Rapid cross-scenario internet of things application building method based on componentization capability of aiot middle platform

Abstract

Embodiments of the present application provide a rapid cross-scenario Internet of Things application building method based on the componentization capability of an Artificial Intelligence of Things (AIoT) middle platform. The method comprises: by means of a visualization interface, receiving a cross-scenario editing instruction sent by a user, and performing matching with a preset scenario knowledge graph according to the cross-scenario editing instruction to determine pluggable components in a preset scenario atomization component library, a scenario analysis algorithm matched in a preset algorithm center, and a scenario logical rule matched in a preset scenario rule library; establishing a communication connection with an edge layer in AIoT, and receiving Internet of Things device data sent by the edge layer; and performing flow construction on the pluggable components according to the scenario logical rule to determine a corresponding component association relationship and component interaction mode, and constructing a cloud service layer middle platform on the basis of the component association relationship, the component interaction mode, and key features. The present application can implement highly-flexible and extensible rapid cross-scenario Internet of Things application building and AIoT service.

Description

Cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Things, in particular to a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability. BACKGROUND

[0002] In modern AIoT (Artificial Intelligence and Internet of Things) architecture, cloud-edge-end collaborative architecture has become the mainstream way to realize intelligent applications. This architecture combines the powerful data processing capability of cloud computing with the real-time data processing advantage of edge computing, which can support a wide range of application scenarios, from industrial automation to smart home systems. However, although the existing AIoT architecture provides certain flexibility and efficiency, there are still some significant shortcomings and deficiencies in the actual deployment and application process.

[0003] Firstly, the demand for AIoT varies greatly in different industries and application scenarios. For example, in a construction site, an intelligent monitoring system needs to be able to identify whether all personnel are wearing safety helmets, while monitoring heavy machinery such as tower cranes to prevent safety accidents caused by improper operation. This kind of application not only requires specific hardware devices to adapt to harsh environmental conditions, but also needs highly customized algorithms such as collision detection and safety monitoring algorithms. In contrast, the AIoT application of community property management may pay more attention to crowd management and fire prevention, which requires the system to effectively identify crowd gathering and timely detect fire hazards such as smoke and firelight detection. This differentiated demand makes it difficult for a single AIoT solution to be widely applicable, and requires customized technology and services for each specific scenario.

[0004] Secondly, the scalability of the system is another important issue. In the existing AIoT architecture, once the system is deployed, the access of new devices often requires updating and redeploying service code. This process not only consumes time and effort, but also each update may affect the stability and continuous online time of the system. With the rapid changes in business needs and the continuous emergence of new technologies, the low flexibility of the existing system obviously cannot meet the market demand. For example, if a new type of sensor or intelligent device needs to be added to the deployed system, a large amount of system testing and verification may be required to ensure the compatibility of the new device and the stability of the overall system.

[0005] Therefore, to overcome these deficiencies, future AIoT architectures need to be more flexible and scalable. This can include developing a more modular system design that allows seamless integration of new devices and services without extensive system reconfiguration or downtime maintenance. Furthermore, by adopting more advanced machine learning and artificial intelligence algorithms, the system's adaptability and response speed to new scenarios can be further improved. Such a system not only better meets the needs of specific industries, but also continuously evolves and improves with technological advances and market changes. SUMMARY

[0006] To solve the problems in the prior art, the present application provides a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability, which can realize highly flexible and scalable cross-scene Internet of Things application rapid building and AIOT service.

[0007] To solve at least one of the above problems, the present application provides the following technical solutions:

[0008] In a first aspect, the present application provides a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability, applied to the cloud service layer in the artificial intelligence Internet of Things, the method comprising:

[0009] Receiving a cross-scene editing instruction sent by a user through a visual interface, matching the cross-scene editing instruction with a preset scene knowledge graph, determining a pluggable component in a preset scene atomization component library, a matching scene analysis algorithm in a preset algorithm center, and a matching scene logic rule in a preset scene rule library;

[0010] Establishing a communication connection with the edge layer in the artificial intelligence Internet of Things, receiving Internet of Things device data sent by the edge layer, performing data format conversion on the Internet of Things device data according to the data format requirements of the pluggable component, and configuring it as a component data source of the pluggable component according to the set data configuration rule, wherein the Internet of Things device data is sent by the intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0011] Performing data analysis on the component data source through the matching scene analysis algorithm, determining the corresponding key features, constructing the process of the pluggable component according to the scene logic rule, determining the corresponding component association relationship and component interaction mode, and constructing the cloud service layer middle platform according to the component association relationship, the component interaction mode, and the key features.

[0012] Further, before matching the cross-scene editing instruction with the preset scene knowledge graph, it comprises:

[0013] determine nodes in a scenario knowledge graph according to attribute information of the historical pluggable components, the historical scenario analysis algorithms and the historical scenario logic rules, and determine edges in the scenario knowledge graph according to the association between the historical pluggable components, the historical scenario analysis algorithms and the historical scenario logic rules;

[0014] construct the scenario knowledge graph according to the nodes and the edges.

[0015] Further, the determining of the matching pluggable components in the preset scenario atomized component library, the matching scenario analysis algorithms in the preset algorithm center and the matching scenario logic rules in the preset scenario rule library according to the scenario requirement, the specific function and the preset scenario knowledge graph comprises:

[0016] determining a graph matching range in the preset scenario knowledge graph according to the scenario requirement and the specific function;

[0017] measuring the similarity between nodes and edges in the graph matching range according to a similarity algorithm, and determining the matching pluggable components in the preset scenario atomized component library, the matching scenario analysis algorithms in the preset algorithm center and the matching scenario logic rules in the preset scenario rule library according to the nodes and edges with the maximum similarity.

[0018] Further, the content analysis of the cross-scenario editing instruction to determine the corresponding scenario requirement and specific function comprises:

[0019] performing semantic analysis on the cross-scenario editing instruction to determine the corresponding scenario requirement;

[0020] determining the specific function most matching the scenario requirement according to a preset scenario function list.

[0021] Further, the receiving of the Internet of Things device data sent by an edge layer in an artificial intelligence Internet of Things, and the configuration of the Internet of Things device data into component data sources of the pluggable components according to a set data configuration rule, wherein the Internet of Things device data is sent by a smart terminal layer in the artificial intelligence Internet of Things through a preset unified service interface, comprises:

[0022] receiving the Internet of Things device data sent by an edge layer in an artificial intelligence Internet of Things, wherein the Internet of Things device data is sent by a smart terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0023] standardizing the Internet of Things device data according to the configuration requirements of the pluggable components, and configuring the Internet of Things device data after the standardization into component data sources of the pluggable components.

[0024] Further, before transmitting the IoT device data sent by the edge layer in the artificial intelligence IoT, the method further comprises:

[0025] performing data cleaning filtering on the IoT device data sent by the intelligent terminal layer in the artificial intelligence IoT through a data cleaning model built in the edge layer in the artificial intelligence IoT;

[0026] performing data analysis on the IoT device data after the data cleaning filtering through a data analysis model built in the edge layer in the artificial intelligence IoT, to obtain IoT device data after the data analysis.

[0027] In a second aspect, the application provides a device for quickly building a cross-scene IoT application based on AIOT middle platform componentization capability, comprising:

[0028] a building element determination module configured to receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, and determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library;

[0029] a building data configuration module configured to establish a communication connection with an edge layer in an artificial intelligence IoT, receive IoT device data sent by the edge layer, perform data format conversion on the IoT device data according to a data format requirement of the pluggable component, and configure the IoT device data as a component data source of the pluggable component according to a set data configuration rule, wherein the IoT device data is sent by an intelligent terminal layer in the artificial intelligence IoT through a preset unified service interface;

[0030] a middle platform building module configured to perform data analysis on the component data source through the matched scene analysis algorithm, determine a corresponding key feature, perform flow construction on the pluggable component according to the scene logic rule, determine a corresponding component association relationship and a component interaction mode, and build a cloud service layer middle platform according to the component association relationship, the component interaction mode, and the key feature.

[0031] In a third aspect, the application provides a system for quickly building a cross-scene IoT application based on AIOT middle platform componentization capability, comprising a cloud service layer, an edge layer, and an intelligent terminal layer in an artificial intelligence IoT, wherein the cloud service layer is connected with the edge layer, and the edge layer is connected with the intelligent terminal layer;

[0032] the cloud service layer comprises:

[0033] The building element determination module is configured to receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, and determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library.

[0034] The building data configuration module is configured to establish a communication connection with an edge layer in an AIOT, receive IoT device data sent by the edge layer, perform data format conversion on the IoT device data according to a data format requirement of the pluggable component, and configure the IoT device data as a component data source of the pluggable component according to a set data configuration rule, wherein the IoT device data is sent by an intelligent terminal layer in the AIOT through a preset unified service interface.

[0035] The middle platform building module is configured to perform data analysis on the component data source through the matched scene analysis algorithm, determine corresponding key features, perform flow construction on the pluggable component according to the scene logic rule, determine a corresponding component association relationship and a component interaction mode, and build a middle platform in a cloud service layer according to the component association relationship, the component interaction mode, and the key features.

[0036] In a fourth aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for quickly building a cross-scene IoT application based on the AIOT middle platform componentization capability.

[0037] In a fifth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the steps of the method for quickly building a cross-scene IoT application based on the AIOT middle platform componentization capability.

[0038] In a sixth aspect, the present application provides a computer program product comprising computer programs / instructions executable on a processor to implement the steps of the method for quickly building a cross-scene IoT application based on the AIOT middle platform componentization capability.

[0039] From the above technical solution, the application provides a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability, receives a cross-scene editing instruction sent by a user through a visual interface, matches the cross-scene editing instruction with a preset scene knowledge graph, determines a pluggable component in a preset scene atomization component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library; establishes a communication connection with an edge layer in an artificial intelligence Internet of Things, receives Internet of Things device data sent by the edge layer; constructs a process of the pluggable component according to the scene logic rule, determines a corresponding component association relationship and a component interaction mode, and constructs a cloud service layer middle platform according to the component association relationship, the component interaction mode, and a key feature, so that highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT service can be realized. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0041] Fig. 1 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0042] Fig. 2 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0043] Fig. 3 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0044] Fig. 4 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0045] Fig. 5 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0046] Fig. 6 is a flowchart of a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability in an embodiment of the present application;

[0047] Fig. 7 is a structural diagram of a cross-scene Internet of Things application rapid building device based on AIOT middle platform componentization capability in an embodiment of the present application;

[0048] FIG. 8 is a structural diagram of a cross-scene Internet of Things application rapid building system based on AIOT middle platform componentization capability in the embodiment of the present application;

[0049] FIG. 9 is a structural schematic diagram of an electronic device in the embodiment of the present application.

[0050] Reference signs:

[0051] Electronic device 9600, central processor 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer storage 9141, application / function storage part 9142, data storage part 9143, driver program storage part 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0053] The acquisition, storage, use, processing, and the like of data in the technical solutions of the present application all comply with relevant provisions of national laws and regulations.

[0054] In view of the prior art, in the existing AIoT architecture, once the system is deployed, the access of new devices often needs to update and redeploy service code. This process not only consumes time and effort, but also each update may affect the stability and continuous online time of the system. With the rapid changes in business needs and the continuous emergence of new technologies, the low flexibility of the existing system obviously cannot meet the market demand. The present application provides a cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability, which receives a cross-scene editing instruction sent by a user through a visual interface, matches the cross-scene editing instruction with a preset scene knowledge graph, determines a pluggable component in a preset scene atomization component library, a scene analysis algorithm matched in a preset algorithm center, and a scene logic rule matched in a preset scene rule library; establishes a communication connection with an edge layer in an artificial intelligence Internet of Things, and receives Internet of Things device data sent by the edge layer; constructs a flow of the pluggable component according to the scene logic rule, determines a corresponding component association relationship and a component interaction mode, and constructs a cloud service layer middle platform according to the component association relationship, the component interaction mode, and a key feature, which can realize highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT service.

[0055] In order to realize highly flexible and scalable cross-scene Internet of Things application rapid construction and AIOT service, an embodiment of a cross-scene Internet of Things application rapid construction method based on AIOT middle platform componentization capability is provided, which is applied to the cloud service layer in the artificial intelligence Internet of Things, as shown in FIG. 1. The cross-scene Internet of Things application rapid construction method based on AIOT middle platform componentization capability specifically includes the following contents:

[0056] Step S101: receiving a cross-scene editing instruction sent by a user through a visual interface, matching the cross-scene editing instruction with a preset scene knowledge graph, determining a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library;

[0057] Optionally, in today's technical environment, the processing of cross-scene editing instructions usually involves highly complex system architecture, especially in dynamic and variable operation scenarios. Step S101 provides an in-depth solution by receiving a cross-scene editing instruction sent by a user through a user-friendly visual interface. The user can send specific operation instructions through this interface, such as adjusting parameters, switching views, or modifying data sources, etc. Once these instructions are received by the system, the next challenge is how to accurately parse and execute these instructions to ensure that the user's needs are met.

[0058] In order to process these instructions, the system first needs to parse the received information and convert it into a structured format that can be understood and processed by machines. In this process, the system will match with a preset scene knowledge graph. The scene knowledge graph is a data structure that contains elements and their relationships in different scenes, such as component dependencies, operation rules, etc. By matching with this graph, the system can quickly identify the specific scene mentioned in the user instruction and the required operation component.

[0059] After confirming the user instruction, the system then selects suitable pluggable components from the preset scene atomized component library. These components are predefined and can be dynamically combined or replaced as needed to adapt to different operation requirements and scene changes. For example, if the user needs to add a new data visualization component in a data analysis application, the system can select a suitable visualization tool from the component library and integrate it into the current scene.

[0060] At the same time, the system also needs to select a matched scene analysis algorithm from the preset algorithm center. These algorithms are optimized and debugged in advance and can analyze and process data in specific scenes, such as data mining, pattern recognition, or prediction analysis, etc. Selecting the appropriate algorithm is crucial to ensure the accuracy and effectiveness of instruction execution.

[0061] In addition, the system also refers to the scene logic rules in the preset scene rule library to ensure that all operations comply with the established business logic and compliance requirements. This step is crucial to ensure that the system operation is not only technically feasible, but also business reasonable.

[0062] Through this series of complex matching and selection process, the system can accurately respond to the user's cross-scene editing instructions, realize highly customized operation and dynamic scene management. The implementation of this technical solution significantly improves the flexibility and user experience of the system, enabling users to interact with the system more intuitively and efficiently, while ensuring the accuracy of the operation and compliance with business rules. In terms of operation efficiency and system reliability, such technical implementation provides great convenience for users, especially in application scenarios that require frequent adjustment and highly personalized configuration.

[0063] Step S102: Establish a communication connection with the edge layer in the artificial intelligence Internet of Things, receive the Internet of Things device data sent by the edge layer, perform data format conversion on the Internet of Things device data according to the data format requirements of the pluggable component, and configure the component data source of the pluggable component according to the set data configuration rules, wherein the Internet of Things device data is sent by the intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0064] Optionally, in modern Internet of Things (IoT) applications, especially in scenarios involving artificial intelligence (AI), how to effectively manage and process the vast data stream from smart devices is a key challenge. Step S102 describes this process in detail, from establishing a communication connection with the edge layer, to receiving and converting Internet of Things device data, and finally configuring the data source for the pluggable component. The entire step reflects the high integration and automated processing capabilities of the technology.

[0065] Internet of Things devices such as sensors and smart meters are usually deployed in scattered geographical locations, and they continuously collect and send various types of data. In the artificial intelligence Internet of Things architecture, the edge layer plays a crucial role, not only reducing the data transmission pressure on the central server, but also performing preliminary data processing and analysis, thereby speeding up the response and reducing bandwidth usage. The first step of step S102 is to establish a communication connection with this edge layer to ensure smooth data transmission.

[0066] Once a stable communication connection is established, the edge layer begins to send Internet of Things device data to the central system. These data are usually collected from the intelligent terminal layer through a pre-set unified service interface, with various formats, including but not limited to temperature readings, energy consumption data, and operating status. Since different devices may use different data formats, the received data need to be converted to meet the needs of downstream processing and analysis. This conversion process involves parsing the original data structure and converting it into the standard format required by the pluggable components. For example, the original data may be unstructured text logs, while the converted data may be structured JSON or XML formats, which are crucial for subsequent data processing and analysis.

[0067] The converted data is then further processed according to the set data configuration rules to configure it as a data source for specific pluggable components. These rules define how data is stored, indexed, and retrieved to support efficient data querying and operations. The design of data configuration rules takes into account the real-time needs of data and long-term storage strategies, ensuring that data can be quickly accessed and supports historical data analysis.

[0068] In terms of technical effects, step S102 greatly optimizes the data processing process, improving the efficiency and accuracy of data processing. By decentralizing data processing tasks to the edge layer, the system can respond more quickly to device state changes, while reducing the load on the central data center and the demand for network bandwidth. The unified conversion and standardized configuration of data formats enable seamless integration and analysis of data from different devices and platforms, improving data availability and value.

[0069] In addition, this highly automated data processing method reduces the need for human intervention, reduces the risk of operational errors, and improves the overall reliability and security of the system. In practical applications, this means that enterprises can more effectively utilize the data generated by their Internet of Things devices, support more complex decision-making processes, and gain a competitive advantage in the market. In summary, step S102 not only improves the efficiency and accuracy of data processing, but also provides strong technical support for the management and use of Internet of Things devices, promoting the development of intelligent applications.

[0070] Step S103: Perform data analysis on the component data source through the matched scene analysis algorithm, determine the corresponding key features, construct the process of the pluggable component according to the scene logic rules, determine the corresponding component association relationship and component interaction mode, and construct the cloud service layer station according to the component association relationship, the component interaction mode, and the key features.

[0071] Optionally, the technical principles and working processes involved in step S103 are the core part of modern Internet of Things and artificial intelligence systems, which build an efficient and intelligent cloud service layer platform based on data collected from Internet of Things devices. The main task of this link is to analyze data through advanced data analysis algorithms, build processes suitable for specific application scenarios, and realize effective cooperation between components.

[0072] After receiving and formatting the data of Internet of Things devices, the system needs to conduct in-depth analysis on these data to extract key features. This process is completed through pre-selected scene analysis algorithms. These algorithms may include machine learning models, statistical analysis methods or deep learning frameworks, aiming to identify patterns, trends and anomalies from a large amount of raw data. For example, for a temperature monitoring system, key features may include daily cycle changes in temperature, abnormal high or low temperature events, etc.

[0073] After determining these key features, the system further operates according to pre-set scene logic rules. Scene logic rules define how various data and events should affect the behavior of the system, including how data triggers specific processes or operations. These rules ensure that the system's response corresponds closely to business logic and operational needs, so that the system can take the right action at the right time.

[0074] Next, the most critical part of step S103 is the process of building pluggable components. In this stage, the system uses scene logic rules to determine the relationship between different components and their interaction methods. This means that the system will dynamically combine and configure various components according to data analysis results to optimize the completion of specific tasks. For example, in the intelligent manufacturing scenario, the data of a sensor may trigger the inspection process of the quality control component, which may further affect the adjustment of the production line.

[0075] Through this method, the system can flexibly adjust the workflow according to real-time data and business rules, optimize resource allocation, and improve efficiency. Finally, using these settings and key features, the system builds a cloud service layer platform, which is a highly integrated service platform that supports the rapid development, deployment and management of various applications and services. The platform not only encapsulates the complexity of business logic and data processing, but also provides easy-to-use interfaces, making it easier for end users and developers to access services and data.

[0076] In terms of technical effects, step S103 significantly improves the intelligent level and operation efficiency of the entire system through intelligent analysis and fine management of data. The identification of key features enables the system to more accurately predict and respond to various situations, while the efficient association and interaction between components ensure smooth and efficient processes. In addition, the construction of the cloud service layer greatly simplifies the development of new services and the maintenance of old services, reduces operating costs, and improves the scalability and flexibility of the system. These technical advantages not only enhance the competitiveness of enterprises, but also provide users with more reliable and efficient service experiences.

[0077] From the above description, it can be seen that the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability provided by the embodiments of the application can receive cross-scene editing instructions sent by a user through a visual interface, match the cross-scene editing instructions with a preset scene knowledge graph, determine pluggable components in a preset scene atomization component library, matching scene analysis algorithms in a preset algorithm center, and matching scene logic rules in a preset scene rule library; establish a communication connection with an edge layer in an artificial intelligence Internet of Things, and receive Internet of Things device data sent by the edge layer; construct a process for the pluggable components according to the scene logic rules, determine corresponding component association relationships and component interaction modes, and construct a cloud service layer middle platform according to the component association relationships, the component interaction modes, and key features, so as to realize highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT services.

[0078] In an embodiment of the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability of the application, referring to FIG. 2, the method can further include the following content:

[0079] Step S201: determining nodes in a scene knowledge graph according to attribute information of the historical pluggable components, the historical scene analysis algorithms, and the historical scene logic rules, and determining edges in the scene knowledge graph according to the association between the historical pluggable components, the historical scene analysis algorithms, and the historical scene logic rules;

[0080] Step S202: constructing the scene knowledge graph according to the nodes and the edges.

[0081] Optionally, in steps S201 and S202, the technical principles and working processes mainly involve constructing a scene knowledge graph, which is a complex system for representing and analyzing the relationships between various components, algorithms, and rules. This graph not only helps the system understand and execute user requirements, but also improves the system's adaptability and intelligent level.

[0082] The construction of the scenario knowledge graph first relies on the analysis of historical data, including the attributes of historical pluggable components, historical scenario analysis algorithms, and historical scenario logic rules. These information includes the function, performance parameters, application scenarios, and usage frequency of each component, the type, applicability, efficiency, and accuracy of the scenario analysis algorithm, and the scope of application, triggering conditions, and execution operations of the scenario logic rule. These detailed attribute information is the basis for constructing knowledge graph nodes, and each attribute can be defined as a node. The detailed definition of the node depends on its role and importance in the business process.

[0083] Next, step S201 also involves determining the edges in the knowledge graph based on the relevance in these historical information. Edges represent the relationship between different nodes, such as dependency, synergy, or mutual exclusion. For example, a specific scenario analysis algorithm may require a specific type of data input, and this demand relationship will be represented as an edge in the knowledge graph. By analyzing historical usage patterns and feedback, the system can identify which components are often used together, which algorithms are more effective for certain types of tasks, and which rules are more suitable in certain situations. Such correlation analysis not only enhances the information richness of the graph, but also makes the graph more accurately reflect the complex relationships in the real world.

[0084] In step S202, the system constructs the scenario knowledge graph based on these defined nodes and edges. This process usually involves complex data structures and algorithms to ensure the accuracy and usability of the graph. The completed knowledge graph is a powerful tool that can support system decision-making, optimize problem-solving processes, predict system behavior, and even automatically adjust strategies to adapt to new operating environments.

[0085] In terms of technical effects, the use of scenario knowledge graphs greatly improves the intelligence and automation level of the system. First, it enables the system to automatically optimize operations based on accumulated experience, predicting and solving potential problems through historical data analysis. Second, the dynamic updating and expansion capabilities of the knowledge graph ensure that the system can continuously evolve to adapt to new business demands and technological changes. In addition, through the graph, the system can more effectively manage and utilize resources, such as optimizing resource allocation by identifying commonly used component and algorithm combinations, reducing redundant operations, and improving efficiency. Ultimately, this approach not only enhances the reliability and performance of the system, but also improves the user's operation experience by providing faster and more accurate services to meet the specific needs of users.

[0086] In an embodiment of the AIOT middle platform component-based cross-scenario Internet of Things application rapid construction method of the present application, as shown in FIG. 3, the following content can also be specifically included:

[0087] Step S301: Determine the matching range in the preset scenario knowledge graph based on the scenario requirements and specific functions;

[0088] Step S302: Measure the similarity between nodes and edges in the matching range using similarity algorithms, and determine the matching pluggable components in the scenario atomization component library, the matching scenario analysis algorithms in the preset algorithm center, and the matching scenario logic rules in the preset scenario rule library based on the nodes and edges with the highest similarity.

[0089] Optionally, steps S301 and S302 constitute a highly specialized knowledge graph matching process, aiming to select components, algorithms, and logic rules that match specific scenario requirements and functions from the preset knowledge graph. This process involves complex data analysis and intelligent algorithms to ensure that the system can provide the most suitable combination of resources for each specific scenario.

[0090] In step S301, the system first needs to clearly understand the scenario requirements and the specific functions required. This usually involves interaction with the user, collecting detailed requirement descriptions such as performance indicators, operating environment, user expectations, etc. Based on these requirements, the system administrator or automated tools will define the matching range of the knowledge graph, i.e., determine which part of the graph's information is relevant to the current requirements. This step is crucial as it determines the direction and efficiency of the subsequent search and matching process. For example, if the scenario requirement is an automated system for temperature control, the matching range may focus on the graph part containing temperature sensors, related control algorithms, and execution rules.

[0091] Step S302 further utilizes similarity algorithms to measure the similarity between nodes and edges in the matching range of the graph. These algorithms may include traditional statistical similarity calculations, machine learning-based pattern recognition techniques, or deep learning methods, which can analyze and compare the attribute information of nodes and the relationship characteristics of edges. Through the calculated similarity scores, the system can identify the most matching components, algorithms, and rules for the current requirements. This process not only considers the consistency of technical parameters, but also considers historical performance data, user feedback, usage frequency, etc., to ensure the effectiveness and reliability of the recommended solutions in actual applications.

[0092] For example, the system may find that a certain temperature sensor performs well in similar applications due to its high precision and fast response time, while a certain temperature control algorithm is frequently adopted due to its optimized energy management and fault prediction capabilities. In addition, a group of rules may be selected due to their high efficiency in handling abnormal situations. This data and algorithm-based matching process greatly enhances the system's adaptability and intelligence level.

[0093] In terms of technical effects, this knowledge graph-based matching method brings significant improvements in system flexibility and efficiency. First, by accurately matching user needs with system resources, the system's operational efficiency and resource utilization can be greatly improved, reducing resource waste. Second, this method supports highly customized service provision, enabling the system to provide more personalized solutions for different users, thereby improving user satisfaction and the system's market competitiveness. In addition, the system's scalability and maintainability are enhanced, as the use of knowledge graphs enables the system to quickly adapt to new technologies and market changes while maintaining the stability and reliability of core functions.

[0094] In summary, through intelligent graph matching and resource optimization, the system not only provides more efficient and accurate services, but also continuously learns and adapts to new operating environments and user needs while maintaining high flexibility and scalability. This technology has broad application prospects and is of great significance for improving the overall performance and user experience of intelligent systems.

[0095] In an embodiment of the AIOT middle platform component-based cross-scene IoT application rapid construction method of the present application, referring to FIG. 4, the following content can also be specifically included:

[0096] Step S401: performing semantic analysis on the cross-scene editing instruction to determine the corresponding scene demand;

[0097] Step S402: determining a specific function that best matches the scene demand according to a preset scene function list.

[0098] Optionally, in modern intelligent systems, the processing of cross-scene editing instructions is a key technology that allows the system to understand and respond to specific instructions from different application scenarios. The implementation of this technology involves two main steps: semantic analysis and function matching, which together ensure that the system can accurately and efficiently identify and execute user instructions.

[0099] The primary task of step S401 is to perform semantic analysis on the cross-scene editing instruction. Semantic analysis is a core technology in the field of natural language processing (NLP), which converts user instructions into a data format that the system can understand and process by analyzing the structure and semantic content of the instructions. Specifically, this step involves multiple sub-tasks such as lexical analysis, syntactic parsing, and semantic understanding. For example, if an intelligent home system receives the instruction "reduce the brightness of the living room lights", the system will first break down the key words in the instruction such as "reduce", "living room", "lights", and "brightness". Then, through syntactic parsing, it determines that "reduce" is the action and the brightness of the "living room lights" is the object being operated. Next, in the semantic understanding stage, the system needs to identify that this operation means adjusting the settings of the light devices, rather than other possible meanings.

[0100] After semantic analysis is completed, step S402 involves determining the specific function that best matches the scene requirement from a pre-set list of scene functions. This step is function-oriented and requires the system to have the ability to filter functions from its database that match the parsed requirements. The system's pre-set list of scene functions is a database containing various function options that cover a range of operations the system may need to perform, such as temperature adjustment, lighting control, security monitoring, etc. Using the previously mentioned smart home system as an example, the system will compare the "adjust lighting" option in the function list and confirm that this function can meet the "reduce living room light intensity" requirement. In this process, the system may also consider user preference settings, historical operation data, and environmental information to ensure the maximum adaptability and personalization of the function selection.

[0101] The implementation effect of this technology is extremely significant. First, through precise semantic analysis and function matching, the system can provide fast and accurate responses, greatly improving user experience. Users do not need complex operations or multiple modifications of instructions, and the system can directly understand and execute. Second, this technology supports high system flexibility and scalability. As the pre-set function list is continuously expanded and optimized, the system can adapt to a wider range of application scenarios and complex user requirements. In addition, the intelligent system can further optimize the function matching algorithm by continuously learning the user's preferences and operation habits, achieving more personalized services.

[0102] Taking a specific application example, consider an office environment integrated with multiple smart devices. Employees can trigger the system to automatically adjust the conference room lighting, projection equipment, and air conditioning through simple voice commands such as "prepare the video conference room." Here, the system needs to parse the instruction and select appropriate lighting adjustment, device startup, and temperature control functions from the function list to meet the specific setup requirements of the conference room. Through this technology, the office environment becomes more intelligent and efficient, greatly improving work efficiency and employee satisfaction.

[0103] In an embodiment of the AIOT middle platform component-based cross-scene IoT application rapid construction method of the present application, referring to FIG. 5, the following content can also be specifically included:

[0104] Step S501: receiving the IoT device data sent by the edge layer in the artificial intelligence Internet of Things, wherein the IoT device data is sent by the intelligent terminal layer in the artificial intelligence Internet of Things through a pre-set unified service interface;

[0105] Step S502: standardizing the IoT device data according to the configuration requirements of the pluggable component, and configuring the IoT device data after the standardization processing as the component data source of the pluggable component.

[0106] Optionally, in the practice of Artificial Intelligence Internet of Things (AIoT), efficient management of data streams is crucial. This process begins with data collection at the intelligent terminal layer, involving data reception, processing, and eventual application. Steps S501 and S502 form the core of this process, ensuring that data can be effectively received and processed to adapt to different application scenarios and needs.

[0107] In step S501, the main task of the system is to receive data from Internet of Things devices sent by the edge layer. In this stage, data mainly comes from the intelligent terminal layer, which includes various sensors and actuators such as temperature sensors, cameras, smart light bulbs, etc. These devices collect and send data through a pre-set unified service interface. The design of this interface standardizes the way data is communicated between different devices, allowing data streams to move smoothly in the Internet of Things to the edge layer. The edge layer mainly acts as a data transfer station, which not only reduces the need for data transmission to the central server, but also can perform preliminary data processing, thus reducing the load of the central server and reducing response time.

[0108] Then, in step S502, these data received from the intelligent terminal layer need to be standardized. Standardization is the key to ensuring that data can be seamlessly connected between different system components. In this process, raw data is converted into a format that meets the basic requirements of all pluggable components. For example, raw data may include various sensor-specific data formats, while standardized data is converted into JSON or XML formats, which are widely supported and easy to handle across platforms. After standardization, these data will be configured as the data source of pluggable components for further data analysis and application.

[0109] This series of technical processes not only improves the efficiency of data processing, but also enhances the flexibility and scalability of the system. Through standardized data interfaces and formats, new devices and services can be more easily integrated into existing systems. In addition, the use of the edge layer greatly reduces the dependence on central data processing facilities, which is particularly important in bandwidth-limited or delay-sensitive applications. For example, in a large factory, it is crucial to monitor and adjust the running status of the production line in real time. By deploying sensors to collect data throughout the factory and performing preliminary processing at the edge layer, various production needs and emergencies can be quickly responded to, thereby optimizing production efficiency and reducing maintenance costs.

[0110] Overall, the implementation of steps S501 and S502 not only improves the efficiency of data processing, but also provides a solid foundation for the reliability and real-time performance of the AIoT system. This efficient and standardized data processing flow is the key to realizing various modern technology applications such as smart cities, smart homes, industrial automation, etc.

[0111] In an embodiment of the AIOT middle platform component-based cross-scene Internet of Things application rapid construction method of the present application, referring to FIG. 6, the following contents can also be specifically included:

[0112] Step S601: Through the data cleaning model built-in in the edge layer of the artificial intelligence Internet of Things, the Internet of Things device data sent by the intelligent terminal layer in the artificial intelligence Internet of Things is cleaned and filtered;

[0113] Step S602: Through the data analysis model built-in in the edge layer of the artificial intelligence Internet of Things, the Internet of Things device data after the data cleaning and filtering is analyzed to obtain the Internet of Things device data after the data analysis.

[0114] Optionally, in step S601, the system first needs to clean and filter the Internet of Things device data sent from the intelligent terminal layer through the data cleaning model built-in in the edge layer. The intelligent terminal layer mainly includes various sensors and devices, such as temperature sensors, video cameras, environmental monitors, etc., which continuously generate a large amount of data. However, these data may contain errors, duplicates or incomplete information, which may affect the quality and accuracy of data analysis. The task of the data cleaning model is to identify and remove these inaccurate or irrelevant data parts, such as correcting obvious error readings, deleting duplicate records or filling missing values. For example, in a smart farm management system, data from a soil humidity sensor may show abnormally high readings due to device failure, and the data cleaning model will identify these abnormalities and correct or mark them according to historical data to prevent these erroneous data from affecting subsequent analysis and decision-making.

[0115] Next, in step S602, the data analysis model built-in in the edge layer will analyze the cleaned and filtered data in depth. This step is the core function in the AIoT system, which involves using statistical methods, machine learning algorithms or deep learning techniques to analyze data and extract meaningful patterns and trends. These analysis results can be used for various applications such as predictive maintenance, resource optimization, behavior analysis, etc. For example, in a smart traffic system, by analyzing traffic flow data from various locations, the model can predict congestion at a specific time and place, and adjust the working mode of traffic lights accordingly to optimize traffic flow and reduce congestion.

[0116] The implementation of these two steps significantly improves the availability and usefulness of data, enabling AIoT systems to respond more accurately to environmental changes and user needs. Data cleaning ensures the quality of the underlying data for analysis, while efficient data analysis provides a scientific basis for decision-making, which is crucial for systems that aim to achieve automated control and intelligent decision-making. By handling these steps at the edge layer, the need for data transmission to the central server can be significantly reduced, resulting in lower latency and improved response speed and reliability of the system. For example, in the field of intelligent manufacturing, real-time monitoring and analysis of production line operation data through edge computing models can allow for immediate adjustments to production parameters, optimizing production efficiency and reducing downtime.

[0117] In summary, steps S601 and S602 not only improve the efficiency and quality of the data processing process, but also enhance the real-time performance and intelligence level of AIoT systems, making their applications in various fields more widespread and effective. This data-driven intelligent system is gradually changing the fields of industrial automation, urban management, environmental monitoring, and others, demonstrating great potential for development and application value.

[0118] In order to be able to realize highly flexible and scalable cross-scene Internet of Things application rapid construction and AIOT service, the present application provides an embodiment of a cross-scene Internet of Things application rapid construction device based on AIOT middle platform componentization capability for implementing all or part of the cross-scene Internet of Things application rapid construction method based on AIOT middle platform componentization capability, as shown in FIG. 7. The cross-scene Internet of Things application rapid construction device based on AIOT middle platform componentization capability specifically includes the following contents:

[0119] The construction element determination module 10 is configured to receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, and determine a pluggable component in a preset scene atomized component library, a matching scene analysis algorithm in a preset algorithm center, and a matching scene logic rule in a preset scene rule library.

[0120] The construction data configuration module 20 is configured to establish a communication connection with an edge layer in an artificial intelligence Internet of Things, receive Internet of Things device data sent by the edge layer, perform data format conversion on the Internet of Things device data according to data format requirements of the pluggable component, and configure the Internet of Things device data as component data sources of the pluggable component according to a set data configuration rule. The Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface.

[0121] The middle platform building module 30 is configured to perform data analysis on the component data source by the matched scene analysis algorithm, determine corresponding key features, perform process construction on the pluggable component according to the scene logic rule, determine corresponding component association relationship and component interaction mode, and construct the cloud service layer middle platform according to the component association relationship, the component interaction mode and the key features.

[0122] As can be seen from the above description, the cross-scene Internet of Things application rapid building device based on the AIOT middle platform componentization capability provided by the embodiments of the present application can receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center and a matched scene logic rule in a preset scene rule library, establish a communication connection with an edge layer in an artificial intelligence Internet of Things, receive Internet of Things device data sent by the edge layer, perform process construction on the pluggable component according to the scene logic rule, determine corresponding component association relationship and component interaction mode, and construct a cloud service layer middle platform according to the component association relationship, the component interaction mode and key features, thereby achieving highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT service.

[0123] In order to achieve highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT service, the present application provides an embodiment of a system of a cross-scene Internet of Things application rapid building device based on AIOT middle platform componentization capability for implementing all or part of the contents of the cross-scene Internet of Things application rapid building method based on AIOT middle platform componentization capability, as shown in FIG. 8, the system includes a cloud service layer, an edge layer and an intelligent terminal layer in an artificial intelligence Internet of Things, the cloud service layer is connected with the edge layer, and the edge layer is connected with the intelligent terminal layer;

[0124] The cloud service layer includes:

[0125] The building element determination module 10 is configured to receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center and a matched scene logic rule in a preset scene rule library;

[0126] The data configuration module 20 is used to establish a communication connection with an edge layer in an artificial intelligence Internet of Things, receive Internet of Things device data sent by the edge layer, perform data format conversion on the Internet of Things device data according to a data format requirement of the pluggable component, and configure the Internet of Things device data as a component data source of the pluggable component according to a set data configuration rule, wherein the Internet of Things device data is sent by a smart terminal layer in the artificial intelligence Internet of Things through a preset unified service interface.

[0127] The middle platform building module 30 is used to perform data analysis on the component data source through a matched scene analysis algorithm, determine corresponding key features, perform flow construction on the pluggable component according to the scene logic rule, determine a corresponding component association relationship and a component interaction mode, and construct a cloud service layer middle platform according to the component association relationship, the component interaction mode, and the key features.

[0128] From the hardware level, in order to realize highly flexible and extensible cross-scene Internet of Things application rapid building and AIOT service, the present application provides an embodiment of an electronic device for realizing all or part of the contents of the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability, which specifically includes the following contents:

[0129] A processor, a memory, a communication interface, and a bus; wherein the processor, the memory, and the communication interface complete mutual communication through the bus; the communication interface is used to realize information transmission between the cross-scene Internet of Things application rapid building device based on the AIOT middle platform componentization capability and a core business system, a user terminal, and related databases and other related devices; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, and the like, and the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented by referring to the embodiments of the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability and the embodiments of the cross-scene Internet of Things application rapid building device based on the AIOT middle platform componentization capability in the embodiments, the contents of which are incorporated herein, and repeated descriptions are omitted.

[0130] It can be understood that the user terminal can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, and the like. The smart wearable device can include smart glasses, a smart watch, a smart bracelet, and the like.

[0131] In actual applications, part of the cross-scene Internet of Things application rapid construction method based on the AIOT middle platform componentization capability can be executed on the electronic device as described above, or all operations can be completed in the client device. Specifically, the selection can be made according to the processing capability of the client device and the restriction of the user's use scene, etc. The present application does not limit this. If all operations are completed in the client device, the client device can also include a processor.

[0132] The above-mentioned client device can have a communication module (i.e., a communication unit) and can be in communication connection with a remote server to realize data transmission with the server. The server can include a server on the task scheduling center side, and in other implementation scenarios, it can also include a server of an intermediate platform, such as a server of a third-party server platform that is in communication link with the task scheduling center server. The server can include a single computer device, or a server cluster composed of multiple servers, or a server structure of a distributed device.

[0133] FIG. 9 is a schematic block diagram of the system structure of an electronic device 9600 according to an embodiment of the present application. As shown in FIG. 9, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that FIG. 9 is exemplary; other types of structures can also be used to supplement or replace this structure to realize telecommunication functions or other functions.

[0134] In an embodiment, the cross-scene Internet of Things application rapid construction method based on the AIOT middle platform componentization capability can be integrated into the central processor 9100. The central processor 9100 can be configured to control as follows:

[0135] Step S101: receiving a cross-scene editing instruction sent by a user through a visual interface, matching the cross-scene editing instruction with a preset scene knowledge graph, and determining a pluggable component in a preset scene atomization component library, a matching scene analysis algorithm in a preset algorithm center, and a matching scene logic rule in a preset scene rule library;

[0136] Step S102: establishing a communication connection with an edge layer in an artificial intelligence Internet of Things, receiving Internet of Things device data sent by the edge layer, performing data format conversion on the Internet of Things device data according to a data format requirement of the pluggable component, and configuring the Internet of Things device data as a component data source of the pluggable component according to a set data configuration rule, wherein the Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0137] Step S103: performing data analysis on the component data source through the matched scene analysis algorithm, determining corresponding key features, constructing a flow of the pluggable component according to the scene logic rule, determining corresponding component association relationship and component interaction mode, and constructing a cloud service layer station according to the component association relationship, the component interaction mode and the key features.

[0138] As can be seen from the above description, the electronic device provided by the embodiment of the application receives a cross-scene editing instruction sent by a user through a visual interface, matches the cross-scene editing instruction with a preset scene knowledge graph, determines a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center and a matched scene logic rule in a preset scene rule library, establishes a communication connection with an edge layer in an artificial intelligence Internet of Things, receives Internet of Things device data sent by the edge layer, constructs a flow of the pluggable component according to the scene logic rule, determines corresponding component association relationship and component interaction mode, and constructs a cloud service layer station according to the component association relationship, the component interaction mode and key features, so that a highly flexible and extensible cross-scene Internet of Things application can be quickly built and AIOT service can be implemented.

[0139] In another embodiment, the cross-scene Internet of Things application quick building device based on the AIOT station componentization capability can be configured separately from the central processor 9100, for example, the cross-scene Internet of Things application quick building device based on the AIOT station componentization capability can be configured as a chip connected with the central processor 9100, and the cross-scene Internet of Things application quick building method function based on the AIOT station componentization capability is realized through the control of the central processor.

[0140] As shown in FIG. 9, the electronic device 9600 can also include a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It should be noted that the electronic device 9600 does not necessarily include all the components shown in FIG. 9; in addition, the electronic device 9600 can also include components not shown in FIG. 9, which can be referred to prior art.

[0141] As shown in FIG. 9, the central processor 9100 is also sometimes referred to as a controller or an operation control, which can include a microprocessor or other processor device and / or a logic device, the central processor 9100 receives input and controls the operation of various components of the electronic device 9600.

[0142] The memory 9140, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The above-mentioned information related to failure can be stored, and in addition, a program for executing the information related to failure can be stored. The central processing unit 9100 can execute the program stored in the memory 9140 to achieve information storage or processing, and the like.

[0143] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to supply power to the electronic device 9600. The display 9160 is used to display display objects such as images and characters. The display 9160 can be, for example, an LCD display, but is not limited thereto.

[0144] The memory 9140 can be a solid state memory such as a read only memory (ROM), a random access memory (RAM), a SIM card, and the like. It can also be a memory that retains information even when power is off, can be selectively erased, and is provided with more data, and examples of such a memory are sometimes referred to as an EPROM, and the like. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 can include an application / function storage section 9142 for storing application programs and function programs or for storing a flow for executing operations of the electronic device 9600 by the central processing unit 9100.

[0145] The memory 9140 can also include a data storage section 9143 for storing data such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. A driver storage section 9144 of the memory 9140 can include various drivers of the electronic device for a communication function and / or for executing other functions of the electronic device such as a messaging application, an address book application, and the like.

[0146] The communication module 9110 is a transmitter / receiver that transmits and receives signals via an antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0147] Based on different communication technologies, multiple communication modules 9110, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc., can be provided in the same electronic device. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132, thereby enabling typical telecommunication functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling the recording of audio on the local device via the microphone 9132 and enabling the playing of stored audio on the local device via the speaker 9131.

[0148] The embodiments of the present application also provide a computer readable storage medium capable of implementing all steps of the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability of the execution subject in the above embodiments, and the computer program is stored on the computer readable storage medium. When the processor executes the computer program, all steps of the cross-scene Internet of Things application rapid building method based on the AIOT middle platform componentization capability of the execution subject in the above embodiments are implemented, for example, the following steps are implemented when the processor executes the computer program:

[0149] Step S101: receiving a cross-scene editing instruction sent by a user through a visual interface, matching the cross-scene editing instruction with a preset scene knowledge graph, determining a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library;

[0150] Step S102: establishing a communication connection with an edge layer in an artificial intelligence Internet of Things, receiving Internet of Things device data sent by the edge layer, performing data format conversion on the Internet of Things device data according to data format requirements of the pluggable component, and configuring the Internet of Things device data as a component data source of the pluggable component according to a set data configuration rule, wherein the Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0151] Step S103: performing data analysis on the component data source through the matched scene analysis algorithm, determining a corresponding key feature, constructing a flow of the pluggable component according to the scene logic rule, determining a corresponding component association relationship and a component interaction mode, and constructing a cloud service layer middle platform according to the component association relationship, the component interaction mode, and the key feature.

[0152] From the above description, the computer readable storage medium provided by the embodiments of the application receives a cross-scene editing instruction sent by a user through a visual interface, matches the cross-scene editing instruction with a preset scene knowledge graph, determines a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library; a communication connection is established with an edge layer in an artificial intelligence Internet of Things, and Internet of Things device data sent by the edge layer is received; a process of the pluggable component is constructed according to the scene logic rule, corresponding component association relationships and component interaction modes are determined, and a cloud service layer middle office is constructed according to the component association relationships, the component interaction modes, and key features, so that highly flexible and extensible cross-scene Internet of Things application rapid construction and AIOT services can be realized.

[0153] The embodiments of the application also provide a computer program product capable of realizing all steps in the cross-scene Internet of Things application rapid construction method based on AIOT middle office componentization capability of an execution subject being a server or a client in the above embodiments, and the computer program / instruction is executed by a processor to realize the steps of the cross-scene Internet of Things application rapid construction method based on AIOT middle office componentization capability, for example, the computer program / instruction realizes the following steps:

[0154] Step S101: receiving a cross-scene editing instruction sent by a user through a visual interface, matching the cross-scene editing instruction with a preset scene knowledge graph, and determining a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library;

[0155] Step S102: establishing a communication connection with an edge layer in an artificial intelligence Internet of Things, receiving Internet of Things device data sent by the edge layer, performing data format conversion on the Internet of Things device data according to data format requirements of the pluggable component, and configuring the Internet of Things device data as component data sources of the pluggable component according to a set data configuration rule, wherein the Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface;

[0156] Step S103: performing data analysis on the component data sources through the matched scene analysis algorithm, determining corresponding key features, constructing a process of the pluggable component according to the scene logic rule, determining corresponding component association relationships and component interaction modes, and constructing a cloud service layer middle office according to the component association relationships, the component interaction modes, and the key features.

[0157] From the above description, the computer program product provided by the embodiment of the present application receives the cross-scene editing instruction sent by the user through the visual interface, matches the cross-scene editing instruction with the preset scene knowledge graph, determines the pluggable components in the preset scene atomized component library, the matched scene analysis algorithm in the preset algorithm center, and the matched scene logic rule in the preset scene rule library; establishes a communication connection with the edge layer in the artificial intelligence Internet of Things, receives the Internet of Things device data sent by the edge layer; constructs a process for the pluggable components according to the scene logic rule, determines the corresponding component association relationship and component interaction mode, and constructs a cloud service layer station according to the component association relationship, the component interaction mode, and the key features, which can realize the rapid construction of a highly flexible and extensible cross-scene Internet of Things application and AIOT service.

[0158] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0159] The present application is described with reference to flowcharts and / or block diagrams of the method, device (apparatus), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0160] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction devices that implement the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0161] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks and / or blocks in the block diagram.

[0162] The principles and implementations of the present application are described in the specific examples, the above examples are only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. A method for quickly building cross-scene Internet of Things applications based on AIOT middle platform componentization capability, characterized in that, The method is applied to a cloud service layer in an artificial intelligence Internet of Things, and the method comprises the following steps: receiving a cross-scene editing instruction sent by a user through a visual interface, and matching the cross-scene editing instruction with a preset scene knowledge graph to determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center, and a matched scene logic rule in a preset scene rule library; wherein the determination of the pluggable component in the preset scene atomized component library comprises: dynamically combining the pluggable component or replacing the pluggable component, the scene analysis algorithm is an algorithm for analyzing and processing data in a specific scene, and the analysis and processing comprises data mining, pattern recognition and / or prediction analysis; establishing a communication connection with an edge layer in the artificial intelligence Internet of Things, receiving Internet of Things device data sent by the edge layer, the Internet of Things data comprising: temperature readings, energy consumption data and / or operating states, performing data format conversion on the Internet of Things device data according to data format requirements of the pluggable component, and configuring the Internet of Things device data as component data sources of the pluggable component according to a set data configuration rule, the set data configuration rule comprising: a storage rule, an index rule and / or a retrieval rule; wherein the Internet of Things device data is sent by a smart terminal layer in the artificial intelligence Internet of Things through a preset unified service interface, the data format conversion of the Internet of Things device data comprises: analyzing an original data structure, the original data structure being an unstructured data format, and the data after the data conversion being a structured data format; performing data analysis on the component data sources through the matched scene analysis algorithm to determine corresponding key features, constructing a flow of the pluggable component according to the scene logic rule to determine corresponding component association relationships and component interaction modes, and constructing a cloud service layer station according to the component association relationships, the component interaction modes and the key features.

2. The AIOT middle platform component-based capability cross-scene Internet of Things application rapid building method according to claim 1, characterized in that, Before the matching of the cross-scene editing instruction with the preset scene knowledge graph, the following steps are included: determining nodes in the scene knowledge graph according to attribute information of historical pluggable components, historical scene analysis algorithms and historical scene logic rules, and determining edges in the scene knowledge graph according to the association among the historical pluggable components, the historical scene analysis algorithms and the historical scene logic rules; constructing the scene knowledge graph according to the nodes and the edges. 3.The AIOT middle platform component-based cross-scene application rapid building method according to claim 1, characterized in that, The matching of the cross-scene editing instruction with the preset scene knowledge graph to determine the pluggable component in the preset scene atomized component library, the matched scene analysis algorithm in the preset algorithm center and the matched scene logic rule in the preset scene rule library comprises the following steps: determining a graph matching range in the preset scene knowledge graph according to a scene requirement and a specific function in the cross-scene editing instruction; The similarity algorithm is used to measure the similarity between nodes and edges in the graph matching range, and the most similar nodes and edges are used to determine the matched pluggable components in the preset scene atomization component library, the matched scene analysis algorithm in the preset algorithm center, and the matched scene logic rule in the preset scene rule library.

4. The AIOT middle platform component-based capability cross-scene Internet of Things application rapid building method according to claim 1, characterized in that, The content of the cross-scene editing instruction is parsed to determine the corresponding scene requirement and specific function, including: The content of the cross-scene editing instruction is parsed to determine the corresponding scene requirement and specific function, including: The preset scene function list is used to determine the specific function that best matches the scene requirement. 5.The AIOT middle platform component-based cross-scene IoT application rapid building method according to claim 1, characterized in that, The IoT device data sent by the edge layer is received, and the IoT device data is configured as the component data source of the pluggable component according to the set data configuration rule, wherein the IoT device data is sent by the intelligent terminal layer in the artificial intelligence IoT through a preset unified service interface, and includes: The IoT device data sent by the edge layer in the artificial intelligence IoT is received, wherein the IoT device data is sent by the intelligent terminal layer in the artificial intelligence IoT through a preset unified service interface; The IoT device data is standardized according to the configuration requirements of the pluggable component, and the standardized IoT device data is configured as the component data source of the pluggable component. 6.The AIOT middle platform component-based cross-scene IoT application rapid building method according to claim 1, characterized in that, Before the IoT device data sent by the edge layer is received, it further includes: The IoT device data sent by the intelligent terminal layer in the artificial intelligence IoT is filtered through the data cleaning model built in the edge layer in the artificial intelligence IoT; The IoT device data filtered by the data cleaning is analyzed through the data analysis model built in the edge layer in the artificial intelligence IoT, and the IoT device data after the data analysis is obtained.

7. An AIOT middle platform component-based cross-scene Internet of Things application rapid construction device, characterized in that, The device includes: The building element determination module is configured to receive cross-scene editing instructions sent by a user through a visual interface, match the cross-scene editing instructions with a preset scene knowledge graph, and determine pluggable components in a preset scene atomization component library, scene analysis algorithms matched in a preset algorithm center, and scene logic rules matched in a preset scene rule library. The determination of the pluggable components in the preset scene atomization component library includes dynamically combining the pluggable components or replacing the pluggable components, the scene analysis algorithm is an algorithm for analyzing and processing data in a specific scene, and the analysis and processing includes data mining, pattern recognition, and / or prediction analysis. The building data configuration module is configured to establish a communication connection with an edge layer in an artificial intelligence IoT, receive IoT device data sent by the edge layer, the IoT data includes temperature readings, energy consumption data, and / or running status, perform data format conversion on the IoT device data according to the data format requirements of the pluggable component, and configure the IoT device data as a component data source of the pluggable component according to a set data configuration rule, the set data configuration rule includes storage rules, indexing rules, and / or retrieval rules. The Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface; the data format conversion of the Internet of Things device data comprises: analyzing an original data structure, the original data structure being an unstructured data format, and the data after the data conversion being a structured data format; The middle platform building module is configured to perform data analysis on the component data source through the matched scene analysis algorithm, determine corresponding key features, perform process construction on the pluggable component according to the scene logic rule, determine corresponding component association relationships and component interaction modes, and construct a cloud service layer middle platform according to the component association relationships, the component interaction modes and the key features.

8. A cross-scene Internet of Things application rapid building system based on AIOT middle platform componentization capability, characterized in that, The system comprises a cloud service layer, an edge layer and an intelligent terminal layer in an artificial intelligence Internet of Things, the cloud service layer is connected with the edge layer, and the edge layer is connected with the intelligent terminal layer; The cloud service layer comprises: The building element determination module is configured to receive a cross-scene editing instruction sent by a user through a visual interface, match the cross-scene editing instruction with a preset scene knowledge graph, determine a pluggable component in a preset scene atomized component library, a matched scene analysis algorithm in a preset algorithm center and a matched scene logic rule in a preset scene rule library, and dynamically combine or replace the pluggable component. The building data configuration module is configured to establish a communication connection with the edge layer in the artificial intelligence Internet of Things, receive Internet of Things device data sent by the edge layer, perform data format conversion on the Internet of Things device data according to data format requirements of the pluggable component, and configure the Internet of Things device data as a component data source of the pluggable component according to a set data configuration rule, wherein the set data configuration rule comprises a storage rule, an index rule and / or a retrieval rule. The Internet of Things device data is sent by an intelligent terminal layer in the artificial intelligence Internet of Things through a preset unified service interface; the data format conversion of the Internet of Things device data comprises: analyzing an original data structure, the original data structure being an unstructured data format, and the data after the data conversion being a structured data format; The middle platform building module is configured to perform data analysis on the component data source through the matched scene analysis algorithm, determine corresponding key features, perform process construction on the pluggable component according to the scene logic rule, determine corresponding component association relationships and component interaction modes, and construct a cloud service layer middle platform according to the component association relationships, the component interaction modes and the key features.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the AIOT middle platform componentization capability-based cross-scene Internet of Things application rapid building method of any one of claims 1 to 6 when executing the program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the AIOT middle platform componentization capability-based cross-scene Internet of Things application rapid building method of any one of claims 1 to 6 when executed by the processor.

Images