Smart home automatic scheduling system and method based on user behavior prediction
By constructing a smart home automation scheduling system based on user behavior prediction, and utilizing machine learning algorithms to predict user behavior and automatically control home devices, the system solves the problem of insufficient understanding of user behavior in existing technologies, and realizes a personalized and intelligent home environment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAMEN DNAKE INTELLIGENT TECH CO LTD
- Filing Date
- 2025-12-06
- Publication Date
- 2026-04-21
AI Technical Summary
Existing smart home systems lack a deep understanding of user behavior, cannot effectively adapt to users' dynamic needs, and struggle to provide a personalized home experience.
A smart home automation scheduling system based on user behavior prediction is constructed. Through data collection, processing and analysis, user behavior prediction and feedback and self-learning modules, machine learning algorithms such as time series analysis, Bayesian networks and deep learning models are used to predict user behavior and automatically control home devices.
It achieves a highly personalized and intelligent home environment, improving the accuracy of device scheduling and user experience.
Smart Images
Figure CN121900207A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of smart home technology, and in particular to a smart home automated scheduling system and method based on user behavior prediction. Background Technology
[0002] Existing smart home systems typically rely on manual user control or pre-set rules for device operation and scheduling. Although some smart home systems have achieved a certain degree of automation, such as adjusting based on time and environmental conditions, these methods often lack a deep understanding of user behavior, cannot effectively adapt to users' dynamic needs, and are difficult to provide a truly personalized home experience. Based on this, we propose a smart home automated scheduling system and method based on user behavior prediction. Summary of the Invention
[0003] This invention proposes a smart home automation scheduling system and method based on user behavior prediction, which solves the problems existing in the prior art.
[0004] To achieve the above objectives, the present invention adopts the following technical solution: A smart home automated scheduling system based on user behavior prediction includes a data acquisition module, a data processing and analysis module, a user behavior prediction module, an automated scheduling module, and a feedback and self-learning module. The data processing and analysis module is connected to the data acquisition module and the user behavior prediction module, respectively. The automated scheduling module is connected to the user behavior prediction module and the feedback and self-learning module, respectively, and the feedback and self-learning module is also connected to the data processing and analysis module.
[0005] Preferably, the data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home, and then sends the collected data to the data processing and analysis module.
[0006] Preferably, the data collected by the data acquisition module includes, but is not limited to: user location information, daily activity trajectory, device usage frequency, indoor temperature, light intensity, and ambient sound level.
[0007] Preferably, the data processing and analysis module processes and analyzes the collected data through edge computing or cloud computing. The data processing and analysis module uses machine learning algorithms, especially cluster analysis in time series analysis, to perform pattern recognition on users' daily behaviors, extract key behavioral features, form user behavior models, and send them to the user behavior prediction module. Machine learning algorithms refer to the process by which machines learn from large amounts of historical data through statistical algorithms, and then use the generated experience models to guide business operations. Time series analysis is the science of studying and predicting the changing patterns of time-ordered observational data sequences. Time series data is very common in real life, such as stock prices, population data, weather data, and e-commerce data. The specific steps of clustering in time series analysis are as follows: Step 1: Select the distance threshold ε and the minimum number of samples threshold MinPts; Step 2: Select a random data point as the core point; Step 3: Find the neighbors of the core point whose distance is less than ε; Step 4: If the number of neighbors of a core point is greater than MinPts, then add the neighbors to the same cluster; Step 5: Repeat steps 2 and 4 until all data points are assigned to clusters.
[0008] Preferably, the user behavior prediction module analyzes historical data and current status, and uses Bayesian networks, hidden Markov models or deep learning models to predict user behavior, generates prediction results and sends them to the automated scheduling module. The prediction results of the user behavior prediction module include the operations that the user may perform in a specific time period and possible device usage patterns. Bayesian networks are one of the most classic algorithms in machine learning. They can estimate uncertain knowledge based on known conditions and have a wide range of applications. Bayesian networks are constructed using Bayes' theorem as the theoretical basis to form a directed acyclic graph. This allows for clear prediction of future information based on existing information through the graph constructed by the Bayesian network. Hidden Markov Models (HMMs) are probabilistic models for time series, describing the process of generating an unobservable random sequence of states from a hidden Markov chain, and then generating an observation from each state to produce an observation random sequence.
[0009] Preferably, the automated scheduling module will execute corresponding equipment control commands based on the prediction results. The automated scheduling module can also schedule the equipment in advance according to the user's daily habits.
[0010] Preferably, the feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the difference between the user's actual behavior and the predicted behavior. The feedback and self-learning module also uses reinforcement learning to enable the scheduling system to continuously learn itself during the user's usage, thereby gradually improving the accuracy of prediction and the precision of scheduling.
[0011] This invention also proposes a smart home automation scheduling method based on user behavior prediction, comprising the following steps: S1: The data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home. The data acquisition module then sends the collected data to the data processing and analysis module. S2: The data processing and analysis module preprocesses the collected data, specifically including the following steps: S201: Clean the collected data to remove noise and abnormal data, ensuring the accuracy and integrity of the data; S202: Identify and handle any outliers that may occur during the data acquisition process; S203: Integrate the cleaned data and store it in the system database for subsequent analysis; S3: The data processing and analysis module uses machine learning algorithms, especially clustering analysis in time series analysis, to perform pattern recognition on users' daily behaviors, extract key behavioral features, and form user behavior models. Specifically, it includes the following steps: S301: Analyze users' long-term behavioral patterns, such as fixed work and rest times and routine operating habits, to form a static behavioral model of users; S302: Identify user behavior patterns under specific circumstances, such as differences in work and rest schedules between weekends and weekdays and special activities on holidays, to form a dynamic behavioral model of users; S303: Based on static and dynamic behavioral data, build a comprehensive user behavior model and continuously learn and optimize the user behavior model; S4: Perform behavior prediction through the user behavior prediction module, which includes the following steps: S401: By analyzing historical data and the current state, it uses Bayesian networks, hidden Markov models, or deep learning models to predict user behavior. S402: Calculate the probability distribution of the user's next possible action, and determine the priority of different operations. The user behavior model calculates the probability distribution of future actions and determines the most likely action based on the output probability distribution. S403: Determine the scheduling strategy of the scheduling system based on the probability distribution, and collect user feedback after execution to adjust and optimize the prediction model; S5: The automated scheduling module will execute corresponding equipment control commands based on the prediction results. The automated scheduling module can also schedule equipment in advance according to the user's daily habits to meet the user's expected needs. S6: The feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the difference between the user's actual behavior and the predicted behavior. The feedback and self-learning module also uses reinforcement learning to schedule the system to continuously learn itself during the user's usage.
[0012] Compared with existing technologies, this invention constructs a user behavior model, uses a prediction algorithm to predict the user's future behavior, and automatically controls home appliances based on the prediction results, thereby achieving a highly personalized and intelligent home environment. Attached Figure Description
[0013] Figure 1 This is a system block diagram of a smart home automation scheduling system based on user behavior prediction proposed in this invention; Figure 2 This is a flowchart of a smart home automation scheduling method based on user behavior prediction proposed in this invention. Detailed Implementation
[0014] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.
[0015] Reference Figure 1 A smart home automation scheduling system based on user behavior prediction includes a data acquisition module, a data processing and analysis module, a user behavior prediction module, an automation scheduling module, and a feedback and self-learning module. The data processing and analysis module is connected to the data acquisition module and the user behavior prediction module, respectively. The automated scheduling module is connected to the user behavior prediction module and the feedback and self-learning module, respectively, and the feedback and self-learning module is also connected to the data processing and analysis module. The data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home. This data is then sent to the data processing and analysis module. The collected data includes, but is not limited to, user location information, daily activity trajectories, device usage frequency, indoor temperature, light intensity, and ambient sound level. The data processing and analysis module uses edge computing or cloud computing to process and analyze the collected data. It employs machine learning algorithms, particularly clustering analysis in time series analysis, to perform pattern recognition on user daily behaviors, extract key behavioral features, form a user behavior model, and send it to the user behavior prediction module. The behavior prediction module analyzes historical data and current status, employing Bayesian networks, Hidden Markov Models, or deep learning models to predict user behavior. The prediction results are then sent to the automated scheduling module. These predictions include possible user actions within a specific timeframe and potential device usage patterns. Based on these predictions, the automated scheduling module executes corresponding device control commands. It can also pre-schedule devices according to user habits. The feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the discrepancy between actual and predicted user behavior. Furthermore, through reinforcement learning, the scheduling system continuously learns from user experience, gradually improving prediction accuracy and scheduling precision.
[0016] Specifically, machine learning algorithms refer to the process by which machines learn from large amounts of historical data through statistical algorithms, and then use the generated experience models to guide business operations. Time series analysis is the science of studying and predicting the changing patterns of time-ordered observational data sequences. Time series data is very common in real life, such as stock prices, population data, weather data, and e-commerce data. The specific steps of clustering in time series analysis are as follows: Step 1: Select the distance threshold ε and the minimum number of samples threshold MinPts; Step 2: Select a random data point as the core point; Step 3: Find the neighbors of the core point whose distance is less than ε; Step 4: If the number of neighbors of a core point is greater than MinPts, then add the neighbors to the same cluster; Step 5: Repeat steps 2 and 4 until all data points are assigned to clusters.
[0017] Furthermore, Bayesian networks are one of the most classic algorithms in machine learning. They can estimate uncertain knowledge based on known conditions and have a wide range of applications. Bayesian networks are constructed using Bayes' theorem as the theoretical basis to form a directed acyclic graph. Thus, the graph constructed by the Bayesian network can be used to clearly predict future information based on existing information. Hidden Markov Models (HMMs) are probabilistic models for time series, describing the process of generating an unobservable random sequence of states from a hidden Markov chain, and then generating an observation from each state to produce an observation random sequence.
[0018] Reference Figure 2 This embodiment also proposes a smart home automation scheduling method based on user behavior prediction, including the following steps: S1: The data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home. The data acquisition module then sends the collected data to the data processing and analysis module. S2: The data processing and analysis module preprocesses the collected data, specifically including the following steps: S201: Clean the collected data to remove noise and abnormal data, ensuring the accuracy and integrity of the data; S202: Identify and handle any outliers that may occur during the data acquisition process; S203: Integrate the cleaned data and store it in the system database for subsequent analysis; S3: The data processing and analysis module uses machine learning algorithms, especially clustering analysis in time series analysis, to perform pattern recognition on users' daily behaviors, extract key behavioral features, and form user behavior models. Specifically, it includes the following steps: S301: Analyze users' long-term behavioral patterns, such as fixed work and rest times and routine operating habits, to form a static behavioral model of users; S302: Identify user behavior patterns under specific circumstances, such as differences in work and rest schedules between weekends and weekdays and special activities on holidays, to form a dynamic behavioral model of users; S303: Based on static and dynamic behavioral data, build a comprehensive user behavior model and continuously learn and optimize the user behavior model; S4: Perform behavior prediction through the user behavior prediction module, which includes the following steps: S401: By analyzing historical data and the current state, it uses Bayesian networks, hidden Markov models, or deep learning models to predict user behavior. S402: Calculate the probability distribution of the user's next possible action, and determine the priority of different operations. The user behavior model calculates the probability distribution of future actions and determines the most likely action based on the output probability distribution. S403: Determine the scheduling strategy of the scheduling system based on the probability distribution, and collect user feedback after execution to adjust and optimize the prediction model; S5: The automated scheduling module will execute corresponding equipment control commands based on the prediction results. The automated scheduling module can also schedule equipment in advance according to the user's daily habits to meet the user's expected needs. S6: The feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the difference between the user's actual behavior and the predicted behavior. The feedback and self-learning module also uses reinforcement learning to schedule the system to continuously learn itself during the user's usage. This embodiment constructs a user behavior model, uses a prediction algorithm to predict the user's future behavior, and automatically controls home appliances based on the prediction results to achieve a highly personalized and intelligent home environment.
[0019] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A smart home automation scheduling system based on user behavior prediction, characterized in that, It includes a data acquisition module, a data processing and analysis module, a user behavior prediction module, an automated scheduling module, and a feedback and self-learning module; The data processing and analysis module is connected to the data acquisition module and the user behavior prediction module, respectively. The automated scheduling module is connected to the user behavior prediction module and the feedback and self-learning module, respectively, and the feedback and self-learning module is also connected to the data processing and analysis module.
2. The smart home automation scheduling system based on user behavior prediction according to claim 1, characterized in that, The data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home. The data acquisition module then sends the collected data to the data processing and analysis module.
3. The smart home automation scheduling system based on user behavior prediction according to claim 2, characterized in that, The data collected by the data acquisition module includes, but is not limited to: user location information, daily activity trajectory, device usage frequency, indoor temperature, light intensity, and ambient sound.
4. The smart home automation scheduling system based on user behavior prediction according to claim 2, characterized in that, The data processing and analysis module processes and analyzes the collected data through edge computing or cloud computing. The data processing and analysis module uses machine learning algorithms, especially cluster analysis in time series analysis, to perform pattern recognition on users' daily behaviors, extract key behavioral features, form user behavior models, and send them to the user behavior prediction module.
5. The smart home automation scheduling system based on user behavior prediction according to claim 4, characterized in that, The user behavior prediction module analyzes historical data and current status, and uses Bayesian networks, hidden Markov models or deep learning models to predict user behavior, generate prediction results and send them to the automated scheduling module. The prediction results of the user behavior prediction module include the operations that the user may perform in a specific time period and possible device usage patterns.
6. The smart home automation scheduling system based on user behavior prediction according to claim 5, characterized in that, The automated scheduling module will execute corresponding equipment control commands based on the prediction results. The automated scheduling module can also schedule equipment in advance according to the user's daily habits.
7. A smart home automation scheduling system based on user behavior prediction according to claim 6, characterized in that, The feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the difference between the user's actual behavior and the predicted behavior. The feedback and self-learning module also uses reinforcement learning to enable the scheduling system to continuously learn itself during the user's usage, gradually improving the accuracy of prediction and the precision of scheduling.
8. A smart home automation scheduling method based on user behavior prediction, applied to the system described in any one of claims 1-7, characterized in that, Includes the following steps: S1: The data acquisition module collects user behavior data, environmental data, and device operation data through various sensors, cameras, and smart devices installed in the smart home. The data acquisition module then sends the collected data to the data processing and analysis module. S2: The data processing and analysis module preprocesses the collected data, specifically including the following steps: S201: Clean the collected data to remove noise and abnormal data, ensuring the accuracy and integrity of the data; S202: Identify and handle any outliers that may occur during the data acquisition process; S203: Integrate the cleaned data and store it in the system database for subsequent analysis; S3: The data processing and analysis module uses machine learning algorithms, especially cluster analysis in time series analysis, to perform pattern recognition on users' daily behaviors, extract key behavioral features, and form user behavior models. Specifically, it includes the following steps: S301: Analyze users' long-term behavioral patterns, such as fixed work and rest times and routine operating habits, to form a static behavioral model of users; S302: Identify user behavior patterns under specific circumstances, such as differences in work and rest schedules between weekends and weekdays and special activities on holidays, to form a dynamic behavioral model of users; S303: Based on static and dynamic behavioral data, build a comprehensive user behavior model and continuously learn and optimize the user behavior model; S4: Perform behavior prediction through the user behavior prediction module, which includes the following steps: S401: By analyzing historical data and the current state, it uses Bayesian networks, hidden Markov models, or deep learning models to predict user behavior. S402: Calculate the probability distribution of the user's next possible action, and determine the priority of different operations. The user behavior model calculates the probability distribution of future actions and determines the most likely action based on the output probability distribution. S403: Determine the scheduling strategy of the scheduling system based on the probability distribution, and collect user feedback after execution to adjust and optimize the prediction model; S5: The automated scheduling module will execute corresponding equipment control commands based on the prediction results. The automated scheduling module can also schedule equipment in advance according to the user's daily habits to meet the user's expected needs. S6: The feedback and self-learning module adjusts the behavior model and optimizes the prediction algorithm based on the difference between the user's actual behavior and the predicted behavior. The feedback and self-learning module also uses reinforcement learning to schedule the system to continuously learn itself during the user's usage.