Intelligent control method and system for household LED light strip

Abstract

The present application discloses an intelligent control method and system for household LED light strips, which uses the time series of ambient light intensity values ​​collected by a light intensity sensor, and uses artificial intelligence-based data processing and analysis technology to perform local time series feature analysis and correlation of the ambient light intensity values, so as to intelligently obtain control instructions for adjusting the luminous power of the household LED light strip to the recommended luminous power value based on the time series significant correlation characteristics of the ambient light intensity values ​​in the full time domain. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and the lighting effect can be more adapted to the current environment, improving the comfort and practicality of lighting, and improving the intelligent level of control.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to an intelligent control method and system for a household LED light strip. Background Art

[0002] With the improvement of living standards, consumers have more diversified demands for home lighting. Home LED light strips are a popular lighting solution. They are composed of a series of small LED (light-emitting diode) lamp beads connected together to form a bendable strip structure. They can be widely used in home interior decoration, such as TV wall background, cabinet bottom, stair lighting, etc., and have become a popular choice for modern home lighting and decoration.

[0003] However, some current LED light strip control systems do not have environmental sensing capabilities and are unable to automatically adjust brightness based on user habits or changes in ambient light in the room, resulting in a low level of intelligent lighting control, which in turn causes energy waste and affects user experience.

[0004] Therefore, an optimized intelligent control method for household LED light strips is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent control method and system for a household LED light strip, which uses the time series of ambient light intensity values ​​collected by a light intensity sensor, and adopts artificial intelligence-based data processing and analysis technology to perform local timing feature analysis and correlation of the ambient light intensity values, so as to intelligently obtain control instructions for adjusting the luminous power of the household LED light strip to the recommended luminous power value based on the significant timing correlation characteristics of the ambient light intensity values ​​in the entire time domain. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be made more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the level of intelligent control can be improved.

[0006] According to one aspect of the present application, there is provided an intelligent control method for a household LED light strip, comprising:

[0007] Get the time series of ambient light intensity values ​​collected by the light intensity sensor;

[0008] Sequence segmentation is performed on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values;

[0009] Performing ambient light intensity time series correlation pattern feature extraction on the set of local time series of the ambient light intensity values ​​to obtain a set of ambient light intensity local time series implicit correlation feature vectors;

[0010] The set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature;

[0011] Based on the temporal correlation saliency representation feature of the full-time-domain ambient light intensity, a control instruction is obtained.

[0012] According to another aspect of the present application, an intelligent control system for a household LED light strip is provided, comprising:

[0013] An ambient light intensity acquisition module is used to obtain a time series of ambient light intensity values ​​acquired by a light intensity sensor;

[0014] An ambient light intensity local time extraction module, used for performing sequence segmentation on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values;

[0015] A local time series association module is used to extract the time series association pattern features of the ambient light intensity from the set of local time series of the ambient light intensity values ​​to obtain a set of local time series implicit association feature vectors of the ambient light intensity;

[0016] A light intensity full-time domain extraction module is used to obtain a full-time domain ambient light intensity temporal correlation saliency representation vector as a full-time domain ambient light intensity temporal correlation saliency representation feature by passing the set of the ambient light intensity local temporal implicit correlation feature vectors through a self-supervised feature sequence saliency enhancement module;

[0017] The control instruction generation module is used to obtain the control instruction based on the temporal correlation saliency representation feature of the full-time-domain ambient light intensity.

[0018] Compared with the prior art, the present application provides an intelligent control method and system for a household LED light strip, which uses the time series of ambient light intensity values ​​collected by the light intensity sensor and uses artificial intelligence-based data processing and analysis technology to perform local time series feature analysis and correlation of the ambient light intensity values, so as to intelligently obtain control instructions for adjusting the luminous power of the household LED light strip to the recommended luminous power value based on the time series significant correlation characteristics of the ambient light intensity values ​​in the full time domain. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the intelligent level of control can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 This is a flow chart of an intelligent control method for a household LED light strip according to an embodiment of the present application.

[0021] Figure 2 Schematic diagram of the architecture of the intelligent control method for household LED light strips according to an embodiment of the present application.

[0022] Figure 3 The present invention is a flowchart of a method for intelligently controlling a household LED light strip according to an embodiment of the present application, in which a set of local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence significance enhancement module to obtain a full-time-domain ambient light intensity temporal correlation significant representation vector as a full-time-domain ambient light intensity temporal correlation significant representation feature.

[0023] Figure 4 A flowchart for calculating the temporal semantic association between each local temporal implicit association feature vector of ambient light intensity in the set of local temporal implicit association feature vectors of ambient light intensity and the center of the ambient light intensity sequence distribution cluster in the intelligent control method for household LED light strips according to an embodiment of the present application to obtain a sequence of temporal semantic associations of ambient light intensity.

[0024] Figure 5 4 is a block diagram of an intelligent control system for a household LED light strip according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0028] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0029] With the improvement of living standards, consumers have more diversified demands for home lighting. Home LED light strips are a popular lighting solution. They are composed of a series of small LED (light-emitting diode) lamp beads connected together to form a bendable strip structure. They can be widely used in home interior decoration, such as TV wall background, cabinet bottom, stair lighting, etc., and have become a popular choice for modern home lighting and decoration.

[0030] However, some current LED light strip control systems do not have environmental sensing capabilities and are unable to automatically adjust brightness based on user habits or changes in ambient light in the room, resulting in a low level of intelligent lighting control, which in turn causes energy waste and affects user experience.

[0031] Therefore, in response to the above technical problems, the technical concept of the present application is to use the time series of ambient light intensity values ​​collected by the light intensity sensor, and use artificial intelligence-based data processing and analysis technology to perform local time series feature analysis and correlation of the ambient light intensity values, so as to intelligently obtain the control instructions for adjusting the luminous power of the household LED light strip to the recommended luminous power value based on the time series significant correlation characteristics of the ambient light intensity values ​​in the full time domain. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the intelligent level of control can be improved.

[0032] Figure 1 This is a flow chart of an intelligent control method for a household LED light strip according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of the intelligent control method for household LED light strips according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the intelligent control method of the household LED light strip includes: S110, obtaining the time series of ambient light intensity values ​​collected by the light intensity sensor; S120, performing sequence segmentation on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values; S130, performing ambient light intensity temporal association pattern feature extraction on the set of local time series of the ambient light intensity values ​​to obtain a set of ambient light intensity local temporal implicit association feature vectors; S140, passing the set of ambient light intensity local temporal implicit association feature vectors through a self-supervised feature sequence significance enhancement module to obtain a full-time domain ambient light intensity temporal association significant representation vector as a full-time domain ambient light intensity temporal association significant representation feature; and, S150, obtaining a control instruction based on the full-time domain ambient light intensity temporal association significant representation feature.

[0033] In step S110, a time series of ambient light intensity values ​​collected by a light intensity sensor is obtained. It should be understood that the ambient light intensity refers to the intensity or brightness level of light in a specific environment, which is usually measured in illuminance (usually in lux, lx), indicating the luminous flux received per unit area. Based on this, in order to adjust the brightness of artificial lighting to ensure that energy consumption is reduced when natural light is sufficient, and to improve human comfort and work efficiency, in the technical solution of the present application, a time series of ambient light intensity values ​​collected by a light intensity sensor is obtained.

[0034] It is worth mentioning that the light intensity sensor is a sensor that converts light signals into electrical signals and is used to measure the light intensity of the surrounding environment. Specifically, it is usually composed of photosensitive elements (such as photodiodes, photoresistors, phototransistors, etc.), which can respond to changes in light and convert the intensity of light into measurable electrical signals. Light intensity sensors are widely used in various fields, including environmental monitoring, industrial automation, smart homes, agriculture, medical equipment, etc.

[0035] In step S120, the time series of the ambient light intensity values ​​is segmented into a sequence to obtain a set of local time series of the ambient light intensity values. Specifically, in an embodiment of the present application, the time series of the ambient light intensity values ​​is segmented into a sequence to obtain a set of local time series of the ambient light intensity values, including: segmenting the time series of the ambient light intensity values ​​based on a predetermined time scale to obtain a set of local time series of the ambient light intensity values. Accordingly, it is considered that the ambient light intensity values ​​usually change over time, and there is different time series feature information in different local time periods, such as a continuous increase or continuous decrease in light intensity in a local time period, etc. Based on this, in order to be able to analyze and process the local time series feature information in different local time periods in a more fine-grained manner, in the technical solution of the present application, the time series of the ambient light intensity values ​​is segmented into a sequence based on a predetermined time scale to obtain a set of local time series of the ambient light intensity values. It should be understandable that by dividing the time series of the ambient light intensity value into multiple local time series of ambient light intensity values, each local time series of the ambient light intensity value represents a smaller time scale of the ambient light intensity value, which can better capture the local timing characteristic changes of the ambient light intensity value in different time periods, and facilitate the subsequent separate analysis and processing of the local timing characteristic changes of each ambient light intensity value, so as to more accurately understand the timing dynamic change law and fluctuation trend of the ambient light intensity value, thereby providing a more intuitive basis for the subsequent formulation of control instructions.

[0036] In step S130, the set of local time series of the ambient light intensity values ​​is subjected to ambient light intensity temporal correlation pattern feature extraction to obtain a set of local time series implicit correlation feature vectors of ambient light intensity. Specifically, in an embodiment of the present application, the set of local time series of the ambient light intensity values ​​is subjected to ambient light intensity temporal correlation pattern feature extraction to obtain a set of local time series implicit correlation feature vectors of ambient light intensity, including: inputting the set of local time series of the ambient light intensity values ​​into an ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to obtain a set of local time series implicit correlation feature vectors of ambient light intensity. It should be understood that, considering that there is different local time series implicit feature information about the ambient light intensity in the set of local time series of the ambient light intensity values. At the same time, there is also mutual correlation and dependency between the local time series of each ambient light intensity value in the set of local time series of the ambient light intensity values ​​between different time spans regarding the ambient light intensity. Accordingly, considering that the one-dimensional convolutional neural network is suitable for processing time series data, it can effectively identify and capture local time series patterns and features in the data, but its ability to extract mutual time series correlations between different time spans in the time series data is relatively weak. Therefore, in the technical solution of the present application, the set of local time series of the ambient light intensity values ​​is further input into the ambient light intensity time series correlation pattern feature extractor based on the one-dimensional extended convolutional neural network model to obtain a set of implicit correlation feature vectors of the local time series of ambient light intensity. In particular, the one-dimensional extended convolutional neural network model controls the size of the hole in the convolution operation through a hyperparameter called the expansion rate. Specifically, the ambient light intensity temporal correlation pattern feature extractor based on the one-dimensional extended convolutional neural network model captures the local characteristics and time domain correlation of ambient light intensity values ​​in different time periods by using extended convolutions of different time lengths. That is, the network not only pays attention to the ambient light intensity value data at the current time point, but also understands its correlation with the data at the previous and next time points. This method can more effectively understand and represent the mutual correlation patterns between the local time series in the set of local time series of the ambient light intensity values, so as to better characterize the implicit correlation characteristics of the local time series of ambient light intensity.

[0037] Specifically, in an embodiment of the present application, the set of local time series of the ambient light intensity values ​​is input into an ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to obtain a set of local time series implicit correlation feature vectors of ambient light intensity, including: inputting the set of local time series of the ambient light intensity values ​​into the ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to process the set of local time series implicit correlation feature vectors of ambient light intensity using the following extended convolution formula;

[0038] Wherein, the extended convolution formula is: ;in, respectively represent the local time series of each ambient light intensity value in the set of local time series of ambient light intensity values, a concatenated vector representing a set of local time series of ambient light intensity values, Indicates a connection operation. represents the local time series of the ambient light intensity values The concatenated vector of represents the predetermined hyperparameters, and Represent the weight matrix and bias vector respectively, represents the convolution operation, The number of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity is represented by The local temporal implicit correlation feature vector of the ambient light intensity.

[0039] In step S140, the set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature. Figure 3 The present invention is a flow chart of the method for intelligently controlling a household LED light strip according to an embodiment of the present application, wherein the set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a temporal correlation saliency representation vector of the ambient light intensity in the entire time domain as a temporal correlation saliency representation feature of the ambient light intensity in the entire time domain. Specifically, in the embodiment of the present application, Figure 3As shown, the set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature, including: S210, calculating the mean vector of the set of the local temporal implicit correlation feature vectors of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster; S220, calculating the correlation between each local temporal implicit correlation feature vector of the ambient light intensity in the set of the local temporal implicit correlation feature vectors of the ambient light intensity and the The temporal semantic association between the centers of the distribution clusters of the ambient light intensity sequence is obtained to obtain a sequence of the temporal semantic association of the ambient light intensity; S230, the sequence of the temporal semantic association of the ambient light intensity is input into the softmax function for normalization based on the soft maximum value to obtain a sequence of ambient light intensity weight factors; and, S240, using the sequence of ambient light intensity weight factors as the weight sequence, the vector-by-vector weighted sum of the set of the local temporal implicit association feature vectors of the ambient light intensity is calculated to obtain the temporal association significant representation vector of the full-time-domain ambient light intensity. Accordingly, considering that there are different degrees of mutual dependence and significant association between different local temporal implicit association features of the ambient light intensity in the set of the local temporal implicit association feature vectors of the ambient light intensity, there are also some temporal feature information that is irrelevant to the task. Based on this, in order to capture and focus on the significant change feature information in the process of ambient light intensity temporal change from the set of local temporal implicit correlation feature vectors of ambient light intensity, in the technical solution of the present application, the set of local temporal implicit correlation feature vectors of ambient light intensity is passed through a self-supervised feature sequence significance enhancement module to obtain a full-time domain ambient light intensity temporal correlation significance representation vector.Specifically, the self-supervised feature sequence saliency enhancement module firstly takes the mean vector of the set of the local temporal implicit correlation feature vectors of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster to summarize the overall trend and distribution characteristics of the set of the local temporal implicit correlation feature vectors of the ambient light intensity, and then calculates the temporal semantic association between each local temporal implicit correlation feature vector of the ambient light intensity and the center of the ambient light intensity sequence distribution cluster to evaluate the importance or significance of each local temporal implicit correlation feature vector of the ambient light intensity relative to the overall trend, so as to find the most representative or most prominent saliency. The local temporal implicit correlation features of ambient light intensity are taken as the basis, and finally, the ambient light intensity weight factor obtained after normalization of the ambient light intensity temporal semantic correlation is weighted and summed up to identify and enhance the significant features that play a key role in the temporal change of ambient light intensity, and the local temporal implicit correlation information of ambient light intensity at different local time points or with different features is integrated into a unified representation to capture the ambient light intensity changes in the entire time domain, so as to obtain a more accurate and discriminative full-time domain ambient light intensity temporal correlation saliency representation vector.

[0040] In the embodiment of the present application, specifically, calculating the mean vector of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster includes: calculating the mean vector of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster using the following mean calculation formula; wherein the mean calculation formula is: ;in, The number of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity is represented by The local temporal implicit correlation feature vector of the ambient light intensity, represents the number of feature vectors in the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity, Represents the center of the distribution cluster of the ambient light intensity sequence.

[0041] Figure 4 The present invention is a flowchart of calculating the temporal semantic association between each local temporal implicit association feature vector of the ambient light intensity in the set of the local temporal implicit association feature vector of the ambient light intensity and the center of the distribution cluster of the ambient light intensity sequence in the intelligent control method of the household LED light strip according to the embodiment of the present application to obtain a sequence of the temporal semantic association of the ambient light intensity. More specifically, in the embodiment of the present application, as Figure 4As shown, the temporal semantic association between each ambient light intensity local temporal implicit association feature vector in the set of the ambient light intensity local temporal implicit association feature vectors and the center of the ambient light intensity sequence distribution cluster is calculated to obtain a sequence of ambient light intensity temporal semantic associations, including: S310, respectively calculating the matrix product between each weight coefficient matrix and the corresponding each ambient light intensity local temporal implicit association feature vector to obtain a sequence of ambient light intensity local temporal implicit association weighted feature vectors; S320, calculating the matrix product between each ambient light intensity local temporal implicit association feature vector in the sequence of ambient light intensity local temporal implicit association weighted feature vectors; S330, adding the partial temporal implicit association weighted feature vector to the corresponding bias vector to obtain a sequence of ambient light intensity local temporal implicit association bias feature vectors; S330, activating the sequence of ambient light intensity local temporal implicit association bias feature vectors to obtain a sequence of ambient light intensity local temporal implicit association activation feature vectors; and, S340, calculating the product of each ambient light intensity local temporal implicit association activation feature vector in the sequence of ambient light intensity local temporal implicit association activation feature vectors and the transposed vector of the center of the ambient light intensity sequence distribution cluster to obtain a sequence of ambient light intensity temporal semantic associations.

[0042] In an embodiment of the present application, specifically, calculating the temporal semantic association between each local temporal implicit association feature vector of the ambient light intensity in the set of local temporal implicit association feature vectors of the ambient light intensity and the center of the ambient light intensity sequence distribution cluster to obtain a sequence of temporal semantic associations of the ambient light intensity includes: calculating the temporal semantic association between each local temporal implicit association feature vector of the ambient light intensity in the set of local temporal implicit association feature vectors of the ambient light intensity and the center of the ambient light intensity sequence distribution cluster using the following temporal semantic association formula to obtain a sequence of temporal semantic associations of the ambient light intensity; wherein the temporal semantic association formula is: ;in, The number of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity is represented by The local temporal implicit correlation feature vector of the ambient light intensity, represents the transposed vector of the center of the distribution cluster of the ambient light intensity sequence, represents the weight coefficient matrix, is the bias vector, express function, The sequence representing the temporal semantic association of the ambient light intensity The temporal semantic correlation of ambient light intensity.

[0043] In the embodiment of the present application, specifically, using the sequence of the ambient light intensity weight factors as the weight sequence, calculating the vector-by-vector weighted sum of the set of the local temporal implicit association feature vectors of the ambient light intensity to obtain the temporal association saliency representation vector of the full-time-domain ambient light intensity, including: calculating the vector-by-vector weighted sum of the set of the local temporal implicit association feature vectors of the ambient light intensity to obtain the temporal association saliency representation vector of the full-time-domain ambient light intensity according to the following weighted formula; wherein the weighted formula is: ;in, The number of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity is represented by The local temporal implicit correlation feature vector of the ambient light intensity, The sequence representing the temporal semantic association of the ambient light intensity The temporal semantic correlation of the ambient light intensity, express function, represents the number of feature vectors in the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity, The temporal correlation saliency representation vector of the full-time-domain ambient light intensity is represented.

[0044] In step S150, a control instruction is obtained based on the temporal association significant representation feature of the full-time-domain ambient light intensity. Specifically, in an embodiment of the present application, a control instruction is obtained based on the temporal association significant representation feature of the full-time-domain ambient light intensity, including: passing the temporal association significant representation vector of the full-time-domain ambient light intensity through a decoder-based power controller to obtain a control instruction, and the control instruction is used to indicate that the luminous power of the household LED light strip is adjusted to the recommended luminous power value. That is, the set of the local temporal implicit association feature vectors of the ambient light intensity is used to perform significant enhancement to obtain the temporal association significant representation feature of the full-time-domain ambient light intensity for classification processing, so as to intelligently obtain the control instruction for adjusting the luminous power of the household LED light strip to the recommended luminous power value. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the intelligent level of control can be improved.

[0045] Preferably, the process of obtaining a control instruction by passing the full-time-domain ambient light intensity temporal correlation significant representation vector through a decoder-based power controller comprises the following steps: calculating a self-mean matrix and a self-standard deviation matrix of the full-time-domain ambient light intensity temporal correlation significant representation vector, wherein the self-mean matrix is The value of the position is the first Position eigenvalue and The mean of the position eigenvalues, and the self-standard deviation matrix The value of the position is the first Position eigenvalue and The method comprises the steps of: calculating the standard deviation of the position eigenvalue; performing matrix multiplication of the transposed vector of the full-time-domain ambient light intensity time series correlation saliency representation vector as the row eigenvector with the self-mean matrix to obtain a first intermediate vector, and performing matrix multiplication of the self-standard deviation matrix with the full-time-domain ambient light intensity time series correlation saliency representation vector to obtain a second intermediate vector; calculating the point sum of the transposed vectors of the first intermediate vector and the second intermediate vector to obtain a third intermediate vector; calculating the matrix product of the self-mean matrix and the self-standard deviation matrix, and performing matrix multiplication of the transposed vector of the full-time-domain ambient light intensity time series correlation saliency representation vector with the matrix product to obtain a fourth intermediate vector; calculating the point sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector to obtain an optimized full-time-domain ambient light intensity time series correlation saliency representation vector; and passing the optimized full-time-domain ambient light intensity time series correlation saliency representation vector through the decoder-based power controller to obtain the control instruction.

[0046] In particular, here, taking into account the local time domain temporal correlation characteristics of the ambient light intensity values ​​expressed by the set of local time series implicit correlation feature vectors of the ambient light intensity, after being significantly distributed through the local time domain temporal characteristics in the global time domain, it will cause the overall local overflow characteristics of the full time domain ambient light intensity temporal correlation significant representation vector, thereby affecting the accuracy of the full time domain ambient light intensity temporal correlation significant representation vector when decoded by the decoder.

[0047] Based on this, the self-mean matrix and self-standard deviation matrix of the group aggregation statistical evaluation of the local distribution of the feature value granularity of the full-time-domain ambient light intensity time series association saliency representation vector are used as the retrieval and response distribution enhancement of the full-time-domain ambient light intensity time series association saliency representation vector, and a reference-free distribution retrieval response framework based on the group aggregation feature distribution open domain of the full-time-domain ambient light intensity time series association saliency representation vector is constructed to avoid the distribution response redundancy caused by the local overflow characteristics of the full-time-domain ambient light intensity time series association saliency representation vector through response superposition, so as to realize the faithfulness constraint of the self-aggregation statistical correlation of the response of the optimized full-time-domain ambient light intensity time series association saliency representation vector to the decoding target domain, and improve the accuracy of the control instructions obtained by the optimized full-time-domain ambient light intensity time series association saliency representation vector through the decoder-based power controller. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the intelligent level of control can be improved.

[0048] In summary, the intelligent control method of the household LED light strip based on the embodiment of the present application is explained, which uses the time series of the ambient light intensity values ​​collected by the light intensity sensor, and adopts the data processing and analysis technology based on artificial intelligence to perform local time series feature analysis and correlation of the ambient light intensity values, so as to intelligently obtain the control instructions for adjusting the luminous power of the household LED light strip to the recommended luminous power value based on the time series significant correlation characteristics of the ambient light intensity values ​​in the whole time domain. In this way, a more energy-saving lighting effect can be achieved, unnecessary energy waste can be reduced, and at the same time, the lighting effect can be more adapted to the current environment, the comfort and practicality of the lighting can be improved, and the intelligent level of control can be improved.

[0049] Figure 5 FIG. 1 is a block diagram of an intelligent control system for a household LED light strip according to an embodiment of the present application. Figure 5As shown, according to the embodiment of the present application, the intelligent control system 100 of the household LED light strip includes: an ambient light intensity acquisition module 110, which is used to obtain the time series of ambient light intensity values ​​collected by the light intensity sensor; an ambient light intensity local time extraction module 120, which is used to perform sequence segmentation on the time series of the ambient light intensity values ​​to obtain a set of local time series of ambient light intensity values; a local time series association module 130, which is used to perform ambient light intensity time series association pattern feature extraction on the set of local time series of the ambient light intensity values ​​to obtain a set of ambient light intensity local time series implicit association feature vectors; a light intensity full-time domain extraction module 140, which is used to pass the set of ambient light intensity local time series implicit association feature vectors through a self-supervised feature sequence significance enhancement module to obtain a full-time domain ambient light intensity time series association significant representation vector as a full-time domain ambient light intensity time series association significant representation feature; and a control instruction generation module 150, which is used to obtain a control instruction based on the full-time domain ambient light intensity time series association significant representation feature.

[0050] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent control system of the household LED light strip have been described in the above reference. Figures 1 to 4 The description of the intelligent control method of the household LED light strip is introduced in detail, and therefore, its repeated description will be omitted.

[0051] As described above, the intelligent control system 100 for household LED light strips according to the embodiment of the present disclosure can be implemented in various wireless terminals, such as a server with an intelligent control algorithm for household LED light strips. In a possible implementation, the intelligent control system 100 for household LED light strips according to the embodiment of the present disclosure can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the intelligent control system 100 for household LED light strips can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the intelligent control system 100 for household LED light strips can also be one of the many hardware modules of the wireless terminal.

[0052] Alternatively, in another example, the intelligent control system 100 of the household LED light strip and the wireless terminal may also be separate devices, and the intelligent control system 100 of the household LED light strip may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0053] The foregoing is merely an example of the principles of the present disclosure, and various modifications may be made by those skilled in the art without departing from the scope of the present disclosure. The above embodiments are presented for the purpose of illustration and not limitation. The present disclosure may also take many forms other than those explicitly described herein. Therefore, it is emphasized that the present disclosure is not limited to the methods, systems and devices explicitly disclosed, but is intended to include variations and modifications within the spirit and scope of the appended claims.

Claims

1. An intelligent control method for a household LED light strip, characterized in that: include: Get the time series of ambient light intensity values ​​collected by the light intensity sensor; Sequence segmentation is performed on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values; Performing ambient light intensity time series correlation pattern feature extraction on the set of local time series of the ambient light intensity values ​​to obtain a set of ambient light intensity local time series implicit correlation feature vectors; The set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature; Based on the temporal correlation saliency representation feature of the full-time-domain ambient light intensity, a control instruction is obtained; The set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature, including: Calculating the mean vector of the set of implicitly associated feature vectors of the local time series of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster; Calculating the temporal semantic association between each ambient light intensity local temporal implicit association feature vector in the set of the ambient light intensity local temporal implicit association feature vectors and the center of the ambient light intensity sequence distribution cluster to obtain a sequence of ambient light intensity temporal semantic associations; Inputting the sequence of the ambient light intensity temporal semantic associations into a softmax function for soft maximum normalization processing to obtain a sequence of ambient light intensity weight factors; The sequence of the ambient light intensity weight factors is used as a weight sequence, and the vector-by-vector weighted sum of the set of the ambient light intensity local temporal implicit association feature vectors is calculated to obtain the full-time-domain ambient light intensity temporal association saliency representation vector.

2. The intelligent control method for household LED light strip according to claim 1, characterized in that: Sequence segmentation is performed on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values, including: sequence segmentation is performed on the time series of the ambient light intensity values ​​based on a predetermined time scale to obtain a set of local time series of the ambient light intensity values.

3. The intelligent control method for household LED light strip according to claim 2, characterized in that: The set of local time series of ambient light intensity values ​​is subjected to ambient light intensity temporal correlation pattern feature extraction to obtain a set of ambient light intensity local temporal implicit correlation feature vectors, comprising: inputting the set of local time series of ambient light intensity values ​​into an ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to obtain a set of ambient light intensity local temporal implicit correlation feature vectors.

4. The intelligent control method for household LED light strip according to claim 3, characterized in that: Inputting the set of local time series of the ambient light intensity values ​​into an ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to obtain a set of local time series implicit correlation feature vectors of ambient light intensity, including: inputting the set of local time series of the ambient light intensity values ​​into the ambient light intensity temporal correlation pattern feature extractor based on a one-dimensional extended convolutional neural network model to process the set of local time series of the ambient light intensity values ​​using the following extended convolution formula to obtain a set of local time series implicit correlation feature vectors of the ambient light intensity; Wherein, the extended convolution formula is: ;in, respectively represent the local time series of each ambient light intensity value in the set of local time series of ambient light intensity values, a concatenated vector representing a set of local time series of ambient light intensity values, Indicates a connection operation. represents the local time series of the ambient light intensity values The concatenated vector of represents the predetermined hyperparameters, and Represent the weight matrix and bias vector respectively, represents the convolution operation, The number of the set of implicitly associated feature vectors of the local temporal sequence of the ambient light intensity is represented by The local temporal implicit correlation feature vector of the ambient light intensity.

5. The intelligent control method for household LED light strip according to claim 4, characterized in that: Calculating the temporal semantic association between each ambient light intensity local temporal implicit association feature vector in the set of the ambient light intensity local temporal implicit association feature vectors and the center of the ambient light intensity sequence distribution cluster to obtain a sequence of ambient light intensity temporal semantic associations, including: Calculating the matrix products of each weight coefficient matrix and each corresponding local temporal implicit correlation feature vector of the ambient light intensity to obtain a sequence of the local temporal implicit correlation weighted feature vector of the ambient light intensity; Adding a corresponding bias vector to each of the local temporal implicitly associated weighted feature vectors of ambient light intensity in the sequence of the local temporal implicitly associated weighted feature vectors of ambient light intensity to obtain a sequence of the local temporal implicitly associated biased feature vectors of ambient light intensity; Activating the sequence of the local temporal implicitly associated bias feature vectors of the ambient light intensity to obtain a sequence of the local temporal implicitly associated activation feature vectors of the ambient light intensity; The product of each ambient light intensity local temporal implicit association activation feature vector in the sequence of the ambient light intensity local temporal implicit association activation feature vector and the transposed vector of the center of the ambient light intensity sequence distribution cluster is calculated to obtain a sequence of the ambient light intensity temporal semantic association degrees.

6. The intelligent control method for household LED light strip according to claim 5, characterized in that: Based on the temporal correlation saliency representation feature of the full-time-domain ambient light intensity, a control instruction is obtained, including: passing the temporal correlation saliency representation vector of the full-time-domain ambient light intensity through a decoder-based power controller to obtain a control instruction, wherein the control instruction is used to indicate that the luminous power of the household LED light strip is adjusted to the recommended luminous power value.

7. An intelligent control system for a household LED light strip, characterized in that: include: An ambient light intensity acquisition module is used to obtain a time series of ambient light intensity values ​​acquired by a light intensity sensor; An ambient light intensity local time extraction module, used for performing sequence segmentation on the time series of the ambient light intensity values ​​to obtain a set of local time series of the ambient light intensity values; A local time series association module is used to extract the time series association pattern features of the ambient light intensity from the set of local time series of the ambient light intensity values ​​to obtain a set of local time series implicit association feature vectors of the ambient light intensity; A light intensity full-time domain extraction module is used to obtain a full-time domain ambient light intensity temporal correlation saliency representation vector as a full-time domain ambient light intensity temporal correlation saliency representation feature by passing the set of the ambient light intensity local temporal implicit correlation feature vectors through a self-supervised feature sequence saliency enhancement module; A control instruction generation module, used to obtain a control instruction based on the temporal correlation saliency representation feature of the full-time-domain ambient light intensity; The set of the local temporal implicit correlation feature vectors of the ambient light intensity is passed through a self-supervised feature sequence saliency enhancement module to obtain a full-time-domain ambient light intensity temporal correlation saliency representation vector as a full-time-domain ambient light intensity temporal correlation saliency representation feature, including: Calculating the mean vector of the set of implicitly associated feature vectors of the local time series of the ambient light intensity as the center of the ambient light intensity sequence distribution cluster; Calculating the temporal semantic association between each ambient light intensity local temporal implicit association feature vector in the set of the ambient light intensity local temporal implicit association feature vectors and the center of the ambient light intensity sequence distribution cluster to obtain a sequence of ambient light intensity temporal semantic associations; Inputting the sequence of the ambient light intensity temporal semantic associations into a softmax function for soft maximum normalization processing to obtain a sequence of ambient light intensity weight factors; The sequence of the ambient light intensity weight factors is used as a weight sequence, and the vector-by-vector weighted sum of the set of the ambient light intensity local temporal implicit association feature vectors is calculated to obtain the full-time-domain ambient light intensity temporal association saliency representation vector.

8. The intelligent control system for household LED light strips according to claim 7, characterized in that: The ambient light intensity local time extraction module is used to segment the time series of the ambient light intensity values ​​based on a predetermined time scale to obtain a set of local time series of the ambient light intensity values.

9. The intelligent control system for household LED light strips according to claim 8, characterized in that: The local time series association module is used to: input the set of local time series of ambient light intensity values ​​into an ambient light intensity time series association pattern feature extractor based on a one-dimensional extended convolutional neural network model to obtain a set of ambient light intensity local time series implicit association feature vectors.

Images