Multi-scene intelligent adaptation system and method based on Internet of Things equipment database

Abstract

The invention provides a multi-scene intelligent adaptation system and method based on an Internet of Things equipment database, and belongs to the technical field of Internet of Things, and the method comprises the steps: S1, constructing an application scene platform library; s2, constructing an Internet of Things equipment feature database; s3, searching and selecting a required scene in the application scene platform library, selecting a required function according to the scene, and performing matching search in the feature database of the Internet of Things equipment by using a multi-dimensional feature matching module; s4, after the matching search is completed, generating a list for the matched and searched target through an equipment list generation module; s5, the user selects the generated list, and efficient and intelligent configuration of equipment is achieved by providing an intelligent means; by shortening the construction period of the Internet of Things system, the construction requirements of a large-scale and complex Internet of Things system are met; the system performance is optimized by considering the multi-dimensional characteristic parameters, compatibility and cooperative work capability of the equipment, and stable and efficient operation of the Internet of Things system is realized.

Description

Technical Field

[0001] This invention belongs to the field of Internet of Things (IoT) technology, specifically relating to a multi-scenario intelligent adaptation system and method based on an IoT device database. Background Technology

[0002] The Internet of Things (IoT) is an information carrier based on the internet, traditional telecommunications networks, etc., enabling all ordinary physical objects that can be independently addressed to form an interconnected network. The current technology structure primarily involves each manufacturer maintaining its own device data, with developers selecting devices and building systems based on experience and requirements. This approach relies on simple human judgment of device functionality and scenario needs, selecting and integrating devices without a systematic or intelligent approach. This method fails to fully leverage the advantages of IoT devices, limiting the widespread application of IoT technology across various fields and leading to several challenges in the configuration and application of IoT devices.

[0003] Existing technologies mainly suffer from the following problems: 1. Difficulty in equipment selection: The lack of systematic and intelligent management methods makes it difficult to quickly and accurately select equipment combinations that meet the needs of specific scenarios from a massive number of devices, affecting the construction efficiency of IoT systems; 2. Low configuration efficiency and prone to errors: Traditional equipment configuration methods that rely on manual experience are inefficient and prone to errors, failing to meet the construction needs of large-scale and complex IoT systems, increasing system construction costs and risks; 3. Neglecting device characteristics and failing to fully consider the compatibility, collaborative capabilities, and multi-dimensional characteristic parameters between devices, resulting in poor performance and resource waste in the constructed IoT systems, making it impossible to achieve efficient operation of IoT systems. Therefore, a multi-scenario intelligent adaptation system and method based on an IoT device database is needed to solve the above problems. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a multi-scenario intelligent adaptation method based on an IoT device database, comprising the following steps: S1: Build an application scenario platform library; S2: Construct an IoT device feature database; S3: Search and select the required scenario in the application scenario platform library, then select the required function according to the scenario, and then use the multi-dimensional feature matching module to perform matching search in the IoT device feature database. S4: After the matching search is completed, the matching search targets will be generated into a list through the device list generation module; S5: The user selects from the generated list.

[0005] Furthermore, the establishment of the application scenario platform library in step S1 specifically includes the following: S11: Establish a scene template library; S12: Configure the rule engine; S13: Establish a library of typical scenario cases.

[0006] Furthermore, the establishment of the IoT device feature database in step S2 specifically includes the following: S21: Set up the structured storage layer for the device basic information table; S22: Set up a multi-dimensional capability description layer.

[0007] Furthermore, the application of the multidimensional feature matching module in step S3 specifically includes the following: S31: Extract requirements; S32: Match and search according to the extracted requirements; S33: Evaluate and filter the results of the matching search; S34: Optimize the results generated after evaluation and screening to generate a list; S35: Present and provide feedback to users.

[0008] Furthermore, the generation of the equipment list in step S4 specifically includes the following: S41: Sort and optimize the targets found by the matching search; S42: Generate a detailed list; S43: Select the display option.

[0009] Furthermore, the application scenario platform library search scenario algorithm specifically includes the following: Let the set of scenarios consisting of the scenario template library and the typical scenario case library be C={C1,C2,…,C…}. p The set of keywords input by the user is K={k1,k2,…,k}. m}; Define scenario c i Matching score Sc with keyword set K i for: Filter out matching scores Sc i The set of scenes C′ with >0, and according to Sc i Sort in descending order.

[0010] Furthermore, the IoT device feature database search algorithm specifically includes the following: Let the device database be D={d1,d2,…,d n}, where d i Indicates the i-th device; The set of keywords entered by the user remains K={k1,k2,…,k m} Define device di Matching score Sd with keyword set K i for: Filter out matching scores Sd i The set of devices D′ > 0, and according to Sd i Sort in descending order.

[0011] Furthermore, the equipment list generation algorithm specifically includes the following: Let the set of device-scene combinations obtained by multidimensional feature matching be . M′={(d1,C1,M1),(d2,c2,M2),…,(d q ,c q M q )}, where M i =M(d i c i ). Equipment list L is as follows: .

[0012] A multi-scenario intelligent adaptation system based on an IoT device database. The intelligent adaptation system includes an IoT device feature database, an application scenario platform library, a multi-dimensional feature matching module, and a device list generation module. When the intelligent adaptation system is executed, it implements any one of the above-described multi-scenario intelligent adaptation methods based on an IoT device database.

[0013] The advantages of this invention are: 1. Dual-database construction and interaction mechanism: Construct an IoT device feature database and an application scenario platform database. Through the interaction between the two, centralized management of device information and rapid response to scenario requirements can be achieved. The structured design of the database and the rich functions of the scenario library provide strong support for the efficient operation of the system.

[0014] 2. Multidimensional Feature Matching Technology: Innovatively utilizes multidimensional feature matching technology to extract user demand keywords from multiple dimensions and match them with the device database. This comprehensively evaluates the compatibility and collaborative capabilities of the devices, achieving precise matching between devices and scenarios and improving the accuracy and efficiency of device selection.

[0015] 3. Dynamically Scalable Architecture: The database and platform layers are decoupled, enabling dynamic scalability and supporting the addition of new device types and scenario templates. This allows the system to adapt to the continuous development of IoT technology and the increasing variety of application scenarios, maintaining its advanced nature and practicality.

[0016] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. Attached Figure Description

[0017] Figure 1This is a schematic diagram of the intelligent adaptation method of the present invention. Detailed Implementation

[0018] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the specific implementation methods, structural features and effects of the present invention are described in detail below with reference to the accompanying drawings and embodiments.

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] In the description of this invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "aligned", "overlapping", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0021] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature; in the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0022] Example 1

[0023] This embodiment provides, for example Figure 1 The multi-scenario intelligent adaptation method based on an IoT device database, as shown, includes the following steps: S1: Build an application scenario platform library; S2: Construct an IoT device feature database; S3: Search and select the required scenario in the application scenario platform library, then select the required function according to the scenario, and then use the multi-dimensional feature matching module to perform matching search in the IoT device feature database. S4: After the matching search is completed, the matching search targets will be generated into a list through the device list generation module; S5: The user selects from the generated list.

[0024] Furthermore, the establishment of the application scenario platform library in step S1 specifically includes the following: S11: Establish a scene template library, providing various scene templates such as smart parks and industrial monitoring, while also supporting user-defined scene requirements to meet the diverse needs of different users; S12: Configure the rule engine. The built-in rule engine automatically filters devices based on user-inputted scenario requirements and functional specifications. During the filtering process, it combines information from the device database to generate a list containing device parameters, deployment diagrams, and compatibility specifications, providing users with detailed device selection suggestions. S13: Establish a typical scenario case library, with pre-set templates for typical scenarios such as smart cities, agriculture, municipal administration, and property management, to facilitate user reference and quick selection, and improve configuration efficiency.

[0025] The application scenario platform library search scenario algorithm specifically includes the following: Let the set of scenarios consisting of the scenario template library and the typical scenario case library be C={C1,C2,…,C…}. p The set of keywords input by the user is K={k1,k2,…,k}. m}; Define scenario c i Matching score Sc with keyword set K i for: Filter out matching scores Sc i The set of scenes C′ with >0, and according to Sc i Sort in descending order.

[0026] Furthermore, the establishment of the IoT device feature database in step S2 specifically includes the following: S21: Set up a structured storage layer for the device basic information table. The device basic information table stores basic data such as the device manufacturer, model, and certification information, providing a foundation for device identification and management. S22: Set up a multi-dimensional capability description layer to describe the device from four dimensions: function, performance, environment, and protocol. The function dimension identifies the device's functions through capability tags such as sensing, control, and communication; the performance dimension measures the device's performance using quantitative indicators such as sampling frequency, accuracy, and response time; the environment dimension specifies the device's operating temperature, protection level, installation method, and other environmental requirements; and the protocol dimension records the communication protocol stacks supported by the device and its compatibility matrix to ensure communication compatibility between devices.

[0027] The IoT device feature database search algorithm specifically includes the following: Let the device database be D={d1,d2,…,d n}, where d i Indicates the i-th device; The set of keywords entered by the user remains K={k1,k2,…,k m} Define device d i Matching score Sd with keyword set K i for: Filter out matching scores Sd i The set of devices D′ > 0, and according to Sd i Sort in descending order.

[0028] Furthermore, the application of the multidimensional feature matching module in step S3 specifically includes the following: S31: Extract requirements by receiving the application scenario selected by the user and the functional requirements input, and extracting multi-dimensional feature keywords such as equipment function, measurement range, accuracy, working environment, etc. S32: Based on the extracted requirements, a matching search is performed. In the IoT device database, a combination of fuzzy matching and exact matching is used to search based on multi-dimensional feature keywords and initially filter out devices that may meet the requirements. S33: Evaluate and filter the results of the matching search, evaluate the matching devices in terms of compatibility, collaborative working ability and other aspects, and comprehensively consider various factors to select the optimal combination of devices. S34: The system evaluates and filters the results, optimizes them to generate a list, sorts and optimizes the selected device combinations according to certain rules, and generates a device list including a deployment topology diagram, parameter comparison table, and precautions. Manual adjustments and re-optimization of device combinations are supported to ensure the list meets individual user needs. S35: Provides user feedback by displaying and presenting a list of devices, including images, functions, parameters, precautions, and other detailed information, in an intuitive way for easy viewing and selection.

[0029] The multidimensional feature matching search algorithm specifically includes the following: Let D′ be the set of devices obtained from the device database and C′ be the set of scenarios obtained from the application scenario platform library; For device d i ∈D′ and scenario c j ∈C′, define a compatibility function I(d i c j If device d i With scene c j Compatibility I(d i c j )=1, otherwise I(d) i c j)=0; Define device d i With scene c j Match score M(d) i c j )for: Where f(d) i c j ) is a matching degree function calculated based on the specific characteristics of the device and the scene. For example, it can comprehensively consider the fit between the device function and the scene requirements, the device performance indicators, etc.

[0030] Filter out M(d) i c j Device-scene combination (d) > 0 i c j Set M′, and according to M(d) i c j Arrange in descending order.

[0031] Furthermore, the generation of the equipment list in step S4 specifically includes the following: S41: Sort and optimize the targets found by matching search, and sort and optimize the filtered device combinations to make the device list more reasonable and practical. S42: Generate a detailed list, providing users with comprehensive device information, including device images, functions, parameters, precautions, and other detailed information. S43: Provide display options to present the device list in an intuitive way, such as in the form of a table or list, so that users can easily view and select suitable IoT devices to build the application scenario system they need.

[0032] The equipment list generation algorithm specifically includes the following: Let the set of device-scene combinations obtained by multidimensional feature matching be . M′={(d1,C1,M1),(d2,c2,M2),…,(d q ,c q M q )}, where M i =M(d i c i ). Equipment list L is as follows: .

[0033] In terms of device matching algorithms, in addition to combining fuzzy matching and exact matching, we can study deep learning-based matching algorithms, using a large amount of device data and scenario requirement data for training, to improve the accuracy and intelligence of matching. In terms of database storage structure, in addition to existing structured storage methods, we can explore using graph databases to store complex relationships between devices, and more efficiently handle queries related to device compatibility and collaborative capabilities. In terms of system architecture, in addition to the current architecture, a microservice architecture could be considered, whereby each functional module is broken down into independent microservices to improve system maintainability and scalability, thus better meeting the needs of large-scale IoT device configuration. A multi-scenario intelligent adaptation system based on an IoT device database. The intelligent adaptation system includes an IoT device feature database, an application scenario platform library, a multi-dimensional feature matching module, and a device list generation module. A multi-scenario intelligent adaptation method based on an IoT device database that implements any of the above when the intelligent adaptation system is executed.

[0034] The core architecture of the dual-database interaction is as follows: The IoT device feature database and application scenario platform library achieve data interoperability through a standardized interface layer, which includes: (1) Data synchronization interface: Real-time synchronization of device library parameters to the scene library matching rules; (2) Requirements parsing interface: converts the requirement keywords in the scenario library into search conditions in the device library; (3) Result feedback interface: The device matching result is sent back to the list generation module of the scene library.

[0035] Secondly, the specific interaction process for centralized management of equipment information is as follows: 1. Management process of equipment feature database: (1) Data collection and standardization Multi-source data access: Manufacturers upload device data (JSON format, including basic device information and capability parameters) via API interface. The system automatically verifies the format (e.g., the "operating voltage" field must include the unit "V"). If it fails, an error message is returned. When users manually enter non-standard devices, the platform provides field prompts (e.g., a function label drop-down box: "sensing / control / communication") and supports the reuse of historical templates (e.g., copying similar sensor parameters for quick modification).

[0036] Structured storage: Basic information layer, storing manufacturer, model, and certification information to relational database tables; Capability description layer, establishing indexes according to function / performance / environment / protocol dimensions (such as performance dimensions including quantitative indicators such as sampling frequency and accuracy).

[0037] (2) Dynamic maintenance and updates Batch management allows administrators to import device data in batches using Excel templates. The templates include required columns (device ID, functional dimensions) and optional columns (scenario adaptation cases). During import, a progress bar and error logs are displayed (such as an incorrect format for "protection level" in a certain row).

[0038] Real-time updates: When the device firmware is upgraded, the manufacturer submits a change request, the system triggers an approval process (automatic verification or manual review), and after approval, a notification is pushed to the subscribers (such as "XX sensor communication protocol upgrade"), and "latest version" is marked on the device details page.

[0039] (3) Multidimensional retrieval and visualization Combined condition search allows users to filter devices using controls such as sliders (temperature range) and checkboxes (protocol type). For example, searching for devices with "operating temperature -20℃~70℃, supports MQTT protocol, and smart agriculture scenarios" will display the results in a card-style list. Clicking on a card will expand the parameter details.

[0040] The data dashboard displays the distribution of devices by manufacturer using bar charts and the scene adaptation rate using pie charts (e.g., sensors account for 60% in smart parks). Click on the charts to drill down and view the specific device list.

[0041] 2. Dual-database interaction enables centralized equipment management: (1) Scene-driven device classification The templates in the application scenario platform library (such as "industrial monitoring") are automatically associated with the device tags in the device library that match the scenario (such as "vibration sensor" and "PLC controller"), forming a scenario-device mapping table.

[0042] (2) Dynamic tag updates When scenario requirements change (such as the addition of "explosion-proof level" requirements to industrial monitoring), the scenario library triggers a refresh of the device library's tags through an interface to ensure that device classifications are synchronized with scenario requirements in real time.

[0043] In addition, the specific interaction flow for rapid response to scenario requirements is as follows: 1. Requirements Input and Analysis (1) Selection of template requirements Users select a template from the scenario library (such as "Smart Agriculture"), and the system pops up a sub-scenario dialog box (such as "Greenhouse Planting / Livestock and Poultry Farming") and displays typical requirements (such as monitoring temperature, humidity and light for greenhouse planting).

[0044] When users customize their needs, they enter text (such as "smart irrigation for home balcony"), and the system uses NLP to parse keywords ("soil moisture" and "automatic watering") and recommends relevant device types (such as "soil moisture sensor") below the input box.

[0045] (2) Demand-equipment feature mapping The requirements are converted into device search criteria using a formula: Formula for generating demand feature vector: R={r1,r2,...,r m}; Where r i The equipment features corresponding to the keywords in the demand (such as the "accuracy" parameter in the equipment library corresponding to "accuracy ±0.5℃").

[0046] (3) Equipment matching and screening Multidimensional feature matching algorithm: Basic matching degree calculation:

[0047] Feature dimension weights (e.g., in smart agriculture, the weight of "environmental adaptability" W3=0.25); The matching score of the device in the i-th dimension is calculated using the discrete / continuous feature similarity formula: Discrete features (such as functional labels): (c is the number of matched tags, m is the total number of required tags); Continuous features (such as sampling frequency): (x represents equipment parameters, x0 represents demand parameters, and λ represents attenuation coefficient).

[0048] Compatibility and Collaboration Assessment: Protocol compatibility:

[0049] S j Protocol compatibility status (1 = fully compatible, 0.5 = partially compatible); P j Protocol weight (e.g., sensor-gateway protocol weight P1=0.6).

[0050] Teamwork ability:

[0051] T l Historical score of the collaboration between the device and other devices; Scene correction factor (industrial scene = 1.2, home scene γ = 0.8).

[0052] (4) Equipment generation and feedback Equipment list generation: Output the optimal combination according to the sorting formula:

[0053] α+β+γ=1 (e.g., α=0.4, emphasizing matching degree); Price sensitivity factor (user-defined, budget priority) =0.1).

[0054] Multimodal display: The list supports table view (parameter comparison) and topology view (device connection relationship), and can be exported as PDF / Word or generate a sharing link (including one-click purchase function).

[0055] Finally, the specific application examples of the formula are as follows: Smart agricultural greenhouse scenario: Requirements: Temperature range -10℃ to 50℃ (accuracy ±0.5℃), LoRa protocol supported, and must be compatible with irrigation controllers; Device A parameters: temperature -15℃~60℃ (accuracy ±0.3℃), LoRa protocol, collaboration success rate 90%, price index 0.6; Calculation process: (1) Functional matching: Requires 2 tags (temperature monitoring, LoRa), all devices are fully matched, F discrete =100; (2) Performance matching score: Temperature range: ; Accuracy: ; Weighted (Performance weight 0.3); (3) Protocol compatibility: Fully compatible with LoRa. ; (4) Cooperative component: (Maximum value 100); (5) Ranking score: Assume α=0.4, β=0.3, γ=0.2, δ=0.1, Equipment A is the preferred choice.

[0056] Let's take building a smart home environment monitoring system as another example: First, the user selects the "Smart Home Environment Monitoring" scenario in the application scenario platform library and enters the functional requirement as "monitor the temperature and humidity of the living room and automatically turn on the air conditioner when the temperature is too high"; Secondly, after receiving the information, the platform extracts multi-dimensional feature keywords such as "temperature monitoring", "humidity monitoring", and "automatic air conditioning activation"; Then, a search is performed in the IoT device database. The multi-dimensional feature matching module comprehensively evaluates the device's functions, parameters, compatibility, and other factors to select temperature and humidity sensors with high accuracy, low energy consumption, and good compatibility with mainstream smart home systems, as well as suitable smart air conditioner controllers. Finally, the device list generation module combines these devices to generate a device list. The list includes pictures of the devices, detailed functional descriptions, parameter specifications, and installation and usage precautions, which are presented to the user in tabular form. The user can select devices based on the list to build a smart home environment monitoring system.

[0057] In summary, this invention provides a multi-scenario intelligent adaptation system and method based on an IoT device database. It not only provides an intelligent means to quickly and accurately select device combinations that meet the needs of specific application scenarios from a massive number of IoT devices, achieving efficient and intelligent device configuration; it also shortens the construction cycle of IoT systems, reduces construction costs, and improves system construction efficiency by reducing manual intervention, meeting the construction needs of large-scale, complex IoT systems; furthermore, by fully considering the multi-dimensional characteristic parameters, compatibility, and collaborative working capabilities of devices, it optimizes device combinations and system performance, improves the performance of IoT systems, reduces resource waste, and achieves stable and efficient operation of IoT systems.

[0058] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A multi-scenario intelligent adaptation method based on an IoT device database, characterized in that: Includes the following steps: S1: Build an application scenario platform library; S2: Construct an IoT device feature database; S3: Search and select the required scenario in the application scenario platform library, then select the required function according to the scenario, and then use the multi-dimensional feature matching module to perform matching search in the IoT device feature database. S4: After the matching search is completed, the matching search targets will be generated into a list through the device list generation module; S5: The user selects from the generated list.

2. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The establishment of the application scenario platform library in step S1 specifically includes the following: S11: Establish a scene template library; S12: Configure the rule engine; S13: Establish a library of typical scenario cases.

3. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The establishment of the IoT device feature database in step S2 specifically includes the following: S21: Set up the structured storage layer for the device basic information table; S22: Set up a multi-dimensional capability description layer.

4. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The application of the multidimensional feature matching module in step S3 specifically includes the following: S31: Extract requirements; S32: Match and search according to the extracted requirements; S33: Evaluate and filter the results of the matching search; S34: Optimize the results generated after evaluation and screening to generate a list; S35: Present and provide feedback to users.

5. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The generation of the equipment list in step S4 specifically includes the following: S41: Sort and optimize the targets found by the matching search; S42: Generate a detailed list; S43: Select the display option.

6. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The application scenario platform library search scenario algorithm includes the following: Let the set of scenarios consisting of the scenario template library and the typical scenario case library be C={C1,C2,…,C…}. p The set of keywords input by the user is K={k1,k2,…,k}. m }; Define scenario c i Matching score Sc with keyword set K i for: Filter out matching scores Sc i The set of scenes C′ with >0, and according to Sc i Sort in descending order.

7. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The algorithm for searching the feature database of IoT devices includes the following: Let the device database be D={d1,d2,…,d n }, where d i Indicates the i-th device; The set of keywords entered by the user remains K={k1,k2,…,k m } Define device d i Matching score Sd with keyword set K i for: Filter out matching scores Sd i The set of devices D′ > 0, and according to Sd i Sort in descending order.

8. The multi-scenario intelligent adaptation method based on an IoT device database as described in claim 1, characterized in that: The equipment list generation algorithm includes the following: Let the set of device-scene combinations obtained by multidimensional feature matching be . M′={(d1,C1,M1),(d2,c2,M2),…,(d q ,c q M q )}, where M i =M(d i c i ). Equipment list L is as follows: .

9. A multi-scenario intelligent adaptation system based on an IoT device database, characterized in that: The intelligent adaptation system includes an IoT device feature database, an application scenario platform library, a multi-dimensional feature matching module, and a device list generation module; When the intelligent adaptation system is executed, it implements a multi-scenario intelligent adaptation method based on an IoT device database as described in any one of claims 1 to 5.

Images