Intelligent task management method and system based on AIoT

Abstract

The invention discloses an intelligent task management method and system based on AIoT. The method comprises the following steps: in a data acquisition stage, performing data interaction with Internet of Things equipment by using Java back-end service, and cleaning and preprocessing acquired data; in the intelligent analysis link, deep mining is carried out on data by means of an AI algorithm, and a task priority model and an equipment adaptation model are constructed. Task allocation is realized through a dynamic scheduling algorithm, and priority-based allocation, load balanced allocation and resource collaborative allocation are supported. And in the real-time execution stage, the Internet of Things equipment monitors the task execution state in real time and feeds back the task execution state according to the task instruction operation. And the closed-loop monitoring displays the task execution condition through a front-end interface. Intelligent, automatic and real-time monitoring of task management is realized, and the task management efficiency and the resource utilization rate are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent retail, in particular to an intelligent task management method and system based on AIoT. BACKGROUND

[0002] With the rapid development of Internet of Things (IoT) and Artificial Intelligence (AI) technologies, more and more devices are connected to the network, forming a huge and complex IoT environment. In this environment, the management of tasks such as monitoring, maintenance, and control of devices becomes particularly important. However, existing task management systems often have many shortcomings.

[0003] For example, patent CN108345639B discloses a task management system and a task management method, which provides a flexible task publishing and corresponding reward providing technology, but its intelligence level is limited. The system relies on manual scripting of tasks, and task generation and distribution require human intervention, cannot automatically generate in-depth analysis of IoT data (such as device status, environmental parameters, and user behavior), and lacks intelligent decision-making capabilities. In addition, the existing system relies on user-initiated queries for monitoring the execution status of tasks, lacks real-time feedback mechanisms, and cannot timely detect abnormalities (such as device failures and task timeouts) in task execution, resulting in delayed problem handling and affecting task completion quality. Task allocation also relies on manually set rules and does not achieve intelligent scheduling based on device performance, load, geographic location, and other multi-dimensional factors. When device status changes or task requirements dynamically adjust, the system cannot optimize task allocation schemes in real time, resulting in low device resource utilization and low task execution efficiency. At the same time, the existing system also lacks real-time processing and analysis capabilities for massive IoT data, cannot identify potential task requirements (such as device failure warnings and user habit predictions) through data mining, and is difficult to achieve active task pushing and dynamic adjustment. Therefore, there is an urgent need for an AIoT-based intelligent task management system and method that can solve the above problems. SUMMARY

[0004] Based on this, the embodiments of the present application provide an AIoT-based intelligent task management method and system, which fully utilizes the stability, high performance, and rich open source library support of Java in backend service development, combines the advantages of Vue 3 in front-end construction of responsive and interactive user interfaces, and realizes the automation and intelligent management of IoT device tasks.

[0005] In a first aspect, an AIoT-based intelligent task management method is provided, which includes:

[0006] S1 Data acquisition: The backend service written by Java is connected to various IoT devices for communication, collects various IoT device data, and performs data preprocessing on the collected data.

[0007] S2 intelligent analysis: the pre-processed data is analyzed in depth by an AI algorithm to construct a task priority model and a device adaptation model; wherein, the task priority model is used to determine the task priority according to the nature and urgency of the task, combined with the task state of the point person; the device adaptation model is used to determine the adaptation degree of each point to different tasks according to the point position, inventory level, and operation condition factors;

[0008] S3 task allocation: dynamic scheduling based on the results of intelligent analysis; wherein, the dynamic scheduling includes priority-based allocation, load balancing allocation, and resource collaborative allocation;

[0009] S4 real-time execution: the Internet of Things device carries out operation according to the received dynamic scheduling instructions, and monitors the data in the task execution process in real time; wherein, the data in the task execution process at least includes point inventory changes, sales fluctuations, and task completion progress;

[0010] S5 closed-loop monitoring: the task execution status is fed back to the user in real time through the front-end interface, and the Java backend continuously monitors and processes the task status.

[0011] Optionally, in the S1 data collection step, data preprocessing includes:

[0012] The collected point person task state, specific point inventory level, surrounding point overall inventory condition, point operation condition, point position, and sales data in recent days are cleaned to remove duplicate data and obviously abnormal data;

[0013] For missing data, mean filling, regression prediction or other data interpolation methods are used for processing;

[0014] Standardize the data and convert different types of data into a unified format and dimension.

[0015] Optionally, in the S2 intelligent analysis step, the construction process of the task priority model includes:

[0016] Collect multi-dimensional data; wherein, the multi-dimensional data at least includes the nature, urgency, point person current task backlog, point inventory level, and point operation state data of the task;

[0017] Classify and evaluate the task priority using a rule-based algorithm or machine learning algorithm;

[0018] Classify the tasks into high, medium, and low priority, and set different priority weights according to the task type, point inventory state, and operation condition factors.

[0019] Optionally, in the task allocation step S3, the dynamic scheduling process includes:

[0020] Priority-based allocation: high-priority tasks are preferentially allocated to point locations with high adaptability in order of task priority from high to low;

[0021] Load balancing allocation: according to the current number of tasks, task difficulty and estimated completion time of the point location manager, a weighted round-robin algorithm or other load balancing algorithm is used to ensure that tasks are evenly distributed to each point location manager;

[0022] Resource collaborative allocation: combining the inventory level of the specific point location and the overall inventory situation of the surrounding point locations, the resource allocation between point locations is coordinated through optimization algorithms to generate inventory transfer tasks, and the transportation path is planned according to the point location and operation situation.

[0023] Optionally, in the real-time execution step S4, the real-time monitoring process includes:

[0024] Using sensor networks and data acquisition modules, real-time acquisition of point location inventory changes, sales fluctuations, task completion progress data during task execution;

[0025] Compare real-time monitoring data with expected data in the task allocation system, and trigger an anomaly detection algorithm when the deviation exceeds the preset threshold;

[0026] Through message queues or event-driven mechanisms, real-time feedback of abnormal information to the task allocation system for re-evaluation of the task allocation scheme.

[0027] Optionally, in the closed-loop monitoring step S5, the task execution status is fed back to the user in real time through the front-end interface, and the Java backend continuously monitors and processes the task status, including:

[0028] The front-end interface built with Vue 3 displays the task execution status, point location state information and task execution progress to the user in the form of charts, lists or maps;

[0029] The Java backend service obtains the latest data of task execution through database queries and data processing, and pushes it to the front-end interface;

[0030] Provide task operation interface, allow users to manually adjust task allocation strategy or query detailed information of specific tasks, at the same time record user's operation log for subsequent analysis.

[0031] In the second aspect, an AIoT-based intelligent task management system is provided, which includes:

[0032] The data acquisition module is configured to communicate with various Internet of Things devices through a Java-written backend service, acquire data of the various Internet of Things devices, and perform data preprocessing on the acquired data.

[0033] The intelligent analysis module is configured to perform deep analysis on the preprocessed data through an AI algorithm, and construct a task priority model and a device adaptation model. The task priority model is configured to determine a task priority according to a nature and an urgency of the task and a task state of a point person. The device adaptation model is configured to determine an adaptation degree of each point to different tasks according to a point position, an inventory level, and an operation condition.

[0034] The task allocation module is configured to perform dynamic scheduling according to a result of the intelligent analysis. The dynamic scheduling includes priority-based allocation, load balancing allocation, and resource collaborative allocation.

[0035] The real-time execution module is configured to cause the Internet of Things devices to perform operations according to received dynamic scheduling instructions, and monitor various data in a task execution process in real time. The various data in the task execution process at least include point inventory changes, sales volume fluctuations, and task completion progress.

[0036] The closed-loop monitoring module is configured to feed back a task execution state to a user in real time through a front-end interface, and continuously monitor and process the task state through a Java backend.

[0037] In a third aspect, an electronic device is provided, including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the AIoT-based intelligent task management method of any one of the first aspect is implemented.

[0038] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. When the processor executes the computer program, the AIoT-based intelligent task management method of any one of the first aspect is implemented.

[0039] In a fifth aspect, a computer program product is provided, which stores a computer program. When the processor executes the computer program, the AIoT-based intelligent task management method of any one of the first aspect is implemented.

[0040] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0041] (1) The AI algorithm is used to perform deep analysis on the Internet of Things data, to realize automatic generation, dynamic scheduling and real-time monitoring of tasks, to reduce manual intervention, and to improve the intelligent level and efficiency of task management.

[0042] (2) Based on multi-dimensional information such as device status, inventory level, geographic location, etc., task allocation is performed, optimal utilization of resources is achieved, system resource utilization is improved, and task execution cost is reduced.

[0043] (3) A full-link real-time monitoring system is constructed, which can real-time feedback task execution status and device operation, timely discover and handle exceptions, guarantee efficient task execution, and improve system reliability and stability. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0045] Figure 1 A step flow chart of an AIoT-based intelligent task management method provided for an embodiment of the present application;

[0046] Figure 2 A block diagram of an AIoT-based intelligent task management system provided for an embodiment of the present application;

[0047] Figure 3 An AIoT-based intelligent task management system architecture diagram provided for an embodiment of the present application;

[0048] Figure 4 A schematic diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0050] In the description of the present application, the terms "include", "have" and any variants thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units explicitly listed, but can also include other steps or units inherent to these processes, methods, products or devices, or steps or units added based on further optimization of the concept of the present application.

[0051] With the rapid development of Internet of Things and artificial intelligence technologies, more and more devices and systems are connected to the network, forming a huge and complex Internet of Things environment. In such an environment, various tasks need to be effectively managed, such as device monitoring, maintenance, control, etc.

[0052] Existing task management systems often lack intelligent and automated capabilities, requiring manual intervention to assign and execute tasks, which is inefficient and prone to errors. In addition, manually created systems are difficult to effectively analyze and process massive amounts of Internet of Things data, and cannot adjust task arrangements in real time according to actual conditions

[0053] Prior art such as CN108345639B provides a task management system and a task management method, the task management system comprising: a task initiation system for publishing product requirements according to product-issued task requirements, obtaining task scripts written by users according to the product requirements, and inputting the task scripts; a task publishing system for generating task basic data and task rules according to the task scripts, storing the task rules, completing the filling action, and publishing tasks; a task reward collection system for obtaining user identity information, obtaining tasks completed by users from the database according to the identity information, and providing rewards for users according to the completed tasks. The implementation of this technology provides a flexible task publishing and corresponding reward providing technology, improving the practicality of the system and the efficiency of the system.

[0054] However, the prior art has the following problems:

[0055] Insufficient intelligence: the existing system relies on manual writing of task scripts, and task generation and distribution require manual intervention, which cannot automatically generate tasks based on in-depth analysis of Internet of Things data (such as device status, environmental parameters, user behavior), resulting in a lack of intelligent decision-making capabilities in task management.

[0056] Real-time monitoring and feedback missing: the existing system relies on user-initiated queries for task execution status monitoring, lacks real-time feedback mechanisms, and cannot timely detect abnormalities (such as device failure, task timeout) in task execution, resulting in delayed problem handling and affecting task completion quality.

[0057] Low degree of automation: task allocation relies on manual rule setting and does not achieve intelligent scheduling based on device performance, load, geographic location, etc. When device status changes or task requirements dynamically adjust, the task allocation scheme cannot be optimized in real time, resulting in low device resource utilization and low task execution efficiency.

[0058] Data processing capability limitations: lack of real-time processing and analysis capabilities for massive amounts of Internet of Things data, unable to identify potential task requirements through data mining (such as device failure warning, user habit prediction), and difficult to achieve proactive task pushing and dynamic adjustment.

[0059] In summary, the present application aims to solve the problem of how to use big data technology to analyze Internet of Things data in real time, realize automatic generation and intelligent sorting of tasks, and how to build a real-time monitoring and feedback mechanism to ensure efficient task execution and timely handling of exceptions.

[0060] The core invention points of the present application are:

[0061] Intelligent task generation: through big data analysis of Internet of Things data (device status, environmental parameters, user behavior), automatically identify task requirements and generate tasks, support dynamic sorting of task priorities.

[0062] Full-link real-time monitoring and feedback: build a real-time monitoring system for task execution status, real-time feedback of task progress and point status, and automatically trigger warning and processing mechanisms combined with abnormal detection algorithms.

[0063] Secondary invention points include task full-process display: through page analysis, optimize task card display, realize personalized task management interface and interaction logic.

[0064] The present application provides an intelligent task management method and system based on the fusion of Java and Vue 3 technology stack, AI and Internet of Things technology. It fully utilizes the stability, high performance and rich open source library support of Java in backend service development, and combines the advantages of Vue 3 in front-end construction of responsive and interactive user interface to realize automatic and intelligent management of Internet of Things device tasks.

[0065] The system adopts a layered architecture design, through the full-link architecture of "data collection - intelligent analysis - dynamic scheduling - real-time execution - closed-loop monitoring", to achieve efficient management of Internet of Things device tasks. In the data collection stage, the backend service written in Java interacts with various Internet of Things devices; in the intelligent analysis stage, AI algorithms implemented by Java are used to deeply mine the collected data; in the dynamic scheduling stage, Java services perform optimal allocation of tasks based on multi-dimensional information of devices and tasks (point responsible person task status, specific point inventory level, overall inventory situation of surrounding points, point operation situation, point location and its sales volume in recent days); in the real-time execution stage, Internet of Things devices carry out operations according to the received task instructions; in the closed-loop monitoring stage, the front-end interface built by Vue 3 feeds back the task execution status to the user in real time, while the Java backend continuously monitors and processes the task status.

[0066] Please refer to Figure 1It shows a flowchart of an AIoT-based intelligent task management method provided by the embodiment of the application, which can include the following steps:

[0067] S1 data collection: the backend service written by Java communicates with various Internet of Things devices, collects various Internet of Things device data, and performs data preprocessing on the collected data.

[0068] In this embodiment, data preprocessing includes:

[0069] The collected point-in-charge task state, specific point-in-charge inventory level, overall inventory situation of surrounding point-in-charge, point-in-charge operation situation, point-in-charge location and sales data in recent days are cleaned to remove duplicate data and obviously abnormal data.

[0070] For missing data, mean filling, regression prediction or other data imputation methods are used for processing.

[0071] The data is standardized to convert different types of data into a unified format and dimension.

[0072] S2 intelligent analysis: the preprocessed data is analyzed in depth through an AI algorithm to construct a task priority model and a device adaptation model.

[0073] The task priority model is used to determine the task priority according to the nature and urgency of the task in combination with the point-in-charge task state; the device adaptation model is used to determine the adaptation degree of each point-in-charge to different tasks according to the device point-in-charge location, inventory level and operation situation factors.

[0074] In this embodiment, the construction process of the task priority model includes:

[0075] Collecting multi-dimensional data; wherein the multi-dimensional data at least includes the nature, urgency, point-in-charge current task backlog, point-in-charge inventory level and point-in-charge operation state data of the task;

[0076] Classifying and evaluating the task priority using a rule-based algorithm or a machine learning algorithm;

[0077] The task is divided into high priority, medium priority and low priority, and different priority weights are set according to the task type, point-in-charge inventory state and operation situation factors.

[0078] S3 task allocation: dynamic scheduling is performed according to the results of intelligent analysis.

[0079] The dynamic scheduling includes priority-based allocation, load balancing allocation and resource collaborative allocation.

[0080] In this embodiment, the process of dynamic scheduling includes:

[0081] Priority-based allocation: high-priority tasks are preferentially allocated to points with high adaptability in order of task priority from high to low;

[0082] Load balancing allocation: according to the current number of tasks, task difficulty and estimated completion time of the point person, a weighted round-robin algorithm or other load balancing algorithm is used to ensure that tasks are evenly distributed to each point person;

[0083] Resource collaborative allocation: combining the inventory level of the specific point and the overall inventory situation of the surrounding points, the resource allocation between points is coordinated through optimization algorithms to generate inventory transfer tasks, and the transportation path is planned according to the point location and operation situation.

[0084] S4 Real-time execution: Internet of Things devices carry out operations according to the received dynamic scheduling instructions and monitor various data in the task execution process in real time.

[0085] Among them, the data monitored in the task execution process at least includes point inventory changes, sales fluctuations, and task completion progress.

[0086] In this embodiment, the process of real-time monitoring includes:

[0087] Using sensor networks and data acquisition modules, real-time point inventory changes, sales fluctuations, and task completion progress data in the task execution process are obtained;

[0088] Compare real-time monitoring data with expected data in the task allocation system, and when the deviation exceeds the preset threshold, trigger the anomaly detection algorithm;

[0089] Through message queues or event-driven mechanisms, abnormal information is fed back to the task allocation system in real time to re-evaluate the task allocation scheme.

[0090] S5 Closed-loop monitoring: the task execution status is fed back to the user in real time through the front-end interface, and the Java backend continuously monitors and processes the task status.

[0091] In this embodiment, the task execution status is fed back to the user in real time through the front-end interface, and the Java backend continuously monitors and processes the task status, which specifically includes:

[0092] The front-end interface built with Vue 3 displays the task execution status, point status information and task execution progress to the user in the form of charts, lists or maps;

[0093] The Java backend service obtains the latest data of task execution through database query and data processing in real time, and pushes it to the front-end interface;

[0094] It provides a task operation interface, allowing users to manually adjust task allocation strategies or query detailed information about specific tasks, while also recording user operation logs for subsequent analysis.

[0095] The following is another specific embodiment of this application:

[0096] 1. Data Preprocessing (Data Acquisition)

[0097] Data cleaning: The collected data, including the task status of the site manager, the inventory level of the specific site, the overall inventory of surrounding sites, the operational status of the site, the location of the site, and its sales volume in recent days, are first cleaned. This involves removing duplicate data, correcting erroneous data (such as obviously abnormal sales volume data), and handling missing values ​​(using methods such as mean imputation and regression prediction).

[0098] 2. Construct an evaluation model (intelligent analysis)

[0099] Task Priority Model: Task priority is determined based on the nature and urgency of the task, combined with the task status of the location manager. For example, if a location manager has a severe backlog of tasks and the new task is a replenishment task, and the location's inventory level is below the safety stock line, then this task should be set to high priority; if the location manager has few tasks and the new task is a routine inspection task, then the priority can be set to low. By comprehensively considering factors such as task type, location operation status, and inventory status, a task priority evaluation model based on rules or machine learning algorithms (such as decision tree algorithms) is constructed.

[0100] Equipment (Location) Adaptation Model: A model is constructed considering factors such as location, inventory level, and operational status. For locations with high sales volume and low inventory levels, replenishment tasks are prioritized; for locations with poor operational performance or potential problems, inspection and maintenance tasks are prioritized. Algorithms such as linear regression and cluster analysis are used to identify the correlation between different tasks and location characteristics, thereby determining the degree of adaptation of each location to different tasks.

[0101] 3. Task allocation strategy (dynamic scheduling)

[0102] Priority-based allocation: Tasks are allocated in descending order of priority. High-priority tasks are matched with locations that have a high degree of suitability. For example, for high-priority emergency replenishment tasks, priority is given to assigning them to locations with low inventory levels and close proximity (based on location information), provided that the overall inventory situation of surrounding locations allows, in order to reduce replenishment time and costs.

[0103] Load balancing allocation: When allocating tasks, the task status of the site managers is considered to avoid excessive concentration of tasks on certain site managers. A load balancing algorithm (such as weighted round-robin) is used to weight tasks based on factors such as the number and difficulty of tasks currently assigned to each site manager, ensuring that tasks are distributed relatively evenly among them and improving overall operational efficiency.

[0104] Resource Coordination and Allocation: Resources are allocated collaboratively based on the specific inventory level of a location and the overall inventory situation of surrounding locations. If a location has insufficient inventory, but surrounding locations have surplus inventory, inventory allocation between locations can be coordinated through task assignment to achieve optimal resource utilization. For example, inventory transfer tasks can be assigned to relevant locations, and transportation routes and times can be rationally arranged based on the location's operational status and location.

[0105] 4. Dynamic adjustment and optimization (executed in real time)

[0106] Real-time monitoring and feedback: The system monitors various data points during task execution in real time, including changes in inventory at different locations, sales fluctuations, and task completion progress. When actual conditions deviate from expectations, the system promptly provides feedback to the task allocation system. For example, if sales at a particular location suddenly increase significantly, leading to faster inventory depletion, the system should be able to detect this in real time and reassess the task allocation plan.

[0107] Model Updates and Optimization: Based on real-time feedback data and task execution results, the task priority model and equipment (location) adaptation model are updated regularly. For example, by analyzing the effectiveness of task allocation and execution over a period of time, algorithms such as reinforcement learning are used to adjust and optimize model parameters, making the task allocation scheme more consistent with actual operational conditions and continuously improving the accuracy and efficiency of task allocation.

[0108] 5. Visualization (Closed-Loop Monitoring)

[0109] Decision support system: Provides managers with suggestions and decision-making basis for task allocation. The system allocates tasks based on the optimal solution.

[0110] Visualized Display: Task status, location status information, and task execution progress are displayed visually on the management interface. The intuitive data presentation on the page facilitates real-time monitoring and adjustment of task allocation strategies by administrators.

[0111] The above method can be applied to the following two scenarios:

[0112] Smart Factory: In a smart factory scenario, Java backend services communicate with production equipment such as machine tools and robots to collect real-time operational data, such as speed, temperature, and pressure. Machine learning algorithms implemented in Java analyze this data to automatically generate equipment maintenance tasks. For example, when an abnormal temperature increase is detected in a machine tool component, a maintenance task is generated promptly. The Java service then schedules the tasks to appropriate robots for maintenance. Simultaneously, based on data from quality inspection equipment, production task allocation is dynamically adjusted. The frontend uses Vue 3 to build a visual interface, allowing managers to monitor equipment status, task progress, and production quality information in real time.

[0113] Intelligent Logistics: In intelligent logistics scenarios, Java backend services interact with warehouse shelf sensors and delivery vehicle GPS devices to exchange data. Based on collected warehouse inventory information, shelf status, and vehicle location information, optimization algorithms implemented in Java intelligently generate goods sorting and delivery tasks. Dynamic scheduling algorithms optimize vehicle delivery routes to improve logistics efficiency. Simultaneously, the Java backend continuously monitors task execution progress, such as whether goods are sorted on time and whether vehicles arrive at their destinations on time. The frontend uses Vue 3 to build a logistics management interface, allowing logistics managers to monitor the real-time transportation status of goods, warehouse inventory, and other information, enabling timely decision-making.

[0114] The effects achieved by this application include intelligent task management: the entire process of task generation, allocation, and monitoring is automated, reducing manual intervention and improving management efficiency by more than 30%.

[0115] Resource optimization: By aggregating the system, system utilization is increased by 25% and task execution time is reduced by 20%.

[0116] Please refer to Figure 2 The diagram illustrates a block diagram of an AIoT-based intelligent task management system provided in an embodiment of this application. The system may include:

[0117] The data acquisition module is used to communicate and connect with various IoT devices through a backend service written in Java, collect data from various IoT devices, and perform data preprocessing on the collected data.

[0118] The intelligent analysis module is used to perform in-depth analysis of preprocessed data using AI algorithms to build a task priority model and an equipment adaptation model. The task priority model is used to determine the task priority based on the nature and urgency of the task, combined with the task status of the site manager. The equipment adaptation model is used to determine the degree of adaptation of each site for different tasks based on factors such as equipment location, inventory level, and operational status.

[0119] The task allocation module is used to perform dynamic scheduling based on the results of intelligent analysis; wherein, the dynamic scheduling includes priority-based allocation, load balancing allocation, and resource collaborative allocation.

[0120] The real-time execution module is used by IoT devices to perform operations based on received dynamic scheduling instructions and to monitor various data during task execution in real time. Among these data, the monitored data include at least changes in point-of-sale inventory, sales fluctuations, and task completion progress.

[0121] The closed-loop monitoring module is used to provide real-time feedback on the task execution status to the user through the front-end interface, while the Java back-end continuously monitors and processes the task status.

[0122] In optional embodiments of this application, such as Figure 3 An architecture diagram of an AIoT (Artificial Intelligence of Things) based intelligent task management system is presented. This system architecture is divided into multiple layers, each with specific functions and components, working together to achieve intelligent task management. The following is a detailed explanation of this architecture diagram:

[0123] Presentation layer:

[0124] Mobile, PC, and Vue: These are the front-end interfaces through which users interact with the system, accessing and operating the system.

[0125] Gateway layer:

[0126] Nginx, Spring Gateway, Ribbon (load balancing): This layer is responsible for handling network request routing, load balancing, and reverse proxying, ensuring that requests can reach the backend service efficiently and stably.

[0127] Business layer:

[0128] Midst-executor service: responsible for tasks such as pulling Weiyun work orders and canceling work orders.

[0129] Weiyun: Handles tasks related to work order management and execution.

[0130] OTS service includes functions such as pushing work order status changes, pushing machine information, creating repair orders, synchronizing work orders with New Beiyang, and New Beiyang executing callbacks.

[0131] FeignAPI Settlement Center: Provides functions such as settlement management for New Beiyang, site settlement management, and new sales settlement management.

[0132] AIOT FeignAPI includes functions such as machine management, fault monitoring, and development management.

[0133] The new CMS FeignAPI is responsible for managing marketing data, including task management, campaign management, and replenishment management.

[0134] Kanban FeignAPI: Provides functions such as shipment analysis, daily average location analysis, and actual sales analysis.

[0135] middleware:

[0136] Eureka, the service registry, is used for service registration and discovery, helping various microservice components to identify and communicate with each other.

[0137] Apollo Configuration Center: Used for centralized management of configuration information and supports dynamic configuration updates.

[0138] RabbitMQ message queue: used for asynchronous message passing, decoupling direct calls between services, and improving the scalability and robustness of the system.

[0139] Business alarms: Monitor the operational status of business operations and trigger alarms when an anomaly is detected.

[0140] ELK (Elasticsearch Log) is used to collect, store, and analyze log data to help monitor system status and troubleshoot problems.

[0141] Access layer:

[0142] MybatisPlus: An enhanced version of the MyBatis ORM framework that simplifies database operations.

[0143] Seata Distributed Transactions: Used to manage transactions in distributed systems and ensure data consistency.

[0144] database:

[0145] MySQL: A relational database used to store structured data.

[0146] Redis: An in-memory database used for caching and fast data access.

[0147] ElasticSearch: A search engine for full-text search and analysis.

[0148] Through the collaboration of these layers and components, the entire system achieves fully automated and intelligent management of the entire process, from data acquisition, intelligent analysis, task allocation, real-time execution to closed-loop monitoring.

[0149] For specific limitations regarding the AIoT-based intelligent task management system, please refer to the limitations of the AIoT-based intelligent task management method mentioned above, which will not be repeated here. Each module in the aforementioned AIoT-based intelligent task management system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0150] In one embodiment, an electronic device is provided, which may be a computer, and its internal structure diagram may be as follows: Figure 4 As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database of the computer device is used for AIoT-based intelligent task management data. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an AIoT-based intelligent task management method.

[0151] Those skilled in the art will understand that, Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described AIoT-based intelligent task management method.

[0153] In one embodiment of this application, a computer program product is provided, including a computer program / instructions, which, when executed by a processor, implements the steps of the above-described AIoT-based intelligent task management method.

[0154] The computer-readable storage medium and computer program product provided in this embodiment are similar in implementation principle and technical effect to the above method embodiments, and will not be repeated here.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in M ​​forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An intelligent task management method based on AIoT, characterized in that, The method includes: S1 Data Acquisition: A backend service written in Java communicates and connects with various IoT devices to collect data from these devices and performs data preprocessing on the collected data. S2 Intelligent Analysis: The pre-processed data is analyzed in depth using AI algorithms to build a task priority model and an equipment adaptation model. The task priority model is used to determine the task priority based on the nature and urgency of the task, combined with the task status of the site manager. The equipment adaptation model is used to determine the degree of adaptation of each site to different tasks based on factors such as equipment location, inventory level, and operational status. S3 Task Allocation: Dynamic scheduling is performed based on the results of intelligent analysis; wherein, the dynamic scheduling includes priority-based allocation, load balancing allocation, and resource collaborative allocation; S4 Real-time Execution: IoT devices operate according to received dynamic scheduling instructions and monitor various data during task execution in real time; among them, the monitored data during task execution includes at least changes in point-of-sale inventory, sales fluctuations, and task completion progress; S5 closed-loop monitoring: The front-end interface provides real-time feedback on the task execution status to the user, while the Java back-end continuously monitors and processes the task status.

2. The intelligent task management method according to claim 1, characterized in that, In the S1 data acquisition step, data preprocessing includes: The collected data on the task status of the person in charge of the location, the inventory level of the specific location, the overall inventory of the surrounding locations, the operation status of the location, the location of the location and its sales volume in the past few days are cleaned to remove duplicate data and obviously abnormal data. For missing data, mean imputation, regression prediction, or other data imputation methods are used to process them; Data is standardized by converting different types of data into a unified format and unit.

3. The intelligent task management method according to claim 1, characterized in that, In the S2 intelligent analysis step, the process of building the task priority model includes: Collect multi-dimensional data; wherein, the multi-dimensional data includes at least the nature of the task, its urgency, the current task backlog of the site manager, the site's inventory level, and the site's operational status data; Use rule-based or machine learning algorithms to classify and evaluate task priorities; Tasks are categorized into high priority, medium priority, and low priority, with different priority weights set based on task type, location inventory status, and operational conditions.

4. The intelligent task management method according to claim 1, characterized in that, In the S3 task allocation step, the dynamic scheduling process includes: Priority-based allocation: tasks are assigned to locations with high suitability in descending order of priority. Load balancing: Based on the current number of tasks, task difficulty, and estimated completion time of the site supervisors, a weighted round-robin algorithm or other load balancing algorithms are used to ensure that tasks are evenly distributed to the site supervisors. Resource Coordination and Allocation: Combining the inventory level of a specific location with the overall inventory situation of surrounding locations, the algorithm coordinates the allocation of resources between locations, generates inventory transfer tasks, and plans transportation routes based on location and operational conditions.

5. The intelligent task management method according to claim 1, characterized in that, In the S4 real-time execution steps, the real-time monitoring process includes: By utilizing sensor networks and data acquisition modules, real-time data on changes in point inventory, sales fluctuations, and task completion progress can be obtained during task execution. The real-time monitoring data is compared with the expected data in the task allocation system. When the deviation exceeds the preset threshold, the anomaly detection algorithm is triggered. Exception information can be fed back to the task allocation system in real time through message queues or event-driven mechanisms, so that the task allocation scheme can be re-evaluated.

6. The intelligent task management method according to claim 1, characterized in that, In the S5 closed-loop monitoring process, the task execution status is fed back to the user in real time through the front-end interface, while the Java back-end continuously monitors and processes the task status, specifically including: The front-end interface built with Vue 3 displays the task execution status, location status information, and task execution progress to the user in the form of charts, lists, or maps. The Java backend service obtains the latest data on task execution in real time through database queries and data processing, and pushes it to the frontend interface. It provides a task operation interface, allowing users to manually adjust task allocation strategies or query detailed information about specific tasks, while also recording user operation logs for subsequent analysis.

7. An AIoT-based intelligent task management system, characterized in that, The system includes: The data acquisition module is used to communicate and connect with various IoT devices through a backend service written in Java, collect data from various IoT devices, and perform data preprocessing on the collected data. The intelligent analysis module is used to perform in-depth analysis of preprocessed data using AI algorithms to build a task priority model and an equipment adaptation model. The task priority model is used to determine the task priority based on the nature and urgency of the task, combined with the task status of the site manager. The equipment adaptation model is used to determine the degree of adaptation of each site for different tasks based on factors such as equipment location, inventory level, and operational status. The task allocation module is used to perform dynamic scheduling based on the results of intelligent analysis; wherein, the dynamic scheduling includes priority-based allocation, load balancing allocation, and resource collaborative allocation. The real-time execution module is used by IoT devices to perform operations based on received dynamic scheduling instructions and to monitor various data during task execution in real time. Among these data, the monitored data include at least changes in point-of-sale inventory, sales fluctuations, and task completion progress. The closed-loop monitoring module is used to provide real-time feedback on the task execution status to the user through the front-end interface, while the Java back-end continuously monitors and processes the task status.

8. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, which, when executed by the processor, implements the AIoT-based intelligent task management method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the AIoT-based intelligent task management method as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the AIoT-based intelligent task management method as described in any one of claims 1 to 6.

Images