as path problem modeling, are key steps to achieve optimization and automated decision-making. Specifically:

[0143] Divide the dataset into a training set and a test set. Select appropriate machine learning algorithms, such as logistic regression, support vector machine, random forest, etc., and use the training set data to train the model. Use the test set data to evaluate the performance of the model. Commonly used evaluation metrics include: accuracy, recall rate, F1 score.

[0144] Define the goal of path optimization, such as minimizing the distance, time, or cost of goods transportation. Abstract the path optimization problem as a graph theory problem, where each location in the warehouse can be regarded as a vertex of the graph, and the transportation path of goods can be regarded as an edge of the graph. Each edge can be assigned a weight, representing the transportation distance, time, or cost. Select appropriate optimization algorithms according to the characteristics of the problem, such as Dijkstra's algorithm, A* search algorithm, genetic algorithm, etc. Implement the selected algorithm using Python or other programming languages. Adjust the parameters of the algorithm through experiments, such as the population size, crossover rate, and mutation rate in the genetic algorithm, to achieve the best performance.

[0145] For example, storing a large number of goods in a limited space, such as an automated storage and retrieval system or a dense rack system. In such environments, the access frequency of goods is high, and it is necessary to frequently adjust the positions of goods to meet the requirements of inbound and outbound.

[0146] Respond to inventory changes in real time and immediately re-plan routes to adapt to new access requests. Use the A* search algorithm or Dijkstra algorithm combined with heuristic rules to find the best path from the starting point to the end point. Introduce a local obstacle avoidance mechanism so that the vehicle can quickly respond when encountering obstacles. Predict access patterns within a certain period in the future based on a machine learning model and pre-plan possible routes.

[0147] In the storage of dangerous goods, warehouses storing inflammable, explosive, chemical and other dangerous goods have extremely high requirements for safety. The characteristics of path planning are as follows:

[0148] Safety first principle: All path selections should give priority to safety and avoid known risk points.

[0149] Low-risk paths first: Even if it is not the shortest path, choose those routes that pass through the fewest potential dangerous areas.

[0150] Emergency evacuation preparation: Preset multiple avoidance routes and regularly check their availability to ensure emergency avoidance in case of emergencies. Build a map model with weight attributes and assign a risk level value to each area. Use the ant colony algorithm to simulate the foraging behavior of insects and explore a path that meets both safety and relatively high efficiency. Cooperate with the intelligent monitoring system to monitor the environmental status in real time, and immediately adjust the path planning once abnormalities are found to ensure operation safety.

[0151] In actual business, there are various scenarios, including high-efficiency access areas, special item handling areas, buffer areas, and static storage areas. The classification method based on the characteristics of logistics activities focuses more on the needs in the actual operation process and can better guide the design and implementation of path planning and other optimization measures.

[0152] Through these steps, the intelligent warehouse management system can effectively train the model to predict and optimize warehouse operations, and at the same time improve the efficiency of goods transportation through path optimization algorithms. These methods not only improve the operation efficiency of the warehouse, but also help to reduce costs and improve customer service levels.

[0153] In the embodiments of this application, through the integrated application of Internet of Things, WebGL 3D visualization technology, data analysis and optimization algorithms, the intelligentization of warehouse management is realized. For details, please refer to Figure 2 。

[0154] Using Internet of Things technology, deploy various sensors to monitor warehouse environmental parameters (such as temperature, humidity) and cargo status information in real time. The data collected by these sensors are aggregated through a gateway and may be subject to preliminary data processing, such as data compression, encryption, etc., and then sent to the server by wired or wireless means.

[0155] The server uses data processing technology to clean and organize the collected raw data. Then, machine learning algorithms are applied to analyze the data and predict future trends. In addition, path optimization algorithms are combined to calculate the optimal cargo transportation routes and storage locations. Based on the data analysis results, control instructions are generated to automatically adjust the equipment and environmental data in the warehouse, etc. The real-time collected data is mapped into the 3D model of the warehouse to display the internal situation of the warehouse. Through WebGL technology, users can intuitively view the real-time status of the warehouse on the web page. A user-friendly interface is provided to support remote monitoring and operation. Users can interact with the real-time updated 3D model of the warehouse through the client interface, such as viewing the detailed information of specific goods or monitoring the environmental conditions in the warehouse. In addition, the warehousing management system adopts a B / S (Browser / Server) architecture, and users can access the 3D model of the warehouse through a browser to achieve remote monitoring of the client (mobile and PC), improving management efficiency. Through these steps, the intelligent warehousing management system can improve the efficiency of warehousing logistics, reduce costs, and enhance customer satisfaction.

[0156] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0157] Corresponding to the visualization-based warehousing management method described in the above embodiments, Figure 3 The block diagram of the visualization-based warehousing management device provided by the embodiment of the present application is shown. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown.

[0158] Refer to Figure 3 , the visualization-based warehousing management device includes:

[0159] An acquisition module, configured to acquire first warehousing data collected based on sensors; wherein, the first warehousing data includes environmental parameters and cargo status information;

[0160] A generation module, configured to analyze the first warehousing data and generate a data analysis result;

[0161] An adjustment module, configured to adjust the objects in the warehouse according to the data analysis result;

[0162] A display module, configured to update a preset visualized 3D model of the warehouse based on the first warehousing data and the data analysis result.

[0163] Refer to Figure 4 , the visualization-based warehousing management device system includes: sensors, a data processing unit, a visualization modeling unit, a client, a server, and a central processing unit (not shown in the figure);

[0164] The sensor is used to collect first warehousing data and send the first warehousing data to the data processing unit;

[0165] The data processing unit is used to analyze the first warehousing data, generate a data analysis result, and generate an adjustment instruction based on the data analysis result; wherein, the adjustment instruction is used to adjust an object in the warehouse;

[0166] The server is used to store the first warehousing data and the data analysis result;

[0167] The visualization modeling unit is used to update a preset visualized three-dimensional model of the warehouse based on the first warehousing data and the data analysis result;

[0168] The client is used to visualize the state of the warehouse and interact with the real-time updated three-dimensional model of the warehouse through the interface of the client;

[0169] The central processing unit is used to coordinate the work of the data processing unit, the visualization modeling unit, the client, and the server.

[0170] It should be noted that, for the content such as information interaction and execution process among the above modules, since it is based on the same concept as the method embodiment of the present application, for its specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details will not be described here.

[0171] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used for illustration. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment, and details will not be described here.

[0172] An embodiment of the present application also provides a computer device, which includes at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, the steps in any of the above method embodiments are implemented.

[0173] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0174] An embodiment of the present application provides a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above method embodiments when executed.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0176] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0177] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0178] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0179] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

[0181] Figure 5 The structural schematic diagram of the computer device provided for an embodiment of this application. As Figure 5 shown, the computer device of this embodiment includes: at least one processor 20 ( Figure 5 only one is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, it implements the steps in any of the above-mentioned embodiments of the visualization-based warehousing management method.

[0182] The computer device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art can understand that Figure 5 merely examples of the computer device, which do not constitute a limitation on the computer device, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0183] The so-called processor 20 may be a central processing unit (CPU), and the processor 20 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0184] The memory 21 may be an internal storage unit of the computer device in some embodiments, such as the hard disk or memory of the computer device. The memory 21 may also be an external storage device of the computer device in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory 21 may also include both the internal storage unit and the external storage device of the computer device. The memory 21 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 21 may also be used to temporarily store data that has been output or will be output.

[0185] For the relevant user personal information that may be involved in the embodiments of this application, it is all processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, for reasonable purposes based on business scenarios, for the personal information actively provided by users during the use of products / services or generated due to the use of products / services, and obtained with user authorization.

[0186] The user's personal information processed by the applicant may vary depending on the specific product / service scenario. It shall be subject to the specific scenario of the user's use of the product / service, and may involve the user's account information, device information, driving information, vehicle information or other relevant information. The applicant will treat the user's personal information and its processing with a high degree of diligence.

[0187] The applicant attaches great importance to the security of the user's personal information and has taken security protection measures that meet industry standards and are reasonable and feasible to protect the user's information and prevent the personal information from being accessed, publicly disclosed, used, modified, damaged or lost without authorization.

Claims

1. A warehouse management method based on visualization, characterized in that: include: Acquire first storage data collected based on sensors; wherein the first storage data includes environmental parameters and cargo status information; Analyze the first storage data to generate data analysis results; Adjusting objects in the warehouse according to the data analysis results; Based on the first storage data and the data analysis result, a preset visualized three-dimensional warehouse model is updated.

2. The visualization-based warehouse management method according to claim 1, characterized in that: The step of analyzing the first storage data to generate data analysis results includes: Predicting the first storage data to generate second storage data; The second warehouse data is analyzed to generate the data analysis result.

3. The visualization-based warehouse management method according to claim 2, characterized in that: The predicting of the first warehouse data to generate the second warehouse data also includes: The first storage data is packaged; wherein the packaged first storage data includes the first storage data and identification information corresponding to the first storage data; the identification information includes at least one of the following: sensor ID, timestamp; The packaged first warehouse data is stored in the server.

4. The visualization-based warehouse management method according to claim 3, characterized in that: The method further comprises: Creating a three-dimensional warehouse model; wherein the objects of the three-dimensional warehouse model include warehouses, shelves, goods, and temperature; Setting attribute fields and identifiers for objects in the warehouse three-dimensional model; wherein the identifiers match the identification information; Exporting the warehouse three-dimensional model as a model file, and loading the model file; After establishing a connection between the client and the server, obtaining the first storage data from the server; Associating the first warehousing data obtained with the attribute fields in the three-dimensional warehouse model after the model file is loaded; According to the associated first warehouse data, updating the display of the warehouse three-dimensional model in real time; The three-dimensional model of the warehouse is rendered, and the status of the warehouse is visualized on the client.

5. The visualization-based warehouse management method according to claim 4, characterized in that: The method further comprises: Interact with the warehouse three-dimensional model updated in real time through the client interface.

6. The visualization-based warehouse management method according to claim 1, characterized in that: The adjusting the objects in the warehouse according to the data analysis result includes: According to the data analysis results, adjust at least one of the following: shelf height, shelf layout, temperature, humidity, transportation route, air conditioning parameters, replenishment strategy.

7. A warehouse management device based on visualization, characterized in that: include: An acquisition module, used to acquire first storage data collected based on a sensor; wherein the first storage data includes environmental parameters and cargo status information; A generating module, used for analyzing the first storage data and generating data analysis results; An adjustment module, used for adjusting objects in the warehouse according to the data analysis results; The display module is used to update a preset visualized three-dimensional warehouse model based on the first storage data and the data analysis result.

8. A warehouse management system based on visualization, characterized in that: include: Sensors, data processing units, visual modeling units, clients, servers, and central processing units; The sensor is used to collect first storage data and send the first storage data to the data processing unit; The data processing unit is used to analyze the first storage data, generate data analysis results, and generate adjustment instructions based on the data analysis results; wherein the adjustment instructions are used to adjust objects in the warehouse; The server is used to store the first storage data and the data analysis result; The visual modeling unit is used to update a preset visual warehouse three-dimensional model based on the first storage data and the data analysis result; The client is used to visualize the state of the warehouse and interact with the three-dimensional model of the warehouse updated in real time through the interface of the client; The central processor is used to coordinate the work of the data processing unit, the visual modeling unit, the client, and the server.

9. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer program product, characterized in that When the computer program product is executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 6.

Images