A data management method and system for an Internet of Things API docking platform

Abstract

The present invention proposes a data management method and system for an Internet of Things API docking platform, which obtains raw data through Internet of Things devices, obtains standardized data through format conversion; performs semantic analysis on standardized data, generates data models and constructs knowledge graphs; stores and tracks data, models, and knowledge graphs; obtains real-time data, performs format conversion and standardization; analyzes standardized real-time data according to pre-built models and knowledge graphs; performs intelligent processing and network optimization on analysis results; extracts image data collected by monitoring equipment; performs intelligent analysis on image data, identifies abnormal situations and issues warnings; and describes abnormal events as structured data and stores them according to the recognition results and preset models. The scheme of the present invention can timely and accurately identify various types of abnormalities, improve recognition accuracy and speed; and describe abnormal events as structured data, which is conducive to subsequent storage, query and analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a data management method and system for an Internet of Things API docking platform. Background Art

[0002] With the continuous development of IoT technology, various IoT devices and applications are widely connected to the network, generating a large amount of data. These data are often scattered in different IoT platforms and API interfaces, lacking effective centralized management and integration. Traditional data management methods have problems such as "different IoT devices and applications use different data formats and API interfaces, making it difficult to achieve cross-platform data interaction and integration" and "lack of a unified data management platform makes it difficult to effectively integrate and analyze data."

[0003] Therefore, there is an urgent need for a new data management method that can effectively solve pain points such as IoT data integration, security management, and analytical applications, and provide unified and efficient data support for IoT applications. Summary of the invention

[0004] Based on the above problems, the present invention proposes a data management method and system for an IoT API docking platform. Through the scheme of the present invention, various types of anomalies can be identified in a timely and accurate manner, improving the recognition accuracy and speed; and abnormal events can be described as structured data, which is conducive to subsequent storage, query and analysis.

[0005] In view of this, one aspect of the present invention proposes a data management method for an Internet of Things API docking platform, comprising:

[0006] Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data;

[0007] Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph;

[0008] Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data;

[0009] Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data;

[0010] Analyze the second data using the data meta-model and the knowledge graph to obtain third data;

[0011] The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm;

[0012] Extracting first image data collected by a preset monitoring device from the second data;

[0013] Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings;

[0014] According to the result of identifying the abnormal situation, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored.

[0015] Optionally, the step of acquiring first original data from the IoT device and performing unified standardization processing on the first original data through an adaptive data format conversion module to obtain the first data includes:

[0016] Build a universal interface that supports different types of IoT devices to upload data;

[0017] Build an adaptive data format conversion module based on machine learning for data formats of different devices;

[0018] Utilizing the adaptive data format conversion module to convert the format of the first raw data, and annotating the converted data with metadata, recording metadata such as device ID, data type, and collection time;

[0019] A transformation log of the first raw data is generated.

[0020] Optionally, the step of using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph includes:

[0021] Inputting the standardized first data into a semantic analysis module;

[0022] Using natural language processing and machine learning technology, perform semantic analysis on the first data, and identify semantic elements such as concepts, entities, and relationships contained in the first data;

[0023] Automatically build a data meta-model based on the semantic analysis results of the previous step;

[0024] Convert the identified semantic elements into nodes and edges in the knowledge graph to build a structured knowledge base containing semantic information;

[0025] Use machine learning technology to continuously learn and optimize semantic analysis, data meta-models, and knowledge graphs.

[0026] Optionally, the step of storing and tracing the first data, the data meta-model and the knowledge graph using blockchain technology through a blockchain-based data storage module to ensure the verifiability and non-tamperability of the first data includes:

[0027] Select a suitable blockchain platform, deploy blockchain network nodes, build a distributed ledger, and generate the first blockchain network;

[0028] Upload the first data, the data metamodel, and the knowledge graph to the first blockchain network, and store the first data, the data metamodel, and the knowledge graph in the form of blocks in a distributed ledger through a smart contract;

[0029] Establish digital identity certificates for identity authentication and authority management for each participant in the IoT API docking platform;

[0030] Set data access control policies based on the different roles of each participant to ensure data security;

[0031] Recording operations of creating, modifying, and accessing the first data, the data metamodel, and the knowledge graph, and generating an audit log;

[0032] Build a data query interface for all participants to query and verify data content according to their needs;

[0033] Optimize the performance and functionality of blockchain networks to support flexible integration of new data types and application scenarios based on business needs and technological development.

[0034] Optionally, the step of analyzing the second data by using the data meta-model and the knowledge graph to obtain third data includes:

[0035] Performing semantic verification and mapping of the second data with the data metamodel;

[0036] Analyze the verified and mapped second data using entities, attributes and relationships in the knowledge graph, and apply inference rules to infer third data; wherein the third data includes: data mining results, algorithm analysis output, prediction model discovery, user feedback, market research results and expert evaluation results;

[0037] According to the requirements of the application scenario, the third data is output in a suitable format.

[0038] Optionally, the real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and combines the network traffic regulation algorithm to dynamically optimize the API response speed, including:

[0039] Using a streaming computing engine to receive and process third data;

[0040] Design real-time analysis algorithms based on business needs to analyze third-party data and obtain real-time analysis results;

[0041] Monitor the access traffic and response time of the API interface, apply a dynamic traffic regulation algorithm based on feedback control, adjust the algorithm parameters according to real-time analysis results, and dynamically optimize the API response speed.

[0042] Optionally, the step of extracting first image data collected by a preset monitoring device from the second data includes:

[0043] Parsing the received second data, identifying and extracting image data frames carrying a mark of a preset monitoring device as first image data;

[0044] According to business requirements, format conversion and compression are performed on the first image data;

[0045] checking the integrity and validity of the extracted first image data;

[0046] Performing basic enhancement and optimization processing on the first image data;

[0047] The extracted first image data is persistently stored to support historical data query and analysis;

[0048] Design a data management module to provide fast retrieval and access capabilities for first image data;

[0049] According to business needs, data encryption and access control measures are implemented to ensure the integrity and confidentiality of the first image data and protect privacy information.

[0050] Optionally, the step of using a monitoring and analysis module based on image recognition to intelligently analyze the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings includes:

[0051] Performing preprocessing operations of format conversion, scale adjustment, and color correction on the first image data to obtain second image data;

[0052] Acquire historical monitoring image data, and construct an image sample data set based on the historical monitoring image data;

[0053] Choose the appropriate deep learning model architecture;

[0054] Use image sample datasets to conduct supervised learning on the model and optimize model parameters;

[0055] Improve the recognition accuracy and generalization ability of the model through model evaluation and tuning;

[0056] Deploy the trained deep learning model to the monitoring and analysis module;

[0057] Define the rules for judging abnormal situations;

[0058] In combination with the judgment rules, a deep learning model is used to intelligently analyze the second image data to identify whether there is an abnormality;

[0059] When there is an abnormal situation, the early warning mechanism is triggered;

[0060] Classify abnormal situations and assess their severity based on business needs.

[0061] Optionally, the step of generating abnormal event description data according to a preset abnormal event model based on the result of identifying the abnormal situation, and storing the abnormal event description data includes:

[0062] Determine the basic information of abnormal events;

[0063] According to the pre-defined abnormal event model, the basic information of the identified abnormal event is converted into standardized abnormal event description data;

[0064] The generated abnormal event description data is stored in a preset database or file system.

[0065] Another aspect of the present invention provides a data management system for an Internet of Things API docking platform, comprising: an Internet of Things device; a monitoring device; and a management server provided with an adaptive data format conversion module, a semantic analysis module, a data storage module, a real-time data stream analysis module, and a monitoring analysis module;

[0066] The management server is configured to:

[0067] Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data;

[0068] Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph;

[0069] Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data;

[0070] Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data;

[0071] Analyze the second data using the data meta-model and the knowledge graph to obtain third data;

[0072] The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm;

[0073] Extracting first image data collected by a preset monitoring device from the second data;

[0074] Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings;

[0075] According to the result of identifying the abnormal situation, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored.

[0076] The data management method for the Internet of Things API docking platform adopts the technical solution of the present invention, including: obtaining first original data from an Internet of Things device, and performing unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data; performing semantic analysis on the standardized first data using a semantic analysis module based on machine learning technology, automatically generating a data meta model and constructing a knowledge graph; using a blockchain-based data storage module, using blockchain technology to store and trace the first data, the data meta model and the knowledge graph, to ensure the verifiability and non-tamperability of the first data; obtaining first real-time data from an Internet of Things device, and converting the first real data into the first real data through an adaptive data format conversion module. The real-time data is uniformly standardized to obtain second data; the second data is analyzed by using the data meta-model and the knowledge graph to obtain third data; the real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic regulation algorithm; first image data collected by a preset monitoring device is extracted from the second data; a monitoring and analysis module based on image recognition is used to intelligently analyze the first image data based on image recognition and deep learning technology to identify abnormal situations and trigger early warnings; according to the results of identifying abnormal situations, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored. Through the scheme of the present invention, by utilizing advanced image recognition and deep learning technologies, various abnormal situations can be identified in a timely and accurate manner, and relevant basic information can be obtained; through continuous data analysis and algorithm optimization, the accuracy and speed of abnormal event identification are continuously improved; according to the predefined abnormal event model, the identified abnormal situation is converted into structured abnormal event description data; the standardized data format is conducive to subsequent storage, query and analysis, and improves the readability and processability of information; the generated abnormal event description data is persistently stored in a database or file system to build a complete abnormal event history record; and reliable data support is provided for subsequent data analysis, tracing and auditing. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a flow chart of a data management method for an Internet of Things API docking platform provided by an embodiment of the present invention;

[0078] Figure 2 It is a schematic block diagram of a data management system for an Internet of Things API docking platform provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0080] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0081] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0082] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0083] Refer to the following Figure 1 to Figure 2 To describe a data management method and system for an Internet of Things API docking platform provided according to some embodiments of the present invention.

[0084] like Figure 1 As shown, an embodiment of the present invention provides a data management method for an Internet of Things API docking platform, comprising:

[0085] Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data;

[0086] In this step, IoT devices include but are not limited to: sensing devices (such as temperature and humidity sensors, light sensors, location sensors (GPS, RFID, Bluetooth, etc.); motion sensors (accelerometers, gyroscopes, etc.), environmental monitoring sensors (air quality, water quality, etc.), physiological health sensors (such as heart rate, blood pressure, etc.), etc.); execution devices (such as industrial automation equipment (mechanical arms, assembly lines, etc.), home smart devices (such as lights, air conditioners, electrical appliances, etc.), drones / robots and other smart mobile devices, etc.); gateway devices (such as routers, bridges, protocol converters, etc.); communication devices (smartphones, tablets, IoT modules (WiFi / Bluetooth / NB-IoT, etc.), IoT gateways, etc.); storage devices (such as cloud storage servers, edge computing devices, etc.); processing devices (such as servers, embedded microprocessors, industrial PCs, etc.); etc. The adaptive data format conversion module includes: a data acquisition adapter that can automatically identify and adapt the data formats of various IoT devices; a unified data model mapping engine that converts raw data into a standardized data model; a real-time data preprocessing function that cleans, corrects, and normalizes the data.

[0087] Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph;

[0088] In this step, the semantic analysis module based on machine learning includes: a natural language processing engine to extract key concepts, attributes and entities in the data; a knowledge graph construction algorithm to establish semantic associations between data and form a knowledge network; and a transfer learning model to quickly adapt to data semantics in different fields using pre-trained models.

[0089] Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data;

[0090] In this step, the blockchain-based data storage module includes: a distributed ledger storage engine that stores data in an unalterable blockchain structure; a smart contract management system that defines and automatically executes rules for data access and sharing; and privacy computing technology that enables secure processing and joint analysis of sensitive data.

[0091] Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data;

[0092] In this step, raw data is obtained from IoT devices in real time through various connection protocols (such as MQTT, HTTP, CoAP, etc.), supporting access to multiple data encoding formats (such as JSON, XML, binary, etc.), and having the ability to automatically identify device types and data formats; dynamically calling the corresponding data parser for parsing according to the device type and data encoding format; converting raw data into a unified target data format through an adaptive data mapping module; supporting the expansion of new device types and data formats without modifying the core system; performing semantic and grammatical checks on the converted data to ensure the integrity and legality of the data; performing unified unit conversion, numerical normalization and other operations on the data according to predefined data standards to generate second data that meets the requirements of the target system; using a cache mechanism to temporarily store data for data loss caused by network anomalies or device offline, and automatically retransmitting when the network is restored; supporting real-time monitoring and query of cached data for troubleshooting and data supplementation; using an asynchronous non-blocking I / O model to handle a large number of device access and data conversion tasks at the same time; using multi-threading / multi-process technology to dynamically expand the system's concurrent processing capabilities according to hardware resources; using memory caching, indexing and other technologies to optimize data storage and query performance. Through the above implementation steps, it can support a variety of IoT device types and data encoding formats, and have adaptive data access capabilities; it can quickly and accurately convert raw data into a standardized target data format; it has mechanisms such as data verification, caching, and retransmission to ensure data integrity and reliability; it adopts an asynchronous non-blocking, multi-threaded / multi-process architecture design to support large-scale device access and data processing; it supports dynamic integration of new device types and data formats without modifying the core system. In short, this solution can effectively obtain real-time data from IoT devices, and through adaptive data format conversion and standardized processing, it provides high-quality data in a unified format for the upper-level application system to meet the various needs of IoT applications.

[0093] Analyze the second data using the data meta-model and the knowledge graph to obtain third data;

[0094] The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm;

[0095] In this step, the real-time data stream analysis module includes: a complex event processing engine that monitors abnormal patterns in data streams in real time and triggers early warnings; a dynamic traffic control algorithm that automatically adjusts the API response strategy based on network load conditions; and a joint optimization engine that coordinates multiple modules such as data analysis, network control, and security policies.

[0096] Extracting first image data collected by a preset monitoring device from the second data;

[0097] Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings;

[0098] In this step, the monitoring and analysis module based on image recognition includes: a video monitoring adapter, which connects to various monitoring devices and unifies the data format; a deep learning image recognition model, which realizes target detection and abnormal behavior recognition of images; a multi-source data fusion engine, which combines video streams, sensor data, etc. for comprehensive analysis.

[0099] According to the result of identifying the abnormal situation, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored.

[0100] By adopting the technical solution of this embodiment and utilizing advanced image recognition and deep learning technologies, various abnormal situations can be identified in a timely and accurate manner, and relevant basic information can be obtained; the accuracy and speed of abnormal event identification can be continuously improved through continuous data analysis and algorithm optimization; the identified abnormal situations can be converted into structured abnormal event description data according to the predefined abnormal event model; the standardized data format is conducive to subsequent storage, query and analysis, and improves the readability and processability of information; the generated abnormal event description data is persistently stored in a database or file system to build a complete abnormal event history record; and reliable data support is provided for subsequent data analysis, tracing and auditing.

[0101] In some possible implementations of the present invention, security measures such as encrypted storage and permission control can be taken for abnormal event data to ensure the security and privacy of the data; reasonable data access permission management can be implemented according to the needs of different roles to prevent unauthorized access; a log recording mechanism can be established to track data access and operation; abnormal event description data can be used in combination with other monitoring data to conduct in-depth abnormal analysis and event correlation; more accurate and comprehensive abnormal event information can be provided to managers to support rapid decision-making and response; the ability to identify and handle abnormal events can be continuously improved through continuous data analysis and feedback optimization; continuous storage and analysis of abnormal events can help discover system vulnerabilities and optimize monitoring strategies; and more valuable data support can be provided for the operation and maintenance management of the monitoring system.

[0102] In general, the solution of this embodiment can realize intelligent identification, standardized description, secure storage and in-depth analysis of abnormal events, providing strong support for improving the overall reliability and operation and maintenance efficiency of the monitoring system.

[0103] In some possible implementations of the present invention, the step of obtaining first original data from an IoT device and performing unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data includes:

[0104] Build a universal interface that supports data upload by different types of IoT devices (this interface needs to define standard data formats and transmission protocols);

[0105] Build an adaptive data format conversion module based on machine learning for data formats of different devices (this module can learn and identify raw data in different formats, extract valid fields, and perform standardization processing; standardization processing includes steps such as data cleaning, missing data filling, and data type conversion, with the purpose of converting data in different formats into a unified internal data format);

[0106] Utilize the adaptive data format conversion module to convert the format of the first raw data, and annotate the converted data with metadata, recording metadata such as device ID, data type, and collection time (such metadata is very important for subsequent data analysis and application);

[0107] Generate a conversion log for the first raw data (which can track the entire process from data collection to standardization, facilitating problem troubleshooting).

[0108] In this embodiment, various types of raw monitoring data (such as video images, temperature, humidity, etc.) are collected through IoT sensors, cameras and other devices; the connectivity and data transmission channel between the collection equipment and the IoT API docking platform are ensured; because the data formats used by IoT devices from different manufacturers are different, it is necessary to use an adaptive data format conversion module to uniformly standardize the raw data; convert it into a unified data format that can be read and understood by the platform, such as JSON, XML, etc.; while converting the format, it is also necessary to perform a quality check on the data; ensure the integrity, accuracy and validity of the data to avoid subsequent analysis errors caused by data quality issues; store the standardized data that has undergone format conversion and quality verification in the database of the IoT API docking platform; and provide a reliable data foundation for subsequent data management, analysis and application.

[0109] Through the above steps, the original data from different IoT devices can be effectively unified in format and quality controlled, eliminating the data gap between different devices / systems, and providing a unified data foundation for subsequent data analysis and application; through format conversion and quality verification, the integrity and accuracy of the data can be guaranteed, and the readability and usability of the data can be enhanced; there is no need to pay attention to the differences in data formats of various devices, simplifying the data access and processing process and improving work efficiency; standardized data formats are conducive to subsequent data mining and machine learning, and improving the data analysis capabilities and intelligence level of the IoT system. In short, the realization of this link builds a high-quality data foundation for the IoT API docking platform, providing solid support for subsequent data management, analysis and application.

[0110] In this embodiment, the specific construction of the adaptive data format conversion module includes the following steps:

[0111] Identify the specific format of the data by analyzing the syntax structure and key fields of the original data (supports common data formats such as JSON, XML, CSV, Excel, etc.);

[0112] Establish a metadata knowledge base for various data formats, including format specifications, field definitions, semantic annotations, etc.

[0113] Dynamically extend metadata information for new data formats;

[0114] Select the appropriate conversion algorithm based on the identified original data format (supporting two-way conversion between various formats to achieve data standardization);

[0115] In this step, according to the identified original data format, select the appropriate conversion algorithm, which can be analyzed from the following aspects: Identify the original data format (before processing the data, you first need to identify the source and format of the data, such as JSON, XML, CSV, binary, etc.; different data formats have different structures and characteristics); Select the appropriate conversion algorithm (according to the identified data format, select the appropriate conversion algorithm. This includes: Parsing algorithm: Parse data in a specific format so that it can be understood and processed by the system. Conversion algorithm: Convert data from one format to another. For example, convert JSON data to XML format, or convert CSV data to database records); Bidirectional conversion support (In many application scenarios, it may be necessary to convert between multiple data formats. Therefore, it is very important to support bidirectional conversion. For example, the system can convert JSON format data to XML, and can also convert XML data back to JSON); Data standardization (By selecting a suitable conversion algorithm, data standardization can be achieved, which means that regardless of the format of the data source, the data can eventually be uniformly converted into a standard format to facilitate subsequent processing and analysis; standardization can improve data consistency and availability, so that data from different sources can be seamlessly combined); Compatibility and scalability (the selected conversion algorithm should have good compatibility and be able to adapt to new formats or changes that may appear in the future. At the same time, the system should be scalable so that new conversion algorithms can be easily added when needed); Through the above analysis, it can be seen that this process ensures the flexible conversion of data between different formats, improves the efficiency and accuracy of data processing, and thus provides a reliable foundation for subsequent data analysis and application.

[0116] During the conversion process, both field semantics and data integrity are maintained;

[0117] The module uses a pluggable component design;

[0118] Supports dynamic expansion of new data formats without modifying the core code;

[0119] Facilitates flexible expansion and upgrading according to business needs;

[0120] Use efficient data analysis and conversion algorithms to ensure conversion efficiency;

[0121] Use technologies such as caching and parallel computing to improve data processing throughput;

[0122] Provide a friendly exception handling mechanism for data with irregular formats or conversion failures;

[0123] Record abnormal information to facilitate subsequent troubleshooting and module optimization.

[0124] Through the above design, the adaptive data format conversion module can realize the recognition and automatic conversion of multiple heterogeneous data formats; provide a flexible and scalable architecture to adapt to changes in business needs; ensure the efficiency and robustness of data conversion, reduce the complexity of data integration, and provide a standardized data foundation for subsequent data analysis and application. In short, this module is a key component of data management of the IoT API docking platform, and plays an important role in standardizing raw data.

[0125] In some possible implementations of the present invention, the step of using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph includes:

[0126] Inputting the standardized first data into a semantic analysis module;

[0127] Using natural language processing and machine learning technology, perform semantic analysis on the first data, and identify semantic elements such as concepts, entities, and relationships contained in the first data;

[0128] Based on the semantic analysis results of the previous step, the data meta-model is automatically constructed (the model contains the definition of data objects, attributes, relationships and other elements, providing metadata foundation for the structured expression of data and subsequent applications);

[0129] Convert the identified semantic elements into nodes and edges in the knowledge graph (nodes represent concepts and entities, and edges represent the semantic relationships between them) to build a structured knowledge base containing semantic information;

[0130] Using machine learning technology, semantic analysis, data meta-models and knowledge graphs are continuously learned and optimized (improving analysis accuracy and knowledge coverage as the amount of processed data increases).

[0131] Through this embodiment, we can upgrade from simple format conversion to deep semantic understanding of data content, and gain insight into the concepts, entities and relationships behind the data; automatically generate data meta-models to provide standardized metadata guidance for data applications; build knowledge graphs to convert data into structured knowledge bases rich in semantic information; based on semantic understanding and knowledge graphs, we can develop more intelligent data applications, such as intelligent question and answer, knowledge reasoning, decision support, etc.; deeply understand the connotation of data, discover hidden patterns and laws, and create more value for subsequent data analysis and applications. In short, the realization of this link has brought about a transformation from "data" to "knowledge" for the IoT API docking platform, greatly improved the ability to understand and apply data, and laid the foundation for the development of more intelligent applications.

[0132] In some possible implementations of the present invention, the following further aspects are included:

[0133] Determine scenario requirements and data characteristics: Analyze key entities, attributes, and relationships in IoT application scenarios; identify the type, format, and semantic characteristics of data sources;

[0134] Establish data meta-model: define the core concepts and entities in the scenario; describe the attributes, relationships and constraints of entities; determine the standards for data exchange, storage and query;

[0135] Construct domain knowledge graph: collect and integrate knowledge resources in related fields; extract entities and relationships and construct knowledge graph; enrich the semantic associations and reasoning rules of the graph;

[0136] Integrate data metamodel and knowledge graph: map entities and attributes in data metamodel to knowledge graph; use knowledge graph to enhance the semantic expression ability of data metamodel; realize bidirectional association and synchronous update of data and knowledge;

[0137] Develop semantic-based application services: Use knowledge graphs to support semantic search, reasoning, question-answering and other functions; feed back semantic analysis results to the data meta-model to improve the accuracy of data analysis; develop intelligent decision-making, prediction and other application services for specific scenarios;

[0138] Continuous optimization and expansion: Continuously improve data meta-models and knowledge graphs based on user feedback; explore cross-domain knowledge integration to improve versatility and adaptability; introduce machine learning and other technologies to continuously enhance semantic analysis capabilities.

[0139] Through this embodiment, the data meta-model and knowledge graph can be fully applied to specific IoT scenarios, improving the level of data semantic understanding and intelligent application, and meeting the personalized needs of different industries.

[0140] In some possible implementations of the present invention, bidirectional synchronization updates between the data meta-model and the knowledge graph can be achieved through the following steps:

[0141] Establish mapping relationships between entities and attributes: Identify the core entities and attributes in the data metamodel; establish mapping relationships between these entities and attributes and the corresponding nodes and attributes in the knowledge graph;

[0142] Synchronize data metamodel to knowledge graph: import entities, attributes and relationship information in data metamodel into knowledge graph; use reasoning mechanism of knowledge graph to supplement and enrich semantic relationships between entities;

[0143] Synchronize the knowledge graph to the data metamodel: monitor changes to entities, attributes, and relationships in the knowledge graph; feed these changes back to the data metamodel to ensure that the data model is always synchronized with the knowledge;

[0144] Establish an automated synchronization mechanism: design events and rules that trigger synchronization, such as adding new entities, changing attributes, etc.; develop automated tools for regular scanning and comparison of data; ensure the reliability and consistency of the synchronization process;

[0145] Handle conflicts during synchronization: Identify conflicts between the data metamodel and the knowledge graph, such as data type mismatch; formulate conflict resolution strategies, such as taking the knowledge graph as the standard or manually intervening in the review; record and manage the change history during synchronization;

[0146] Provide visual synchronization monitoring: develop a dashboard to display the synchronization status and change history; support manual intervention and manual adjustment of synchronization rules.

[0147] This two-way synchronization mechanism ensures that the data meta-model and knowledge graph remain highly consistent, supporting semantic analysis and decision-making services for IoT applications. It also promotes the accumulation and continuous optimization of knowledge, and improves the intelligence level of the entire IoT system.

[0148] In some possible implementations of the present invention, the step of storing and tracing the first data, the data meta-model and the knowledge graph using blockchain technology through a blockchain-based data storage module to ensure the verifiability and non-tamperability of the first data includes:

[0149] Select a suitable blockchain platform (such as Ethereum, Hyperledger Fabric, etc.), deploy blockchain network nodes, build a distributed ledger, and generate the first blockchain network;

[0150] In this step, when selecting a suitable blockchain platform, the following key factors need to be considered: performance (such as transaction throughput: the number of transactions processed per second; transaction confirmation time: the time when the transaction is finally written to the blockchain; scalability: the number of concurrent transactions supported and the size of the data; etc.), security (such as the security of the consensus mechanism: resistance to 51% attacks and other security issues; the security of the cryptographic algorithm: resistance to quantum computing attacks; the security of smart contracts: prevention of smart contract vulnerabilities; etc.), programmability (such as the maturity and availability of the smart contract language, the perfection of the development tools and SDKs, the community activity and the ecological environment, etc.), supervision and compliance (whether it complies with industry regulatory policies and standards, supports various types of digital assets, provides compliance functions such as privacy protection, etc.), cost and deployment (the cost of node deployment and maintenance, transaction fees and resource consumption, integration difficulty and development investment, etc.); based on these factors, you can compare mainstream blockchain platforms, such as Ethereum, Hyperledger Fabric, Corda, EOS, etc., and select the platform that best suits the application scenario of the Internet of Things API docking platform involved in this embodiment. Through the solution in this step, choose a blockchain platform with high throughput and low confirmation time to support large-scale data storage and transaction needs; choose a blockchain platform with high security to resist various attacks and ensure the security of data and transactions; choose a blockchain platform with relatively complete development tools and SDKs to reduce the complexity of development and integration and improve development efficiency; choose a blockchain platform that meets industry regulatory standards to ensure system compliance and reduce regulatory risks; choose a blockchain platform with good scalability to support future business growth and the addition of new functions; choose a blockchain platform with low deployment and operating costs to reduce the total cost of ownership of the system; taking all these factors into consideration, choose the blockchain platform that is most suitable for the IoT API docking platform, which can bring high performance, high security, high availability and other technical advantages to the system, and lay a solid foundation for future business development.

[0151] Upload the first data, the data metamodel, and the knowledge graph to the first blockchain network, and store the first data, the data metamodel, and the knowledge graph in the form of blocks in a distributed ledger through a smart contract;

[0152] Establish digital identity certificates for identity authentication and authority management for each participant in the IoT API docking platform;

[0153] Set data access control policies based on the different roles of each participant to ensure data security;

[0154] Recording operations of creating, modifying, and accessing the first data, the data metamodel, and the knowledge graph, and generating an audit log;

[0155] Build a data query interface for all participants to query and verify data content according to their needs (using the consensus mechanism of blockchain to ensure the accuracy and consistency of query results);

[0156] Optimize the performance and functionality of blockchain networks to support flexible integration of new data types and application scenarios based on business needs and technological development.

[0157] Through the scheme of this embodiment, the distributed ledger and encryption technology of blockchain can be used to ensure the authenticity and integrity of data; the whole process of data operation can be traced back to reduce the risk of data tampering; through identity authentication and access control, refined permission management of data can be achieved; the privacy of data can be protected to meet relevant laws and regulations and compliance requirements; the blockchain network is naturally cross-organizational collaborative, which can achieve data sharing and collaboration between different participants and improve data utilization efficiency; blockchain technology can automatically execute processes such as data management and auditing, reduce manual intervention, and reduce the operating cost of data management; the data immutability guaranteed by blockchain enhances the trust of data users and provides a reliable foundation for subsequent analysis and application based on these data. In short, the realization of this link brings blockchain-enabled data management capabilities to the IoT API docking platform, greatly improves the security, credibility and value of data, and lays the foundation for the robustness and sustainable development of the entire platform system.

[0158] In some possible implementations of the present invention, the step of analyzing the second data using the data meta-model and the knowledge graph to obtain the third data includes:

[0159] Performing semantic verification and mapping of the second data with the data metamodel;

[0160] Analyze the verified and mapped second data using entities, attributes and relationships in the knowledge graph, and apply inference rules to infer third data;

[0161] In this step, the third data includes but is not limited to: data mining results, algorithm analysis output, prediction model discovery, user feedback, market research results and expert evaluation results, etc.

[0162] According to the needs of the application scenario, the third-party data is output in a suitable format (providing visualization, reports, etc. to intuitively present the analysis results; supporting real-time updating and incremental calculation of the third-party data).

[0163] In this step, according to the requirements of the application scenario, the third data is output in a suitable format and can be analyzed from the following aspects:

[0164] Application scenario requirements:

[0165] Different application scenarios have different requirements for data presentation and content. For example, a security monitoring scenario may require real-time alarm information, while a business analysis scenario may focus more on data trends and statistical reports.

[0166] Suitable output format:

[0167] The output format should be customized according to user needs. Common formats include:

[0168] Visualization: Use charts, dashboards, etc. to display data intuitively, so that users can quickly understand and analyze data. For example, line charts show trends and pie charts show proportions.

[0169] Reports: Generate structured documents containing detailed analysis results and statistical data for decision makers to conduct in-depth research and reference.

[0170] Visually present analysis results:

[0171] Through clear visualization and reporting, users can better understand the analysis results and identify trends and anomalies. This intuitiveness can improve users' decision-making efficiency.

[0172] Real-time updates:

[0173] In order to maintain the timeliness of data, the output third-party data should support real-time updates, which means that the system can continuously receive new data and immediately reflect it in the visualization interface or report.

[0174] Incremental calculation:

[0175] When processing large-scale data, incremental computing can improve efficiency. It allows the system to process only new or changed data instead of recalculating all data each time, thereby speeding up response time.

[0176] In summary, this process ensures that the results of data analysis are delivered to users in the right form at the right time, thereby achieving effective decision support and business optimization.

[0177] Through the scheme of this embodiment, combined with the data metamodel and knowledge graph, the second data is deeply analyzed, the implicit relationship between the data can be discovered, and more valuable third data can be generated; according to the application requirements, the analysis results are output and presented in a suitable form; the real-time update and incremental calculation of the results are supported to meet the dynamic changes of business needs; the data metamodel and knowledge graph have good scalability and can adapt to business development; the analysis model and algorithm can be migrated and reused across application scenarios. In short, this solution can make full use of the data metamodel and knowledge graph to conduct in-depth analysis of the second data, dig out more valuable third data, provide decision support and business insights for upper-level applications, and meet various analysis needs of IoT applications.

[0178] In some possible implementations of the present invention, the real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and combines the network traffic regulation algorithm to dynamically optimize the API response speed, including:

[0179] Use streaming computing engines (such as Apache Spark Streaming, Apache Flink, etc.) to receive and process third-party data;

[0180] Design real-time analysis algorithms (including complex event processing, time series analysis, prediction models, etc.) to analyze third-party data and obtain real-time analysis results;

[0181] Monitor the access traffic and response time of the API interface, apply dynamic traffic regulation algorithms based on feedback control (such as current limiting, load balancing, etc.), adjust algorithm parameters according to real-time analysis results, and dynamically optimize API response speed.

[0182] In this embodiment, it also includes: pushing real-time analysis results to the upper-level application system in a suitable format; providing real-time monitoring and alarm functions to detect abnormal situations in a timely manner; supporting persistent storage and offline analysis of results to meet historical data query needs; adopting a distributed, microservice architecture design to improve the scalability and elasticity of the system; using containers and orchestration technology to achieve automated deployment and operation and maintenance; applying performance tuning technologies, such as memory management, I / O optimization, etc., to improve system performance.

[0183] Through the scheme of this embodiment, it is possible to quickly and accurately analyze and process the real-time data stream intelligently; dig out valuable insights and opinions for business decision-making and optimization; dynamically adjust the parameters of the network traffic control algorithm according to the real-time analysis results; ensure that the API interface maintains a fast response under high concurrent access; adopt a distributed, microservice architecture design to support horizontal expansion and automatic scaling; improve the fault tolerance and availability of the system to meet the needs of different business scenarios; use containers and orchestration technology to achieve automated deployment and operation and maintenance; improve system stability and reduce manual operation and maintenance costs; improve the overall performance of the system through memory management, I / O optimization and other technologies; reasonably use computing and storage resources to improve resource utilization. In short, this solution can make full use of real-time data stream analysis technology and network traffic control algorithms to intelligently analyze and process third-party data, and dynamically optimize the API response speed, providing fast and accurate decision support for upper-level application systems, and meeting the requirements of IoT applications for real-time and scalability.

[0184] In some possible implementations of the present invention, the step of extracting the first image data collected by a preset monitoring device from the second data includes:

[0185] Parsing the received second data, identifying and extracting image data frames carrying a mark of a preset monitoring device as first image data;

[0186] According to business requirements, format conversion and compression are performed on the first image data (to reduce storage and transmission loads);

[0187] Checking the integrity and validity (such as resolution, encoding format, etc.) of the extracted first image data;

[0188] Performing basic enhancement and optimization processing (such as brightness / contrast adjustment, noise elimination, etc.) on the first image data;

[0189] The extracted first image data is persistently stored to support historical data query and analysis;

[0190] Design a data management module to provide fast retrieval and access capabilities for first image data;

[0191] According to business needs, data encryption and access control measures are implemented to ensure the integrity and confidentiality of the first image data and protect privacy information.

[0192] In this embodiment, the setting of monitoring equipment can be carried out according to the following steps: determine the location and number of monitoring equipment to be deployed according to specific business scenarios and application requirements; evaluate the purpose and expected effect of monitoring, such as security monitoring, equipment operation monitoring, environmental monitoring, etc.; select appropriate monitoring equipment types according to monitoring requirements, such as IP cameras, infrared detectors, temperature and humidity sensors, etc.; consider the functional characteristics, resolution, transmission protocol, power supply and other factors of the equipment, and select products that meet the requirements; determine the installation location of the equipment, considering factors such as coverage, light conditions, and risk of equipment damage; install and connect according to the equipment instructions to ensure that the equipment can work normally; debug and test the equipment to ensure that the monitoring equipment can collect data normally; connect the monitoring equipment to the network to ensure that the equipment is connected to the network. The equipment should be able to stably connect to the data center or cloud platform; set appropriate network parameters, such as IP address, subnet mask, gateway, etc., to ensure smooth access to the equipment; consider the network security requirements of the equipment, such as identity authentication, encrypted transmission, etc.; configure the data interface at the data receiving end (such as the data center or cloud platform) to support data reporting of the monitoring equipment; select appropriate data transmission protocols, such as RTSP, ONVIF, MQTT, etc., to ensure smooth data transmission; test whether the data receiving end can correctly receive and parse data from the monitoring equipment; establish a regular inspection and maintenance mechanism for monitoring equipment to ensure long-term stable operation of the equipment; pay attention to the software upgrades and vulnerability patches of the equipment to maintain the security of the equipment system; regularly back up and archive the monitoring data to ensure the integrity of historical data. Through the above steps, the preset monitoring equipment can be reasonably deployed and configured to provide a stable and reliable data source for subsequent data collection and analysis. At the same time, factors such as equipment security and privacy protection also need to be considered to ensure that monitoring behavior is legal and compliant.

[0193] Through the scheme of this embodiment, it is possible to receive video stream data from monitoring equipment in real time and reliably; support multiple video protocols and encoding formats to meet the needs of different devices and systems; be able to quickly and accurately extract image data frames from the second data stream; perform necessary format conversion and compression processing on the extracted image data to reduce storage and transmission loads; ensure that the extracted image data is complete, clear, and available through data verification and basic processing; improve the reliability and availability of image data, and provide a high-quality data source for subsequent applications; provide persistent storage and fast retrieval functions for image data, support historical data query and analysis, and meet business needs; implement necessary security measures to protect the confidentiality and integrity of image data; ensure the security of user privacy information and meet relevant regulatory requirements. In short, this solution can reliably extract high-quality image data from the second data, provide a valuable data source for subsequent image analysis, object recognition and other applications, and also has good data management and security protection capabilities to meet the needs of IoT applications for data processing and privacy protection.

[0194] In some possible implementations of the present invention, the step of using a monitoring and analysis module based on image recognition to intelligently analyze the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering an early warning includes:

[0195] Performing preprocessing operations of format conversion, scale adjustment, and color correction on the first image data to obtain second image data;

[0196] Obtain historical monitoring image data, and construct an image sample data set (including normal and abnormal image samples) based on the historical monitoring image data;

[0197] Choose the appropriate deep learning model architecture (such as convolutional neural network (CNN), object detection model, etc.);

[0198] In this step, the selection of appropriate deep learning model architecture, especially convolutional neural network (CNN) and target detection model, can be considered from the following aspects: task requirements (different deep learning models are suitable for different tasks. For example, CNN is particularly suitable for tasks such as image classification and feature extraction, while target detection models (such as YOLO and Faster R-CNN) are specifically used to identify multiple objects and their locations in an image), data type (if image data is processed, convolutional neural network (CNN) can effectively capture spatial features in the image due to its local connection and weight sharing characteristics; for tasks that require simultaneous identification of multiple objects and determination of their locations, target detection models are a more appropriate choice), model complexity (CNN is relatively simple and suitable for basic image processing tasks; target detection models are more complex and usually require higher computing resources and training time, but can provide richer information), performance requirements (in application scenarios such as real-time monitoring, it is key to choose fast and efficient models (such as the YOLO series); in scenarios that require high precision, you may tend to use more complex models (such as Faster R-CNN). R-CNN), although it is slower), available resources (consider available computing resources and time. If resources are limited, you may need to choose a lighter model (such as MobileNet) to balance performance and efficiency), scalability and flexibility (when choosing a model, you also need to consider its scalability and flexibility, for example, whether it can be easily transferred or used in combination with other models), etc. Through understanding of these aspects, you can better choose a deep learning model architecture that suits specific application scenarios and needs, thereby improving the overall performance and effectiveness of the system.

[0199] Use image sample datasets to conduct supervised learning on the model and optimize model parameters;

[0200] Improve the recognition accuracy and generalization ability of the model through model evaluation and tuning;

[0201] Deploy the trained deep learning model to the monitoring and analysis module;

[0202] Define the judgment rules for abnormal situations (such as object intrusion, equipment failure, environmental abnormality, etc.);

[0203] In combination with the judgment rules, a deep learning model is used to intelligently analyze the second image data to identify whether there is an abnormality;

[0204] When an abnormal situation occurs, the early warning mechanism is triggered (such as sending alarm information, recording event logs, etc.);

[0205] Classify abnormal situations and assess their severity based on business needs.

[0206] This embodiment may also include: feeding back relevant data (images, test results, etc.) of abnormal events to manual analysis and review; continuously optimizing and iterating the model based on the manual analysis results to improve accuracy and reliability; regularly evaluating model performance, and adjusting and optimizing according to business needs.

[0207] Through the scheme of this embodiment, deep learning technology can be used to automatically analyze and detect anomalies in image data; greatly improve the intelligence level of the monitoring system and reduce the workload of manual review; can detect abnormal situations in image data in real time, such as intrusion, failure, anomaly, etc.; quickly trigger the early warning mechanism to provide timely abnormal event notifications for managers; continuously improve the accuracy and reliability of monitoring and analysis through manual feedback and model iteration; adapt to changes in business needs, continuously optimize and upgrade the monitoring and analysis module; reduce the time and labor costs required for manual monitoring, and improve the overall efficiency of the monitoring system; provide managers with more accurate and timely abnormal event information and improve decision-making support capabilities; timely discover and warn of abnormal situations, which helps to improve the overall security prevention capabilities; combined with video monitoring and other means, provide all-round security protection for the Internet of Things system. In short, this solution can make full use of deep learning technology to realize automated intelligent monitoring and analysis, and greatly improve the security and operation and maintenance efficiency of Internet of Things applications. At the same time, it also provides a reliable basic support for subsequent data analysis, event warning, etc.

[0208] In some possible implementations of the present invention, the step of generating abnormal event description data according to a preset abnormal event model based on the result of identifying the abnormal situation, and storing the abnormal event description data includes:

[0209] Determine the basic information of the abnormal event (the basic information of the abnormal event includes but is not limited to: the type of abnormal event, the time of occurrence, the location of occurrence, the description of the event process, multimedia data related to the abnormal event, etc.);

[0210] According to the pre-defined abnormal event model, the basic information of the identified abnormal event is converted into standardized abnormal event description data;

[0211] The abnormal event description data includes event ID, event type, occurrence time, occurrence location, abnormal situation description, and related multimedia content such as images, videos, sensor data, etc.;

[0212] The generated abnormal event description data is stored in a preset database or file system.

[0213] In this embodiment, it also includes: implementing basic operations such as adding, deleting, modifying, and checking abnormal event data to meet daily management needs; designing appropriate data storage structures and indexing mechanisms according to business needs to improve data retrieval efficiency; implementing security protection measures for abnormal event data, such as encrypted storage, permission control, etc., to ensure data security; setting appropriate data access permissions according to the needs of different roles to prevent unauthorized access; establishing a log recording mechanism to track data access and operations; using abnormal event description data in combination with other monitoring data to conduct in-depth abnormal analysis and event correlation; formulating targeted response measures based on the analysis results, such as triggering early warning notifications, automatic processing, manual intervention, etc.; and continuously improving the identification and processing mechanism of abnormal events through continuous data analysis and feedback optimization.

[0214] Through the scheme of this embodiment, structured abnormal event description data can be generated to facilitate subsequent storage, query and analysis; improve the readability and processability of abnormal event information; store abnormal event data persistently, build a complete abnormal event history record, and provide reliable data support for subsequent data analysis, tracing and auditing; ensure the security and privacy of abnormal event data, prevent data leakage and illegal access; realize reasonable data access permission management according to the needs of different roles; use abnormal event data, combined with other monitoring data, to conduct in-depth abnormal analysis and event association; provide managers with more accurate and comprehensive abnormal event information to support rapid decision-making and response; continuously improve the identification and processing capabilities of abnormal events through continuous optimization; continuous storage and analysis of abnormal events help to discover system vulnerabilities and optimize monitoring strategies; provide more valuable data support for the operation and maintenance management of the monitoring system. In short, the scheme can convert the results of abnormal event identification into standardized data descriptions, and perform persistent storage and security management, providing a reliable basis for subsequent data analysis and application. At the same time, it can also improve the overall reliability and operation and maintenance efficiency of the monitoring system.

[0215] See also Figure 2, another embodiment of the present invention provides a data management system for an Internet of Things API docking platform, including: an Internet of Things device; a monitoring device; and a management server provided with an adaptive data format conversion module, a semantic analysis module, a data storage module, a real-time data stream analysis module, and a monitoring analysis module;

[0216] The management server is configured to:

[0217] Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data;

[0218] Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph;

[0219] Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data;

[0220] Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data;

[0221] Analyze the second data using the data meta-model and the knowledge graph to obtain third data;

[0222] The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm;

[0223] Extracting first image data collected by a preset monitoring device from the second data;

[0224] Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings;

[0225] According to the result of identifying the abnormal situation, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored.

[0226] It should be known that Figure 2The block diagram of the data management system for the Internet of Things API docking platform is only for illustration, and the number of modules shown does not limit the scope of protection of the present invention. The data management system for the Internet of Things API docking platform provided in this embodiment can be used to execute the corresponding embodiments of the data management method for the Internet of Things API docking platform. For the specific implementation process, please refer to the description of the embodiments of each method, which will not be repeated here.

[0227] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0228] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0229] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. 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, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0230] The units described above 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.

[0231] In addition, each functional unit in each embodiment of the present application 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.

[0232] If the above-mentioned 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 memory. Based on this understanding, the technical solution of the present application is essentially 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 memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0233] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0234] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0235] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A data management method for an Internet of Things API docking platform, characterized in that: include: Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data; Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph; Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data; Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data; Analyze the second data using the data meta-model and the knowledge graph to obtain third data; The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm; Extracting first image data collected by a preset monitoring device from the second data; Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings; According to the result of identifying the abnormal situation, generating abnormal event description data according to a preset abnormal event model, and storing the abnormal event description data; The step of obtaining the first original data from the IoT device and performing unified standardization processing on the first original data through the adaptive data format conversion module to obtain the first data includes: Build a universal interface that supports different types of IoT devices to upload data; Build an adaptive data format conversion module based on machine learning for data formats of different devices; Utilizing the adaptive data format conversion module to convert the format of the first raw data, and annotating the converted data with metadata, recording metadata such as device ID, data type, and collection time; generating a conversion log of the first original data; The step of using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generating a data meta-model and constructing a knowledge graph includes: Inputting the standardized first data into a semantic analysis module; Using natural language processing and machine learning technology, perform semantic analysis on the first data, and identify semantic elements such as concepts, entities, and relationships contained in the first data; Automatically build a data meta-model based on the semantic analysis results of the previous step; Convert the identified semantic elements into nodes and edges in the knowledge graph to build a structured knowledge base containing semantic information; Use machine learning technology to continuously learn and optimize semantic analysis, data meta-models, and knowledge graphs; The step of storing and tracing the first data, the data meta-model and the knowledge graph by using blockchain technology through a blockchain-based data storage module to ensure the verifiability and non-tamperability of the first data includes: Select a suitable blockchain platform, deploy blockchain network nodes, build a distributed ledger, and generate the first blockchain network; Upload the first data, the data metamodel, and the knowledge graph to the first blockchain network, and store the first data, the data metamodel, and the knowledge graph in the form of blocks in a distributed ledger through a smart contract; Establish digital identity certificates for identity authentication and authority management for each participant in the IoT API docking platform; Set data access control policies based on the different roles of each participant to ensure data security; Recording operations of creating, modifying, and accessing the first data, the data metamodel, and the knowledge graph, and generating an audit log; Build a data query interface for all participants to query and verify data content according to their needs; Optimize the performance and functionality of blockchain networks to support flexible integration of new data types and application scenarios based on business needs and technological development.

2. The data management method for the Internet of Things API docking platform according to claim 1 is characterized in that: The step of analyzing the second data by using the data meta-model and the knowledge graph to obtain the third data includes: Performing semantic verification and mapping of the second data with the data metamodel; Analyze the verified and mapped second data using entities, attributes and relationships in the knowledge graph, and apply inference rules to infer third data; wherein the third data includes: data mining results, algorithm analysis output, prediction model discovery, user feedback, market research results and expert evaluation results; According to the requirements of the application scenario, the third data is output in a suitable format.

3. The data management method for the Internet of Things API docking platform according to claim 2 is characterized in that: The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and combines the network traffic control algorithm to dynamically optimize the API response speed, including: Using a streaming computing engine to receive and process third data; Design real-time analysis algorithms based on business needs to analyze third-party data and obtain real-time analysis results; Monitor the access traffic and response time of the API interface, apply a dynamic traffic regulation algorithm based on feedback control, adjust the algorithm parameters according to real-time analysis results, and dynamically optimize the API response speed.

4. The data management method for the Internet of Things API docking platform according to claim 3 is characterized in that: The step of extracting the first image data collected by the preset monitoring device from the second data includes: Parsing the received second data, identifying and extracting image data frames carrying a mark of a preset monitoring device as first image data; According to business requirements, format conversion and compression are performed on the first image data; checking the integrity and validity of the extracted first image data; Performing basic enhancement and optimization processing on the first image data; The extracted first image data is persistently stored to support historical data query and analysis; Design a data management module to provide fast retrieval and access capabilities for first image data; According to business needs, data encryption and access control measures are implemented to ensure the integrity and confidentiality of the first image data and protect privacy information.

5. The data management method for the Internet of Things API docking platform according to claim 4 is characterized in that: The step of using the monitoring and analysis module based on image recognition to intelligently analyze the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings includes: Performing preprocessing operations of format conversion, scale adjustment, and color correction on the first image data to obtain second image data; Acquire historical monitoring image data, and construct an image sample data set based on the historical monitoring image data; Choose the appropriate deep learning model architecture; Use image sample datasets to conduct supervised learning on the model and optimize model parameters; Improve the recognition accuracy and generalization ability of the model through model evaluation and tuning; Deploy the trained deep learning model to the monitoring and analysis module; Define the rules for judging abnormal situations; In combination with the judgment rules, a deep learning model is used to intelligently analyze the second image data to identify whether there is an abnormality; When there is an abnormal situation, the early warning mechanism is triggered; Classify abnormal situations and assess their severity based on business needs.

6. The data management method for the Internet of Things API docking platform according to claim 5 is characterized in that: The step of generating abnormal event description data according to a preset abnormal event model based on the result of identifying the abnormal situation, and storing the abnormal event description data includes: Determine the basic information of abnormal events; According to the pre-defined abnormal event model, the basic information of the identified abnormal event is converted into standardized abnormal event description data; The generated abnormal event description data is stored in a preset database or file system.

7. A data management system for an Internet of Things API docking platform, applied to the data management method for an Internet of Things API docking platform as claimed in any one of claims 1 to 6, characterized in that: include: IoT devices; Monitoring equipment; and a management server provided with an adaptive data format conversion module, a semantic analysis module, a data storage module, a real-time data stream analysis module and a monitoring analysis module; The management server is configured to: Acquire first original data from an IoT device, and perform unified standardization processing on the first original data through an adaptive data format conversion module to obtain first data; Using a semantic analysis module based on machine learning technology to perform semantic analysis on the standardized first data, automatically generate a data meta-model and construct a knowledge graph; Through a blockchain-based data storage module, the first data, the data meta-model and the knowledge graph are stored and traced using blockchain technology to ensure the verifiability and non-tamperability of the first data; Acquire first real-time data from an Internet of Things device, and perform unified standardization processing on the first real-time data through an adaptive data format conversion module to obtain second data; Analyze the second data using the data meta-model and the knowledge graph to obtain third data; The real-time data stream analysis module uses real-time data stream analysis technology to intelligently analyze and process the third data, and dynamically optimizes the API response speed in combination with the network traffic control algorithm; Extracting first image data collected by a preset monitoring device from the second data; Using a monitoring and analysis module based on image recognition, intelligently analyzing the first image data based on image recognition and deep learning technology, identifying abnormal situations and triggering early warnings; According to the result of identifying the abnormal situation, abnormal event description data is generated according to a preset abnormal event model, and the abnormal event description data is stored.

Images