A kind of intelligent equipment control system and method based on artificial intelligence

By deploying multiple sensors and advanced algorithms, combining user behavior data, intelligently identify user situations and automatically adjust home devices, the problem of separation of environmental perception and user behavior in smart home systems and static prediction models is solved, and personalized comfortable environment management is realized and energy optimization.

CN118550245BActive Publication Date: 2024-11-26SUZHOU GUANWEN STORAGE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411050034.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-26
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

In smart home systems, the environment perception and user behavior are separated, the prediction model is static, and the situation recognition is simple, resulting in poor personalized and proactive services.

Method used

By deploying multiple sensors to collect indoor and outdoor environment data, combining user historical behavior data, using Bayesian network, K-means clustering, ARIMA and STM models and other algorithms to predict user behavior and identify the current situation, and automatically use cosine similarity algorithms to automatically Adjust home smart devices.

Benefits of technology

It realizes intelligent management of personalized and comfortable environments, improves the convenience and comfort of life, optimizes energy utilization, and enhances the efficient foresight and adaptability of smart homes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118550245B_ABST
    Figure CN118550245B_ABST
Patent Text Reader

Abstract

The present invention discloses an intelligent device control system and method based on artificial intelligence, which relates to the field of intelligent terminal technology, including deploying multiple sensors to collect indoor and outdoor environmental data; collecting historical behavior data of users on home intelligent devices, analyzing user preferences and habits; combining user location information, activity patterns and time information to predict user future behaviors and needs; identifying the user's current scenario based on the collected indoor and outdoor environmental data and user behavior data; and automatically adjusting home intelligent devices based on the identified current scenario and user preferences. Through real-time data transmission, combined with detailed user behavior analysis, preference identification and prediction models, the system can accurately judge the user scenario and automatically adjust home appliances, realizing intelligent management of personalized comfortable environments, which not only improves the convenience and comfort of life, but also optimizes energy utilization, and demonstrates the efficient predictability and adaptability of smart homes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent terminal technology, and in particular to an intelligent device control system and method based on artificial intelligence. Background Art

[0002] Driven by the Internet of Things and AI, smart home technology has developed rapidly, integrating sensors and data analysis to optimize the living environment and achieve automated control. However, it still faces limitations such as the separation of environmental perception and user behavior, static prediction models, and simple scenario recognition, which affect the effectiveness of personalized and proactive services.

[0003] The present invention comprehensively collects environmental and behavioral data through the comprehensive deployment of sensor networks, deeply integrates user preferences, location and time information, innovates prediction models, intelligently identifies scenarios and dynamically adjusts home appliances, solves existing technical problems, and improves system accuracy and user experience. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent device control system and method based on artificial intelligence to solve the problems of separation of environmental perception and user behavior, static prediction model, simple scenario recognition, etc., which affect the personalized and proactive service effects.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an artificial intelligence-based smart device control method, which includes deploying a variety of sensors to collect indoor and outdoor environmental data;

[0008] Collect historical behavior data of users on home smart devices and analyze user preferences;

[0009] Combine user location information, activity patterns, and time information to predict user future behavior;

[0010] Identify the user’s current context based on the collected indoor and outdoor environment data and user behavior data;

[0011] Automatically adjust smart home devices based on the current context and user preferences.

[0012] As a preferred solution of the intelligent device control method based on artificial intelligence of the present invention, wherein: the multiple sensors include a temperature sensor, a humidity sensor, a light sensor, a sound sensor and an air quality sensor;

[0013] The indoor and outdoor environmental data include temperature, humidity, light intensity, sound and air quality.

[0014] As a preferred solution of the intelligent device control method based on artificial intelligence of the present invention, the deployment of multiple sensors to collect indoor and outdoor environmental data includes:

[0015] The locations of multiple sensors are calculated through the Bayesian network algorithm, and multiple sensors are deployed to collect indoor and outdoor environmental data in real time. WiFi technology is used to transmit indoor and outdoor environmental data in real time.

[0016] As a preferred solution of the artificial intelligence-based intelligent device control method of the present invention, wherein: the analysis of user preferences includes:

[0017] Collect historical behavior data of users interacting with home smart devices from the smart home system database;

[0018] Time series interpolation was used to handle occasional missing data points, and Z-score was used to identify and handle outliers;

[0019] Extract usage frequency features, active time features, device usage duration features, operation sequence features, and operating environment features;

[0020] Based on all the features, use the K-means clustering algorithm, set the K value, and get K behavior patterns;

[0021] Use ARIMA and STM models to conduct time series analysis on K behavior patterns to reveal preference patterns;

[0022] Integrate ARIMA and STM models into smart home systems to analyze behavioral patterns in real time and automatically adjust home smart devices based on preferences.

[0023] As a preferred solution of the intelligent device control method based on artificial intelligence of the present invention, wherein: the prediction of the user's future behavior includes:

[0024] Use the mobile phone GPS to accurately locate the user's real-time location at home, record the location data, combine it with historical behavior data, identify the activity path, integrate the smart device usage records, combine it with time tags, record the timestamp of each behavior, and establish a temporal association between behavior and location;

[0025] Based on the temporal association between behavior and location, K-means clustering is used, and the K value is set to obtain K path patterns;

[0026] Based on K path patterns, define a set of path patterns and its associated location sequence and time window , calculate the matching degree;

[0027] First, define a weighted distance function D to measure the current position and Mode starting point The distance is expressed as,

[0028] ;

[0029] in, and are weight factors for position and time, It's location To Mode Middle position physical distance, is the current time T converted to relative to the mode The absolute value of the window offset;

[0030] Then, calculate the overall matching degree , expressed as,

[0031] ;

[0032] Among them, k traverses the pattern All locations in , For all The sum of

[0033] Finally, based on the calculated matching degree , find the path pattern with the highest matching degree , predict the user’s next behavior.

[0034] As a preferred solution of the intelligent device control method based on artificial intelligence of the present invention, wherein: the identification of the user's current scenario based on the collected indoor and outdoor environment data and user behavior data refers to the identification of the user's current scenario based on the path mode with the highest matching degree. ,As a model of the user’s current activity context, the current indoor and outdoor environment data and the user’s historical behavior characteristics are further integrated to construct the user behavior context, so that the system can accurately identify the user’s current context.

[0035] As a preferred solution of the artificial intelligence-based smart device control method of the present invention, wherein: the automatic adjustment of home smart devices according to the identified current scenario and user preferences includes:

[0036] Using the cosine similarity algorithm, the matching degree F between the identified scenario and the user's historical preference is calculated, expressed as,

[0037] ;

[0038] in, A vector representing the user's historical preferences, a vector representing the current scenario features, a vector representing the user's historical preferences modulus, a vector representing the current scenario features modulus;

[0039] Set the matching degree threshold to A;

[0040] When F≥A, it indicates that the current scenario highly matches the user's historical preferences. According to the identified scenario and user preferences, the home intelligent devices are automatically adjusted;

[0041] When F<A, it indicates a low matching degree, meaning there are significant differences between the current scenario and the user's preferences. The user checks whether the data is abnormal to avoid incorrect operations.

[0042] In a second aspect, the present invention provides an intelligent device control system based on artificial intelligence, including an environmental monitoring and data collection module for deploying a variety of sensors to collect indoor and outdoor environmental data;

[0043] a behavior analysis and preference learning module for collecting the user's historical behavior data on home intelligent devices and analyzing the user's preferences;

[0044] a behavior prediction module for predicting the user's future behavior by combining the user's location information, activity pattern, and time information;

[0045] a scenario recognition module for identifying the user's current scenario based on the collected indoor and outdoor environmental data and user behavior data;

[0046] an intelligent regulation module for automatically adjusting home intelligent devices according to the identified current scenario and user preferences.

[0047] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent device control method based on artificial intelligence described in the first aspect of the present invention is implemented.

[0048] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by the processor, any step of the intelligent device control method based on artificial intelligence described in the first aspect of the present invention is implemented.

[0049] The beneficial effects of the present invention are as follows: by optimizing sensor layout and real-time data transmission through Bayesian networks, combined with detailed user behavior analysis, preference recognition and prediction models, the system can accurately judge user scenarios and automatically adjust home appliances, thereby realizing intelligent management of personalized comfortable environments, which not only improves the convenience and comfort of life, but also optimizes energy utilization, demonstrating the efficient predictability and adaptability of smart homes. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 This is a flow chart of the intelligent device control method based on artificial intelligence in Example 1.

[0052] Figure 2 This is a diagram for determining whether the home smart device in Example 1 is automatically adjusted. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments. Example 1

[0056] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an intelligent device control method based on artificial intelligence, comprising the following steps:

[0057] S1. Deploy a variety of sensors to collect indoor and outdoor environmental data.

[0058] The Bayesian network algorithm is used to calculate the positions of various sensors, deploy various sensors, collect indoor and outdoor environmental data in real time, and use WiFi technology to transmit indoor and outdoor environmental data in real time;

[0059] The Bayesian network is a graphical probability model that describes the conditional dependencies between variables through a directed acyclic graph structure and achieves efficient reasoning and learning with the help of conditional probability tables.

[0060] It should be noted that the Bayesian network algorithm is used to optimize the sensor layout, ensure the efficient distribution of sensors, capture indoor and outdoor environmental information in real time, and use WiFi to transmit data instantly, which improves the timeliness and accuracy of data collection.

[0061] S2. Collect historical behavior data of users on home smart devices and analyze user preferences.

[0062] Collect historical behavior data of users interacting with home smart devices from the smart home system database;

[0063] Use time series interpolation to handle occasional missing data points and use Z-score to identify and handle outliers

[0064] Extract key behavioral features, including usage frequency features, active time features, device usage duration features, operation sequence features, and operating environment features;

[0065] Based on all features, use the K-means clustering algorithm to randomly select K points from the key behavior features as the initial centroids, set K=3, corresponding to going home, going out, and sleeping, calculate the distance from each feature to all centroids, and assign it to the cluster corresponding to the nearest centroid. For each cluster, recalculate the mean of all samples in the cluster and use it as the new centroid. Repeat the above two steps until the iterative centroid does not change significantly. Classify the user's behavior data points into the cluster represented by the nearest centroid, thus forming a classification of going home behavior pattern, going out behavior pattern, and sleeping behavior pattern;

[0066] Use ARIMA and STM models to conduct time series analysis on home behavior patterns, out behavior patterns, and sleep behavior patterns to reveal preference patterns;

[0067] Preferences for home behavior patterns: prefer cooling in summer, prefer heating in winter, prefer fresh air in winter due to low humidity;

[0068] Out-of-home behavior mode preference: prefer to turn off all furniture smart devices;

[0069] Sleeping behavior pattern preference: dark lighting preference, low noise preference;

[0070] Integrate ARIMA and STM models into the smart home system to analyze home behavior patterns, outing behavior patterns, and sleeping behavior patterns in real time, and automatically adjust home smart devices according to preferences.

[0071] It should be noted that through a detailed analysis of the history of user interaction with smart devices, time series interpolation is used to fill in data gaps, and Z-score is used to remove outliers to ensure data quality. The application of K-means clustering and ARIMA and STM models effectively refines user behavior patterns and preferences, laying the foundation for personalized service customization.

[0072] S3. Combine the user's location information, activity pattern and time information to predict the user's future behavior.

[0073] Use the mobile phone GPS to accurately locate the user's real-time location at home, record the location data, combine it with historical behavior data, identify the activity path, integrate the smart device usage records, combine it with time tags, record the timestamp of each behavior, and establish a temporal association between behavior and location;

[0074] Based on the temporal association between behavior and location, K-means clustering was used to identify common behavior path patterns. K was set to 3, and the path patterns included morning route path pattern, post-dinner relaxation path pattern, and bedtime preparation path pattern.

[0075] The morning route path pattern will be in the kitchen and living room;

[0076] After dinner, the relaxation path mode will be in the living room and study;

[0077] The bedtime preparation path mode will be in the bedroom;

[0078] Based on the path pattern, define a set of path patterns and its associated location sequence and time window , calculate the matching degree;

[0079] First, define a weighted distance function D to measure the current position and Mode starting point The distance is expressed as,

[0080] ;

[0081] in, and are weight factors for position and time, It's location To Mode Middle position physical distance, is the current time T converted to relative to the mode The absolute value of the window offset;

[0082] Then, calculate the overall matching degree , expressed as,

[0083] ;

[0084] Among them, k traverses the pattern All locations in , For all The sum of

[0085] Finally, based on the calculated matching degree , find the behavior pattern with the highest matching degree , predict the user’s next behavior;

[0086] It should be noted that the integrated GPS positioning and K-means path pattern analysis, combined with time series data, can accurately predict user behavior paths.

[0087] S4. Identify the user's current situation based on the collected indoor and outdoor environment data and user behavior data.

[0088] According to the calculated matching Get the user's current location, combine the current environment and historical behavior characteristics, and identify the user's current context.

[0089] On the way home: the user is near home and during commuting time;

[0090] Preparing for rest: the user is in the living room or study;

[0091] Out-of-town scenario: The user's location is shown as far away from the residential area;

[0092] Night preparation scenario: the user moves to the bedroom, and the time is bedtime;

[0093] It should be noted that by combining the user location and behavioral characteristics identified by the matching degree, the system can accurately judge the current situation. This dynamic situation recognition mechanism enables the system to respond to environmental changes in real time and improves environmental adaptability.

[0094] S5. Automatically adjust home smart devices based on the identified current scenario and user preferences.

[0095] Using the cosine similarity algorithm, the matching degree F between the identified scenario and the user's historical preference is calculated, expressed as,

[0096] ;

[0097] in, A vector representing the user's historical preferences, represents the current scenario feature vector, Represents the user's historical preference vector The model, Represents the current scenario feature vector Model;

[0098] Set the matching threshold A=0.7;

[0099] When F ≥ 0.7, it means that the current scenario is highly matched with the user's historical preferences, and the home smart devices are automatically adjusted according to the identified scenario and user preferences;

[0100] When F<0.7, it indicates a low degree of match, which means that the current scenario is significantly different from the user's preference. The user should check whether the data is abnormal to avoid incorrect operations.

[0101] Historical behavior data includes device ID, user ID, event timestamp, switch status, operation duration, and setting parameters;

[0102] A variety of sensors including temperature sensors, humidity sensors, light sensors, sound sensors, and air quality sensors;

[0103] Indoor and outdoor environmental data include temperature, humidity, light intensity, sound and air quality.

[0104] Smart home devices include smart lights, curtains, air conditioners, humidifiers, speakers and air purifiers.

[0105] It should be noted that by matching the current scenario with preferences through cosine similarity, home appliances are automatically adjusted to ensure that the environment settings that best suit the user's preferences are provided when the match is highly matched, while basic settings are maintained when the match is low to prevent misoperation and ensure user control.

[0106] This embodiment also provides an artificial intelligence-based intelligent device control system, including an environmental monitoring and data acquisition module for deploying a variety of sensors to collect indoor and outdoor environmental data;

[0107] Behavior analysis and preference learning module, which is used to collect historical behavior data of users on home smart devices and analyze user preferences;

[0108] Behavior prediction module, which is used to predict the user's future behavior by combining the user's location information, activity pattern and time information;

[0109] A context recognition module is used to identify the user's current context based on the collected indoor and outdoor environment data and user behavior data;

[0110] The intelligent control module is used to automatically adjust home smart devices based on the current situation and user preferences.

[0111] This embodiment also provides a computer device, which is suitable for the case of an intelligent device control method based on artificial intelligence, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent device control method based on artificial intelligence proposed in the above embodiment.

[0112] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0113] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for controlling an intelligent device based on artificial intelligence as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0114] In summary, the beneficial effect of the present invention is that by optimizing the sensor layout and real-time data transmission through the Bayesian network, combined with detailed user behavior analysis, preference recognition and prediction models, the system can accurately judge the user scenario and automatically adjust home appliances, realizing the intelligent management of personalized comfortable environment, which not only improves the convenience and comfort of life, but also optimizes energy utilization, demonstrating the efficient predictability and adaptability of smart homes. Example 2

[0115] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the intelligent device control method based on artificial intelligence are provided.

[0116] To verify the effectiveness of the present invention, a comprehensive experiment was designed to simulate daily use in a smart home environment. The experiment was conducted in a modern house equipped with an advanced sensor network and an integrated smart home system that integrates temperature sensors, humidity sensors, light sensors, sound sensors, and air quality sensors. The experiment covered a one-month household life cycle to ensure the comprehensiveness and representativeness of the data.

[0117] Sensor deployment and data collection: Bayesian network algorithm is used to optimize sensor layout to ensure coverage of key areas throughout the house. WiFi is used to transmit temperature, humidity, light intensity, sound level and air quality data to the central processing unit in real time. The sensor updates data every minute to ensure real-time environmental monitoring.

[0118] User behavior data collection and analysis: The interaction data between family members and home smart devices were collected. Time series interpolation was used to process occasionally missing data points, and the Z-score method was used to identify and remove outliers. The K-means clustering algorithm was used to divide user behavior patterns into three categories: "going home", "going out" and "sleeping", and the ARIMA and STM models were combined to deeply explore the user's preference patterns, such as preference for cooling in summer and heating in winter.

[0119] Behavior prediction and scenario recognition: Using the GPS information of family members' mobile phones, real-time positioning and combining historical behavior path patterns, predict the user's next behavior. Define the behavior path patterns in the morning, after dinner and before bedtime, and calculate the matching degree between the current location and the pattern through weighted and distance functions to achieve high-precision behavior prediction.

[0120] Intelligent device adaptive adjustment: Automatically adjust the device based on the current scenario recognition and the cosine similarity between the user preference vector and the current scenario feature vector. When the matching degree F ≥ 0.7, the preference setting is automatically executed, otherwise the basic setting is maintained to reduce the risk of misoperation.

[0121] The details are shown in the following table:

[0122] Table 1 Experimental record table

[0123]

[0124] Through the comparative analysis of the above data, the following significant beneficial effects can be observed:

[0125] 1. Enhanced real-time responsiveness: The average automatic adjustment response time is 4 seconds, which is about 73% faster than traditional manual control or simple automation systems, significantly improving the user experience.

[0126] 2. Environmental adaptability: By monitoring environmental data in different areas, the operating parameters of home appliances can be dynamically adjusted to effectively maintain the comfort of the indoor environment.

[0127] 3. Accurate matching: In terms of behavioral pattern matching, the recognition accuracy of key scenarios, including going home and going to bed, is as high as 92%, ensuring the accuracy and timeliness of smart device adjustments and reducing unnecessary human intervention.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for controlling an intelligent device based on artificial intelligence, characterized in that: include, Deploy a variety of sensors to collect indoor and outdoor environmental data; Collect historical behavior data of users on home smart devices and analyze user preferences; Combine user location information, activity patterns, and time information to predict user future behavior; Identify the user’s current context based on the collected indoor and outdoor environment data and user behavior data; Automatically adjust home smart devices based on the current situation and user preferences; The analyzing of user preferences includes: Collect historical behavior data of users interacting with home smart devices from the smart home system database; Time series interpolation was used to handle occasional missing data points, and Z-score was used to identify and handle outliers; Extract usage frequency features, active time features, device usage duration features, operation sequence features, and operating environment features; Based on all the features, use the K-means clustering algorithm, set the K value, and get K behavior patterns; Use ARIMA and STM models to conduct time series analysis on K behavior patterns to reveal preference patterns; Integrate ARIMA and STM models into smart home systems to analyze behavioral patterns in real time and automatically adjust smart home devices based on preferences; The prediction of the user's future behavior includes: Use the mobile phone GPS to accurately locate the user's real-time location at home, record the location data, combine it with historical behavior data, identify the activity path, integrate the smart device usage records, combine it with time tags, record the timestamp of each behavior, and establish a temporal association between behavior and location; Based on the temporal association between behavior and location, K-means clustering is used, and the K value is set to obtain K path patterns; Based on K path patterns, define a set of path patterns and its associated location sequence and time window , calculate the matching degree; First, define a weighted distance function D to measure the current position and Mode starting point The distance is expressed as, ; in, and are weight factors for position and time, It's location To Mode Middle position physical distance, is the current time T converted to relative to the mode The absolute value of the window offset; Then, calculate the overall matching degree , expressed as, ; Among them, k traverses the pattern All locations in , For all The sum of Finally, based on the calculated matching degree , find the path pattern with the highest matching degree , predict the user’s next behavior; The identification of the user's current situation based on the collected indoor and outdoor environment data and user behavior data refers to the identification of the user's current situation based on the path mode with the highest matching degree. , as a model of the user's current activity context, it further integrates the current indoor and outdoor environment data with the user's historical behavior characteristics to build the user's behavior context, and the system accurately identifies the user's current situation; The automatic adjustment of the home smart device according to the identified current scenario and user preferences includes: Using the cosine similarity algorithm, the matching degree F between the identified scenario and the user's historical preference is calculated, expressed as, ; in, A vector representing the user's historical preferences, represents the current scenario feature vector, Represents the user's historical preference vector The model, Represents the current scenario feature vector Model; Set the matching threshold to A; when When , it means that the current scenario is highly matched with the user's historical preferences, and the home smart devices are automatically adjusted according to the identified scenario and user preferences; when , it indicates a low match, which means that the current scenario is quite different from the user's preference. The user should check whether the data is abnormal to avoid incorrect operations.

2. The method for controlling an intelligent device based on artificial intelligence according to claim 1, characterized in that: The multiple sensors include temperature sensors, humidity sensors, light sensors, sound sensors and air quality sensors; The indoor and outdoor environmental data include temperature, humidity, light intensity, sound and air quality.

3. The method for controlling an intelligent device based on artificial intelligence as claimed in claim 2, characterized in that: The deployment of multiple sensors to collect indoor and outdoor environmental data includes: The locations of multiple sensors are calculated through the Bayesian network algorithm, and multiple sensors are deployed to collect indoor and outdoor environmental data in real time. WiFi technology is used to transmit indoor and outdoor environmental data in real time.

4. An intelligent device control system based on artificial intelligence, based on the intelligent device control method based on artificial intelligence according to any one of claims 1 to 3, characterized in that: include, Environmental monitoring and data collection module, used to deploy a variety of sensors to collect indoor and outdoor environmental data; Behavior analysis and preference learning module, which is used to collect historical behavior data of users on home smart devices and analyze user preferences; Behavior prediction module, which is used to predict the user's future behavior by combining the user's location information, activity pattern and time information; A context recognition module is used to identify the user's current context based on the collected indoor and outdoor environment data and user behavior data; The intelligent control module is used to automatically adjust home smart devices based on the current situation and user preferences.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent device control method based on artificial intelligence described in any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent device control method based on artificial intelligence described in any one of claims 1 to 3 are implemented.