Store intelligent operation event whole-link management and control method based on edge-cloud cooperation

Abstract

This invention relates to the field of intelligent store operation management, and discloses a method for end-to-end control of intelligent store operation events based on edge-cloud collaboration. The method includes the following steps: constructing an integrated cloud-based control platform; collecting multi-source data from store edge hardware devices; relying on an edge-cloud hierarchical linkage identification architecture to determine device anomaly risks; completing multi-dimensional risk root cause tracing; automatically generating risk handling task data packages and pushing them to store employees; and establishing a complete session control link. This invention optimizes the accuracy of store anomaly identification and task matching efficiency, solving the problems of low intelligence, poor traceability, and delayed handling in traditional store management.

Description

Technical Field

[0001] This invention relates to the field of intelligent store operation management, and in particular to a method for full-link control of intelligent store operation events based on edge-cloud collaboration. Background Technology

[0002] Currently, intelligent operation and management of offline stores mostly adopt centralized cloud-based or isolated local management models, lacking the support of an integrated edge-cloud collaborative architecture. Traditional solutions rely on a single dimension for on-site data collection, often depending on single video or simple sensor data, making it difficult to achieve comprehensive status awareness. At the same time, event recognition often uses fixed threshold rules, which can only identify obvious surface anomalies and cannot uncover hidden risks related to customer flow, equipment, personnel, and transactions. Furthermore, account permissions, control strategies, and scheduling tasks are often managed independently and in a decentralized manner, lacking a unified configuration and session link management mechanism, which easily leads to problems such as permission confusion, incorrect task assignment, and data asynchrony.

[0003] Existing store operation incident handling systems generally suffer from pain points due to the fragmentation and disconnect between perception, identification, scheduling, and execution, failing to form a closed-loop control process across the entire chain. Most systems only complete abnormal event alarms, unable to automatically generate standardized handling tasks, let alone accurately match store managers and staff roles for targeted assignment, relying on subjective human judgment for handling, resulting in low efficiency and inconsistent standards; at the same time, the data interaction between edge devices and the cloud lacks optimization mechanisms, resulting in defects such as large raw data transmission volume, high bandwidth consumption, task loss in network outage scenarios, and inability to track and monitor execution status in real time, making it difficult to meet the refined and intelligent operation and management needs of large-scale chain stores.

[0004] This patent is based on an edge-cloud collaborative architecture to build a full-link management and control system for intelligent store operation events, which is used to solve the above problems and realize closed-loop intelligent management and control of the entire process of store perception, event recognition, task generation and implementation. Summary of the Invention

[0005] This invention overcomes the shortcomings of existing technologies and provides a method for full-link management and control of intelligent store operation events based on edge-cloud collaboration.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: The first aspect of this invention provides a method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration, comprising the following steps: An integrated management and control platform was built, and by combining edge hardware devices and employee identity information in stores, a two-way mapping relationship between employee roles, management and control strategies and edge devices was completed, resulting in an optimized integrated management and control platform. Within the target store, based on the optimized integrated management and control platform, control the edge hardware devices to collect data and preprocess the data, outputting the target edge structured features; Based on the target edge structured features, an edge-cloud hierarchical linkage method is adopted to assess the risk of the edge hardware devices of the target store and output the abnormal risk level of the edge hardware devices. By combining the optimized integrated management and control platform, the root causes of risks in edge hardware devices are identified, and corresponding risk handling task data packages for target stores are generated. By optimizing the integrated management and control platform, risk management task data packages for target stores are pushed to employees of the target stores in a targeted manner, and a session management and control link is established.

[0007] Furthermore, in a preferred embodiment of the present invention, the construction of an integrated management and control platform, and the binding of employee roles, management and control strategies, and edge devices in the store by combining edge hardware devices and employee identity information, to obtain an optimized integrated management and control platform, specifically involves: Identify stores that require full-chain operation and management, and mark them as target stores. In the target stores, build an integrated management and management platform, wherein the integrated management and management platform is cloud-based and integrates a role and permission configuration module, an operation strategy library module, a task scheduling module, and a session lifecycle management module. In the integrated management and control platform, all management and control resource information of the target store is accessed. This information is used by the integrated management and control platform to update and manage all management and control resource information of the target store, thus obtaining the target integrated management and control platform. In the target store, obtain all edge hardware devices and their corresponding specifications and functional attributes, determine the identity information of all employees in the target store, and use it to build an edge device resource archive and a standardized employee role archive. At the same time, import the edge device resource archive and the standardized employee role archive into the target integrated management and control platform for updating. Introduce a historical data network database to retrieve the operational scenario classifications of target stores and the corresponding control strategies for different operational scenarios; By using the integrated target management platform, and combining the operational scenario classification of target stores with the corresponding management strategies for different operational scenarios, the platform sets the criteria for judging abnormal events, risk level classification, and task assignment rules within the target stores. Define the target store's control area, assign roles and responsibilities to employees in the target store and bind their operation permissions within the target integrated control platform, and associate and match the target store's operation scenarios with the corresponding control strategies, edge hardware devices, and target store control areas to establish a two-way mapping relationship between employee roles, control strategies, and edge devices, and output an optimized integrated control platform.

[0008] Furthermore, in a preferred embodiment of the present invention, the step of controlling edge hardware devices to collect data and preprocess the data within the target store based on the optimized integrated management and control platform, and outputting the target edge structured features, specifically includes: Based on the optimized integrated management and control platform, all edge hardware devices in the target store are controlled in real time to collect data. During data collection, data of the same type is collected based on the device type of the edge hardware device and labeled as edge hardware device data. At the same time, the collection frequency and collection sequence are controlled to be the same through the optimized integrated management and control platform during the collection process. All edge hardware device data undergoes data preprocessing, including real-time noise reduction filtering, redundant data removal, and unified timestamp calibration, before being saved to the optimized integrated management and control platform. Key structured feature types are retrieved from historical network databases and used to extract and save structured features of all edge hardware device data after data preprocessing within the optimized integrated management and control platform, thereby obtaining the target edge structured features.

[0009] Furthermore, in a preferred embodiment of the present invention, the step of using a hierarchical edge-cloud linkage approach based on the target edge structured features to assess the risk of edge hardware devices in the target store and outputting the abnormal risk level of the edge hardware devices specifically involves: Within the optimized integrated management and control platform, control edge hardware devices perform preliminary anomaly screening of the target edge's structured features; Among them, in the historical network database, the preliminary anomaly screening and identification logic corresponding to the target edge structured features is retrieved and preset in the corresponding edge hardware device to perform preliminary anomaly screening on the target edge structured features and output the preliminary anomaly identification results. The preliminary anomaly identification results include the location of the anomaly on the edge hardware device, the time of the anomaly, the business scenario to which the anomaly belongs, and the preliminary anomaly type. The initial anomaly identification results are synchronously stored in the optimized integrated management and control platform. Through the optimized integrated management and control platform, hidden risks are mined from the initial anomaly identification results. The method for uncovering hidden risks involves retrieving and retrieving historical similar anomaly identification results associated with the primary anomaly identification results from the historical network database, as well as the corresponding operating data of the target store during the same period. Within the optimized integrated management and control platform, based on the multi-dimensional feature association comparison analysis method, the similarity between the primary anomaly identification result and the historical similar anomaly identification results is calculated. If the similarity is greater than the preset value, the operational risks of the target store's operating data corresponding to the historical similar anomaly identification results in the same period are retrieved from the historical network database and output as the implicit risks of the primary anomaly identification results. Within the optimized integrated management and control platform, the initial anomaly identification results and corresponding hidden risks are analyzed based on risk level classification rules to determine the anomaly risk level of edge hardware devices.

[0010] Furthermore, in a preferred embodiment of the present invention, the step of combining the optimized integrated management and control platform to determine the root causes of risks in edge hardware devices and generating corresponding risk management task data packages for target stores specifically includes: The abnormal risk level of edge hardware devices is stored in the optimized integrated management and control platform. Combined with the initial abnormal identification results and the corresponding hidden risks, the root causes of risks of edge hardware devices are determined within the optimized integrated management and control platform. The root causes of risks associated with edge hardware devices can be identified as device malfunctions, human error, and environmental factors. In the edge device resource archive of the optimized integrated management and control platform, real-time operating parameters of edge hardware devices are analyzed. If the real-time operating parameters of the edge hardware devices are not within the corresponding standard parameter threshold in the edge device resource archive, it is determined that the root cause of the risk of the edge hardware devices lies in the device's own failure factors. In optimizing the integrated management and control platform, the employee operation records and employee on-duty data of edge hardware devices at the time of the anomaly are retrieved and compared with the management and control strategies corresponding to different operating scenarios. If the employee operation records and employee on-duty data do not match the standard values ​​in the management and control strategies, it is determined that the root cause of the risk of the edge hardware devices is due to human factors. By optimizing the integrated management and control platform to retrieve the environmental data of the target store at the time of the anomaly, if the environmental data does not remain within the corresponding standard threshold, it is determined that the root cause of the risk of the edge hardware device is environmental factors. By optimizing the integrated management and control platform, the root causes of risks in edge hardware devices are analyzed, and risk management task data packages for target stores are generated.

[0011] Furthermore, in a preferred embodiment of the present invention, the step of analyzing the root causes of risks in edge hardware devices through an optimized integrated management and control platform to generate a risk management task data package for the target store specifically includes: By combining the root causes of risks, abnormal risk levels, corresponding primary anomaly identification results, and corresponding hidden risks of edge hardware devices, abnormal operational events of the target store are packaged and generated in the optimized integrated management and control platform. By optimizing the task dispatch rules in the integrated management and control platform, abnormal operational events of target stores are matched, and the handling priority of abnormal operational events is output. The method for outputting the priority of handling abnormal operation events is to match the abnormal operation event permissions of employees in the target store in the role permission configuration module based on the two-way mapping relationship between employee roles, control strategies and edge devices. By using the historical data network database, retrieve and recall the best handling cases of similar abnormal operational events at the same time, and mark them as the best handling cases in history; In optimizing the integrated management and control platform, the platform combines the employee permission matching results for abnormal operational events in the target store to divide the handling steps for abnormal operational events, and generates risk handling task data packages for the target store in the integrated management and control platform by combining the best historical handling cases.

[0012] Furthermore, in a preferred embodiment of the present invention, the step of optimizing the integrated management and control platform, specifically pushing risk management task data packages of the target store to the employees of the target store, and establishing a session management and control link, involves: Within the optimized integrated management and control platform, risk management task data packets for target stores are independently session encoded, and target task sessions are generated in conjunction with the session lifecycle management module. The target task session is pushed to the terminal devices of the employees in the target store. Combined with the target store employees' permission matching results for abnormal operation events, and in conjunction with the task scheduling module, the output of the target task session on the terminal devices of the employees in the target store is controlled to match the abnormal operation event handling steps corresponding to the abnormal operation event permission matching results. During the target task session push, the integrated management and control platform is optimized to record the push time and the handling status of abnormal operational events in real time, thereby generating a session management and control link.

[0013] This invention addresses the technical deficiencies in the existing technology and offers the following advantages: It constructs an integrated cloud-based management and control platform, combining multi-source data collection from store edge hardware devices. Relying on an edge-cloud hierarchical linkage identification architecture, it achieves device anomaly risk assessment, completes multi-dimensional risk root cause tracing, automatically generates risk handling task data packages, and pushes them to store employees, establishing a complete session management and control chain. This invention optimizes the accuracy of store anomaly identification and task matching efficiency, solving the problems of low intelligence, poor traceability, and delayed handling in traditional store management. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0015] Figure 1 A flowchart illustrating a method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration is shown. Figure 2 A flowchart illustrating the method for generating risk management task data packages for target stores is shown. Detailed Implementation

[0016] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flowchart illustrating a method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration is shown, including the following steps: S102: Build an integrated management and control platform, and combine edge hardware devices and employee identity information in stores to complete the two-way mapping relationship between employee roles, management and control strategies and edge devices, thereby optimizing the integrated management and control platform; S104: Within the target store, based on the optimized integrated management and control platform, control the edge hardware devices to collect data and preprocess the data, and output the target edge structured features; S106: Based on the target edge structured features, adopt the edge-cloud hierarchical linkage method to determine the risk of the edge hardware devices of the target store and output the abnormal risk level of the edge hardware devices. S108: Combined with the optimized integrated management and control platform, the root causes of risks in edge hardware devices are determined, and corresponding risk handling task data packages for target stores are generated. S110: By optimizing the integrated management and control platform, risk management task data packages for target stores are pushed to employees of the target stores in a targeted manner, and a session management and control link is established.

[0019] Furthermore, in a preferred embodiment of the present invention, the construction of an integrated management and control platform, and the binding of employee roles, management and control strategies, and edge devices in the store by combining edge hardware devices and employee identity information, to obtain an optimized integrated management and control platform, specifically involves: Identify stores that require full-chain operation and management, and mark them as target stores. In the target stores, build an integrated management and management platform, wherein the integrated management and management platform is cloud-based and integrates a role and permission configuration module, an operation strategy library module, a task scheduling module, and a session lifecycle management module. In the integrated management and control platform, all management and control resource information of the target store is accessed. This information is used by the integrated management and control platform to update and manage all management and control resource information of the target store, thus obtaining the target integrated management and control platform. In the target store, obtain all edge hardware devices and their corresponding specifications and functional attributes, determine the identity information of all employees in the target store, and use it to build an edge device resource archive and a standardized employee role archive. At the same time, import the edge device resource archive and the standardized employee role archive into the target integrated management and control platform for updating. Introduce a historical data network database to retrieve the operational scenario classifications of target stores and the corresponding control strategies for different operational scenarios; By using the integrated target management platform, and combining the operational scenario classification of target stores with the corresponding management strategies for different operational scenarios, the platform sets the criteria for judging abnormal events, risk level classification, and task assignment rules within the target stores. Define the target store's control area, assign roles and responsibilities to employees in the target store and bind their operation permissions within the target integrated control platform, and associate and match the target store's operation scenarios with the corresponding control strategies, edge hardware devices, and target store control areas to establish a two-way mapping relationship between employee roles, control strategies, and edge devices, and output an optimized integrated control platform.

[0020] It's important to note that the cloud-based integrated management and control platform integrates four core modules: permission configuration, policy library, task scheduling, and session management. This achieves centralized control and unified management, avoiding the problems of fragmented functions, independent modules, and poor compatibility inherent in traditional store systems. All store management resources are connected to the cloud platform, enabling resource aggregation and updates, and providing a visualized cloud-based aggregation of store management resources. Edge hardware devices, including but not limited to those connected to the cloud platform within the store, collect edge hardware parameters and employee identity information to establish an edge device resource archive and a standardized employee role archive, which are then synchronized to the cloud to support subsequent data mapping. Historical databases are introduced to retrieve management and control strategies corresponding to different store operating scenarios. These strategies are tailored to the actual operating conditions of the stores, and rules for anomaly detection, risk classification, and task assignment are developed based on these scenarios to avoid subjective judgment. Store management areas are divided, and employee responsibilities are assigned. Personnel, management strategies, edge devices, and management areas are interconnected and matched to generate an optimized integrated management and control platform.

[0021] Furthermore, in a preferred embodiment of the present invention, the step of controlling edge hardware devices to collect data and preprocess the data within the target store based on the optimized integrated management and control platform, and outputting the target edge structured features, specifically includes: Based on the optimized integrated management and control platform, all edge hardware devices in the target store are controlled in real time to collect data. During data collection, data of the same type is collected based on the device type of the edge hardware device and labeled as edge hardware device data. At the same time, the collection frequency and collection sequence are controlled to be the same through the optimized integrated management and control platform during the collection process. All edge hardware device data undergoes data preprocessing, including real-time noise reduction filtering, redundant data removal, and unified timestamp calibration, before being saved to the optimized integrated management and control platform. Key structured feature types are retrieved from historical network databases and used to extract and save structured features of all edge hardware device data after data preprocessing within the optimized integrated management and control platform, thereby obtaining the target edge structured features.

[0022] It's important to note that the platform acts as a central control hub, uniformly issuing data collection commands to manage real-time data collection from all peripheral hardware devices in the store. It also uniformly constrains the collection frequency and time nodes of all devices to ensure time consistency. This aims to avoid data incomparability and failed correlation analysis caused by inconsistent collection rhythms and time misalignments between different devices. Subsequently, the collected raw device data undergoes noise reduction filtering, invalid and redundant data removal, and unified timestamp calibration. After processing, it is saved to the control platform, achieving the goals of eliminating environmental interference noise and invalid duplicate data, standardizing data time references, and purifying the raw data source. Later, key structured feature types are retrieved, and the output is structured features. The aim is to retain only core features related to store operations and equipment anomalies, achieving data simplification, strong feature targeting, reduced cloud computing pressure, and improved anomaly identification speed.

[0023] Furthermore, in a preferred embodiment of the present invention, the step of using a hierarchical edge-cloud linkage approach based on the target edge structured features to assess the risk of edge hardware devices in the target store and outputting the abnormal risk level of the edge hardware devices specifically involves: Within the optimized integrated management and control platform, control edge hardware devices perform preliminary anomaly screening of the target edge's structured features; Among them, in the historical network database, the preliminary anomaly screening and identification logic corresponding to the target edge structured features is retrieved and preset in the corresponding edge hardware device to perform preliminary anomaly screening on the target edge structured features and output the preliminary anomaly identification results. The preliminary anomaly identification results include the location of the anomaly on the edge hardware device, the time of the anomaly, the business scenario to which the anomaly belongs, and the preliminary anomaly type. The initial anomaly identification results are synchronously stored in the optimized integrated management and control platform. Through the optimized integrated management and control platform, hidden risks are mined from the initial anomaly identification results. The method for uncovering hidden risks involves retrieving and retrieving historical similar anomaly identification results associated with the primary anomaly identification results from the historical network database, as well as the corresponding operating data of the target store during the same period. Within the optimized integrated management and control platform, based on the multi-dimensional feature association comparison analysis method, the similarity between the primary anomaly identification result and the historical similar anomaly identification results is calculated. If the similarity is greater than the preset value, the operational risks of the target store's operating data corresponding to the historical similar anomaly identification results in the same period are retrieved from the historical network database and output as the implicit risks of the primary anomaly identification results. Within the optimized integrated management and control platform, the initial anomaly identification results and corresponding hidden risks are analyzed based on risk level classification rules to determine the anomaly risk level of edge hardware devices.

[0024] It should be noted that the optimized integrated management and control platform serves as the control end, issuing identification commands to edge hardware devices for local preliminary screening of structured features. This approach boasts advantages such as fast screening response speed, no need for large-scale data uploads, and strong real-time performance. The screening and identification logic differs for each edge device, with pre-set logic ensuring it aligns with the store's historical operational patterns, offering strong adaptability and iterative updates. This logic performs preliminary anomaly screening of the target edge's structured features, outputting initial anomaly identification results. Because other factors may lead to hidden risks in the target store's edge hardware devices, the cloud needs to conduct in-depth analysis of the potential risks hidden behind apparent anomalies. The edge-cloud hierarchical linkage mechanism involves the edge device handling apparent anomaly screening, while the cloud handles in-depth analysis, achieving a hierarchical linkage analysis mechanism. Based on multi-dimensional feature association comparison analysis, the similarity between the initial anomaly identification results and historical similar anomaly identification results is calculated, providing data support for risk assessment. Subsequently, data association patterns are used to uncover potential hidden dangers, enabling anomaly risk prediction, preventing secondary derivative failures, and finally, risk quantification and grading are completed, providing a tiered basis for subsequent task prioritization, staff matching, and response plan generation.

[0025] Furthermore, in a preferred embodiment of the present invention, the step of optimizing the integrated management and control platform, specifically pushing risk management task data packages of the target store to the employees of the target store, and establishing a session management and control link, involves: Within the optimized integrated management and control platform, risk management task data packets for target stores are independently session encoded, and target task sessions are generated in conjunction with the session lifecycle management module. The target task session is pushed to the terminal devices of the employees in the target store. Combined with the target store employees' permission matching results for abnormal operation events, and in conjunction with the task scheduling module, the output of the target task session on the terminal devices of the employees in the target store is controlled to match the abnormal operation event handling steps corresponding to the abnormal operation event permission matching results. During the target task session push, the integrated management and control platform is optimized to record the push time and the handling status of abnormal operational events in real time, thereby generating a session management and control link.

[0026] It's important to note that in the optimized integrated management platform, each risk handling task data package is assigned a unique and independent session code. This is linked to the session lifecycle management module to generate a dedicated target task session. The advantage is that tasks are isolated from each other and do not interfere with each other, facilitating individual retrieval. Subsequently, the target task session is pushed to the terminals of store employees with matching permissions. Based on the task scheduling module and the employee's permission matching results for abnormal operational events, only the abnormal handling steps corresponding to their permissions and job responsibilities are displayed on the employee's terminal. Throughout the task session push and subsequent execution, the optimized integrated management platform records key information in real time, such as the task push time, employee read / unread status, handling progress, and completion status, maintaining a complete log to form a complete and traceable session management chain. This chain enables full-process status tracking of task issuance, reception, execution, and completion, providing complete data for post-event verification, accountability, and process optimization.

[0027] Figure 2 A flowchart illustrating a method for generating risk management task data packages for target stores is shown, including the following steps: S202: By combining the optimized integrated management and control platform, the root causes of risks in edge hardware devices are determined, and corresponding risk handling task data packages for target stores are generated. S204: Analyze the root causes of risks in edge hardware devices by optimizing the integrated management and control platform, and generate risk handling task data packages for target stores.

[0028] Furthermore, in a preferred embodiment of the present invention, the step of combining the optimized integrated management and control platform to determine the root causes of risks in edge hardware devices and generating corresponding risk management task data packages for target stores specifically includes: The abnormal risk level of edge hardware devices is stored in the optimized integrated management and control platform. Combined with the initial abnormal identification results and the corresponding hidden risks, the root causes of risks of edge hardware devices are determined within the optimized integrated management and control platform. The root causes of risks associated with edge hardware devices can be identified as device malfunctions, human error, and environmental factors. In the edge device resource archive of the optimized integrated management and control platform, real-time operating parameters of edge hardware devices are analyzed. If the real-time operating parameters of the edge hardware devices are not within the corresponding standard parameter threshold in the edge device resource archive, it is determined that the root cause of the risk of the edge hardware devices lies in the device's own failure factors. In optimizing the integrated management and control platform, the employee operation records and employee on-duty data of edge hardware devices at the time of the anomaly are retrieved and compared with the management and control strategies corresponding to different operating scenarios. If the employee operation records and employee on-duty data do not match the standard values ​​in the management and control strategies, it is determined that the root cause of the risk of the edge hardware devices is due to human factors. By optimizing the integrated management and control platform to retrieve the environmental data of the target store at the time of the anomaly, if the environmental data does not remain within the corresponding standard threshold, it is determined that the root cause of the risk of the edge hardware device is environmental factors. By optimizing the integrated management and control platform, the root causes of risks in edge hardware devices are analyzed, and risk management task data packages for target stores are generated.

[0029] It's important to note that risks have underlying causes. Combining primary anomalies with latent risks, and further considering the anomaly risk level, allows for root cause analysis of risks in edge hardware devices. First, all anomalies in edge hardware devices are categorized into three fixed types: device malfunction, human error, and environmental factors. For each category, the existence of a corresponding malfunction is determined using appropriate criteria. The identified root cause information (device malfunction, human error, and environmental factors) is then integrated with anomaly risk levels and location information to create a standardized risk management task data package within the platform. This data package unifies scattered anomaly information, root cause conclusions, and risk levels into a standardized data carrier, serving as a unified data format for subsequent task assignment, personnel matching, and session management.

[0030] Furthermore, in a preferred embodiment of the present invention, the step of analyzing the root causes of risks in edge hardware devices through an optimized integrated management and control platform to generate a risk management task data package for the target store specifically includes: By combining the root causes of risks, abnormal risk levels, corresponding primary anomaly identification results, and corresponding hidden risks of edge hardware devices, abnormal operational events of the target store are packaged and generated in the optimized integrated management and control platform. By optimizing the task dispatch rules in the integrated management and control platform, abnormal operational events of target stores are matched, and the handling priority of abnormal operational events is output. The method for outputting the priority of handling abnormal operation events is to match the abnormal operation event permissions of employees in the target store in the role permission configuration module based on the two-way mapping relationship between employee roles, control strategies and edge devices. By using the historical data network database, retrieve and recall the best handling cases of similar abnormal operational events at the same time, and mark them as the best handling cases in history; In optimizing the integrated management and control platform, the platform combines the employee permission matching results for abnormal operational events in the target store to divide the handling steps for abnormal operational events, and generates risk handling task data packages for the target store in the integrated management and control platform by combining the best historical handling cases.

[0031] It's important to note that by integrating multi-dimensional information on the root causes of risks from edge hardware devices, anomaly risk levels, initial anomaly identification results, and latent risks, this information is uniformly organized and packaged within the optimized integrated management platform. This forms standardized abnormal operational events for target stores, ensuring comprehensive information dimensions and a consistent format to avoid biases in subsequent judgments due to missing information. Based on pre-set task assignment rules, generated abnormal operational events are matched against these rules, automatically assigning a priority for handling each event. Furthermore, based on the bidirectional mapping relationship between employee roles, management strategies, and edge devices, the role and permission configuration module automatically matches store employees with the corresponding handling permissions and jurisdiction for each abnormal operational event—essentially, task assignment. After filtering historical best-case handling examples from the database, handling methods are derived. These historical best-case handling processes are supported by past examples, ensuring greater compliance, rationality, and practicality, thus reducing trial-and-error costs. Finally, based on the employee permission matching results, corresponding handling tasks and steps are divided. Simultaneously, process details are optimized by referring to historical best-case handling examples, ultimately integrating and packaging them within the platform to generate standardized risk handling task data packages.

[0032] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration, characterized in that, Includes the following steps: An integrated management and control platform was built, and by combining edge hardware devices and employee identity information in stores, a two-way mapping relationship between employee roles, management and control strategies and edge devices was completed, resulting in an optimized integrated management and control platform. Within the target store, based on the optimized integrated management and control platform, control the edge hardware devices to collect data and preprocess the data, outputting the target edge structured features; Based on the target edge structured features, an edge-cloud hierarchical linkage method is adopted to assess the risk of the edge hardware devices of the target store and output the abnormal risk level of the edge hardware devices. By combining the optimized integrated management and control platform, the root causes of risks in edge hardware devices are identified, and corresponding risk handling task data packages for target stores are generated. By optimizing the integrated management and control platform, risk management task data packages for target stores are pushed to employees of the target stores in a targeted manner, and a session management and control link is established.

2. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 1, characterized in that, The aforementioned construction of an integrated management and control platform, combined with edge hardware devices and employee identity information within the store, establishes a two-way mapping relationship between employee roles, management strategies, and edge devices, resulting in an optimized integrated management and control platform. Specifically: Identify stores that require full-chain operation and management, and mark them as target stores. In the target stores, build an integrated management and management platform, wherein the integrated management and management platform is cloud-based and integrates a role and permission configuration module, an operation strategy library module, a task scheduling module, and a session lifecycle management module. In the integrated management and control platform, all management and control resource information of the target store is accessed. This information is used by the integrated management and control platform to update and manage all management and control resource information of the target store, thus obtaining the target integrated management and control platform. In the target store, obtain all edge hardware devices and their corresponding specifications and functional attributes, determine the identity information of all employees in the target store, and use it to build an edge device resource archive and a standardized employee role archive. At the same time, import the edge device resource archive and the standardized employee role archive into the target integrated management and control platform for updating. Introduce a historical data network database to retrieve the operational scenario classifications of target stores and the corresponding control strategies for different operational scenarios; By using the integrated target management platform, and combining the operational scenario classification of target stores with the corresponding management strategies for different operational scenarios, the platform sets the criteria for judging abnormal events, risk level classification, and task assignment rules within the target stores. Define the target store's control area, assign roles and responsibilities to employees in the target store and bind their operation permissions within the target integrated control platform, and associate and match the target store's operation scenarios with the corresponding control strategies, edge hardware devices, and target store control areas to establish a two-way mapping relationship between employee roles, control strategies, and edge devices, and output an optimized integrated control platform.

3. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 1, characterized in that, Within the target store, based on the optimized integrated management and control platform, edge hardware devices are controlled to collect data and preprocess the data to output the target edge structured features, specifically: Based on the optimized integrated management and control platform, all edge hardware devices in the target store are controlled in real time to collect data. During data collection, data of the same type is collected based on the device type of the edge hardware device and labeled as edge hardware device data. At the same time, the collection frequency and collection sequence are controlled to be the same through the optimized integrated management and control platform during the collection process. All edge hardware device data undergoes data preprocessing, including real-time noise reduction filtering, redundant data removal, and unified timestamp calibration, before being saved to the optimized integrated management and control platform. Key structured feature types are retrieved from historical network databases and used to extract and save structured features of all edge hardware device data after data preprocessing within the optimized integrated management and control platform, thereby obtaining the target edge structured features.

4. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 1, characterized in that, Based on the target edge structured features, and using an edge-cloud hierarchical linkage approach, the risk assessment of the edge hardware devices in the target store is performed, and the abnormal risk level of the edge hardware devices is output. Specifically: Within the optimized integrated management and control platform, control edge hardware devices perform preliminary anomaly screening of the target edge's structured features; Among them, in the historical network database, the preliminary anomaly screening and identification logic corresponding to the target edge structured features is retrieved and preset in the corresponding edge hardware device to perform preliminary anomaly screening on the target edge structured features and output the preliminary anomaly identification results. The preliminary anomaly identification results include the location of the anomaly on the edge hardware device, the time of the anomaly, the business scenario to which the anomaly belongs, and the preliminary anomaly type. The initial anomaly identification results are synchronously stored in the optimized integrated management and control platform. Through the optimized integrated management and control platform, hidden risks are mined from the initial anomaly identification results. The method for uncovering hidden risks involves retrieving and retrieving historical similar anomaly identification results associated with the primary anomaly identification results from the historical network database, as well as the corresponding operating data of the target store during the same period. Within the optimized integrated management and control platform, based on the multi-dimensional feature association comparison analysis method, the similarity between the primary anomaly identification result and the historical similar anomaly identification results is calculated. If the similarity is greater than the preset value, the operational risks of the target store's operating data corresponding to the historical similar anomaly identification results in the same period are retrieved from the historical network database and output as the implicit risks of the primary anomaly identification results. Within the optimized integrated management and control platform, the initial anomaly identification results and corresponding hidden risks are analyzed based on risk level classification rules to determine the anomaly risk level of edge hardware devices.

5. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 1, characterized in that, The integrated management and control platform is optimized to determine the root causes of risks in edge hardware devices and generate corresponding risk management task data packages for target stores, specifically as follows: The abnormal risk level of edge hardware devices is stored in the optimized integrated management and control platform. Combined with the initial abnormal identification results and the corresponding hidden risks, the root causes of risks of edge hardware devices are determined within the optimized integrated management and control platform. The root causes of risks associated with edge hardware devices can be identified as device malfunctions, human error, and environmental factors. In the edge device resource archive of the optimized integrated management and control platform, real-time operating parameters of edge hardware devices are analyzed. If the real-time operating parameters of the edge hardware devices are not within the corresponding standard parameter threshold in the edge device resource archive, it is determined that the root cause of the risk of the edge hardware devices lies in the device's own failure factors. In optimizing the integrated management and control platform, the employee operation records and employee on-duty data of edge hardware devices at the time of the anomaly are retrieved and compared with the management and control strategies corresponding to different operating scenarios. If the employee operation records and employee on-duty data do not match the standard values ​​in the management and control strategies, it is determined that the root cause of the risk of the edge hardware devices is due to human factors. By optimizing the integrated management and control platform to retrieve the environmental data of the target store at the time of the anomaly, if the environmental data does not remain within the corresponding standard threshold, it is determined that the root cause of the risk of the edge hardware device is environmental factors. By optimizing the integrated management and control platform, the root causes of risks in edge hardware devices are analyzed, and risk management task data packages for target stores are generated.

6. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 5, characterized in that, The process involves optimizing the integrated management and control platform to analyze the root causes of risks in edge hardware devices and generating risk management task data packages for target stores. Specifically: By combining the root causes of risks, abnormal risk levels, corresponding primary anomaly identification results, and corresponding hidden risks of edge hardware devices, abnormal operational events of the target store are packaged and generated in the optimized integrated management and control platform. By optimizing the task dispatch rules in the integrated management and control platform, abnormal operational events of target stores are matched, and the handling priority of abnormal operational events is output. The method for outputting the priority of handling abnormal operation events is to match the abnormal operation event permissions of employees in the target store in the role permission configuration module based on the two-way mapping relationship between employee roles, control strategies and edge devices. By using the historical data network database, retrieve and recall the best handling cases of similar abnormal operational events at the same time, and mark them as the best handling cases in history; In optimizing the integrated management and control platform, the platform combines the employee permission matching results for abnormal operational events in the target store to divide the handling steps for abnormal operational events, and generates risk handling task data packages for the target store in the integrated management and control platform by combining the best historical handling cases.

7. The method for end-to-end management and control of intelligent store operation events based on edge-cloud collaboration as described in claim 1, characterized in that, The process involves optimizing the integrated management and control platform to push risk management task data packages for target stores directly to the store's employees and establishing a session management link. Specifically: Within the optimized integrated management and control platform, risk management task data packets for target stores are independently session encoded, and target task sessions are generated in conjunction with the session lifecycle management module. The target task session is pushed to the terminal devices of the employees in the target store. Combined with the target store employees' permission matching results for abnormal operation events, and in conjunction with the task scheduling module, the output of the target task session on the terminal devices of the employees in the target store is controlled to match the abnormal operation event handling steps corresponding to the abnormal operation event permission matching results. During the target task session push, the integrated management and control platform is optimized to record the push time and the handling status of abnormal operational events in real time, thereby generating a session management and control link.

Images