Intelligent park comprehensive information management platform and construction method thereof

Abstract

The invention relates to the technical field of information management, particularly provides an intelligent park comprehensive information management platform and a construction method thereof, and solves the problem that risks of data leakage and network attack are increased due to centralized storage and processing of a large amount of data. The system comprises a data security management assembly, a monitoring and early warning assembly and a management and analysis assembly. The method comprises the following steps: developing a data encryption module, realizing access permission management, and setting access permissions of different levels; video monitoring and sensor equipment are integrated, and various activity and environment parameters in the park are collected in real time; developing an automatic recognition algorithm for abnormal behaviors and environment changes; an early warning mechanism is realized, when an abnormal condition is detected, an emergency plan is automatically triggered, and an early warning notification is sent to related personnel; integrating various data sources in the park; and the components are integrated to form a complete intelligent park comprehensive information management platform. According to the invention, an intelligent park comprehensive information management platform is constructed.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an intelligent park comprehensive information management platform and a construction method thereof. Background Art

[0002] The park's comprehensive information management involves comprehensive monitoring and management of various resources, facilities, personnel and activities within the park. Existing technologies mainly include the Internet of Things (IoT), big data analysis, cloud computing, artificial intelligence (AI) and geographic information systems (GIS). These technologies work together to achieve real-time collection, processing and analysis of various information within the park, thereby improving the park's operational efficiency and management level. Traditional park comprehensive information management technologies include: the Internet of Things (IoT) collects environmental data, equipment status and other information within the park in real time through sensors and network devices; big data analysis processes and analyzes the collected massive data to extract valuable information and support decision-making; cloud computing provides powerful computing and storage capabilities to support large-scale data processing and storage; artificial intelligence (AI) uses machine learning and deep learning technologies to achieve intelligent identification and prediction of various complex situations within the park; geographic information systems (GIS) combine map data to achieve spatial management and analysis of various resources and facilities within the park. The defects of these traditional technologies are: data between different systems and devices are difficult to communicate, forming information islands, affecting overall management efficiency; the integration and application of multiple technologies increase the complexity of the system, making maintenance and management difficult; the centralized storage and processing of large amounts of data increases the risk of data leakage and network attacks.

[0003] Prior art 1, Chinese patent, application number: 202310516493.3 discloses a smart park management platform based on big data, including a cloud platform and a smart park management platform. The smart park management platform is connected to the network end with an enterprise entry system, an equipment management system, an energy management system, a comprehensive security and fire protection management system, a smart customer service management system, a smart park basic information management system, a smart basic communication management system, and a park external information management system. Although the smart park management platform based on big data can provide enterprises with various infrastructure rental services, reduce enterprise investment costs, efficiently integrate offline resources, form a one-stop office model, and improve enterprise office efficiency, and the smart park can integrate the platform and establish a complete enterprise data collection and achievement display system. While improving the comprehensive influence of the park, it can also provide information support to the local government; however, the lack of special technical means to protect data privacy makes it more likely that various data will be leaked.

[0004] Prior art 2, application number: CN202310612330.5 discloses a comprehensive operation system and method for park management, including a comprehensive operation service platform, an information collection module, an information management identification module, a network security management system, and a visualization engine system; the comprehensive operation service platform performs operations within the park; the collection module collects production capacity parameters, energy consumption parameters, and enterprise information within the park, and connects with the visualization engine system; the information identification module detects personnel information within the park; the network security management system determines the health of the network and generates early warning information based on the health; the visualization engine system displays the internal buildings of the park. Although it effectively highlights the development trend characteristics of the operating status of equipment in the park, and thus greatly improves the timeliness of abnormal equipment maintenance and response, it provides enterprise managers with efficient and comprehensive management means, making park management more convenient and efficient; however, it involves many technologies, which puts forward high requirements on the degree of integration of each system; at the same time, it increases the research and development and use costs of the system.

[0005] Prior art three, Chinese patent, application number 202310798981.8 discloses a park comprehensive service management cloud storage system, which is equipped with a property management module and a security management module for managing the security management of things in the park, and a park enterprise information management module and a financial management module for the management query of park enterprise information business and finance, and a human resources management module is set for the enterprise operation management process. Although the Internet of Things technology is used in the security and energy consumption management modules to conduct real-time monitoring and analysis of various areas of the park, automated management and fault diagnosis, and provide personalized property services and solutions according to the different needs of enterprises in the park, and the data of various enterprises in the park can be shared through the park enterprise service platform, and data encryption and data access and download permission selection are set at the front end of data sharing; but its structure is relatively simple and the degree of intelligence is low, which is not conducive to the effective improvement of the comprehensive service quality of the park.

[0006] At present, the existing technologies 1, 2 and 3 have the problem that the centralized storage and processing of a large amount of data increases the risk of data leakage and network attacks. Therefore, the present invention provides an intelligent park comprehensive information management platform and a construction method thereof. Summary of the invention

[0007] In order to achieve the above object, the present invention adopts the following technical scheme:

[0008] One aspect of the present invention provides a smart park comprehensive information management platform, comprising the following steps:

[0009] Data security management component, used to encrypt operational data within the park and set access rights management for interactive data; record and monitor all data access and operation behaviors, and promptly detect and respond to potential security threats;

[0010] The monitoring and early warning component is used to monitor various activities and environmental parameters in the park in real time through video surveillance and sensors; automatically identify abnormal behaviors or environmental changes and issue early warnings in a timely manner; and automatically trigger emergency plans when abnormal situations are detected;

[0011] The management and analysis component is used to integrate various data sources within the park, use big data analysis to conduct in-depth mining of operational data, and provide decision support; the park's operating status and key indicators are displayed through a dashboard.

[0012] In an optional implementation, the data security management component includes:

[0013] The data classification and identification module is used to classify and identify the operational data within the park. According to the sensitivity of the data, the operational data within the park is divided into high-sensitivity data, medium-sensitivity data and low-sensitivity data; each piece of data is labeled with a sensitivity level through data labeling;

[0014] The encryption strategy and configuration module is used to use asymmetric encryption algorithms for highly sensitive data and lightweight encryption algorithms for medium and low sensitive data. Different encryption strategies are configured according to the storage location of operational data.

[0015] The data encryption and storage module is used to perform encryption processing when the operational data is generated or received; store the encrypted operational data in a certified secure storage environment, and perform integrity verification on the operational data through hashing; and automatically decrypt the data through key management when a user or system requests access to the operational data.

[0016] In an optional implementation, the monitoring and early warning component includes:

[0017] The multi-source data acquisition module is used to collect the behavior data and environmental parameters in the park in real time through the video surveillance equipment, sensor network and access control system deployed in the park; and clean the collected behavior data and environmental parameters;

[0018] The extraction and recognition module is used to extract key behavior features from the video stream using computer vision technology and identify normal and abnormal behavior patterns; it performs real-time analysis on environmental data collected by sensors, extracts key environmental parameter change features, and identifies abnormal changes in environmental parameters through time series analysis and anomaly detection algorithms;

[0019] The anomaly detection module is used to identify abnormal behaviors that do not conform to normal behavior patterns based on the extracted behavioral features and using anomaly detection algorithms; to monitor environmental parameters in real time and use anomaly detection algorithms to identify abnormal changes in environmental parameters; and when abnormal behaviors or environmental changes are detected, the system automatically generates an early warning signal.

[0020] In an optional implementation, the extraction and recognition module includes:

[0021] The feature extraction submodule is used to extract multi-dimensional features from the video stream. The multi-dimensional features include movement trajectory, dwell time, posture estimation and facial expression analysis features to form a comprehensive behavior feature vector;

[0022] The deep analysis submodule is used to map multi-dimensional features to high-dimensional feature space to form feature embedding vectors; learn high-dimensional representations of normal and abnormal behavior patterns through deep learning models; and classify feature embedding vectors using classifiers to distinguish normal and abnormal behaviors;

[0023] The threshold adjustment submodule is used to analyze the distribution characteristics of the current video stream in real time, calculate the mean and standard deviation; calculate the dynamic threshold based on the distribution characteristics; when the similarity between the behavior characteristics and the normal mode is lower than the dynamic threshold, it is determined to be abnormal behavior.

[0024] In an optional implementation, the depth analysis submodule includes:

[0025] The feature generation unit is used to generate a three-dimensional trajectory sequence through feature embedding vectors, calculate the target's residence time in a specific area, and form residence time features; use convolutional neural networks to extract skeleton key points from video frames to generate posture feature vectors; and combine with expression classifiers to generate expression features;

[0026] The feature embedding unit is used to extract spatial features using convolutional neural networks to capture local and global information in video frames. At the same time, it uses recurrent convolutional neural networks to capture time series features and generate feature embedding in the time dimension.

[0027] The behavior differentiation unit is used to perform nonlinear mapping on feature embeddings and learn high-dimensional representations of normal and abnormal behaviors. The classifier is used to classify the feature embedding vectors and distinguish normal and abnormal behaviors.

[0028] In an optional implementation, the feature embedding unit includes:

[0029] The convolution operation subunit is used to scan the video frame through multi-layer convolution kernels to extract the skeleton key points of the human body; the key points are mapped to a high-dimensional posture feature vector, which reflects the posture information of the target; through the convolution operation, the movement pattern of the facial muscles is captured, and the expression features are encoded into an expression feature vector for emotion analysis or behavior judgment; by performing convolution operations on the global and local areas of the video frame, the shape, contour and background information of the target are extracted;

[0030] The feature capture subunit is used to connect each frame of the video frame sequence in series through a loop connection to form a continuous time series; it captures the behavior trend of the target in the time dimension, whether the target stays in a certain area, and whether it changes direction frequently; the behavior trend is encoded into a time series feature vector for behavior pattern analysis;

[0031] The vector integration subunit is used to integrate the spatial feature vector extracted by the convolutional neural network and the time series feature vector extracted by the recurrent convolutional neural network through feature fusion to generate a unified feature embedding vector; the generated feature embedding vector contains the spatial features and time series features of the target.

[0032] In an optional implementation, the anomaly detection module includes:

[0033] The behavioral feature anomaly detection submodule is used to compare the defined normal behavioral features such as personnel movement trajectory, residence time and abnormal aggregation with the behavioral features that do not conform to the normal behavior pattern;

[0034] The environmental parameter anomaly detection submodule is used to compare the defined normal parameter ranges such as temperature and air quality with the environmental parameter changes that exceed the normal range;

[0035] The warning signal generation submodule is used to automatically generate a warning signal when abnormal behavior or abnormal changes in environmental parameters are detected.

[0036] In an optional implementation, the management and analysis component includes:

[0037] The data analysis module is used to aggregate the park operation data in time series, calculate daily, weekly and monthly key indicators, identify patterns and trends in the operation data, and generate statistical reports and trend charts; decompose the park operation data in time series, separate the trend, seasonality and random components, and predict future operation trends;

[0038] The report generation module is used to mine association rules in park operation data, identify the association between different events, and analyze the causal relationship in park operation; identify the key factors affecting park operation by setting intervention variables and control groups, and provide diagnostic insights; generate diagnostic reports based on association rules and causal analysis results;

[0039] The suggestion generation module is used to collect and process park operation data in real time, build a rule-based decision engine, and automatically generate decision suggestions according to preset business rules and logic; the decision results are displayed in the form of dashboards, reports and notifications, providing real-time operation status, forecast results and optimization suggestions to support managers' decision-making process.

[0040] In an optional implementation, it is suggested that the generation module includes:

[0041] The trigger logic submodule is used to match the operational data with the preset business rules. After the operational data enters the rule engine, the data is judged according to the preset rule conditions. When the data meets the specific rule conditions, the rule engine triggers the corresponding suggestions or actions.

[0042] The decision suggestion logic submodule is used to generate corresponding decision suggestions based on specific scenarios when the rule engine triggers the suggestion;

[0043] The real-time update submodule of the recommendations is used to update the optimized recommendations to the dashboard in real time and generate an optimization report that details the optimization process and effects of the recommendations.

[0044] Another aspect of the present invention provides a method for constructing an intelligent park comprehensive information management platform, comprising the following steps:

[0045] Develop data encryption modules to implement access rights management and set different levels of access rights; develop logging and monitoring systems to record and monitor all data access and operation behaviors in real time, and promptly detect and respond to potential security threats;

[0046] Integrate video surveillance and sensor equipment to collect real-time data on various activities and environmental parameters within the park; develop automatic recognition algorithms for abnormal behaviors and environmental changes; implement early warning mechanisms that automatically trigger emergency plans when abnormal situations are detected and send early warning notifications to relevant personnel;

[0047] Integrate various data sources within the park, including equipment data, personnel data, and environmental data; use big data analysis technology to conduct in-depth mining of operational data and provide decision support; develop dashboard functions to intuitively display the park's operating status and key indicators;

[0048] Integrate the components to form a complete smart park comprehensive information management platform; conduct comprehensive system testing, including functional testing, performance testing and security testing; deploy the platform to the actual park environment, conduct a trial run, make necessary adjustments and optimizations based on the trial run results, and then officially go online; regularly collect user feedback and data analysis results to continuously optimize and upgrade the platform.

[0049] The data security management component of the present invention encrypts the operational data in the park through an encryption algorithm to ensure the security of the data during transmission and storage, and prevent data leakage and tampering; by setting access rights, it ensures that only authorized personnel can access specific data and systems to prevent unauthorized access; records and monitors all data access and operation behaviors, promptly discovers and responds to potential security threats, and ensures the security and stability of the system. The significance achieved: through encryption and permission management, the security of park data is ensured, data leakage and illegal access are prevented, and the information security of the park is maintained; through security audits and monitoring, security threats are promptly discovered and handled, the occurrence of security accidents is reduced, and the management efficiency and security of the park are improved. The monitoring and early warning component monitors various activities and environmental parameters in the park in real time through video monitoring and sensors and other equipment to ensure the real-time and accuracy of park operations; uses AI algorithms and data models to automatically identify abnormal behaviors or environmental changes, and issues early warnings in a timely manner to reduce potential risks; when abnormal situations are detected, emergency plans are automatically triggered to quickly respond to and handle emergencies and reduce losses. Significance achieved: Through real-time monitoring and anomaly identification, potential safety hazards can be discovered and handled in a timely manner, and the security level of the park can be improved; by automatically triggering emergency plans, emergency events can be quickly responded to, losses can be reduced, and the emergency management capabilities of the park can be improved. The management and analysis components integrate various data sources in the park, including equipment data, personnel data, and environmental data, and conduct unified data management and analysis to ensure the integrity and consistency of the data; use big data analysis technology to conduct in-depth mining of operational data, provide decision support, and help managers make scientific decisions; display the park's operating status and key indicators through the dashboard, so that managers can quickly grasp the park's operating status and improve management efficiency. Significance achieved: Through big data analysis, scientific decision support is provided to help managers make more reasonable and effective decisions and improve the park's operating efficiency; through visual display, managers can intuitively understand the park's operating status and improve the transparency and efficiency of management. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0051] Figure 1This is a block diagram of the intelligent park comprehensive information management platform provided in Example 1 of the present invention;

[0052] Figure 2 This is a block diagram of a data security management component provided in Embodiment 2 of the present invention;

[0053] Figure 3 This is a block diagram of the monitoring and early warning components provided in Embodiment 3 of the present invention;

[0054] Figure 4 This is a block diagram of an extraction and recognition module provided in Embodiment 4 of the present invention;

[0055] Figure 5 This is a block diagram of the depth analysis submodule provided in Embodiment 5 of the present invention;

[0056] Figure 6 This is a block diagram of a feature embedding unit provided in Embodiment 6 of the present invention;

[0057] Figure 7 This is a block diagram of an abnormality detection module provided in Embodiment 7 of the present invention;

[0058] Figure 8 This is a block diagram of the management and analysis components provided in Embodiment 8 of the present invention;

[0059] Fig. 9 This is a block diagram of a suggestion generation module provided in Embodiment 9 of the present invention;

[0060] Fig.10 A flow chart of a method for constructing a smart park comprehensive information management platform provided in Embodiment 10 of the present invention;

[0061] Fig.11 is a block diagram of an electronic device provided in Embodiment 11 of the present invention;

[0062] Fig.12 This is a block diagram of the computer-readable storage medium provided in Example 12 of the present invention. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0064] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0065] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or, "connection" can be a direct connection, or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense, for example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, and can also be understood as electrical connection between different components in a circuit structure through physical lines such as copper foil or wires on a printed circuit board (PCB) that can transmit electrical signals to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an air-spaced / non-contact manner, for example, two components are electrically connected by capacitive coupling to transmit electrical signals.

[0066] In the embodiments of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change of the orientation of the components in the drawings.

[0067] The embodiments of the present invention can be widely used in various scenarios such as smart parks, industrial parks, science and technology parks, and commercial complexes. Specific applications include but are not limited to the following aspects: In smart industrial parks, the platform can be used to monitor the operating status of production equipment, environmental parameters (such as temperature, humidity, air quality, etc.) and personnel activities; through real-time monitoring and data analysis, it can timely detect equipment failures or environmental anomalies, automatically trigger early warnings and emergency plans, and reduce the occurrence of production interruptions and safety accidents. At the same time, through big data analysis, optimize production processes and improve production efficiency. In science and technology parks, the platform can be used to manage scientific research equipment, office facilities, personnel flow and other information in the park; through data integration and analysis, it can provide decision support for scientific researchers and managers, optimize resource allocation, and improve scientific research efficiency. At the same time, through video monitoring and sensor equipment, ensure the safety of the park and prevent scientific research data leakage. In commercial complexes, the platform can be used to monitor the passenger flow, environmental parameters (such as temperature, humidity, air quality, etc.) and equipment operating status in shopping malls; through real-time monitoring and data analysis, it can optimize shopping mall operations and improve customer experience. For example, adjust the layout of shops according to passenger flow data, adjust the air conditioning and lighting systems according to environmental parameters, and improve energy efficiency. At the same time, through the early warning mechanism, safety hazards can be discovered and handled in time to ensure the safety of customers and employees. In office parks, the platform can be used to manage information such as office equipment, personnel entry and exit, and conference room reservations; through data integration and analysis, it can optimize office resource allocation and improve office efficiency. For example, parking management can be optimized based on personnel entry and exit data, and the reservation system can be optimized based on the use of conference rooms. At the same time, video monitoring and sensor equipment can be used to ensure the safety and comfort of the office environment. In logistics parks, the platform can be used to monitor the operating status of logistics equipment, the cargo storage environment (such as temperature, humidity, etc.) and personnel activities; through real-time monitoring and data analysis, the logistics process can be optimized and logistics efficiency can be improved. For example, equipment scheduling can be optimized based on the operating status of the equipment, and storage conditions can be optimized based on the cargo storage environment. At the same time, through the early warning mechanism, safety hazards can be discovered and handled in time to ensure the safety of goods and personnel. In smart communities, the platform can be used to manage public facilities, environmental parameters (such as temperature, humidity, air quality, etc.) and personnel activities within the community; through real-time monitoring and data analysis, community management can be optimized and the quality of life of residents can be improved. For example, the operating status of public facilities can be adjusted based on environmental parameters, and community services can be optimized based on personnel activity data. At the same time, through the early warning mechanism, safety hazards are discovered and handled in a timely manner to ensure the safety of residents. The smart park comprehensive information management platform embodiment of this embodiment can be widely used in various smart parks and related scenarios. Through data security management, monitoring and early warning, management and analysis and other functions, the security, management efficiency and operation level of the park are improved, providing comprehensive support for the intelligent management of the park.

[0068] Embodiment 1:

[0069] like Figure 1 As shown, an embodiment of the present invention provides a smart park comprehensive information management platform, including:

[0070] Data security management component, used to encrypt operational data within the park and set access rights management for interactive data; record and monitor all data access and operation behaviors, and promptly detect and respond to potential security threats;

[0071] The monitoring and early warning component is used to monitor various activities and environmental parameters in the park in real time through video surveillance and sensors; automatically identify abnormal behaviors or environmental changes and issue early warnings in a timely manner; and automatically trigger emergency plans when abnormal situations are detected;

[0072] The management and analysis component is used to integrate various data sources within the park, including equipment data, personnel data, and environmental data; use big data analysis to conduct in-depth mining of operational data to provide decision support; and display the park's operating status and key indicators through a dashboard.

[0073] In the above embodiment, the data security management component of this embodiment encrypts the operational data in the park through an encryption algorithm to ensure the security of data during transmission and storage, and prevent data leakage and tampering; by setting access rights, ensure that only authorized personnel can access specific data and systems to prevent unauthorized access; record and monitor all data access and operation behaviors, timely discover and respond to potential security threats, and ensure the security and stability of the system. The significance achieved: through encryption and permission management, ensure the security of park data, prevent data leakage and illegal access, and maintain the information security of the park; through security auditing and monitoring, timely discover and deal with security threats, reduce the occurrence of security accidents, and improve the management efficiency and security of the park. The monitoring and early warning component monitors various activities and environmental parameters in the park in real time through video monitoring and sensors and other equipment to ensure the real-time and accuracy of park operations; using AI algorithms and data models, automatically identify abnormal behaviors or environmental changes, and issue early warnings in time to reduce potential risks; when abnormal situations are detected, automatically trigger emergency plans, quickly respond to and handle emergencies, and reduce losses. Significance achieved: Through real-time monitoring and anomaly identification, potential safety hazards can be discovered and handled in a timely manner, and the security level of the park can be improved; by automatically triggering emergency plans, emergency events can be quickly responded to, losses can be reduced, and the emergency management capabilities of the park can be improved. The management and analysis components integrate various data sources in the park, including equipment data, personnel data, and environmental data, and conduct unified data management and analysis to ensure the integrity and consistency of the data; use big data analysis technology to conduct in-depth mining of operational data, provide decision support, and help managers make scientific decisions; display the park's operating status and key indicators through the dashboard, so that managers can quickly grasp the park's operating status and improve management efficiency. Significance achieved: Through big data analysis, scientific decision support is provided to help managers make more reasonable and effective decisions and improve the park's operating efficiency; through visual display, managers can intuitively understand the park's operating status and improve the transparency and efficiency of management.

[0074] In summary, this embodiment jointly builds a comprehensive information management platform for an intelligent park, providing strong support for the daily operation and management of the park. The data security management component ensures the information security of the park; the monitoring and early warning component improves the security and emergency response capabilities of the park; the management and analysis component improves the scientific nature of the park's decision-making and management efficiency. The combined effect of these components not only improves the operational efficiency and management level of the park, but also provides solid technical support for the sustainable development of the park.

[0075] Embodiment 2:

[0076] like Figure 2As shown, based on Example 1, the data security management component provided by the embodiment of the present invention includes:

[0077] The data classification and identification module is used to classify and identify the operational data within the park. According to the sensitivity of the data, the operational data within the park is divided into highly sensitive data (such as financial data and personnel privacy data), medium sensitive data (such as equipment operation data) and low sensitive data (such as log data); each piece of data is labeled with a sensitivity level through data labeling;

[0078] The encryption strategy and configuration module is used to use asymmetric encryption algorithms for highly sensitive data and lightweight encryption algorithms for medium and low sensitive data. Different encryption strategies are configured according to the storage location of operational data.

[0079] The data encryption and storage module is used to perform encryption processing when the operational data is generated or received; store the encrypted operational data in a certified secure storage environment, and perform integrity verification on the operational data through hashing; and automatically decrypt the data through key management when a user or system requests access to the operational data.

[0080] In the above embodiment, the data classification and identification module of this embodiment can automatically classify the operational data in the park into three sensitivity levels of high, medium and low according to the sensitivity of the data; and label each piece of data with a sensitivity level to facilitate encryption policy configuration and access control. The significance achieved: Through classification and identification, differentiated security measures can be taken for data of different sensitivity levels to improve management efficiency; highly sensitive data (such as financial data, personnel privacy data) can be protected first to reduce the risk of data leakage or abuse; and ensure that sensitive data is reasonably protected. The encryption strategy and configuration module uses asymmetric encryption algorithms (such as RSA and ECC) for highly sensitive data to ensure the security of data transmission and storage; lightweight encryption algorithms (such as AES-CTR and ChaCha20) are used for medium and low sensitivity data to reduce computing overhead while ensuring security; different encryption strategies are configured according to the storage location of the data (such as local storage and cloud storage) to ensure the security of data in different environments. Significance achieved: Different encryption algorithms are used for data of different sensitivity levels to avoid resource waste and improve system performance; encryption strategies can be adjusted dynamically according to actual needs to adapt to changes in park operations; asymmetric encryption algorithms provide stronger security for highly sensitive data, and lightweight encryption algorithms provide efficient security protection for medium and low-sensitivity data. The data encryption and storage module immediately performs encryption processing when the operation data is generated or received to ensure that the data is always encrypted during transmission and storage; the encrypted data is stored in a certified secure storage environment to prevent the data from being illegally accessed or tampered with; the data integrity is checked through a hash algorithm (such as SHA-256) to ensure that the data has not been tampered with during storage and transmission; when a user or system requests access to the data, the key management system automatically decrypts the data to ensure data availability. Significance achieved: Encryption processing ensures that data will not be stolen or leaked during storage and transmission; hash verification ensures that the data has not been tampered with, improving data reliability; the automatic decryption mechanism simplifies the process of user access to data and improves user experience; the combination of a secure storage environment and a key management system further improves data security.

[0081] In summary, this embodiment builds a multi-level data security protection system through data classification, encryption policy configuration, encrypted storage and integrity verification; different encryption algorithms are used for data of different sensitivity levels to optimize the use of system resources; data encryption, storage and decryption processes are realized in real time and automated, which improves the system's response speed and user experience. Significance achieved: Through multi-level security measures, the risks of data leakage, tampering and abuse are effectively reduced; refined management and automated processes improve the efficiency of data security management and reduce the cost and risk of manual operations; secure storage and automatic decryption mechanisms ensure data availability and ensure the continuity of park business. The data security management component provides comprehensive, efficient and reliable data security protection for park operations, helping the park achieve digital transformation and high-quality development.

[0082] Embodiment 3:

[0083] like Figure 3 As shown, based on Example 1, the monitoring and early warning component provided by the embodiment of the present invention includes:

[0084] The multi-source data acquisition module is used to collect the behavior data and environmental parameters in the park in real time, including video stream, temperature, humidity, air quality and personnel flow, through the video surveillance equipment, sensor network and access control system deployed in the park; and clean the collected behavior data and environmental parameters;

[0085] The extraction and recognition module is used to use computer vision technology to extract key behavioral features from video streams, such as movement trajectories, dwell time, and abnormal aggregation of personnel, and identify normal and abnormal behavior patterns; perform real-time analysis on environmental data collected by sensors, extract key environmental parameter change features, such as sudden temperature changes and air quality degradation, and identify abnormal changes in environmental parameters through time series analysis and anomaly detection algorithms;

[0086] The anomaly detection module is used to identify abnormal behaviors that do not conform to normal behavior patterns based on the extracted behavioral features and using anomaly detection algorithms; to monitor environmental parameters in real time and use anomaly detection algorithms to identify abnormal changes in environmental parameters; and when abnormal behaviors or environmental changes are detected, the system automatically generates an early warning signal.

[0087] In the above embodiment, the multi-source data acquisition module of this embodiment collects the behavior data and environmental parameters in the park in real time through multi-source devices such as video surveillance equipment, sensor networks and access control systems to ensure the comprehensiveness and real-time nature of the data; cleans the collected raw data, removes noise and outliers, ensures the accuracy and consistency of the data, and provides a high-quality data basis for analysis and processing. The significance achieved: providing accurate and comprehensive data support for feature extraction, anomaly detection and early warning is the basis of the entire monitoring and early warning system; through real-time collection and cleaning, it ensures that the behavior and environmental changes in the park can be captured in time, providing data guarantee for rapid response to potential threats. The extraction and recognition module uses computer vision technology to extract key behavior features from the video stream, such as personnel movement trajectory, residence time and abnormal aggregation, etc., to provide a basis for behavior pattern recognition; real-time analysis of the environmental data collected by the sensor is performed to extract key environmental parameter change features, such as temperature mutation and air quality degradation, etc., to provide a basis for environmental anomaly detection; through time series analysis and anomaly detection algorithms, normal behavior patterns and abnormal behavior patterns are identified to ensure that the system can accurately distinguish between normal and abnormal situations. Significance achieved: Through behavioral feature extraction and pattern recognition, the system can automatically identify normal and abnormal behaviors in the park, reduce manual intervention, and improve monitoring efficiency; through real-time analysis of environmental parameters, the system can timely detect abnormal changes in the environment, ensure environmental safety in the park, and avoid safety accidents caused by environmental problems. The detection and classification module uses anomaly detection algorithms based on the extracted behavioral features to identify abnormal behaviors that do not conform to normal behavior patterns; monitor environmental parameters in real time, and use anomaly detection algorithms to identify abnormal changes in environmental parameters; when abnormal behavior or environmental changes are detected, the system automatically generates warning signals and pushes them to relevant managers in real time through multiple channels (such as SMS, email, alarm system, etc.). Significance achieved: Through automated anomaly detection and warning signal generation, potential security threats can be discovered and responded to in the first place, reducing the occurrence of safety accidents; according to the severity of the warning signal, the system automatically triggers the corresponding emergency plan to ensure safety in the park and reduce losses.

[0088] In summary, this embodiment provides an accurate and comprehensive data foundation for the entire monitoring and early warning system, ensuring real-time monitoring and rapid response; through intelligent feature extraction and pattern recognition, the system can automatically identify normal and abnormal behaviors and ensure the safety of behaviors and the environment in the park; through automated abnormal detection and early warning signal generation, the system can detect and respond to potential security threats in the first place and reduce the occurrence of security accidents. The various modules work together to ensure that the intelligent park comprehensive information management platform can automatically identify, warn and respond to abnormal behaviors and environmental changes, and ensure the safe operation of the park.

[0089] Embodiment 4:

[0090] like Figure 4 As shown, based on Example 3, the extraction and recognition module provided by the embodiment of the present invention includes:

[0091] The feature extraction submodule is used to extract multi-dimensional features from the video stream. The multi-dimensional features include movement trajectory, dwell time, posture estimation, and facial expression analysis to form a comprehensive behavior feature vector.

[0092] The deep analysis submodule is used to map multi-dimensional features to high-dimensional feature space to form feature embedding vectors; learn high-dimensional representations of normal and abnormal behavior patterns through deep learning models; and classify feature embedding vectors using classifiers to distinguish normal and abnormal behaviors;

[0093] The threshold adjustment submodule is used to analyze the distribution characteristics of the current video stream in real time, calculate the mean and standard deviation; calculate the dynamic threshold based on the distribution characteristics; when the similarity between the behavior characteristics and the normal mode is lower than the dynamic threshold, it is determined to be abnormal behavior.

[0094] The expression for calculating the dynamic threshold is:

[0095]

[0096] In the formula, T represents the dynamic threshold, which is used to determine whether the behavior feature is abnormal; μ represents the mean of the current video stream, which represents the average level of the behavior feature; σ represents the standard deviation of the current video stream, which represents the degree of fluctuation of the behavior feature; k 1 represents the tuning parameter used to control the threshold sensitivity based on the standard deviation; k 2 represents the adjustment parameter used to control the threshold sensitivity based on context information; k 3 represents the adjustment parameter used to control the threshold sensitivity based on the trend derivative; k 4 Represents adjustment parameters used to control the threshold sensitivity based on trend integration; Context represents context information, indicating the context relevance of the behavior features in the current video stream; for example, the behavior features of a specific time period, a specific scene, or a specific group of people; Trend represents trend information, indicating the changing trend of the behavior features in the current video stream. For example, the upward or downward trend of the behavior features; The first-order time derivative representing trend information indicates the rate of change of behavioral characteristics; The integral that represents trend information represents the cumulative effect of behavioral characteristics over a period of time.

[0097] In the above embodiment, the feature extraction submodule of this embodiment extracts multi-dimensional features such as movement trajectory, dwell time, posture estimation, facial expression analysis, etc. from the video stream to form a comprehensive behavior feature vector; through multi-dimensional features, it can more comprehensively describe the behavior pattern of individuals and capture subtle behavior changes that are difficult to identify by traditional methods; it can cope with complex scenes (such as crowded environments, light changes, etc.) and extract stable and representative behavior features. Significance achieved: The extraction of multi-dimensional features provides a rich data basis for subsequent deep analysis and significantly improves the accuracy of behavior recognition; through features such as posture and expression, it can better understand the behavior intention of individuals and provide support for personalized services and anomaly detection; the introduction of multi-dimensional features enables the system to maintain a high recognition ability in the face of complex environments. The deep analysis submodule maps multi-dimensional features to high-dimensional feature space to form a feature embedding vector, which is convenient for subsequent pattern learning and classification; through a deep learning model (such as CNN+RNN architecture), learn the high-dimensional representation of normal behavior patterns and abnormal behavior patterns, and capture the time and space characteristics of behavior; use a classifier to classify the feature embedding vector, distinguish normal behavior from abnormal behavior, and achieve efficient recognition. Significance achieved: The deep learning model can extract deep patterns from complex behavioral data and significantly improve the recognition ability of behavioral patterns; through the learning of high-dimensional feature space, it can better handle complex behavioral patterns and adapt to diverse application scenarios; the introduction of deep learning technology enables the system to have stronger self-learning and adaptive capabilities, and can continuously optimize the recognition model. The threshold adjustment submodule calculates the mean and standard deviation in real time according to the distribution characteristics of the current video stream, and dynamically adjusts the threshold for determining abnormalities; according to the distribution characteristics of the data, the threshold is dynamically calculated to ensure that the threshold can adapt to different environments and behavioral patterns; when the similarity between the behavioral characteristics and the normal pattern is lower than the dynamic threshold, it is determined to be abnormal behavior, achieving accurate anomaly detection. Significance achieved: The dynamic threshold can be adjusted according to the distribution characteristics of real-time data, avoiding the misjudgment problem caused by the fixed threshold, and significantly improving the accuracy of anomaly detection; the adaptive threshold can cope with complex and changing environments and behavioral patterns, so that the system can maintain efficient operation in different scenarios; by dynamically adjusting the threshold, the false alarm rate can be effectively reduced, the misjudgment of normal behavior can be reduced, and the reliability of the system can be improved.

[0098] In summary, the submodules of this embodiment jointly construct an efficient and intelligent behavior recognition system. The deep analysis submodule mainly uses a deep learning model to perform high-dimensional representation and classification of behavioral features, focusing on learning the patterns of normal and abnormal behaviors from a data-driven perspective; the threshold adjustment submodule focuses more on dynamically adjusting the threshold according to the distribution characteristics of real-time data to adapt to different scenarios and changes, ensuring the flexibility and accuracy of judgment. The feature extraction submodule provides comprehensive and high-quality behavioral feature data, laying the foundation for analysis; the deep analysis submodule extracts deep-level patterns from complex behavioral data through deep learning technology, significantly improving the recognition ability; the threshold adjustment submodule dynamically adjusts the threshold to ensure that abnormal behavior can be accurately determined in different scenarios and reduce the false alarm rate. Through the collaborative work of these submodules, not only can normal and abnormal behaviors be efficiently identified, but also complex and changeable environments and behavior patterns can be adapted, providing strong technical support for application scenarios such as security management and behavior analysis.

[0099] Embodiment 5:

[0100] like Figure 5 As shown, based on Example 4, the depth analysis submodule provided in this embodiment of the present invention includes:

[0101] The feature generation unit is used to generate a three-dimensional trajectory sequence through feature embedding vectors, calculate the target's residence time in a specific area, and form residence time features; use convolutional neural networks to extract skeleton key points from video frames to generate posture feature vectors; and combine with expression classifiers to generate expression features;

[0102] The feature embedding unit is used to extract spatial features using convolutional neural networks to capture local and global information in video frames. At the same time, it uses recurrent convolutional neural networks to capture time series features and generate feature embedding in the time dimension.

[0103] The behavior differentiation unit is used to perform nonlinear mapping on feature embeddings and learn high-dimensional representations of normal and abnormal behaviors. The classifier is used to classify the feature embedding vectors and distinguish normal and abnormal behaviors.

[0104] In the above embodiment, the feature generation unit of this embodiment generates a three-dimensional trajectory sequence of the target through a feature embedding vector, which can accurately describe the target's motion path in space; calculates the target's residence time in a specific area, which can reflect the target's behavior pattern and activity law; uses a convolutional neural network to extract skeleton key points from video frames to generate a posture feature vector, which can capture the target's body posture and action pattern; combines the expression classifier to generate expression features, which can reflect the target's emotional state and psychological activities. Significance achieved: The feature generation unit provides rich input data for subsequent in-depth analysis through the extraction of multi-dimensional features; these features can not only describe the target's physical behavior, but also reflect its emotional and psychological state, laying the foundation for a comprehensive analysis of the behavior pattern. The feature embedding unit uses a convolutional neural network to extract local and global information from the video frame, generates a spatial feature vector, and can capture the target's position and morphological changes in space; uses a recurrent convolutional neural network to capture time series features and generate feature embedding in the time dimension, which can reflect the target's dynamic changes and behavioral trends in time. Significance achieved: The feature embedding unit maps the multi-dimensional information in the video stream to a high-dimensional feature space through the collaborative extraction of spatial features and time series features; feature embedding can not only retain the detailed information of the original data, but also capture the temporal evolution of the behavior pattern, providing a high-dimensional feature representation for behavior differentiation. The behavior differentiation unit performs nonlinear mapping on the feature embedding, learns the high-dimensional representation of normal and abnormal behaviors, and can capture the complexity and diversity of behavior patterns; classifies the feature embedding vector using a classifier to distinguish between normal and abnormal behaviors, and can achieve accurate recognition and judgment of behavior patterns. Significance achieved: The behavior differentiation unit achieves accurate distinction between normal and abnormal behaviors through nonlinear mapping and classifier training; this distinction can not only identify potential abnormal behaviors, but also provide a basis for subsequent decision-making and intervention, thereby improving the intelligence level and application value of the system.

[0105] In summary, this embodiment jointly realizes the comprehensive extraction, mapping and classification of multi-dimensional features in the video stream. Through the collaborative work of these units, the behavior pattern of the target can be accurately captured, normal behavior and abnormal behavior can be distinguished, and powerful technical support is provided for application scenarios such as intelligent monitoring and behavior analysis. The hierarchical technical architecture not only improves the analysis ability of the system, but also provides broad space for future functional expansion and optimization.

[0106] Embodiment 6:

[0107] like Figure 6 As shown, based on Example 5, the feature embedding unit provided in this embodiment of the present invention includes:

[0108] The convolution operation subunit is used to scan the video frame through multi-layer convolution kernels to extract the skeleton key points of the human body (such as the head, shoulders, elbows and knees, etc.); the key points are mapped to a high-dimensional posture feature vector, which reflects the posture information of the target; through the convolution operation, the movement pattern of facial muscles, such as smiling, frowning and blinking, is captured, and the expression features are encoded into an expression feature vector for emotion analysis or behavior judgment; by performing convolution operations on the global and local areas of the video frame, the shape, contour and background information of the target are extracted;

[0109] The feature capture subunit is used to connect each frame of the video frame sequence in series through a loop connection to form a continuous time series; it captures the behavior trend of the target in the time dimension, such as whether the target stays in a certain area, whether it changes direction frequently, etc. The behavior trend is encoded into a time series feature vector for behavior pattern analysis;

[0110] The vector integration subunit is used to integrate the spatial feature vector extracted by the convolutional neural network and the time series feature vector extracted by the recurrent convolutional neural network through feature fusion to generate a unified feature embedding vector; the generated feature embedding vector contains the spatial features (such as posture, expression) and time series features (such as motion trajectory, behavior trend) of the target.

[0111] In the above embodiment, the convolution operation subunit of this embodiment scans the video frame through multi-layer convolution kernels, extracts the skeleton key points of the human body (such as the head, shoulders, elbows and knees, etc.), and maps these key points into a high-dimensional posture feature vector; at the same time, captures the movement pattern of facial muscles (such as smiling, frowning and blinking, etc.) and encodes it into an expression feature vector. In addition, by performing convolution operations on the global and local areas of the video frame, the shape, contour and background information of the target are extracted. Significance achieved: The feature vector can describe the posture and expression information of the target in detail, as well as the shape and background relationship of the target in space; it provides basic data for emotional analysis, behavior judgment and more complex scene understanding. The feature capture subunit connects each frame of data in the video frame sequence in series through a cyclic connection to form a continuous time series; captures the behavior trend of the target in the time dimension, such as whether the target stays in a certain area, whether it changes direction frequently, etc.; the behavior trend is encoded as a time series feature vector. Significance achieved: The time series feature vector can reflect the dynamic changes of the target over time and help analyze the target's behavior pattern, such as motion trajectory, dwell time, etc.; it is of great significance for understanding the target's long-term behavior pattern and predicting future behavior. The vector integration subunit integrates the spatial feature vector extracted by the convolutional neural network and the time series feature vector extracted by the recurrent convolutional neural network through feature fusion to generate a unified feature embedding vector; the vector contains the target's spatial features (such as posture, expression) and time series features (such as motion trajectory, behavior trend). Significance achieved: The unified feature embedding vector can comprehensively consider the spatial and temporal characteristics of the target and provide a comprehensive, multi-dimensional description; it provides strong support for more complex behavior analysis, scene understanding and intelligent decision-making.

[0112] In summary, the feature embedding unit of this embodiment can extract rich spatial and temporal features from video frames and generate a unified feature embedding vector, providing comprehensive and multi-dimensional data support for emotion analysis, behavior judgment, behavior pattern analysis, etc.

[0113] Embodiment 7:

[0114] like Figure 7 As shown, based on Example 3, the anomaly detection module provided by the embodiment of the present invention includes:

[0115] The behavioral feature anomaly detection submodule is used to compare the defined normal behavioral features such as personnel movement trajectory, residence time and abnormal aggregation with the behavioral features that do not conform to the normal behavior pattern;

[0116] The following behavioral features are extracted from the video stream:

[0117] Personnel movement trajectory: represented by a vector sequence, T = [(p1 ,t 1 ),(p 2 ,t 2 ),…,(p n ,t n )], where p i =(x i ,y i ) represents position, t represents time;

[0118] Residence time: expressed as residence time Δt, Δt = t end -t start ;

[0119] Abnormal aggregation: expressed by aggregation density D,

[0120] By comparing with normal behavior patterns, abnormal behavior is detected. The specific calculation process is as follows:

[0121] Calculate the behavioral characteristics mean μ and standard deviation σ of the normal behavior pattern;

[0122] For dwell time:

[0123]

[0124] Abnormal judgment: If a behavior feature f exceeds the range of normal behavior patterns, it is considered abnormal behavior;

[0125] For dwell time:

[0126] Δt>μ Δt +3σ Δt or Δt<μ Δt -3σ Δt

[0127] Abnormal detection of personnel movement trajectory:

[0128] Calculate the velocity sequence v of the moving trajectory = [v 1 ,v 2 ,…,v n-1 ],in

[0129] Calculate the statistical characteristics of the speed:

[0130]

[0131] Determine whether there is abnormal speed:

[0132] v i >μ v +3σ v or v i <μ v-3σ v

[0133] Detection of abnormal aggregation:

[0134] Calculate the statistical characteristics of the cluster density D:

[0135]

[0136] Determine whether there is abnormal aggregation:

[0137] D i >μ D +3σ D

[0138] The environmental parameter anomaly detection submodule is used to compare the defined normal parameter ranges such as temperature and air quality with the environmental parameter changes that exceed the normal range;

[0139] Calculation of environmental parameters:

[0140] Temperature: expressed as a time series, T = [T 1 ,T 2 ,…,T n ];

[0141] Humidity: expressed as a time series, H = [H 1 ,H 2 ,…,H n ].

[0142] Air quality: expressed as a time series, AQ = [AQ 1 ,AQ 2 ,…,AQ n ].

[0143] Detection of abnormal environmental parameter changes, the specific calculation process is as follows:

[0144] Calculate the statistical characteristics of environmental parameters:

[0145] Calculate the mean μ and standard deviation σ of environmental parameters:

[0146] For temperature:

[0147]

[0148] Abnormal judgment:

[0149] If a certain environmental parameter p exceeds the normal range, it is considered an abnormal change;

[0150] For temperature:

[0151] T i >μ T +3σ Tor T i <μ T -3σ T

[0152] Detect sudden changes in environmental parameters through time series analysis.

[0153] Calculate the temperature difference sequence ΔT = [T 2 -T 1 ,T 3 -T 2 ,…,T n -T n-1 ] and determine whether there is a mutation:

[0154] ΔT i >δ ΔT

[0155] where δ ΔT is the predefined mutation threshold;

[0156] Detection of air quality degradation:

[0157] Calculate statistical characteristics of air quality:

[0158]

[0159] Determine whether there is a decrease in air quality:

[0160] AQ i <μ AQ -3σ AQ

[0161] The warning signal generation submodule is used to automatically generate a warning signal when abnormal behavior or abnormal changes in environmental parameters are detected; the specific process is as follows:

[0162] If abnormal behavior is detected, an early warning signal is generated. Alert 1:

[0163]

[0164] Environmental abnormality warning:

[0165] If abnormal changes in environmental parameters are detected, an early warning signal is generated.

[0166]

[0167] The warning signals of abnormal behavior and environmental abnormalities are integrated to generate the final warning signal.

[0168] In the above embodiment, the behavior feature abnormality detection submodule of this embodiment can quantify and describe the behavior pattern of individuals or groups by extracting behavioral features such as personnel movement trajectory, residence time and abnormal aggregation; by comparing with the normal behavior pattern, statistical methods (such as mean and standard deviation) are used to identify behaviors that deviate from the normal pattern, especially through the 3σ principle (that is, data falling outside the mean ± 3 times the standard deviation is considered abnormal) to judge abnormal behavior. Significance: In public places or specific areas, abnormal behaviors such as abnormal aggregation and long-term residence can be discovered in time, which helps to prevent the occurrence of security incidents; through the analysis of behavioral data, the behavior pattern of the crowd can be deeply understood, providing data support for urban management, safety planning, etc. The environmental parameter abnormality detection submodule monitors environmental parameters such as temperature, humidity and air quality in real time to ensure that these parameters are within the normal range; through statistical analysis, changes in environmental parameters that exceed the normal range are identified, especially through the 3σ principle to judge abnormalities. Significance: Timely discovery of abnormal changes in environmental parameters, such as excessively high or low temperatures, reduced air quality, etc., helps to protect public health and safety; provides data support for environmental management and regulation, and helps relevant departments take timely measures to improve environmental quality. When abnormal behavior or abnormal changes in environmental parameters are detected, the early warning signal generation submodule can automatically generate an early warning signal and promptly notify relevant personnel or systems; it combines the early warning signals of abnormal behavior and abnormal environment to generate a comprehensive early warning signal to improve the accuracy and comprehensiveness of the early warning. Significance: Through the automated early warning system, it can quickly respond to abnormal situations, reduce reaction time, and improve the efficiency of emergency response; it provides managers with real-time early warning information to help them make quick and accurate decisions.

[0169] In summary, the various submodules of this embodiment jointly construct a comprehensive and efficient anomaly detection system. Through real-time monitoring and analysis of behavioral characteristics and environmental parameters, the system can promptly detect and warn of abnormal situations, thereby ensuring public safety, health and environmental quality. It not only improves the intelligence level of the monitoring system, but also provides strong technical support for urban management and social security.

[0170] Embodiment 8:

[0171] like Figure 8 As shown, based on Example 1, the management and analysis component provided by the embodiment of the present invention includes:

[0172] The data analysis module is used to aggregate the park operation data in time series, calculate key indicators on a daily, weekly and monthly basis, such as equipment operation time, energy consumption and personnel turnover, identify patterns and trends in the operation data, and generate statistical reports and trend charts; decompose the park operation data in time series, separate trend, seasonality and random components, and predict future operation trends;

[0173] The report generation module is used to mine association rules in park operation data, identify the association between different events, and analyze the causal relationship in park operation; identify the key factors affecting park operation by setting intervention variables and control groups, and provide diagnostic insights; generate diagnostic reports based on association rules and causal analysis results;

[0174] The suggestion generation module is used to collect and process park operation data in real time, build a rule-based decision engine, and automatically generate decision suggestions according to preset business rules and logic; the decision results are displayed in the form of dashboards, reports, notifications, etc., providing real-time operation status, forecast results and optimization suggestions to support managers' decision-making process.

[0175] In the above embodiments, the data analysis module of this embodiment can perform detailed aggregation and decomposition of the park operation data through time series analysis, identify trends, seasonality and random components in the data, help to deeply understand the internal structure of the data, and provide a basis for predicting future trends; calculate daily, weekly and monthly key indicators, such as equipment operation time, energy consumption and personnel flow, etc., to monitor the operation status of the park in real time and detect abnormal situations in time; through data analysis, it can identify patterns and trends in operation data, help managers understand the dynamic changes in operations, and make response strategies in advance. Significance achieved: Through in-depth data analysis, it is possible to optimize resource allocation, reduce waste, and improve the overall operational efficiency of the park; through time series decomposition and prediction, it is possible to predict future operation trends in advance, helping managers to formulate long-term plans and strategies; the generated statistical reports and trend charts provide a scientific basis for managers' decision-making, enhancing the accuracy and foresight of decision-making. The report generation module can identify the correlation between different events by mining the association rules in the park operation data, helping managers understand the causal chain between events; by setting intervention variables and control groups, it can identify the key factors affecting the park operation, provide diagnostic insights, and help managers find the root cause of the problem; according to the association rules and causal analysis results, a detailed diagnostic report is generated to provide a basis for managers' decision-making. Significance achieved: Through association rules and causal analysis, the park's operation strategy can be optimized, unnecessary resource waste can be reduced, and operational efficiency can be improved; the generated diagnostic report can help managers quickly locate problems and provide solutions to reduce risks in operation; through in-depth analysis, the park can be refined and the management level and operation quality can be improved. The suggestion generation module can collect and process park operation data in real time to ensure the timeliness and accuracy of the data; build a rule-based decision engine, which can automatically generate decision suggestions according to preset business rules and logic to improve the efficiency and accuracy of decision-making; display the decision results in the form of dashboards, reports, notifications, etc., provide real-time operation status, prediction results and optimization suggestions, and help managers make decisions quickly. Significance achieved: Through the automated decision-making engine, decision suggestions can be generated quickly, reducing the time cost of decision-making and improving decision-making efficiency; decision suggestions generated based on real-time data and preset rules can enhance the scientificity and accuracy of decisions and reduce the interference of human factors; through real-time operation status display and optimization suggestions, it can support managers' real-time management and improve the response speed and operational flexibility of the park.

[0176] In summary, the management and analysis components of this embodiment cooperate with each other to jointly improve the efficiency, scientificity and flexibility of park operations; through data analysis, report generation and suggestion generation, managers can better understand the dynamic changes of park operations, optimize resource allocation, improve operational efficiency, and quickly respond to changes in the market and environment to achieve sustainable development of the park.

[0177] Embodiment 9:

[0178] like Fig. 9 As shown, based on Example 8, the suggestion generation module provided in this embodiment of the present invention includes:

[0179] The trigger logic submodule is used to match the operational data with the preset business rules. After the operational data enters the rule engine, the data is judged according to the preset rule conditions. When the data meets the specific rule conditions, the rule engine triggers the corresponding suggestions or actions.

[0180] The decision suggestion logic submodule is used to generate corresponding decision suggestions according to specific scenarios when the rule engine triggers the suggestion. Its logic can be summarized as follows:

[0181] Scene recognition: First, identify the characteristics of the current scene (such as equipment type, energy consumption source, reasons for personnel movement, etc.);

[0182] Suggestion matching: Based on the scene characteristics, the system matches the most suitable suggestion from the preset suggestion library;

[0183] Suggestion generation: present the matched suggestions in text or chart form for managers’ reference;

[0184] The real-time update submodule of the recommendations is used to update the optimized recommendations to the dashboard in real time and generate an optimization report that details the optimization process and effects of the recommendations.

[0185] In the above embodiment, the trigger logic submodule of this embodiment performs real-time analysis of operational data through a rule engine, and can quickly and accurately match data with preset business rules; for example, equipment operating hours, energy consumption data, personnel flow data, etc. will be monitored in real time and compared with preset thresholds or trends; the trigger logic not only relies on static thresholds, but also dynamically adjusts based on factors such as trends in historical data and seasonal changes to ensure that the triggered recommendations are more accurate. Significance achieved: Through accurate data matching and triggering mechanisms, the system can quickly identify potential problems or optimization opportunities and reduce the time cost of manual intervention; for example, when the equipment operating hours exceed the safety threshold, the system can trigger maintenance recommendations in a timely manner to avoid production interruptions caused by equipment failures; the dynamic and flexible nature of the trigger logic enables the system to adapt to different business scenarios and demonstrate a higher level of intelligence. The decision suggestion logic submodule can match the most suitable suggestion from the preset suggestion library according to the characteristics of the current scenario (such as equipment type, energy consumption source, personnel turnover reason, etc.); for example, for equipment overheating, the system will generate specific maintenance suggestions; for excessive energy consumption, the system will generate energy-saving measures suggestions; it can generate different levels of suggestions (such as emergency suggestions, long-term optimization suggestions) according to factors such as urgency and business goals; at the same time, the suggestion generation logic will combine the manager's preferences and historical operating habits to provide personalized suggestions. Significance achieved: Through scenario-based suggestion generation, managers can obtain more targeted decision support and avoid blind decision-making; for example, through energy-saving measures, enterprises can reasonably adjust resource use and reduce operating costs; personalized suggestion generation logic enables the system to better meet the needs of different users and improve user satisfaction. The suggestion real-time update submodule can update the optimized suggestions to the dashboard in real time and generate a detailed optimization report to explain the optimization process and effect of the suggestions; dynamically adjust the suggestion content according to the effect data after the suggestion is executed (such as whether the equipment failure rate is reduced and whether the energy consumption is reduced); the suggestion generation, execution and feedback form a closed loop to ensure the scientificity and effectiveness of the suggestions. Significance achieved: Through real-time updates and feedback mechanisms, the system can continuously optimize the content of suggestions to ensure that the suggestions always match the actual needs; detailed optimization reports can enable managers to clearly understand the optimization process and effects of the suggestions and enhance their trust in the system; the closed-loop management mechanism enables the system to continuously learn and optimize, promoting continuous improvement and innovation of the enterprise.

[0186] To sum up, through precise rule matching, scenario-based suggestion generation and real-time optimization feedback, the system of this embodiment can greatly improve the operational efficiency and intelligence level of the enterprise; for example, it can reduce the failure rate through equipment maintenance suggestions and reduce energy consumption costs through energy-saving measures suggestions; personalized suggestion generation and detailed optimization reports enable the system to better meet user needs and enhance user trust in the system.

[0187] Embodiment 10:

[0188] like Fig.10 As shown, based on Embodiments 1 to 9, the method for constructing the intelligent park comprehensive information management platform provided by the embodiment of the present invention comprises the following steps:

[0189] Step S100: Develop a data encryption module to implement access rights management and set different levels of access rights; develop a log recording and monitoring system to record and monitor all data access and operation behaviors in real time, and promptly discover and respond to potential security threats;

[0190] Step S200: Integrate video surveillance and sensor equipment to collect various activities and environmental parameters in the park in real time; develop automatic recognition algorithms for abnormal behaviors and environmental changes; implement an early warning mechanism, automatically trigger an emergency plan when an abnormal situation is detected, and issue an early warning notification to relevant personnel;

[0191] Step S300: Integrate various data sources in the park, including equipment data, personnel data, and environmental data; use big data analysis technology to conduct in-depth mining of operational data to provide decision support; develop dashboard functions to intuitively display the park's operational status and key indicators;

[0192] Step S400: Integrate the components to form a complete intelligent park comprehensive information management platform; conduct comprehensive system testing, including functional testing, performance testing, and security testing; deploy the platform to the actual park environment, conduct a trial run, make necessary adjustments and optimizations based on the trial run results, and then officially go online; regularly collect user feedback and data analysis results to continuously optimize and upgrade the platform.

[0193] In the above embodiment, the development of the data security management component in step S100 of this embodiment ensures that the operational data in the park is effectively protected during transmission and storage to prevent data leakage and tampering; by setting different levels of access rights, it ensures that only authorized personnel can access sensitive data to enhance data security; it records and monitors all data access and operation behaviors in real time, promptly discovers and responds to potential security threats, and improves the security protection capabilities of the system. The significance achieved: ensure the security and privacy of park data, prevent data leakage and illegal access, and provide security guarantees for the normal operation of the park; through real-time monitoring and response mechanisms, it can quickly respond to security threats, reduce potential security risks, and improve the overall security level of the park. The development of the monitoring and early warning component in step S200 collects various activities and environmental parameters in the park in real time to provide comprehensive data support; it can promptly discover abnormal situations and reduce the omissions of human monitoring; when abnormal situations are detected, the emergency plan is automatically triggered, and an early warning notification is issued to relevant personnel to improve the emergency response speed. Significance achieved: Through real-time monitoring and automatic identification, abnormal situations can be discovered and handled in a timely manner, the possibility of accidents can be reduced, and the safety and stable operation of the park can be guaranteed; the automated early warning and emergency response mechanism can improve the efficiency of emergency handling, reduce human errors, and enhance the emergency management capabilities of the park. Step S300 Management and analysis component development integrates various data sources in the park, including equipment data, personnel data, and environmental data, etc., to provide comprehensive data support; conducts in-depth mining of operational data, provides decision support, and helps managers make scientific decisions; intuitively displays the park's operational status and key indicators, so that managers can grasp the park's situation in real time. Significance achieved: Through data integration and analysis, the park's operational status can be fully understood, providing a scientific basis for decision-making and improving management efficiency; the dashboard function enables managers to quickly obtain key information, respond in a timely manner, and improve the park's operational efficiency and decision-making level. Step S400: System integration and continuous optimization: Integrate all components to form a complete intelligent park comprehensive information management platform to ensure that all components work together; ensure the stability and reliability of the platform through functional testing, performance testing, and security testing; deploy the platform to the actual park environment and conduct a trial run to ensure that the platform can operate normally in actual operations; regularly collect user feedback and data analysis results, and continuously optimize and upgrade the platform to adapt to the changing needs of the park. Significance achieved: Through system integration and testing, ensure the stability and reliability of the platform, and provide a solid technical foundation for the intelligent management of the park; deployment and trial operation can verify the performance of the platform in the actual environment and ensure that the platform can meet the actual needs of the park; continuous optimization and upgrading can enable the platform to continuously adapt to the changing needs of the park and enhance the long-term value and use effect of the platform.

[0194] To sum up, through data security management, monitoring and early warning, management and analysis, system integration and continuous optimization, the platform of this embodiment can not only ensure the security and stability of the park, but also improve the management efficiency and decision-making level of the park, and provide comprehensive support for the intelligent management of the park.

[0195] Fig.11 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0196] The electronic device may include a central processing unit / microprocessor / main control chip, etc.; a storage medium, coupled to the central processing unit / microprocessor / main control chip, etc., and storing computer executable instructions therein, for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0197] The central processing unit / microprocessor / main control chip etc. may include but are not limited to, for example, one or more processors or microprocessors etc.

[0198] The storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0199] In addition, the electronic device may also include (but not limited to) a data bus, an input / output bus / external bus / device bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0200] The central processing unit / microprocessor / main control chip etc. can communicate with external devices via an I / O bus via a wired or wireless network (not shown).

[0201] The storage medium may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when executed by a central processing unit / microprocessor / main control chip, etc.

[0202] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0203] Fig.12 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0204] like Fig.12As shown, instructions are stored on a non-transitory computer-readable storage medium, and the instructions are, for example, computer-readable instructions. When the computer-readable instructions are executed by the processor, the various methods described above can be executed. The non-transitory computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-transitory non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0205] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0206] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0207] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0208] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the various embodiments of the method of the present invention through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0209] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A comprehensive information management platform for an intelligent park, characterized in that: The following steps are involved: Data security management component, used to encrypt operational data within the park and set access rights management for interactive data; record and monitor all data access and operation behaviors, and promptly detect and respond to potential security threats; The monitoring and early warning component is used to monitor various activities and environmental parameters in the park in real time through video surveillance and sensor equipment; automatically identify abnormal behaviors or environmental changes and issue early warnings in a timely manner; and automatically trigger emergency plans when abnormal situations are detected; The management and analysis component is used to integrate various data sources within the park, use big data analysis to conduct in-depth mining of operational data, and provide decision support; the park's operating status and key indicators are displayed through a dashboard.

2. The intelligent park comprehensive information management platform according to claim 1, characterized in that: Data security management components, including: The data classification and identification module is used to classify and identify the operational data within the park. According to the sensitivity of the data, the operational data within the park is divided into high-sensitivity data, medium-sensitivity data and low-sensitivity data; Use data labeling to label each piece of data with a sensitivity level; The encryption strategy and configuration module is used to use asymmetric encryption algorithms for highly sensitive data and lightweight encryption algorithms for medium and low sensitive data. Different encryption strategies are configured according to the storage location of operational data. The data encryption and storage module is used to perform encryption processing when the operational data is generated or received; store the encrypted operational data in a certified secure storage environment, and perform integrity verification on the operational data through hashing; and automatically decrypt the data through key management when a user or system requests access to the operational data.

3. The intelligent park comprehensive information management platform according to claim 1, characterized in that: Monitoring and early warning components, including: The multi-source data acquisition module is used to collect the behavior data and environmental parameters in the park in real time through the video surveillance equipment, sensor network and access control system deployed in the park; and clean the collected behavior data and environmental parameters; The extraction and recognition module is used to extract key behavior features from the video stream using computer vision technology and identify normal and abnormal behavior patterns; it performs real-time analysis on environmental data collected by sensors, extracts key environmental parameter change features, and identifies abnormal changes in environmental parameters through time series analysis and anomaly detection algorithms; An anomaly detection module, used to identify abnormal behaviors that do not conform to normal behavior patterns based on the extracted behavior features and using an anomaly detection algorithm; Environmental parameters are monitored in real time, and abnormal changes in environmental parameters are identified using anomaly detection algorithms; when abnormal behavior or environmental changes are detected, the system automatically generates an early warning signal.

4. The intelligent park comprehensive information management platform as claimed in claim 3, characterized in that: Extraction and recognition module, including: The feature extraction submodule is used to extract multi-dimensional features from the video stream. The multi-dimensional features include movement trajectory, dwell time, posture estimation and facial expression analysis features to form a comprehensive behavior feature vector; The deep analysis submodule is used to map multi-dimensional features to high-dimensional feature space to form feature embedding vectors; learn high-dimensional representations of normal and abnormal behavior patterns through deep learning models; and classify feature embedding vectors using classifiers to distinguish normal and abnormal behaviors; The threshold adjustment submodule is used to analyze the distribution characteristics of the current video stream in real time, calculate the mean and standard deviation; calculate the dynamic threshold based on the distribution characteristics; when the similarity between the behavior characteristics and the normal mode is lower than the dynamic threshold, it is determined to be abnormal behavior.

5. The intelligent park comprehensive information management platform as claimed in claim 4, characterized in that: In-depth analysis submodule, including: The feature generation unit is used to generate a three-dimensional trajectory sequence through feature embedding vectors, calculate the target's residence time in a specific area, and form residence time features; use convolutional neural networks to extract skeleton key points from video frames to generate posture feature vectors; and combine with expression classifiers to generate expression features; The feature embedding unit is used to extract spatial features using convolutional neural networks to capture local and global information in video frames. At the same time, it uses recurrent convolutional neural networks to capture time series features and generate feature embedding in the time dimension. The behavior differentiation unit is used to perform nonlinear mapping on feature embeddings and learn high-dimensional representations of normal and abnormal behaviors. The classifier is used to classify the feature embedding vectors and distinguish normal and abnormal behaviors.

6. The intelligent park comprehensive information management platform as claimed in claim 5, characterized in that: Feature embedding unit, including: The convolution operation subunit is used to scan the video frame through multi-layer convolution kernels to extract the skeleton key points of the human body; the key points are mapped to a high-dimensional posture feature vector, which reflects the posture information of the target; through the convolution operation, the movement pattern of the facial muscles is captured, and the expression features are encoded into an expression feature vector for emotion analysis or behavior judgment; by performing convolution operations on the global and local areas of the video frame, the shape, contour and background information of the target are extracted; The feature capture subunit is used to connect each frame of the video frame sequence in series through a loop connection to form a continuous time series; it captures the behavior trend of the target in the time dimension, whether the target stays in a certain area, and whether it changes direction frequently; the behavior trend is encoded into a time series feature vector for behavior pattern analysis; The vector integration subunit is used to integrate the spatial feature vector extracted by the convolutional neural network and the time series feature vector extracted by the recurrent convolutional neural network through feature fusion to generate a unified feature embedding vector; the generated feature embedding vector contains the spatial features and time series features of the target.

7. The intelligent park comprehensive information management platform as claimed in claim 3, characterized in that: Anomaly detection module, including: The behavioral feature anomaly detection submodule is used to compare the defined personnel movement trajectory, residence time and abnormal aggregation normal behavioral features with the behavioral features that do not conform to the normal behavior pattern; The environmental parameter anomaly detection submodule is used to compare the defined normal parameter ranges such as temperature and air quality with the environmental parameter changes that exceed the normal range; The warning signal generation submodule is used to automatically generate a warning signal when abnormal behavior or abnormal changes in environmental parameters are detected.

8. The intelligent park comprehensive information management platform according to claim 1, characterized in that: Management and analysis components, including: The data analysis module is used to aggregate the park operation data in time series, calculate daily, weekly and monthly key indicators, identify patterns and trends in the operation data, and generate statistical reports and trend charts; decompose the park operation data in time series, separate the trend, seasonality and random components, and predict future operation trends; The report generation module is used to mine association rules in park operation data, identify the association between different events, and analyze the causal relationship in park operation; identify the key factors affecting park operation by setting intervention variables and control groups, and provide diagnostic insights; generate diagnostic reports based on association rules and causal analysis results; The suggestion generation module is used to collect and process park operation data in real time, build a rule-based decision engine, and automatically generate decision suggestions according to preset business rules and logic; The decision results are displayed in the form of dashboards, reports and notifications, providing real-time operation status, forecast results and optimization suggestions to support managers' decision-making process.

9. The intelligent park comprehensive information management platform according to claim 8, characterized in that: It is recommended to generate modules, including: The trigger logic submodule is used to match the operational data with the preset business rules. After the operational data enters the rule engine, the data is judged according to the preset rule conditions. When the data meets the specific rule conditions, the rule engine triggers the corresponding suggestions or actions. The decision suggestion logic submodule is used to generate corresponding decision suggestions based on specific scenarios when the rule engine triggers the suggestion; The real-time update submodule of the recommendations is used to update the optimized recommendations to the dashboard in real time and generate an optimization report that details the optimization process and effects of the recommendations.

10. A method for constructing an intelligent park comprehensive information management platform, characterized in that: The following steps are involved: Develop data encryption modules to implement access rights management and set different levels of access rights; develop logging and monitoring systems to record and monitor all data access and operation behaviors in real time, and promptly detect and respond to potential security threats; Integrate video surveillance and sensor equipment to collect real-time data on various activities and environmental parameters within the park; develop automatic recognition algorithms for abnormal behaviors and environmental changes; Implement an early warning mechanism. When an abnormal situation is detected, the emergency plan is automatically triggered and an early warning notification is issued to relevant personnel; Integrate various data sources within the park, including equipment data, personnel data, and environmental data; use big data analysis technology to conduct in-depth mining of operational data and provide decision support; develop dashboard functions to intuitively display the park's operating status and key indicators; Integrate the components to form a complete smart park comprehensive information management platform; conduct comprehensive system testing, including functional testing, performance testing and security testing; deploy the platform to the actual park environment, conduct trial operation, adjust and optimize according to the trial operation results, and then officially put it online; regularly collect user feedback and data analysis results to continuously optimize and upgrade the platform.

Images