An intelligent lighting remote control system with scene linkage management

Abstract

The present invention discloses an intelligent lighting remote control system for scene linkage management, comprising a scene linkage management module, a cloud server, a scene monitoring module and a lighting remote control module; the present invention adopts voiceprint recognition to perform identity authentication, thereby improving the security and reliability of identity authentication, and ensuring the security of user data and privacy through the setting of identity authentication and authority levels; through an intelligent prediction model and a proportional integral differential control algorithm, intelligent adjustment of lighting parameters is achieved, including automatic adjustment of parameters such as brightness, color, and switch status, providing a personalized lighting experience, and realizing intelligent lighting control according to environmental data and equipment status data to meet the lighting needs of users in different scenarios. Users can perform remote control through a cloud server, and remote adjustment of lighting equipment can be achieved without on-site operation, thereby improving user convenience and flexibility, and enhancing user experience and operational convenience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent lighting remote control system for scene linkage management. Background Art

[0002] With the improvement of the quality of life, smart home has gradually been integrated into people's daily life as a new lifestyle. Through the Internet of Things technology, smart home connects a variety of smart devices in the home to realize functions such as lighting control, indoor and outdoor remote control, burglar alarm, and environmental monitoring, bringing convenience and intelligent experience to users. Smart home not only meets the daily functions of traditional living, but also provides all-round information interaction for user convenience.

[0003] However, the limitations of traditional lighting systems have led to some problems, such as cumbersome manual operation and low efficiency. These problems are usually caused by the lack of intelligence, automation and remote control functions in traditional lighting systems. Traditional systems cannot intelligently adjust lighting parameters according to environmental changes and user needs. The lack of intelligence and remote control functions limits the development of energy utilization, user experience and lighting control. At the same time, during the operation of smart home systems, a large amount of personal information and family life data needs to be collected and processed, and there is a risk of privacy leakage. Therefore, improving the system's intelligence level, user experience and security is the key direction of the current development of lighting systems. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent lighting remote control system with scene linkage management, which combines functions such as identity authentication, intelligent prediction, and remote control to provide users with an intelligent and convenient lighting experience, solves the problems of cumbersome operation and low efficiency in traditional lighting systems, and at the same time improves the system's intelligence level, user experience, and security.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides an intelligent lighting remote control system for scene linkage management, including a scene linkage management module, a cloud server, a scene monitoring module and a lighting remote control module.

[0007] The scene linkage management module obtains the scene linkage management authority by sending a request to the cloud server and performing identity authentication, remotely sets the scene linkage management, and manages the linkage control information of different scenes;

[0008] The cloud server is used to receive the linkage control information request from the scene linkage management module and transmit the control command to the lighting remote control module;

[0009] The scene monitoring module is used to monitor the device status and environmental data in the scene to achieve intelligent lighting control and improve the safety and efficiency of the system;

[0010] Among them, during the monitoring process, the equipment status data in the same scene or different scenes are collected, and an intelligent prediction model is established for intelligent prediction;

[0011] The lighting remote control module receives control instructions from the cloud server and remotely controls and adjusts the status of the lighting equipment according to the set scene.

[0012] Furthermore, the identity verification process includes:

[0013] S11, the user enters his / her identity, and a voice sample of the user is recorded by a sound collection device;

[0014] S12. The collected voice samples are subjected to voiceprint feature extraction and analysis to extract the user's unique voiceprint features, such as pitch, timbre, voice rhythm and other biometric features;

[0015] S13, establishing a voiceprint feature model of the user according to the extracted voiceprint features, associating the voiceprint features of the user with the identity, and storing the model in the cloud server;

[0016] S14. When the user authenticates his / her identity, a voice sample is recorded again, and the sound data input by the user is compared with the established voiceprint feature model for matching verification. When the verification is passed, the permission for scene linkage management is granted.

[0017] Furthermore, the permissions for scene linkage management include a first permission level and a second permission level. The first permission level is used to switch between different scene modes, and to adjust parameters of existing scene modes or add new scene modes. The second permission level is used to switch between different scene modes.

[0018] Furthermore, the scene linkage management module includes a scene database and a scene linkage unit.

[0019] The scenario database is used to store device association information in different scenarios;

[0020] The scene linkage unit is used to link devices by setting a linkage time according to a remote instruction issued by a user after obtaining the first permission.

[0021] Furthermore, the cloud server includes a matching storage unit for storing the voiceprint feature model and the result of user identity authentication. When the authentication is passed, scene linkage management operations are performed according to the authority level.

[0022] Furthermore, the scene monitoring module includes a data acquisition unit, a data processing and analysis unit and an intelligent prediction model unit.

[0023] The data acquisition unit is used to collect device status data and environmental data in real time under the scene, and transmit them to the data processing and analysis unit;

[0024] The data processing and analysis unit processes, cleans and analyzes the collected data, extracts features and information as input of the intelligent prediction model, and establishes the intelligent prediction model;

[0025] The intelligent prediction model unit is used to predict the device status and environmental data in the scene, and implement intelligent lighting control strategies based on the prediction results.

[0026] Furthermore, the intelligent prediction model includes device status prediction and lighting control prediction, and the specific construction process includes:

[0027] Collect device status data and environmental data in different time periods under the same scenario, and extract key features of the device from the acquired data;

[0028] The extracted features are adaptively normalized, and the standardized parameters are dynamically adjusted according to the distribution of the feature data to adapt to the variation range and distribution of different features. The specific feature value after adaptive normalization is expressed as: X=(x-μ) / σ, where x represents the original feature value, μ represents the dynamic mean of the feature, and σ represents the dynamic standard deviation of the feature;

[0029] The equipment status data and environmental data of different time periods are integrated into a time series data set, which is divided into a training set and a test set in chronological order. The training set is used to train the equipment status prediction and lighting control prediction models, and the model is fitted according to the features in the time series data set.

[0030] Among them, the fitting is used to predict the future equipment status and lighting control situation, and the ARIMA model is used for fitting, which specifically includes:

[0031] X_t=c+Σ(φ_i*X_(ti))+Σ(θ_j*ε_(tj))+ε_t;

[0032] Among them, X_t is the predicted value at time point t, c is the constant term, φ_i is the autoregressive model parameter, θ_j is the moving average model parameter, ε_t is the white noise error term, and the calculated parameters (c, φ_i, θ_j) are used to represent the predicted value of the time series.

[0033] Furthermore, when collecting and extracting data features, we collect device status data and environmental data in different scenarios.

[0034] Then, the data is marked with scenes to distinguish data in different scenes;

[0035] Extract the features of device status data and environmental data based on data in different scenarios;

[0036] After feature extraction, the features extracted from different scenarios are associated and combined through data analysis and feature engineering methods;

[0037] Specifically, it includes: merging the values ​​of the same feature in different scenarios to create a new feature column, splicing the data in different scenarios into a new feature sequence in chronological order, and performing difference calculation on the merged feature sequence to obtain the difference between adjacent time points.

[0038] Assuming the merged feature sequence is Y=[y_1,y_2,y_3,...,y_n], the difference sequence D_Y between adjacent time points is expressed as:

[0039] D_Y=[y_2-y_1,y_3-y_2,y_4-y_3,...,y_n-y_(n-1)];

[0040] The calculated difference sequence D_Y reflects the change of the characteristic value between adjacent time points, and then the calculated characteristic difference sequence D_Y is applied to the adaptive normalization processing in the same scenario.

[0041] Furthermore, the predicted values ​​are converted into device states and lighting control parameters in scene applications, and the output values ​​of parameter control are calculated using the proportional-integral-differential control algorithm to perform intelligent adjustment of device states and lighting parameters;

[0042] The proportional-integral-derivative control algorithm calculates the control output value through the proportional term, integral term and differential term. The specific calculation formula is:

[0043] Among them, the proportional term is: P=Kp*e(t), where Kp is the proportional gain and e(t) is the error at the current moment. The output is adjusted according to the current error to quickly respond to changes in the system;

[0044] Integral term: I=Ki*∫e(t)dt, where Ki is the integral gain and e(t) is the error at the current moment. The integral term is used to eliminate the steady-state error of the system and integrate the current and historical errors.

[0045] Differential term: D=Kd*de(t) / dt, where Kd is the differential gain, de(t) / dt is the rate of change of the error. The differential term is used to predict the trend of the error change and prevent overshoot and oscillation.

[0046] Output value: Output=P+I+D.

[0047] Furthermore, the implementation process of the intelligent lighting remote control system for scene linkage management includes the following steps:

[0048] S1: The user obtains permission through identity authentication, remotely sets the scene, and manages the linkage control information of different scenes;

[0049] S2: After the identity verification is passed, the devices are associated with each other or switched to different scene modes according to the obtained permission level;

[0050] When the first permission level is obtained, different scene modes are switched, parameters of existing scene modes are adjusted, and new scene modes are added. When the second permission level is obtained, different scene modes are switched;

[0051] S3: When the user passes the identity authentication and obtains the first level of authority, the user can associate the device by issuing a remote command and setting the association time;

[0052] S4: In the scenario mode, by monitoring the device status data and environmental data in the scenario, an intelligent prediction model is established to predict the device parameters and environmental parameters;

[0053] Among them, the equipment status data and environmental data of different time periods in the same scenario are collected, and then the key features are extracted, and the feature data are adaptively standardized. After the features in the same or different scenarios are adaptively standardized, the feature data are trained, and the model is fitted according to the features in the time series data set to obtain the predicted value, which is used to evaluate the parameters of the equipment status and environmental data;

[0054] S5: According to the prediction results, the proportional integral differential control algorithm is used to calculate the output value of the parameter control, and the device status and lighting parameters are adjusted intelligently to stabilize the parameters of the device in the desired state;

[0055] S6: Receive remote instructions, remotely adjust the status of lighting equipment according to the set scene, and realize remote lighting control.

[0056] The beneficial effects of the present invention are:

[0057] The voiceprint feature is used for identity authentication to improve the security and reliability of identity authentication, reduce the risk of identity fraud, and ensure the security of user data and privacy through the setting of identity authentication and permission levels, reduce the risk of privacy leakage, improve the security of the system and user trust, and solve the risk of privacy leakage in traditional systems;

[0058] Through intelligent prediction models and proportional-integral-differential control algorithms, intelligent adjustment of lighting parameters is achieved, including automatic adjustment of parameters such as brightness, color, and switch status, providing a personalized lighting experience, and realizing intelligent lighting control based on environmental data and equipment status data to meet users' lighting needs in different scenarios; users can remotely control through cloud servers and remotely adjust lighting equipment without on-site operation, which improves user convenience and flexibility, realizes remote management and adjustment of lighting equipment status anytime and anywhere, and improves user experience and operational convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0060] Figure 1 A schematic diagram of the structure of an intelligent lighting remote control system for scene linkage management provided in Example 1 of the present application;

[0061] Figure 2 A flowchart of identity authentication steps for a smart lighting remote control system with scene linkage management provided in Example 1 of the present application;

[0062] Figure 3 A flowchart of the steps for constructing an intelligent prediction model for an intelligent lighting remote control system with scene linkage management provided in Example 1 of the present application;

[0063] Figure 4 A flow chart of the implementation process of an intelligent lighting remote control system with scene linkage management provided in Example 1 of the present application. DETAILED DESCRIPTION

[0064] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0065] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0066] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0067] Example 1

[0068] See also Figure 1-Figure 4 This embodiment provides an intelligent lighting remote control system with scene linkage management, which combines identity authentication, intelligent prediction, remote control and other functions to provide users with an intelligent and convenient lighting experience, solves the problems of cumbersome operation and low efficiency in traditional lighting systems, and at the same time improves the system's intelligence level, user experience and security.

[0069] The present invention provides an intelligent lighting remote control system for scene linkage management, including a scene linkage management module, a cloud server, a scene monitoring module and a lighting remote control module.

[0070] The scene linkage management module obtains the scene linkage management authority by sending a request to the cloud server and performing identity authentication, remotely sets the scene linkage management, and manages the linkage control information of different scenes;

[0071] The identity verification process includes:

[0072] S11. When performing identity verification, the user first enters his / her identity, and a voice sample of the user is recorded by a sound collection device;

[0073] S12. The collected voice samples are subjected to voiceprint feature extraction and analysis to extract the user's unique voiceprint features, such as pitch, timbre, voice rhythm and other biometric features;

[0074] S13, establishing a voiceprint feature model of the user according to the extracted voiceprint features, associating the voiceprint features of the user with the identity, and storing the model in the cloud server;

[0075] Specifically, the user's voiceprint feature model is dynamic and is used to monitor the user's voice state changes in real time, such as emotions, speaking speed, etc., and adjust the model parameters according to the voiceprint features in different states. By continuously collecting the user's voice data, it can be adjusted and updated according to the user's actual situation to adapt to the voiceprint features in different states.

[0076] S14. When the user authenticates his / her identity, a voice sample is recorded again, and the sound data input by the user is compared with the established voiceprint feature model for matching verification. When the verification is passed, the permission for scene linkage management is granted.

[0077] Specifically, the permission of scene linkage management controls the scope of operation permissions of different users in scene linkage management through different permission levels, ensures the security of users' personal information and data, and reduces the risk of privacy leakage. The permission levels include the first permission level and the second permission level. The first permission level is set as the administrator permission, which can switch different scene modes, and can also adjust the parameters of existing scene modes or add new scene modes. Specifically, the administrator can switch between different scenes, set different lighting modes in different time periods or different usage scenarios, adjust the parameters of existing scene modes, including adjusting the brightness, color, color temperature and other parameters of the light, add new scene modes, and set new lighting scenes according to needs to meet different usage needs;

[0078] Set the second permission level to normal permission, and you can switch between different scene modes. Specifically, you can switch between existing scene modes and select a lighting mode that suits your current needs.

[0079] By setting permission levels, administrators can have more operating permissions, including more in-depth settings and adjustments to the system, while ordinary users have more basic operating permissions and can make simple adjustments and switches in existing scene modes. This can ensure the security of the system and avoid unauthorized operations, while ensuring that users at different permission levels can easily control lighting and switch scenes.

[0080] Furthermore, the scene linkage management module includes a scene database and a scene linkage unit.

[0081] The scenario database is used to store device association information in different scenarios;

[0082] The scene linkage unit is used to link devices by setting a linkage time according to a remote instruction issued by a user after obtaining the first permission.

[0083] The cloud server is used to receive the linkage control information request from the scene linkage management module and transmit the control command to the lighting remote control module;

[0084] Among them, it includes a matching storage unit for storing the voiceprint feature model and the results of user identity authentication. When the verification is passed, the scene linkage management operations are performed according to the authority level, including switching between different scenes or associating between devices.

[0085] The scene monitoring module is used to monitor the device status and environmental data in the scene to achieve intelligent lighting control and improve the safety and efficiency of the system;

[0086] During the monitoring process, the equipment status data in the same scenario or different scenarios are collected, and intelligent predictions are performed through intelligent prediction models.

[0087] Furthermore, the scene monitoring module includes a data acquisition unit, a data processing and analysis unit and an intelligent prediction model unit.

[0088] The data acquisition unit is used to collect device status data and environmental data in real time under the scene, and transmit it to the next step of data processing and analysis unit;

[0089] The data processing and analysis unit processes, cleans and analyzes the collected data, extracts useful features and information as input of the intelligent prediction model, and establishes the intelligent prediction model;

[0090] The intelligent prediction model unit is used to predict the device status and environmental data in the scene, and implement intelligent lighting control strategies based on the prediction results.

[0091] Furthermore, the intelligent prediction model includes device status prediction and lighting control prediction, and the specific construction process includes:

[0092] S21. Collect device status data at different time periods in the same scene, including information such as brightness, color, switch status, etc.; and collect environmental data at different time periods in the same scene, including light intensity, temperature, humidity, etc.;

[0093] Among them, the key features of the equipment are extracted from the acquired data, including the change trend of brightness, color distribution, the frequency of switch status and the change of equipment operation parameters. The characteristics of environmental data include the change trend of light intensity, the mean and volatility of temperature, the change of humidity, etc.

[0094] S22, performing adaptive normalization processing on the extracted features, dynamically adjusting normalization parameters according to the distribution of feature data, to adapt to the variation range and distribution of different features, specifically:

[0095] X=(x-μ) / σ, where X represents the eigenvalue after adaptive normalization, x represents the original eigenvalue, μ represents the dynamic mean of the feature, and σ represents the dynamic standard deviation of the feature.

[0096] Specifically, the equipment status data and environmental data of different time periods are integrated into a time series data set, which is divided into a training set and a test set in chronological order. The earlier data is retained as the training set for training the model, and the later data is retained as the test set. It is ensured that the time point in the test set is after the training set, which is used to evaluate the model performance.

[0097] S23. Based on the processed feature data, establish models for equipment status prediction and lighting control prediction, use training sets to train the equipment status prediction and lighting control prediction models, and fit the models according to the features in the time series data set; through fitting, use it to predict future equipment status and lighting control conditions, infer future development trends based on historical data and feature information, and help make reasonable predictions and decisions.

[0098] Fitting is done through the ARIMA model, including:

[0099] X_t=c+Σ(φ_i*X_(ti))+Σ(θ_j*ε_(tj))+ε_t;

[0100] Among them, X_t is the predicted value at time point t, c is the constant term, φ_i is the autoregression (AR) model parameter, θ_j is the moving average (MA) model parameter, ε_t is the white noise error term, and the calculated parameters (c, φ_i, θ_j) are used to represent the predicted value of the time series.

[0101] By collecting lighting equipment status and environmental data, extracting key features and performing adaptive standardization processing, a device status and lighting control prediction model is established. This process includes data integration, feature extraction, model training and fitting using the ARIMA model. It aims to predict future device status and lighting control conditions, and provide decision support for formulating reasonable intelligent lighting control strategies to improve the intelligence, efficiency and user experience of the system.

[0102] Furthermore, when collecting and extracting data features, we collect device status data and environmental data in different scenarios.

[0103] Then, the data is scene-tagged, that is, scene labels or scene categories are added to the data to distinguish data in different scenes. For example, scene tags can be added for different rooms, different time periods, or different usage scenarios.

[0104] Based on the data in different scenarios, extract the features related to the device status data and environmental data, extract the lighting equipment features such as brightness, color, switch status, and environmental features such as light intensity, temperature, and humidity;

[0105] After feature extraction, the features extracted from different scenarios are associated and combined through data analysis and feature engineering methods;

[0106] This includes merging the values ​​of the same feature in different scenarios to create a new feature column, splicing the data in different scenarios into a new feature sequence in chronological order, and performing difference calculation on the merged feature sequence to obtain the difference between adjacent time points.

[0107] Assuming the merged feature sequence is Y=[y_1,y_2,y_3,...,y_n], the difference sequence D_Y between adjacent time points is expressed as:

[0108] D_Y=[y_2-y_1,y_3-y_2,y_4-y_3,...,y_n-y_(n-1)]

[0109] The calculated difference sequence D_Y reflects the changes of the characteristic values ​​between adjacent time points, which helps to capture the changing trend and volatility of the characteristic values. The calculated characteristic difference sequence D_Y is applied to adaptive standardization processing in the same scenario, and then an intelligent prediction model is established.

[0110] By collecting equipment status data and environmental data in different scenarios and applying them to the intelligent prediction model established in the same scenario, parameter predictions can be performed in different scenarios. By using the model established by cross-scenario data, intelligent prediction and control can be achieved in different scenarios, thereby improving the intelligence level of the system and user experience.

[0111] Furthermore, the predicted values ​​are converted into device states and lighting control parameters in scene applications. Based on the predicted values, the brightness, color, switch state of the device, and parameters such as the brightness and color temperature of the light are determined. Based on the predicted device states and lighting control parameters, the device states and lighting parameters are adjusted to realize intelligent lighting control strategies.

[0112] According to the prediction results, the brightness, color, switch status of the device, as well as the brightness, color temperature and other parameters of the light are obtained;

[0113] According to the prediction results, the proportional-integral-differential control algorithm is used to calculate the output value of the parameter control, realize the intelligent adjustment of the equipment status and lighting parameters, and stabilize the parameters of the equipment in the desired state;

[0114] Among them, the proportional-integral-differential control algorithm calculates the control output value through the proportional term, integral term and differential term to stabilize the parameters in the desired state. The specific calculation formula is:

[0115] Among them, the proportional term is: P=Kp*e(t), where Kp is the proportional gain and e(t) is the error at the current moment. The output is adjusted according to the current error to quickly respond to changes in the system;

[0116] Integral term: I=Ki*∫e(t)dt, where Ki is the integral gain and e(t) is the error at the current moment. The integral term is used to eliminate the steady-state error of the system and integrate the current and historical errors.

[0117] Differential term: D=Kd*de(t) / dt, where Kd is the differential gain, de(t) / dt is the rate of change of the error. The differential term is used to predict the trend of the error change and prevent overshoot and oscillation.

[0118] Output value: Output=P+I+D.

[0119] Automatic adjustment is achieved through an intelligent control system to improve lighting effects and user experience. The formulated control strategy is applied to actual scenarios. Intelligent lighting control is achieved by controlling equipment and lighting parameters. It can not only automatically adjust brightness, color temperature and other parameters according to the environment and user needs to provide a comfortable lighting environment, but also save energy and extend equipment life. At the same time, it improves user comfort and work efficiency. The automatic adjustment function in the same or different scenarios makes the system more intelligent and flexible, bringing users a smarter and more convenient lighting experience.

[0120] The lighting remote control module receives control instructions from the cloud server, remotely adjusts the state of the lighting equipment according to the set scene, and realizes remote lighting control.

[0121] Specifically, remote lighting control includes: the user sends a remote control request to the cloud server; after the cloud server verifies the user's identity, it generates corresponding control instructions based on the user's instructions; the generated control instructions are transmitted to the lighting remote control module through the cloud server; after receiving the control instructions, the lighting remote control module adjusts the brightness, color, switch status, etc. of the lighting equipment to achieve remote lighting control.

[0122] Furthermore, a process for implementing a scene linkage management intelligent lighting remote control system includes the following steps:

[0123] S1: The user obtains permission through identity authentication, remotely sets the scene, and manages the linkage control information of different scenes;

[0124] S2: After the identity verification is passed, the devices are associated with each other or switched to different scene modes according to the obtained permission level;

[0125] When the first permission level is obtained, different scene modes can be switched, parameters of existing scene modes can be adjusted, and new scene modes can be added. When the second permission level is obtained, different scene modes can be switched;

[0126] S3: When the user passes the identity authentication and obtains the first level of authority, the user can associate the device by issuing a remote command and setting the association time;

[0127] S4: In the scenario mode, by monitoring the device status data and environmental data in the scenario, an intelligent prediction model is established to predict the device parameters and environmental parameters;

[0128] Among them, the equipment status data and environmental data in different time periods under the same scenario are collected, and then the key features are extracted and the feature data is adaptively standardized;

[0129] Or collect device status data and environmental data in different scenarios, mark the data for different scenarios, distinguish the data in different scenarios, extract key features, associate and combine the features extracted in different scenarios, splice the data in different scenarios into a new feature sequence in chronological order, calculate the difference between the merged feature sequences, obtain the difference between adjacent time points, and then apply the calculated difference to the adaptive standardization processing in the same scenario;

[0130] After adaptively normalizing the features in the same or different scenarios, the feature data is trained, and the model is fitted according to the features in the time series data set to obtain the predicted value, which is used to evaluate the parameters of the equipment status and environmental data;

[0131] S5: According to the prediction results, the proportional integral differential control algorithm is used to calculate the output value of the parameter control, and the device status and lighting parameters are adjusted intelligently to stabilize the parameters of the device in the desired state;

[0132] S6: Receive remote instructions, remotely adjust the status of lighting equipment according to the set scene, and realize remote lighting control.

[0133] In this embodiment, through the identity authentication function, the smart home system can ensure that only authorized users can operate the system, thereby improving the security of the system. The intelligent prediction function can predict future lighting needs based on device status data and environmental data, realize intelligent lighting adjustment, and improve the intelligence level of the system. The remote control function enables users to remotely control lights through mobile phones or other devices anytime and anywhere, thereby improving user convenience and flexibility; enabling the smart home system to intelligently adjust lights according to user preferences and needs, providing personalized lighting experience, while solving the problems of cumbersome operation and low efficiency in traditional lighting systems. Users can easily realize intelligent control of lights through the smart home system, improving user experience and comfort. At the same time, the system's intelligent prediction function and remote control function improve the intelligence level of the system, providing users with a more intelligent and convenient lighting experience, while ensuring the security of the system and the privacy protection of user data.

[0134] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent lighting remote control system with scene linkage management, characterized in that: Including scene linkage management module, cloud server, scene monitoring module and lighting remote control module, The scene linkage management module obtains the permission for scene linkage management by sending a request to the cloud server and using voiceprint features for identity authentication, remotely sets the scene linkage management, and manages the linkage control information of different scenes; The permission for scene linkage management includes a first permission level and a second permission level. The first permission level is used to switch between different scene modes, adjust parameters of existing scene modes or add new scene modes, and the second permission level is used to switch between different scene modes. The cloud server is used to receive the linkage control information request from the scene linkage management module and transmit the control command to the lighting remote control module; The scene monitoring module is used to monitor the device status and environmental data in the scene; In the monitoring process, the device status data in the same scene or different scenes are collected, and an intelligent prediction model is established for intelligent prediction; the intelligent prediction model includes device status prediction and lighting control prediction, and the specific construction process includes: Collect device status data and environmental data in different time periods under the same scenario, and extract key features of the device from the acquired data; Adaptively normalize the extracted features and dynamically adjust the normalization parameters according to the distribution of feature data to adapt to the range and distribution of different features; The equipment status data and environmental data of different time periods are integrated into a time series data set, which is divided into a training set and a test set in chronological order. The training set is used to train the equipment status prediction and lighting control prediction models, and the model is fitted according to the features in the time series data set. Among them, the ARIMA model is used to predict the future equipment status and lighting control conditions; The lighting remote control module receives control instructions from the cloud server and remotely controls and adjusts the status of the lighting equipment according to the set scene; The implementation process of the remote control system includes the following steps: S1. The user obtains permission through identity authentication, remotely sets the scene, and manages the linkage control information of different scenes; S2. After the identity verification is passed, the devices are associated with each other or switched to different scene modes according to the obtained permission level. When the first permission level is obtained, different scene modes are switched, parameters of existing scene modes are adjusted, and new scene modes are added. When the second permission level is obtained, different scene modes are switched; S3. When the user passes the identity authentication and obtains the first level of authority, the user issues a remote command and associates the device by setting the association time; S4. In the scenario mode, by monitoring the device status data and environmental data in the scenario, an intelligent prediction model is established to predict the device parameters and environmental parameters. Among them, the equipment status data and environmental data of different time periods in the same scenario are collected, and then the key features are extracted, and the feature data are adaptively standardized. After the features in the same or different scenarios are adaptively standardized, the feature data are trained, and the model is fitted according to the features in the time series data set to obtain the predicted value, which is used to evaluate the parameters of the equipment status and environmental data; S5. According to the prediction results, the predicted values ​​are converted into the device status and lighting control parameters in the scene application, and the output value of the parameter control is calculated using the proportional integral differential control algorithm to perform intelligent adjustment of the device status and lighting parameters to stabilize the parameters of the device in the desired state; S6. Receive remote instructions, remotely adjust the status of lighting equipment according to the set scene, and realize remote lighting control.

2. According to claim 1, the intelligent lighting remote control system for scene linkage management is characterized in that: The process of using voiceprint features for identity authentication includes: The user enters his / her identity and a voice sample of the user is recorded by a sound collection device; The collected voice samples are subjected to voiceprint feature extraction and analysis to extract the user's unique voiceprint features; A user's voiceprint feature model is established based on the extracted voiceprint features, the user's voiceprint features are associated with the identity, and stored in the cloud server; When the user authenticates their identity, a voice sample is recorded again, and the sound data entered by the user is compared with the established voiceprint feature model for matching and verification. When the verification is passed, the permission for scene linkage management is granted.

3. According to claim 1, the intelligent lighting remote control system for scene linkage management is characterized in that: The scene linkage management module includes a scene database and a scene linkage unit. The scenario database is used to store device association information in different scenarios; The scene linkage unit is used to link devices by setting a linkage time according to a remote instruction issued by a user after obtaining the first permission.

4. The intelligent lighting remote control system for scene linkage management according to claim 1 is characterized in that: The cloud server includes a matching storage unit for storing the voiceprint feature model and the result of user identity authentication. When the authentication is passed, the scene linkage management operation is performed according to the authority level.

5. According to claim 1, the intelligent lighting remote control system for scene linkage management is characterized in that: The scene monitoring module includes a data acquisition unit, a data processing and analysis unit, and an intelligent prediction model unit. The data acquisition unit is used to collect device status data and environmental data in real time under the scene, and transmit them to the data processing and analysis unit; The data processing and analysis unit processes, cleans and analyzes the collected data, extracts features and information as input of the intelligent prediction model, and establishes the intelligent prediction model; The intelligent prediction model unit is used to predict the device status and environmental data in the scene, and implement intelligent lighting control strategies based on the prediction results.

6. The intelligent lighting remote control system for scene linkage management according to claim 1 is characterized in that The adaptively normalized eigenvalue is expressed as: X=(x-μ) / σ, where x represents the original eigenvalue, μ represents the dynamic mean of the feature, and σ represents the dynamic standard deviation of the feature; Fitting is done through the ARIMA model, including: X_t=c+Σ(φ_i*X_(ti))+Σ(θ_j*ε_(tj))+ε_t; Among them, X_t is the predicted value at time point t, c is the constant term, φ_i is the autoregressive model parameter, θ_j is the moving average model parameter, ε_t is the white noise error term, and the calculated parameters (c, φ_i, θ_j) are used to represent the predicted value of the time series.

7. The intelligent lighting remote control system for scene linkage management according to claim 5 is characterized in that: When collecting and extracting data features, collect device status data and environmental data in different scenarios. Then, the data is marked with scenes to distinguish data in different scenes; Extract the features of device status data and environmental data based on data in different scenarios; After feature extraction, the features extracted from different scenarios are associated and combined through data analysis and feature engineering methods; Specifically, it includes: merging the values ​​of the same feature in different scenarios to create a new feature column, splicing the data in different scenarios into a new feature sequence in chronological order, and performing difference calculation on the merged feature sequence to obtain the difference between adjacent time points. Assuming the merged feature sequence is Y=[y_1,y_2,y_3,...,y_n], the difference sequence D_Y between adjacent time points is expressed as: D_Y=[y_2-y_1,y_3-y_2,y_4-y_3,...,y_n-y_(n-1)]; The calculated difference sequence D_Y reflects the change of the characteristic value between adjacent time points, and then the calculated characteristic difference sequence D_Y is applied to the adaptive normalization processing in the same scenario.

8. The intelligent lighting remote control system with scene linkage management according to claim 1 is characterized in that: The proportional-integral-differential control algorithm calculates the control output value through the proportional term, the integral term and the differential term. The specific calculation formula is: Among them, the proportional term is: P=Kp*e(t), where Kp is the proportional gain and e(t) is the error at the current moment. The output is adjusted according to the current error to quickly respond to changes in the system; Integral term: I=Ki*∫e(t)dt, where Ki is the integral gain and e(t) is the error at the current moment. The integral term is used to eliminate the steady-state error of the system and integrate the current and historical errors. Differential term: D=Kd*de(t) / dt, where Kd is the differential gain, de(t) / dt is the rate of change of the error. The differential term is used to predict the trend of the error change and prevent overshoot and oscillation. Output value: Output=P+I+D.

Images