Smart home management and control method and system based on time sequence data driving

Abstract

The invention discloses an intelligent home control method and system based on time sequence data driving. The method comprises the following steps: collecting operation state data and environment sensing data of equipment through wireless connection between an intelligent home control middle platform and the home equipment; the operation state data and the environment sensing data are stored and managed through a cloud database and are sorted according to timestamps; performing mode mining on the sorted operation state time sequence data and environment sensing time sequence data, extracting a user behavior mode, and storing the user behavior mode in a cloud database in a pattern form; when the state of the home equipment is changed or a specific task is executed, the http trigger calls a corresponding cloud function in the cloud function library through an http request mode, performs data access on data in the cloud database, retrieves a user behavior mode previously stored in the cloud database, and controls and manages new equipment according to the user behavior mode; more flexible equipment control and management are realized, and the comfort level and life quality of the user are improved.

Description

Technical Field

[0001] This invention relates to the field of smart home control, and in particular to a smart home management and control method and system based on time-series data. Background Technology

[0002] Smart homes, designed to create a superior residential experience and manage daily affairs, have seen widespread application and promotion in recent years. However, existing smart home systems are limited by fixed schedules and a narrow scope of application, failing to achieve true "intelligence," and their promotion has been constrained by this limitation.

[0003] Smart home products generate a large number of IoT devices every moment. This constantly generated time-series data helps smart home products learn user behavior patterns, thereby better managing and improving users' quality of life. However, current smart home products have not made good use of data as a new factor of production, which is a waste of production resources.

[0004] Therefore, personalized technologies for smart homes driven by time-series data sequences urgently need to be studied. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, this application provides a smart home management and control method and system based on time-series data.

[0006] Firstly, this application provides a smart home management and control method based on time-series data, the method comprising:

[0007] Design a personalized user interface. After user authentication, register or log in to the smart home control platform and collect the operating status data and environmental sensor data of home devices by wirelessly connecting with IoT devices in the home.

[0008] The collected operational status data and environmental sensor data are stored and managed through a cloud database, and the operational status data and environmental sensor data are processed. The processed operational status data and environmental sensor data are sorted according to timestamps to generate operational status time-series data and environmental sensor time-series data.

[0009] The running status time series data and environmental sensing time series data are transformed. The transformed running status time series data and environmental sensing time series data are then subjected to pattern mining using a hierarchical time series pattern graph mining algorithm to extract user behavior patterns. The mined user behavior patterns are then stored in a cloud database in the form of a pattern.

[0010] When the status of home devices changes or a specific task is performed, the HTTP trigger calls the corresponding cloud function in the cloud function library through an HTTP request. The cloud function is used to access data in the cloud database and retrieve user behavior patterns previously stored in the cloud database.

[0011] The smart home control platform is associated with the new device, and the new device is controlled and managed according to the user behavior pattern.

[0012] By adopting the above technical solutions, users can securely register and log in to the smart home control platform through identity authentication. They can then wirelessly connect using mobile phones, tablets, or computers, conveniently collecting operational status data and environmental sensor data from their homes. Cloud database technology allows for centralized storage and management of large amounts of operational status and environmental sensor data, improving data security and reliability while facilitating data processing, analysis, and mining. By setting up time-series mining algorithms, in-depth analysis of operational status and environmental sensor data can uncover user behavior habits, enabling the system to better understand user needs and preferences, thus achieving more personalized device services. By setting up HTTP triggers to call corresponding cloud functions in the cloud function library via HTTP requests, access and data operations can be performed on the cloud database. Even in high-throughput scenarios, server overload issues will not occur, enabling more flexible and automated device control and management, improving user comfort and quality of life.

[0013] Preferably, for users who are using the smart home control system for the first time, a personal account is created by providing basic personal information, and a username and password are selected.

[0014] For users who are not first-time users of the smart home control system, they can authenticate their identity by entering their username and password. After successful authentication, they can log in to the smart home control platform and view their basic personal information.

[0015] Users can connect to IoT devices in their homes via Bluetooth wireless communication technology using mobile phones, tablets, or computers. Users can set the data collection frequency and transmission speed through the smart home control platform to collect real-time operating status data and environmental sensor data of home devices.

[0016] By adopting the above technical solution, users can create personal accounts in the system by providing basic personal information. These accounts can store users' personal information, device configurations, and historical data, providing personalized service experiences. An identity authentication mechanism ensures that only authenticated users can access relevant data, protecting user privacy and data security. The smart home control platform allows users to set data collection frequency and transmission speed to collect operational status data from home devices and environmental sensors. Users can adjust the data collection frequency and transmission speed according to their application needs, preferences, and device performance, thereby optimizing data transmission and processing volume and saving device and network resources.

[0017] Preferably, the collected operational status data and environmental sensor data are transmitted to an established cloud database for storage, and the operational status data and environmental sensor data are aggregated, classified, and managed.

[0018] The classified operating status data and environmental sensor data are cleaned and noise-removed to remove outliers and reduce random fluctuations, thereby obtaining operating status processing data and environmental sensor processing data.

[0019] The operation status processing data and environmental sensing processing data are sorted according to timestamps to generate operation status time series data and environmental sensing time series data.

[0020] By adopting the above technical solution and storing the collected operational status data and environmental sensor data in a cloud database, the security, reliability, and scalability of data storage are ensured. Users can access and obtain operational status data and environmental sensor data anytime, anywhere, facilitating subsequent data processing and analysis. By cleaning and noise reduction operations on the operational status data and environmental sensor data, abnormal data caused by equipment failure or sensor errors are removed, and random fluctuations are eliminated, ensuring the accuracy and reliability of the data. Sorting the operational status data and environmental sensor data according to timestamps and performing time series analysis reveals the patterns and trends in the changes of equipment operating status and environmental conditions over time, providing support for intelligent decision-making in smart home control systems.

[0021] Preferably, the operating status time series data and environmental sensing time series data are converted in terms of data format, data type and data structure to adapt to the requirements of the pattern mining algorithm and generate standard operating status time series data and standard environmental sensing time series data.

[0022] The standard operating state time series data and standard environmental sensing time series data are subjected to pattern mining using a hierarchical time series model graph mining algorithm to extract user behavior patterns.

[0023] The extracted user behavior patterns are stored in a cloud database in the form of patterns.

[0024] By adopting the above technical solution, the time-series data of operational status and environmental sensing are transformed to meet the requirements of pattern mining algorithms, facilitating subsequent pattern mining and analysis. Using a hierarchical time-series model graph mining algorithm, recurring patterns and trends in the data can be identified and represented as a hierarchical structure, thus more intuitively displaying the characteristics and relationships of user behavior patterns and extracting these patterns. Storing the extracted user behavior patterns in pattern form allows for effective organization and utilization of this data, while also facilitating the querying and retrieval of specific user behavior patterns, supporting the automated control of smart homes.

[0025] Preferably, a series of subsequences of operating status data and subsequences of environmental sensing data are generated by arranging them in chronological order from the standard operating status time-series data and the standard environmental sensing time-series data;

[0026] A timing diagram is constructed for each of the aforementioned operating state data subsequence and environmental sensing data subsequence, generating an operating state timing diagram and an environmental sensing timing diagram;

[0027] From each of the running state timing diagrams and environmental sensing timing diagrams, running state features and environmental sensing features representing the patterns of the running state data subsequences and environmental sensing data subsequences are extracted. The extracted running state features and environmental sensing features are then clustered to generate clustering results.

[0028] The clustering results are converted into a hierarchical pattern diagram. The hierarchical pattern diagram is analyzed to extract features that represent user behavior patterns and generate user behavior patterns.

[0029] By adopting the above technical solution, and generating a series of operational status data and environmental sensor data subsequences, different data granularities can be selected to analyze user behavior patterns. Shorter data granularities can capture short-term changes in user behavior, while longer data granularities can reveal longer-term behavioral trends. By constructing time-series diagrams, the operational status data subsequences and environmental sensor data subsequences can be presented graphically, facilitating intuitive observation and analysis of the data and easily identifying anomalies. By observing the time-series diagrams, features representing the patterns of the data subsequences are extracted, and clustering algorithms are used to reduce the dimensionality of the high-dimensional feature space, grouping similar features together to simplify data complexity. Different user behavior patterns are identified through clustering results, and converting the clustering results into hierarchical pattern diagrams can more intuitively display the relationships and hierarchical structures between different user behavior patterns. This provides important basis for intelligent decision-making in smart home control systems, helping to improve the convenience, comfort, and security of home life.

[0030] Preferably, when the status of home appliances changes or when a specific task is performed, the user sends an HTTP request to the server. After receiving the HTTP request, the server sends the HTTP request to the cloud function library through an HTTP trigger.

[0031] After receiving the HTTP request, the cloud function library searches for and calls the corresponding cloud function based on the information in the HTTP request;

[0032] After the cloud function is invoked, it performs data access operations on the data in the cloud database and retrieves the user behavior patterns previously stored in the cloud database.

[0033] By adopting the above technical solution, cloud functions corresponding to the trigger in the cloud function library are called through the HTTP trigger. The cloud functions access and manipulate the cloud database to retrieve data related to user behavior patterns. Even in high-throughput scenarios, there will be no server overload problem, achieving more flexible and automated device control and management.

[0034] Preferably, after authentication, the cloud function connects to the cloud database using the database's API key;

[0035] The cloud function retrieves data from the cloud database based on the specified query language and retrieval fields. It then further processes and transforms the retrieved data to extract features that represent user behavior patterns, generates user behavior patterns, and returns these user behavior patterns to the HTTP trigger as an HTTP response.

[0036] By adopting the above technical solution, API key authentication ensures that only authorized cloud functions can access the cloud database, preventing unauthorized access and potential data leakage risks. During the retrieval process, the cloud function filters data according to specified conditions, narrowing the data range and improving retrieval efficiency. The generated Silver Fox behavior pattern is returned to the HTTP trigger as an HTTP response, which then transmits it to the smart home system. This allows the smart home system to promptly feed back the user behavior pattern and automatically adjust device parameters based on the received user behavior pattern.

[0037] Preferably, the new device is connected to the smart home control platform and communicates with the smart home control platform;

[0038] After a new device is connected, the smart home control platform models the new device. During the modeling process, the smart home control platform matches user behavior patterns retrieved from the cloud database to generate user behavior pattern matching results.

[0039] Based on the user behavior pattern matching results, the smart home control platform generates automatic control rules for the new device;

[0040] During the operation of the new equipment, the new equipment is controlled and managed according to the aforementioned automatic control rules.

[0041] By adopting the above technical solutions, and matching user behavior patterns retrieved from the cloud database with the characteristics of new devices, the smart home control platform can better understand user needs and preferences, and generate corresponding control rules for new devices, thereby improving the system's intelligence and user experience.

[0042] Secondly, a smart home management system based on time-series data includes:

[0043] The smart home control platform is used to design personalized user interfaces. After user authentication, users can register or log in to the smart home control platform and collect the operating status data and environmental sensor data of home devices through wireless connection with IoT devices in the home.

[0044] The cloud database module is used to store and manage the collected operation status data and environmental sensing data, and to process the operation status data and environmental sensing data. The processed operation status data and environmental sensing data are sorted according to timestamps to generate operation status time series data and environmental sensing time series data.

[0045] The data conversion module is used to convert the running status time-series data and the environmental sensing time-series data.

[0046] The user behavior pattern mining module is used to perform pattern mining on the transformed running state time series data and environmental sensing time series data through a hierarchical time series pattern graph mining algorithm, extract user behavior patterns, and store the mined user behavior patterns in the form of a pattern in a cloud database.

[0047] The cloud function library module is used for centralized storage and management of cloud functions, and to use cloud functions to perform data access operations on data in the cloud database and retrieve user behavior patterns previously stored in the cloud database.

[0048] HTTP triggers are used to trigger the execution of cloud functions in the cloud function library. When the status of home devices changes or a specific task is performed, the HTTP trigger calls the corresponding cloud function in the cloud function library through an HTTP request.

[0049] Preferably, the smart home control platform includes:

[0050] The control unit is used to generate automatic control rules for the new device based on the user behavior pattern, and to control and manage the new device according to the automatic control rules.

[0051] Compared with the prior art, the present invention has the following characteristics and beneficial effects:

[0052] 1. Through identity authentication, users can securely register and log in to the smart home control platform, connecting wirelessly via mobile phones, tablets, or computers. Users can easily collect operational status data from home devices and environmental sensor data. Cloud database technology centrally stores and manages large amounts of operational status and environmental sensor data, improving data security and reliability while facilitating data processing, analysis, and mining. Time-series mining algorithms are implemented to deeply analyze operational status and environmental sensor data, uncovering user behavior habits and enabling the system to better understand user needs and preferences, thus providing more personalized device services. By setting HTTP triggers, corresponding cloud functions in the cloud function library are invoked via HTTP requests, allowing access to and manipulation of the cloud database. Even in high-throughput scenarios, server overload issues are avoided, enabling more flexible and automated device control and management, improving user comfort and quality of life.

[0053] 2. By transforming the time-series data of operational status and environmental sensing, the transformed data is adapted to the requirements of pattern mining algorithms, facilitating subsequent pattern mining and analysis. Using a hierarchical time-series model graph mining algorithm, recurring patterns and trends in the data can be identified and represented as a hierarchical structure, thus more intuitively displaying the characteristics and relationships of user behavior patterns and extracting these patterns. Storing the extracted user behavior patterns in pattern form allows for effective organization and utilization of this data, while also facilitating the querying and retrieval of specific user behavior patterns, supporting the automated control of smart homes.

[0054] 3. By calling the corresponding cloud function in the cloud function library through the HTTP trigger, the cloud function accesses and manipulates the cloud database to retrieve data related to user behavior patterns. Even in high-throughput scenarios, there will be no server overload problem, enabling more flexible and automated device control and management. Attached Figure Description

[0055] Figure 1 This embodiment mainly illustrates a step-by-step flowchart of a smart home management and control method based on time-series data.

[0056] Figure 2 This is a flowchart illustrating the steps of sub-step S2, which is the main feature of this embodiment.

[0057] Figure 3 This is a flowchart illustrating the steps of sub-step S3, which is the main feature of this embodiment.

[0058] Figure 4 This is a flowchart illustrating the steps of sub-step S32, which is the main embodiment of this invention.

[0059] Figure 5 This is a flowchart illustrating the steps of sub-step S4, which is the main feature of this embodiment.

[0060] Figure 6 This is a flowchart illustrating the steps of sub-step S43, which is the main embodiment of this invention.

[0061] Figure 7 This is a flowchart illustrating the steps of sub-step S5, which is the main embodiment of this invention.

[0062] Figure 8 This is a structural block diagram of a smart home management and control system based on time-series data, which is the main feature of this embodiment.

[0063] Explanation of reference numerals in the attached diagram: 1. Smart Home Control Platform; 11. Control Unit; 2. Cloud Database Module; 3. Data Conversion Module; 4. User Behavior Pattern Mining Module; 5. Cloud Function Library Module; 6. HTTP Trigger. Detailed Implementation

[0064] The present invention will be further described in detail below with reference to the following embodiments.

[0065] Reference Figure 1 A smart home management and control method and system based on time-series data, the method comprising the following steps:

[0066] S1. Design a personalized user interface. After user authentication, users can register or log in to the smart home control platform and collect the operating status data and environmental sensor data of home devices through wireless connection with IoT devices in the home.

[0067] S2. The collected operating status data and environmental sensing data are stored and managed through a cloud database, and the operating status data and environmental sensing data are processed. The processed operating status data and environmental sensing data are sorted according to timestamps to generate operating status time-series data and environmental sensing time-series data.

[0068] S3. The running status time series data and environmental sensing time series data are transformed. The transformed running status time series data and environmental sensing time series data are then subjected to pattern mining using a hierarchical time series pattern graph mining algorithm to extract user behavior patterns. The mined user behavior patterns are then stored in the cloud database in the form of patterns.

[0069] S4. When the status of home devices changes or a specific task is performed, the HTTP trigger calls the corresponding cloud function in the cloud function library through an HTTP request. The cloud function is used to access data in the cloud database and retrieve the user behavior patterns previously stored in the cloud database.

[0070] S5. Associate the smart home control platform with the new device, and control and manage the new device according to the user behavior pattern.

[0071] Specifically, through identity authentication, users can securely register and log in to the smart home control platform, wirelessly connecting via mobile phone, tablet, or computer to easily collect data on the operating status of home devices and environmental sensors. Utilizing cloud database technology, large amounts of operating status and environmental sensor data can be centrally stored and managed. This centralized data storage and management approach improves data security and reliability while facilitating data processing, analysis, and mining. By setting time-series pattern mining algorithms, in-depth analysis and processing of operating status and environmental sensor data can be performed to uncover user usage patterns, helping to achieve personalized services and recommendations; for example, if a user habitually turns on the air conditioner around 9 PM, the system can automatically turn it on. When home device status changes or specific tasks are performed, such as during business trips or moving, HTTP triggers can call corresponding functions in the cloud function library via HTTP requests. The cloud function library provides reusable function libraries for rapid development and deployment of smart home applications, enabling more flexible and automated device control and management, allowing users to live more conveniently and comfortably.

[0072] Furthermore, a personalized user interface is designed. After user authentication, they can register or log in to the smart home control platform. The specific steps for collecting operational status data and environmental sensor data of home devices through wireless connection are as follows:

[0073] For first-time users of the smart home control system, a personal account is created by providing basic personal information, along with a username and password.

[0074] For users who are not first-time users of the smart home control system, they can authenticate their identity by entering their username and password. After successful authentication, they can log in to the smart home control platform and view their basic personal information.

[0075] Users can connect to IoT devices in their homes via Bluetooth wireless communication technology using mobile phones, tablets, or computers. Users can set the data collection frequency and transmission speed through the smart home control platform to collect real-time operating status data and environmental sensor data of home devices.

[0076] Specifically, by providing basic personal information, a preliminary trust relationship can be established, helping users create a personal account within the system. This account can store the user's personal information, device configuration, and historical data, ensuring that only authenticated users can access the system. Based on the collected user information, a personalized experience can be provided, such as adjusting device operating modes according to the user's lifestyle and preferences. Username and password authentication ensures that only authenticated users can access relevant data, protecting user privacy and data security. Bluetooth wireless communication technology connects to IoT devices in the home, collecting real-time data on device operation status and environmental sensors. Users can set the data collection frequency and transmission speed according to their needs and preferences, optimizing data transmission and processing volume, thereby saving device and network resources. Through real-time data collection, users can remotely monitor the operating status of home devices and environmental conditions from a smart home control platform, enabling timely operation or adjustments.

[0077] Reference Figure 2 The specific step S2 includes the following sub-steps:

[0078] S21. The collected operational status data and environmental sensor data are transmitted to the established cloud database for storage, and the operational status data and environmental sensor data are aggregated, classified and managed.

[0079] S22. Perform cleaning and noise reduction operations on the classified operating status data and environmental sensor data to remove outliers and reduce random fluctuations in the operating status data and environmental sensor data, thereby obtaining operating status processing data and environmental sensor processing data.

[0080] S23. Sort the operation status processing data and environmental sensing processing data according to timestamps to generate operation status time series data and environmental sensing time series data.

[0081] Specifically, cloud databases provide secure, reliable, and scalable data storage services, suitable for storing large amounts of operational status data and environmental sensor data. Storing collected operational status and environmental sensor data through cloud databases ensures the security, reliability, and scalability of data storage. Data aggregation refers to the integration and classification of data from different sources. Through aggregation and classification management, operational status and environmental sensor data can be better organized and utilized. Due to potential equipment failures, sensor errors, etc., operational status and environmental sensor data undergo cleaning and noise reduction operations to remove outliers and eliminate random fluctuations, avoiding interference with data analysis and obtaining more accurate and reliable data. Time series refers to data sequences arranged chronologically. By sorting operational status and environmental sensor time series data by timestamps and performing time series analysis, the patterns and trends of data changes over time can be revealed, supporting intelligent decision-making in smart home control systems.

[0082] Reference Figure 3 The specific step S3 includes the following sub-steps:

[0083] S31. The operating status time series data and environmental sensing time series data are converted in terms of data format, data type and data structure to adapt to the requirements of the pattern mining algorithm and generate standard operating status time series data and standard environmental sensing time series data.

[0084] S32. The standard operating state time series data and standard environmental sensing time series data are subjected to pattern mining using a hierarchical time series model graph mining algorithm to extract user behavior patterns.

[0085] S33. The extracted user behavior pattern is stored in the cloud database in the form of a pattern.

[0086] Specifically, to better suit the needs of pattern mining algorithms, the original data format, type, and structure need to be transformed to better extract user behavior patterns. Hierarchical time series model graph mining (HTMM) is an effective pattern mining method for extracting user behavior patterns. Through HTMM, patterns and trends in the data can be discovered and represented as a hierarchical structure, thus more intuitively displaying the characteristics and relationships of user behavior patterns and extracting them. Storing the extracted user behavior patterns in pattern form allows for effective organization and utilization of this data, while also facilitating the querying and retrieval of specific user behavior patterns, supporting the automated control of smart homes.

[0087] Reference Figure 4 The specific step S32 includes the following sub-steps:

[0088] S321. Generate a series of operating status data subsequences and environmental sensing data subsequences by arranging them in chronological order from the standard operating status timing data and standard environmental sensing timing data.

[0089] S322. Construct a timing diagram for each of the said operating state data subsequence and environmental sensing data subsequence, and generate an operating state timing diagram and an environmental sensing timing diagram.

[0090] S323. Extract the operating state features and environmental sensing features representing the patterns of the operating state data subsequence and environmental sensing data subsequence from each of the operating state timing diagrams and environmental sensing timing diagrams, and cluster the extracted operating state features and environmental sensing features to generate clustering results.

[0091] S324. The clustering results are converted into a hierarchical pattern diagram. The hierarchical pattern diagram is analyzed to extract features that represent user behavior patterns and generate user behavior patterns.

[0092] Specifically, standard operating status time-series data and standard environmental sensor time-series data are arranged chronologically to generate a series of operating status data subsequences and environmental sensor data subsequences. These data subsequences represent the operating status and environmental sensor data of the device within a specific time period. By generating data subsequences, different data granularities (time lengths) can be selected to analyze user behavior patterns. Shorter granularities can capture short-term changes in user behavior, while longer granularities can reveal longer-term behavioral trends. By constructing time-series plots, the operating status data subsequences and environmental sensor data subsequences can be presented graphically, facilitating intuitive observation and analysis of the data. Furthermore, time-series plots can easily identify abnormal data, such as sudden peaks or sustained high-value areas. These anomalies may indicate device malfunctions or abrupt changes in environmental conditions, requiring special attention. By observing the time-series plots, features representing the patterns of the data subsequences are extracted, and clustering algorithms are used to reduce the dimensionality of the high-dimensional feature space, grouping similar features into one category, thereby simplifying the complexity of the data. Clustering results identify different user behavior patterns. For example, data subsequences within the same cluster may represent the same user behavior pattern, while data subsequences in different clusters may represent different user behavior patterns. Transforming the clustering results into a hierarchical pattern diagram can more intuitively display the relationships and hierarchical structure between different user behavior patterns, providing an important basis for intelligent decision-making in smart home control systems and helping to improve the convenience, comfort, and security of home life.

[0093] Reference Figure 5 The specific step S4 includes the following sub-steps:

[0094] S41. When the status of home appliances changes or a specific task is performed, the user sends an HTTP request to the server. After receiving the HTTP request, the server sends the HTTP request to the cloud function library through an HTTP trigger.

[0095] S42. After receiving the HTTP request, the cloud function library searches for and calls the corresponding cloud function based on the information in the HTTP request.

[0096] S43. After the cloud function is called, it performs data access operations on the data in the cloud database and retrieves the user behavior patterns previously stored in the cloud database.

[0097] Specifically, when home appliances change status or perform specific tasks, users send HTTP requests to the server. Upon receiving the request, the server uses an HTTP trigger to forward it to the cloud function library. The cloud function library then uses the information in the received HTTP request to locate and invoke the corresponding cloud function. Once invoked, the cloud function accesses and manipulates data in the cloud database according to specific logic and algorithms, retrieving data related to user behavior patterns. This data may include user habits, preferences, and historical behavior, providing crucial insights for understanding and controlling user behavior patterns. Furthermore, it avoids server overload issues even in high-throughput scenarios, enabling more flexible and automated device control and management.

[0098] Reference Figure 6 The specific step S43 includes the following sub-steps:

[0099] S431. After authentication, the cloud function connects to the cloud database using the database's API key.

[0100] S432. The cloud function retrieves data from the cloud database based on the specified query language and retrieval fields, further processes and transforms the retrieved data to extract features representing user behavior patterns, generates user behavior patterns, and returns the user behavior patterns to the HTTP trigger in the form of an HTTP response.

[0101] Specifically, after authentication, the cloud function connects to the cloud database using the database's API key, ensuring that only authorized cloud functions can access the cloud database and preventing unauthorized access and potential data leakage risks. The cloud function retrieves data related to user behavior patterns from the cloud database based on specified query language and search fields. During the retrieval process, the cloud function may filter data according to specific conditions to narrow down the data range and improve processing efficiency. Further processing and transformation of the retrieved data, such as data cleaning, format conversion, and numerical calculations, are performed to extract features representing user behavior patterns, including user activity type, activity time, and activity frequency. Based on the extracted features, a final user behavior pattern can be generated, reflecting the user's device usage habits, preferences, and activity patterns. The generated user behavior pattern is returned to the HTTP trigger as an HTTP response. Upon receiving the HTTP response, the HTTP trigger passes the user behavior pattern in the response to the smart home control platform for automated parameter adjustments to home devices.

[0102] Reference Figure 7 The specific step S5 includes the following sub-steps:

[0103] S51. Connect the new device to the smart home control platform and communicate with the smart home control platform.

[0104] S52. After a new device is connected, the smart home control platform models the new device. During the modeling process, the smart home control platform matches the user behavior patterns previously retrieved from the cloud database and generates user behavior pattern matching results.

[0105] S53. Based on the user behavior pattern matching results, the smart home control platform generates automatic control rules for the new device.

[0106] S54. During the operation of the new equipment, the new equipment is controlled and managed according to the automatic control rules.

[0107] Specifically, new devices are connected to the smart home control platform, enabling them to communicate and interact with existing devices, thus achieving overall control and management of the smart home system. After the new devices are connected, the smart home control platform models them, including describing and defining their physical characteristics, communication protocols, and control interfaces. During the modeling process, user behavior patterns retrieved from the cloud database are matched with the characteristics of the new devices. Based on the matching results, the smart home control platform can generate automatic control rules for the new devices. These rules can include the device's operating mode, parameter settings, and linkage relationships. During the operation of the new devices, the smart home control platform can perform real-time control and management based on these automatic control rules, thereby optimizing the control strategy for the new devices and improving the system's intelligence and user satisfaction.

[0108] Reference Figure 8 A time-series data-driven smart home management system is described. This system employs a time-series data-driven smart home management method, including a smart home control platform 1, a cloud database module 2, a data conversion module 3, a user behavior pattern mining module 4, a cloud function library module 5, and an HTTP trigger 6. The system collects operational status data and environmental sensor data from home devices by wirelessly connecting the smart home control platform 1 to IoT devices. The cloud database module 2 stores and manages the collected operational status and environmental sensor data, processes the data, and sorts the processed data according to timestamps to generate time-series operational status and environmental sensor data. The system then utilizes data conversion... Module 3 transforms the runtime status time-series data and environmental sensing time-series data. The hierarchical time-series pattern mining algorithm of the user behavior pattern mining module 4 then performs pattern mining on the transformed runtime status time-series data and environmental sensing time-series data to extract user behavior patterns. These patterns are stored in the cloud database as patterns. When the status of home devices changes or a specific task is performed, the HTTP trigger 6 calls the corresponding cloud function in the cloud function library module 5 via an HTTP request. The cloud function accesses data in the cloud database and retrieves the previously stored user behavior patterns. The smart home control platform 1 is then associated with the new device, and the new device is controlled and managed based on the user behavior patterns.

[0109] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A time-series data-driven intelligent home management and control method, characterized in that, The method comprises the following steps: designing a personalized user interaction interface, after identity authentication, the user registers or logs in the smart home control center, and collects the running state data and environmental sensing data of the home devices through wireless connection with the home Internet of Things devices; store and manage the collected running state data and environmental sensing data through the cloud database, and process the running state data and environmental sensing data, sort the processed running state data and environmental sensing data according to the timestamp, and generate running state time series data and environmental sensing time series data; convert the running state time series data and environmental sensing time series data, mine the converted running state time series data and environmental sensing time series data through a hierarchical time series pattern mining algorithm, extract the user behavior pattern, and store the extracted user behavior pattern in the form of pattern in the cloud database; When the state of the home device changes or performs a specific task, the HTTP trigger calls the corresponding cloud function in the cloud function library through the HTTP request, retrieves the user behavior pattern previously stored in the cloud database by using the cloud function to access the data in the cloud database; associate the smart home control center with the new device, and control and manage the new device according to the user behavior pattern. 2.The time-series data-driven intelligent home management and control method of claim 1, wherein, The step of designing a personalized user interaction interface, after identity authentication, the user registers or logs in the smart home control center, and collects the running state data and environmental sensing data of the home devices through wireless connection with the home Internet of Things devices, comprises: For users who use the smart home management and control system for the first time, create a personal account by providing personal basic information, and select a username and password at the same time; For users who do not use the smart home management and control system for the first time, perform identity authentication by inputting a username and password, and log in the smart home control center after identity authentication. After logging in, the user can view personal basic information; The user connects with the home Internet of Things devices through Bluetooth wireless communication technology by using a mobile phone, tablet computer or computer device, sets the data collection frequency and transmission speed through the smart home control center, and collects the running state data and environmental sensing data of the home devices in real time. 3.The time-series data-driven intelligent home management and control method of claim 1, wherein, The step of storing and managing the collected running state data and environmental sensing data through the cloud database, and processing the running state data and environmental sensing data, sorting the processed running state data and environmental sensing data according to the timestamp, and generating running state time series data and environmental sensing time series data, comprises: transmit the collected running state data and environmental sensing data to the established cloud database for storage, and aggregate and classify the running state data and environmental sensing data; perform cleaning and noise elimination operations on the classified running state data and environmental sensing data to remove outliers in the running state data and environmental sensing data and reduce random fluctuations of the running state data and environmental sensing data, and obtain running state processing data and environmental sensing processing data; The operation state processing data and the environment sensing processing data are sorted according to timestamps to generate operation state time series data and environment sensing time series data. 4.The time-series data-driven intelligent home management and control method of claim 1, wherein, The operation state time series data and the environment sensing time series data are data-converted, pattern mining is performed on the converted operation state time series data and the environment sensing time series data by using a hierarchical time series model graph mining algorithm, user behavior patterns are extracted, and the extracted user behavior patterns are stored in a cloud database in the form of pattern. The operation state time series data and the environment sensing time series data are data-converted in terms of data format, data type and data structure to adapt to the requirements of the pattern mining algorithm, and standard operation state time series data and standard environment sensing time series data are generated. The standard operation state time series data and the standard environment sensing time series data are pattern-mined by using the hierarchical time series model graph mining algorithm, and user behavior patterns are extracted. The standard operation state time series data and the standard environment sensing time series data are pattern-mined by using the hierarchical time series model graph mining algorithm, and user behavior patterns are extracted.

5. The time-series data-driven intelligent home management and control method according to claim 4, characterized in that, A series of operation state data subsequences and environment sensing data subsequences are generated by arranging the standard operation state time series data and the standard environment sensing time series data in chronological order. A time series graph is constructed for each of the operation state data subsequences and the environment sensing data subsequences, and operation state time series graphs and environment sensing time series graphs are generated. Operation state features and environment sensing features representing the operation state data subsequence and the environment sensing data subsequence patterns are extracted from each of the operation state time series graphs and the environment sensing time series graphs, the extracted operation state features and environment sensing features are clustered, and clustering results are generated. The clustering results are converted into a hierarchical pattern graph, the hierarchical pattern graph is analyzed, features representing user behavior patterns are extracted, and user behavior patterns are generated. When the state of the home equipment changes or a specific task is performed, the http trigger calls the corresponding cloud function in the cloud function library by using an http request, and the cloud function accesses the data in the cloud database to retrieve the user behavior patterns previously stored in the cloud database. 6.The time-series data-driven intelligent home management and control method of claim 1, wherein, When the state of the home equipment changes or a specific task is performed, the user sends an http request to the server, the server receives the http request, and the http trigger sends the http request to the cloud function library. The cloud function library receives the http request, finds and calls the corresponding cloud function according to the information in the http request. The cloud function is called to access the data in the cloud database to retrieve the user behavior patterns previously stored in the cloud database. The cloud function is called to access the data in the cloud database to retrieve the user behavior patterns previously stored in the cloud database.

7. The time-series data-driven intelligent home management and control method according to claim 6, characterized in that, ​ After the cloud function is authenticated, the cloud function is connected to the cloud database using an API key of the database; The cloud function retrieves data in the cloud database according to a specified query language and a retrieval field, further processes and converts the retrieved data, extracts features representing user behavior patterns, generates user behavior patterns, and returns the user behavior patterns to the HTTP trigger in the form of an HTTP response. 8.The time-series data-driven intelligent home management and control method of claim 1, wherein, The step of associating the smart home control center with the new device and controlling and managing the new device according to the user behavior pattern comprises: accessing the new device to the smart home control center and communicating with the smart home control center; After the new device is accessed, the smart home control center models the new device, and in the modeling process, the smart home control center matches the user behavior pattern retrieved from the cloud database previously, and generates a user behavior pattern matching result; Based on the user behavior pattern matching result, the smart home control center generates an automatic control rule for the new device; During the operation of the new device, the new device is controlled and managed according to the automatic control rule.

9. A time-series data-driven intelligent home management and control system, characterized in that, A smart home control method based on time series data driving according to any one of claims 1-8, comprising: a smart home control center (1) for designing a personalized user interaction interface, after the user is authenticated, the user registers or logs in the smart home control center, and collects the running state data and environmental sensing data of the devices in the home through wireless connection with the Internet of Things devices in the home; a cloud database module (2) for storing and managing the collected running state data and environmental sensing data, and processing the running state data and environmental sensing data, sorting the processed running state data and environmental sensing data according to the time stamp, and generating running state time series data and environmental sensing time series data; a data conversion module (3) for converting the running state time series data and environmental sensing time series data; a user behavior pattern mining module (4) for mining patterns from the converted running state time series data and environmental sensing time series data through a hierarchical time series pattern mining algorithm, extracting user behavior patterns, and storing the mined user behavior patterns in the form of pattern in the cloud database; a cloud function library module (5) for centralized storage and management of cloud functions, and data access operations on data in the cloud database using cloud functions to retrieve user behavior patterns previously stored in the cloud database; an HTTP trigger (6) for triggering cloud functions in the cloud function library to execute, and when the state of the home device changes or a specific task is executed, the HTTP trigger calls the corresponding cloud function in the cloud function library through an HTTP request. 10.The time-series data-driven intelligent home management and control system according to claim 9, wherein, The smart home control center further comprises: a control unit (11) for generating an automatic control rule for a new device according to the user behavior pattern, and controlling and managing the new device according to the automatic control rule.

Images