Offline entertainment intelligent operation management system

Through IoT technology and machine learning algorithms, intelligent inventory management in the offline entertainment industry is realized, which solves the problem of inefficiency of traditional manual management, realizes the automation and accuracy of inventory management, and improves operational efficiency and inventory optimization.

CN119047968AInactive Publication Date: 2024-11-29GUANGDONG WEIKU ANIMATION TECHNOLOGY CO LTD
View PDF 0 Cites 10 Cited by

Patent Information

Application Number
CN202411006883.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The inventory management of the existing offline entertainment industry relies on manual management, resulting in inefficiency, error-prone, slow response, lack of dynamic demand forecasts, resulting in frequent stock backlogs and out-of-stock, which cannot meet the rapid development needs of the modern entertainment industry.

Method used

Using IoT technology and machine learning algorithms, the real-time collection of inventory data by deploying sensors in entertainment facilities and commodity storage areas, combining the data analysis module to automatically predict replenishment demand, generate replenishment orders, and realize electronic and automation through supplier collaboration modules. Order processing.

Benefits of technology

It realizes automation and accuracy of inventory management, reduces manual intervention errors, improves operational efficiency, avoids inventory backlog and out of stock, reduces operating costs, and optimizes inventory levels.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047968A_ABST
    Figure CN119047968A_ABST
Patent Text Reader

Abstract

The invention discloses an offline entertainment intelligent operation management system, and relates to the technical field of intelligent operation management, and the system comprises the following components: an Internet of Things data collection module which is used for deploying Internet of Things sensors in storage areas of entertainment facilities, props and commodities, collecting the information of the inventory quantity, position and state in real time, and sending the information to a server; according to the system, the stock state is monitored in real time, the real-time data is collected by using the Internet of Things technology, and the efficient data processing and analysis module is combined, so that the stock change trend can be quickly identified, and the future replenishment demand can be predicted; the automatic intelligent prediction and replenishment process reduces the dependence on manual intervention, reduces errors and delay caused by human factors, improves the accuracy and response speed of inventory management, and greatly improves the overall operation efficiency through the automatic replenishment decision and order execution process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation management, and in particular to an offline entertainment intelligent operation management system. Background Art

[0002] With the rapid development of social economy and the continuous improvement of people's living standards, the offline entertainment industry has ushered in unprecedented development opportunities. From traditional amusement parks and cinemas to emerging VR experience halls and escape rooms, various forms of entertainment projects have emerged in an endless stream, greatly enriching people's leisure and entertainment life. However, with the diversification and expansion of entertainment projects, the inventory management of entertainment facilities, props and commodities has become increasingly complex and important. Efficient and accurate inventory management is not only related to the operating costs of entertainment companies, but also directly affects customers' consumption experience and satisfaction.

[0003] However, in the existing offline entertainment operation management, traditional manual management methods are still widely used in inventory management. The inventory quantity, location, and status information of entertainment facilities, props, and merchandise mostly rely on manual counting and recording, which is not only inefficient, but also prone to inaccurate and untimely data problems. In the replenishment link, replenishment decisions are mainly based on the experience and judgment of managers, lacking scientific basis and accurate predictions, which often leads to inventory backlogs and out-of-stock phenomena. In addition, manual management methods also have many obstacles in collaboration with suppliers, such as untimely order delivery and poor information communication, which seriously affect the efficiency and accuracy of the replenishment process.

[0004] To sum up, the traditional offline entertainment inventory management method can no longer meet the needs of the rapid development of the modern entertainment industry. There are many problems such as low efficiency of automated replenishment, easy errors, slow response, and lack of dynamic demand forecasting, which seriously restrict the development of the offline entertainment industry. Therefore, the development of an offline entertainment intelligent operation and management system based on the Internet of Things technology, especially the realization of intelligent inventory management functions, is of great practical significance and urgency for improving the operational efficiency and management level of the offline entertainment industry. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an offline entertainment intelligent operation and management system, which can realize real-time monitoring of entertainment facilities, props and merchandise inventory by utilizing Internet of Things technology, and automatically predict and adjust replenishment strategies through advanced data analysis and machine learning algorithms to meet the modern entertainment industry's demand for efficient and accurate inventory management.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an offline entertainment intelligent operation and management system, characterized in that the system includes the following components:

[0007] IoT data collection module: IoT sensors are deployed in the storage areas of entertainment facilities, props and commodities to collect information on inventory quantity, location and status in real time, and transmit it to the central processing system via wireless network;

[0008] Data processing and analysis module: The central processing system receives data from the IoT data collection module, processes and analyzes inventory data using machine learning algorithms, identifies inventory change trends, and predicts the consumption rate and replenishment needs of each item in the future;

[0009] Automatic replenishment forecasting and decision-making module: Based on the output results of the data processing and analysis module and the preset inventory threshold, the module automatically calculates the replenishment quantity and generates a replenishment order. The module also has an intelligent adjustment function, which can dynamically adjust the replenishment strategy according to market changes and special factors of holidays;

[0010] Supplier collaboration and order execution module: The replenishment orders generated by the automatic replenishment forecasting and decision-making module will be sent directly to the cooperative supplier system to realize the electronic and automated processing of orders. At the same time, this module supports order status tracking and feedback to ensure the smooth progress of the replenishment process;

[0011] User interaction and report generation module: provides an intuitive user interface to facilitate managers to view key information on inventory status, replenishment progress and sales analysis, and automatically generates various operational reports to provide data support for decision-making.

[0012] Furthermore, the IoT data acquisition module installs IoT sensors in the warehouse, shelves and key locations of the entertainment facility. These sensors include barcode scanners, cameras, infrared sensors, weight sensors, and RFID readers, which are used to capture the existence, location, quantity and status information of items, that is, the RFID reader reads the RFID tag attached to the item to obtain the unique identifier of the item, the camera recognizes the visual features of the item, and the weight sensor detects the total weight change on the shelf. The sensor sends the collected data to the central processing system through the wireless network. After arriving at the central processing system, the data is pre-processed, including data cleaning, deduplication, format conversion and preliminary anomaly detection, and the data is stored in a database for subsequent analysis and retrieval.

[0013] Furthermore, the IoT data acquisition module uses statistical anomaly detection to perform preliminary data anomaly analysis, selects features for anomaly detection from the preprocessed data, namely temperature, humidity, and inventory level, and calculates the real-time data value X of the sensor using a series of sensor readings x collected within a specific time period. i , by calculating X = {x1, x2, ..., x i}, its average n is the total number of readings, variance Its standard deviation is And the outliers in the data set are preliminarily detected based on the mean value and standard deviation, that is, And set the threshold point S to compare the Z value. When |Z|>S, it is considered that x i Anomalies, further analysis is performed on the identified outliers to determine their causes and take appropriate measures.

[0014] Furthermore, the data processing and analysis module receives data on inventory quantity, location and status collected in real time from the Internet of Things data collection module, and at the same time, obtains external data sources of historical sales data and related market trend data, integrates these multi-source data, establishes a unified data format and storage structure, and extracts meaningful features from the original data, that is, for inventory data, extracts features of inventory turnover rate, inventory holding days, and inventory change rate in different time periods, screens and optimizes the extracted features, selects features with high correlation with inventory consumption rate and replenishment demand, uses machine learning algorithms to establish a prediction model for inventory consumption rate and replenishment demand, uses historical data to train the established prediction model, optimizes the model's performance by adjusting the model's parameters, uses cross-validation technology to evaluate the model's accuracy and generalization ability, selects the optimal model, uses the trained model to predict the consumption rate and replenishment demand of each item in the future, analyzes and interprets the prediction results, and provides data support for subsequent replenishment decisions.

[0015] Furthermore, the data processing and analysis module uses a machine learning algorithm to establish a forecasting model for inventory consumption rate and replenishment demand, and forecasts the consumption rate and replenishment demand of each item in the future. The application process is as follows:

[0016] Data collection and problem definition: Collect historical inventory data, including the time series of inventory quantity, corresponding sales data, inventory changes in different time periods, and factors affecting inventory consumption, namely seasons, holidays, and promotional activities, as feature variables, divide the data into training sets, validation sets, and test sets, and clarify the prediction goal, namely predicting the inventory consumption rate and replenishment demand in the future;

[0017] Feature engineering: extract useful features from raw data, i.e. average consumption rate of items, seasonal consumption patterns, holiday effects;

[0018] Dataset division: The data is divided into training set and test set. The training set is used to train the machine learning model to help the model learn data features and patterns, including time series data, sales data, inventory levels, seasonal factors, and special event markers. The test set is used to evaluate the performance of the trained model and check the model's predictive ability for unseen data, including date, time code, sales volume, current inventory level, historical replenishment volume, holidays, promotion activity markers, actual inventory consumption rate, and replenishment demand;

[0019] Model establishment: Set the linear regression model in the form of y is the forecast of inventory consumption rate and replenishment demand, ω i is the model parameter weight to be learned, x i is the input feature variable, ω0 is the bias term;

[0020] Model training: Use the training set data to learn the model parameters by minimizing the loss function. The loss function is in the form of: m is the number of training samples, y j is the actual inventory consumption rate and replenishment requirement, is the predicted value of the model, and the gradient descent method is used to optimize the loss function;

[0021] Model verification and adjustment: Use the verification set data to verify the trained model and evaluate the model's performance indicators, namely the root mean square error. According to the verification results, adjust the model's hyperparameters, namely the learning rate and number of iterations, and retrain the model.

[0022] Model testing and application: Use the test set data to test the final model, verify the model's generalization ability on new data, apply the trained model to actual inventory data processing and analysis, and predict inventory consumption rate and replenishment demand.

[0023] Furthermore, the data processing and analysis module predicts the consumption rate and replenishment demand of each item in the future through the prediction model. During the model training process, the gradient descent method is used to update the parameter ω i ,Right now α is the learning rate, which is used to control the step size of parameter update. By continuously and iteratively updating the parameters of the model along the negative gradient direction of the objective function, the value of the objective function gradually decreases, thereby finding the minimum value of the objective function to optimize the parameters of the model.

[0024] Furthermore, the data processing and analysis module uses the mean square error to measure the average difference between the model prediction value and the true value during the model verification and adjustment process. The smaller the value, the better the prediction effect of the model. During the model training process, as the optimization objective function, the mean square error is minimized by adjusting the model parameters so that the model can better fit the training data.

[0025] Furthermore, the automatic replenishment forecasting and decision-making module receives processed and analyzed inventory data, consumption rate forecasting data and replenishment demand forecasting data from the data processing and analysis module, compares the current inventory quantity with a preset inventory threshold, and when the inventory quantity is lower than the threshold, calculates the replenishment quantity based on the consumption rate forecasting data and the preset replenishment lead time, and generates a replenishment order based on the calculated replenishment quantity. The replenishment order should include detailed information on the name, specifications, quantity, delivery date and delivery location of the replenishment items, taking into account market changes, namely the sudden increase and decrease in market demand, holidays and special factors of promotional activities, and dynamically adjusts the replenishment quantity and replenishment time according to preset rules, and automatically sends the generated replenishment order to the cooperative supplier system, receives the supplier's order confirmation information, and ensures the accuracy and effectiveness of the order.

[0026] Furthermore, the automatic replenishment forecasting and decision module determines whether the current inventory level has reached the critical value that triggers the replenishment operation through a preset inventory threshold, and compares the real-time monitored inventory quantity with the preset threshold to determine whether replenishment is needed. The judgment process is as follows:

[0027] Set the current quantity of the inventory item to I dqsl , the lower limit of the inventory threshold is set to I kcxx , the upper limit of inventory threshold is I kcsx

[0028] When I dqsl ≤I kcxx When the inventory is judged to be insufficient and replenishment is needed, the replenishment quantity L is the time required from placing a replenishment order to the goods entering the warehouse, and the safety stock threshold is S. is the average demand;

[0029] When I kcsx <I dqsl <I kcxx When the inventory is within the normal range, there is no need to replenish the stock for the time being, but continuous monitoring is required;

[0030] At that time dqsl ≥I kcsx , judged that there was excess inventory, adjusted the purchasing plan and took promotional measures to reduce inventory.

[0031] Furthermore, the supplier collaboration and order execution module determines the replenishment demand based on the automatic replenishment forecasting and decision-making module, and automatically generates replenishment orders. These orders contain specific information on the type, quantity and estimated delivery time of the goods. The generated replenishment orders will be sent directly to the system of the cooperative supplier in electronic form. After receiving the order, the supplier begins to process the order, from stocking, packaging to delivery. The status of each stage will be updated in real time and fed back to the system, recording the supplier's delivery time, product quality and response speed indicators, and regularly generating supplier performance reports. Managers display inventory status, replenishment progress, and sales data based on user interaction and report generation modules, and display various key indicators in real time through charts, namely inventory levels, sales trends, and replenishment frequency. Users are allowed to select different report types, including inventory reports, sales analysis, and supplier performance, and can set the report generation frequency, namely daily, weekly, and monthly. The system also provides predictive analysis and cost-benefit analysis to help management make more informed decisions based on data.

[0032] Compared with the prior art, this offline entertainment intelligent operation and management system has the following beneficial effects:

[0033] 1. This system can quickly identify inventory change trends and predict future replenishment needs by monitoring inventory status in real time, using real-time data collected by Internet of Things technology, and combining it with efficient data processing and analysis modules. This automated intelligent forecasting and replenishment process reduces reliance on manual intervention and reduces errors and delays caused by human factors, thereby improving the accuracy and response speed of inventory management. The automated replenishment decision-making and order execution process also greatly improves overall operational efficiency.

[0034] 2. Through accurate inventory consumption rate prediction and automated replenishment, this system can avoid capital occupation and storage costs caused by excessive inventory, while also reducing sales opportunities lost due to out-of-stock situations. Intelligent replenishment strategies can be dynamically adjusted based on market demand fluctuations, promotional activities, and special factors of holidays to optimize inventory levels, avoid inventory backlogs and out-of-stock situations, and maximize cost-effectiveness. In addition, system automation reduces the manpower cost of manual management and further reduces operating costs.

[0035] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 This is a process operation diagram of an offline entertainment intelligent operation management system.

[0038] Figure 2 The present invention is a flow chart of an offline entertainment intelligent operation and management system. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Embodiment 1

[0041] The present embodiment provides an offline entertainment intelligent operation and management system, which collects inventory data in real time through Internet of Things sensors, and combines big data analysis and machine learning algorithms for prediction. It can automatically and accurately identify inventory change trends and replenishment needs. From data collection, processing, and analysis to the generation and sending of replenishment orders, the entire process is highly automated, reducing human errors and delays, thereby significantly improving operational efficiency.

[0042] In the specific implementation, IoT sensors, including RFID tags and wireless sensors, are first deployed in the entertainment facility storage area, prop warehouse and merchandise shelves of the arcade. RFID tags are installed on gaming equipment to identify the usage status and location of the equipment. Weight sensors are installed on merchandise shelves to monitor the inventory quantity of goods in real time. The sensors collect information such as inventory quantity, location, and status at a set frequency, and transmit the data to the central processing system through a wireless network. The weight sensors collect weight data of the merchandise shelves every 5 minutes and send it to the central processing system in a timely manner. The central processing system performs pre-processing operations such as cleaning, deduplication and format conversion on the received data to remove abnormal data and ensure the accuracy and completeness of the data. For weight data that obviously deviates from the normal range, the system marks it and further analyzes the reasons.

[0043] Then, the central processing system receives data from the IoT data acquisition module and integrates multi-source data such as historical sales data and market trend data. For example, this week's inventory data is compared and analyzed with the sales data of the same period last week, and meaningful features such as inventory turnover rate and sales growth rate in different time periods are extracted from the original data. The inventory turnover rate of each commodity in the past month is calculated, and a machine learning algorithm is used to establish a prediction model for inventory consumption rate and replenishment demand. A linear regression model is used to train the model based on historical sales data and inventory change data to predict the consumption rate of various game props in the next week. The trained model is verified using the validation set data, and the model parameters are adjusted according to the verification results to improve the accuracy and generalization ability of the model. If the prediction error of the model on the validation set is large, the model's hyperparameters are adjusted and retrained. The trained model is used to predict the inventory consumption rate and replenishment demand in the future, and the prediction results are analyzed to provide a basis for subsequent replenishment decisions. The model predicts that the demand for props in a popular game will increase significantly next week, and the system issues an early warning.

[0044] Secondly, set reasonable inventory thresholds according to different product types and sales conditions. For example, for best-selling game coins, set the inventory threshold to 1,000 coins. When the inventory quantity is lower than the threshold, the system calculates the replenishment quantity based on the consumption rate forecast data and the replenishment lead time. For example, the average daily consumption rate of a game item is 10, the replenishment lead time is 3 days, the current inventory is 20, and the inventory threshold is 50. The calculated replenishment quantity is 10×3+50-20=60. Generate a replenishment order based on the calculated replenishment quantity, and make dynamic adjustments based on special factors such as market changes and holidays. Before the weekend or holidays, appropriately increase the replenishment quantity, automatically send the replenishment order to the supplier system, and receive the supplier's order confirmation information in a timely manner.

[0045] Next, after receiving the replenishment order, the supplier will promptly prepare, pack and ship the goods, and provide real-time feedback on the order status to the system. After shipping, the supplier will upload information such as the logistics order number to the system to facilitate users to query the order status. The system tracks the logistics status of the order in real time to ensure that the goods can be delivered on time. For example, by connecting with the logistics company's system, the transportation location and estimated arrival time of the goods can be obtained in real time. Based on indicators such as the supplier's delivery time, product quality and response speed, the supplier's performance is regularly evaluated, and suppliers with outstanding performance are rewarded, while suppliers with poor performance are communicated and improved.

[0046] Finally, an intuitive user interface is provided, where managers can view the inventory quantity of game coins, the progress of current replenishment orders, and sales statistics of various commodities in real time on the system interface. The system automatically generates various operational reports, such as inventory reports, sales analysis reports, etc. Managers can customize the content and format of the reports as needed, including total inventory, inventory turnover rate, out-of-stock commodity lists, etc. The system conducts in-depth analysis of the collected data and provides decision support for management. By analyzing sales data, if it is found that the popularity of a certain game has declined, management can consider adjusting the game layout and launching promotional activities.

[0047] In summary, this embodiment elaborates on the entire process of the offline entertainment intelligent operation management system from data collection to decision execution, and demonstrates how to realize the automation and intelligence of inventory management through Internet of Things technology and machine learning algorithms, thereby improving operational efficiency and reducing operating costs. By implementing this system, entertainment venues can more accurately predict inventory demand, optimize replenishment processes, improve customer satisfaction, and achieve sustainable business growth.

[0048] Embodiment 2

[0049] An offline entertainment intelligent operation and management system in this embodiment places special emphasis on machine learning models. By predicting the consumption rate and replenishment demand of items in the future, the replenishment process is automatically triggered, avoiding capital occupation due to inventory backlogs and revenue loss due to out-of-stock conditions, thereby reducing overall inventory costs. By ensuring an adequate supply of entertainment facilities, props and merchandise, the customer's entertainment experience is improved and customer satisfaction is enhanced.

[0050] First, the central processing system receives real-time inventory quantity, location and status data from the IoT data acquisition module, as well as historical sales data and related market trend data, such as holiday information and promotion activity arrangements. These multi-source data are integrated to establish a unified data format and storage structure. Statistical anomaly detection is used to perform preliminary data anomaly analysis. Features for anomaly detection, namely temperature, humidity, and inventory level, are selected from the preprocessed data. A series of sensor readings x collected within a specific time period are used to i , by calculating X = {x1, x2, ..., x i}, its average variance Its standard deviation is And the outliers in the data set are preliminarily detected based on the mean value and standard deviation, that is, And set the threshold point S to compare the Z value. When |Z|>S, it is considered that x iAnomalies and extract meaningful features from the original data. For inventory data, extract features such as inventory turnover rate, inventory holding days, inventory change rate in different time periods, etc. Consider the impact of factors such as seasons, holidays, and promotional activities on inventory consumption, and extract corresponding features, such as seasonal consumption patterns and holiday effects.

[0051] Then, using machine learning algorithms, a forecasting model for inventory consumption rate and replenishment demand is established, and the model is set in the form of: The data is divided into training set, validation set and test set, and the model is trained using the training set data. The model parameters are learned by minimizing the loss function, that is, And gradient descent is used to optimize the loss function, that is Use the validation set data to validate the trained model and evaluate the model's performance indicators. The mean square error is used to measure the average difference between the model's predicted value and the true value. The smaller the value, the better the model's prediction effect. Use the trained model to predict the consumption rate and replenishment demand of each item in the future, and analyze and interpret the prediction results. For example, analyze the inventory consumption trends of different regions and different commodities, identify potential problems or opportunities, and provide data support for subsequent replenishment decisions.

[0052] Secondly, the processed and analyzed inventory data, consumption rate forecast data and replenishment demand forecast data are received from the data processing and analysis module, and the current inventory quantity is compared with the preset inventory threshold. For example, the lower limit of the inventory threshold of a popular game prop in the game area is set to 50 pieces. When the inventory quantity is less than 50 pieces, it is judged that the inventory is insufficient and replenishment is required. When the inventory quantity is lower than the threshold, the replenishment quantity is calculated based on the consumption rate forecast data and the preset replenishment lead time (such as replenishment 2 days in advance). According to the calculated replenishment quantity, a replenishment order is generated. The replenishment order should include detailed information of the replenishment items, such as name, specification, quantity, delivery date, delivery location, etc., taking into account special factors such as market changes (such as a sudden popularity of a game leading to increased demand), holidays (such as increased passenger flow during the Spring Festival) and promotional activities, and according to preset rules, the replenishment quantity and replenishment time are dynamically adjusted. For example, one week before the Spring Festival, the replenishment quantity of various popular game props in the game area is automatically increased, and communication with suppliers in advance to ensure timely delivery.

[0053] Finally, the generated replenishment order is automatically sent to the cooperating supplier system, and the supplier's order confirmation information is received to ensure the accuracy and effectiveness of the order, track the order status in real time, and promptly handle possible problems that may arise during the order execution process, such as delayed delivery by the supplier, to ensure the smooth progress of the replenishment process.

[0054] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An offline entertainment intelligent operation and management system, It is characterized in that The system consists of the following components: IoT data collection module: IoT sensors are deployed in the storage areas of entertainment facilities, props and commodities to collect information on inventory quantity, location and status in real time, and transmit it to the central processing system via wireless network; Data processing and analysis module: The central processing system receives data from the IoT data collection module, processes and analyzes inventory data using machine learning algorithms, identifies inventory change trends, and predicts the consumption rate and replenishment needs of each item in the future; Automatic replenishment forecasting and decision-making module: Based on the output results of the data processing and analysis module and the preset inventory threshold, the module automatically calculates the replenishment quantity and generates a replenishment order. The module also has an intelligent adjustment function, which can dynamically adjust the replenishment strategy according to market changes and special factors of holidays; Supplier collaboration and order execution module: The replenishment orders generated by the automatic replenishment forecasting and decision-making module will be sent directly to the cooperative supplier system to realize the electronic and automated processing of orders. At the same time, this module supports order status tracking and feedback to ensure the smooth progress of the replenishment process; User interaction and report generation module: provides an intuitive user interface to facilitate managers to view key information on inventory status, replenishment progress and sales analysis, and automatically generates various operational reports to provide data support for decision-making.

2. An offline entertainment intelligent operation and management system according to claim 1, It is characterized in that The IoT data acquisition module installs IoT sensors in the warehouse, shelves and key locations of the entertainment facility. These sensors include barcode scanners, cameras, infrared sensors, weight sensors, and RFID readers, which are used to capture the existence, location, quantity and status information of items, that is, the RFID reader reads the RFID tag attached to the item to obtain the unique identifier of the item, the camera recognizes the visual features of the item, and the weight sensor detects the total weight change on the shelf. The sensor sends the collected data to the central processing system through the wireless network. After arriving at the central processing system, the data is pre-processed, including data cleaning, deduplication, format conversion and preliminary anomaly detection, and the data is stored in a database for subsequent analysis and retrieval.

3. An offline entertainment intelligent operation and management system according to claim 2, It is characterized in that The IoT data acquisition module uses statistical anomaly detection to perform preliminary data anomaly analysis, selects features for anomaly detection from the preprocessed data, namely temperature, humidity, and inventory level, and calculates the real-time data value X of the sensor using a series of sensor readings x collected within a specific time period. i , by calculating X = {x 1 , x 2 , ..., x i }, its average n is the total number of readings, variance Its standard deviation is And the outliers in the data set are preliminarily detected based on the mean value and standard deviation, that is, And set the threshold point S to compare the Z value. When |Z|>S, it is considered that x i Anomalies, further analysis is performed on the identified outliers to determine their causes and take appropriate measures.

4. The offline entertainment intelligent operation and management system according to claim 1, It is characterized in that The data processing and analysis module receives data on inventory quantity, location and status collected in real time from the Internet of Things data collection module, and at the same time, obtains external data sources of historical sales data and related market trend data, integrates these multi-source data, establishes a unified data format and storage structure, and extracts meaningful features from the original data, that is, for inventory data, extracts features of inventory turnover rate, inventory holding days, and inventory change rate in different time periods, screens and optimizes the extracted features, selects features with high correlation with inventory consumption rate and replenishment demand, uses machine learning algorithms to establish a prediction model for inventory consumption rate and replenishment demand, uses historical data to train the established prediction model, optimizes the performance of the model by adjusting the parameters of the model, uses cross-validation technology to evaluate the accuracy and generalization ability of the model, selects the optimal model, uses the trained model to predict the consumption rate and replenishment demand of each item in the future, analyzes and interprets the prediction results, and provides data support for subsequent replenishment decisions.

5. An offline entertainment intelligent operation and management system according to claim 4, It is characterized in that The data processing and analysis module uses machine learning algorithms to establish a forecasting model for inventory consumption rate and replenishment demand, and forecasts the consumption rate and replenishment demand of each item in the future. The application process is as follows: Data collection and problem definition: Collect historical inventory data, including the time series of inventory quantity, corresponding sales data, inventory changes in different time periods, and factors affecting inventory consumption, namely seasons, holidays, and promotional activities, as feature variables, divide the data into training sets, validation sets, and test sets, and clarify the prediction goal, namely predicting the inventory consumption rate and replenishment demand in the future; feature Engineering: Extract useful features from raw data, i.e. average consumption rate of items, seasonal consumption patterns, holiday effects; Dataset division: The data is divided into training set and test set. The training set is used to train the machine learning model to help the model learn data features and patterns, including time series data, sales data, inventory levels, seasonal factors, and special event markers. The test set is used to evaluate the performance of the trained model and check the model's predictive ability for unseen data, including date, time code, sales volume, current inventory level, historical replenishment volume, holidays, promotion activity markers, actual inventory consumption rate, and replenishment demand; Model establishment: Set the linear regression model in the form of y is the forecast of inventory consumption rate and replenishment demand, ω i is the model parameter weight to be learned, x i is the input feature variable, ω 0 is the bias term; Model training: Use the training set data to learn the model parameters by minimizing the loss function. The loss function is in the form of: m is the number of training samples, y j is the actual inventory consumption rate and replenishment requirement, is the predicted value of the model, and the gradient descent method is used to optimize the loss function; Model verification and adjustment: Use the verification set data to verify the trained model and evaluate the model's performance indicators, namely the root mean square error. According to the verification results, adjust the model's hyperparameters, namely the learning rate and number of iterations, and retrain the model. Model testing and application: Use the test set data to test the final model, verify the model's generalization ability on new data, apply the trained model to actual inventory data processing and analysis, and predict inventory consumption rate and replenishment demand.

6. An offline entertainment intelligent operation and management system according to claim 5, It is characterized in that The data processing and analysis module predicts the consumption rate and replenishment demand of each item in the future through the prediction model. During the model training process, the gradient descent method is used to update the parameter ω i ,Right now α is the learning rate, which is used to control the step size of parameter update. By continuously and iteratively updating the parameters of the model along the negative gradient direction of the objective function, the value of the objective function gradually decreases, thereby finding the minimum value of the objective function to optimize the parameters of the model.

7. An offline entertainment intelligent operation and management system according to claim 5, It is characterized in that The data processing and analysis module uses the mean square error to measure the average difference between the model prediction value and the true value during the model verification and adjustment process. The smaller the value, the better the prediction effect of the model. During the model training process, as the optimization objective function, the mean square error is minimized by adjusting the model parameters so that the model can better fit the training data.

8. The offline entertainment intelligent operation and management system according to claim 1, It is characterized in that The automatic replenishment forecasting and decision-making module receives processed and analyzed inventory data, consumption rate forecasting data and replenishment demand forecasting data from the data processing and analysis module, compares the current inventory quantity with a preset inventory threshold, and when the inventory quantity is lower than the threshold, calculates the replenishment quantity based on the consumption rate forecasting data and the preset replenishment lead time, and generates a replenishment order based on the calculated replenishment quantity. The replenishment order should include detailed information such as the name, specification, quantity, delivery date and delivery location of the replenishment items, and dynamically adjusts the replenishment quantity and replenishment time according to preset rules in consideration of market changes, namely, sudden increases and decreases in market demand, holidays and special promotional activities, and automatically sends the generated replenishment order to the cooperative supplier system, receives the supplier's order confirmation information, and ensures the accuracy and effectiveness of the order.

9. An offline entertainment intelligent operation and management system according to claim 8, It is characterized in that The automatic replenishment forecasting and decision-making module determines whether the current inventory level has reached the critical value that triggers the replenishment operation through the preset inventory threshold, and compares the real-time monitored inventory quantity with the preset threshold to decide whether replenishment is needed. The judgment process is as follows: Set the current quantity of the inventory item to I dqsl , the lower limit of the inventory threshold is set to I kcxx , the upper limit of inventory threshold is I kcsx When I dqsl ≤I kcxx When the inventory is judged to be insufficient and replenishment is needed, the replenishment quantity L is the time required from placing a replenishment order to the goods entering the warehouse, and the safety stock threshold is S. is the average demand; When I kcsx <I dqsl <I kcxx When the inventory is within the normal range, there is no need to replenish the stock for the time being, but continuous monitoring is required; At that time dqsl ≥I kcsx , judged that there was excess inventory, adjusted the purchasing plan and took promotional measures to reduce inventory.

10. The offline entertainment intelligent operation and management system according to claim 1, It is characterized in that The supplier collaboration and order execution module determines the replenishment demand according to the automatic replenishment forecasting and decision-making module, and automatically generates replenishment orders. These orders contain information on specific commodity types, quantities and estimated delivery times. The generated replenishment orders will be sent directly to the system of the cooperative supplier in electronic form. After receiving the order, the supplier begins to process the order, from stocking, packaging to delivery. The status of each stage will be updated in real time and fed back to the system, recording the supplier's delivery time, product quality and response speed indicators, and regularly generating supplier performance reports. Managers display inventory status, replenishment progress, and sales data based on user interaction and report generation modules, and display various key indicators in real time through charts, namely inventory levels, sales trends, and replenishment frequency. Users are allowed to select different report types, including inventory reports, sales analysis, and supplier performance, and can set the report generation frequency, namely daily, weekly, and monthly. The system also provides predictive analysis and cost-benefit analysis to help management make more informed decisions based on data.

Citation Information

Cited By

  • Consignment sale system management system and method thereof

    CN119228273A

  • E-commerce inventory dynamic optimization model system based on real-time big data

    CN119671461A

  • E-commerce inventory dynamic optimization model system based on real-time big data

    CN119671461B

  • Intelligent gas station operation optimization system and method based on big data and artificial intelligence

    CN119849860A

  • Aluminum profile production material demand prediction management method and system

    CN120181513A