Intelligent linkage control method, device, equipment and medium for lighting system

Abstract

The present application discloses an intelligent linkage control method, device, equipment and medium for a lighting system, which collects sensing data of a sensing terminal; based on the sensing data, queries are made on each first time node at which the first sensing terminal triggers sensing, and whether the second sensing terminal triggers sensing within a specified number of time windows after the first time node, and counts the corresponding trigger times of the second sensing terminal in each time window according to the query result; establishes a first sequence of data according to the sorting of the time windows and the corresponding trigger times of the second sensing terminal in each time window; inputs the first sequence of data into a neural network, predicts the adjacent relationship between the first sensing terminal and the second sensing terminal, and obtains a first prediction result; based on the first prediction result, performs linkage control on the second lighting terminal based on the state of the first lighting terminal. This method can achieve better lighting effects. The present application can be widely used in the field of intelligent control technology.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to an intelligent linkage control method, device, equipment and medium for a lighting system. Background Art

[0002] At present, all walks of life have carried out energy-saving transformation of lighting. One of the transformations is energy saving based on intelligent control, that is, turning on, off or dimming lamps based on sensing. In order to save energy, one strategy is to disperse the lighting, that is, the power of a single or a single group of lamps that sense people or cars is reduced, and it will not be very bright, and the lighting range is limited. However, if people or cars move quickly, the sensing may not be timely, resulting in a decrease in the lighting experience. Therefore, in this case, linkage control is generally used, that is, when a single lamp senses someone, the adjacent lamps are also turned on.

[0003] In the current related technologies, in most cases, lights that require linkage need to be manually set up, which not only requires a large workload but also has a coarse control granularity, which can easily lead to a decrease in power consumption or lighting experience.

[0004] In summary, the problems existing in related technologies need to be solved urgently. Summary of the invention

[0005] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, an object of embodiments of the present application is to provide a method, device, equipment and medium for intelligent linkage control of a lighting system.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0008] On the one hand, an embodiment of the present application provides an intelligent linkage control method for a lighting system, wherein the lighting system includes a plurality of lighting terminals and a plurality of sensing terminals, and each lighting terminal corresponds to one sensing terminal; the method includes:

[0009] Collecting sensing data from each sensing terminal within a predetermined time period;

[0010] According to the sensing data, query each first time node at which the first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals;

[0011] According to the sensing data, query whether the second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal;

[0012] According to the order of the time windows, a first sequence of data is established according to the corresponding triggering times of the second sensing terminal in each of the time windows;

[0013] Inputting the first sequence data into a trained neural network, predicting the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal;

[0014] According to the first prediction result, the second lighting terminal is linked and controlled based on the state of the first lighting terminal; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

[0015] In addition, the intelligent linkage control method of a lighting system according to the above embodiment of the present application may also have the following additional technical features:

[0016] Furthermore, in one embodiment of the present application, inputting the first sequence data into a trained neural network comprises:

[0017] According to the predetermined time period, querying the corresponding target neural network;

[0018] The first sequence data is input into the trained target neural network.

[0019] Furthermore, in one embodiment of the present application, the neural network is trained by the following steps:

[0020] Acquire sample sensing data and label data of each sample sensing terminal; wherein the label data is used to characterize the real result of the neighbor relationship between the sample sensing terminals;

[0021] According to the sample sensing data, query each second time node at which the first sample sensing terminal triggers sensing; wherein the first sample sensing terminal is any sensing terminal among all the sample sensing terminals;

[0022] According to the sample sensing data, query whether the second sample sensing terminal triggers sensing within a specified number of time windows after each of the second time nodes, and count the corresponding triggering times of the second sample sensing terminal in each of the time windows according to the query result; wherein the second sample sensing terminal is any sensing terminal among all the sample sensing terminals except the first sample sensing terminal;

[0023] According to the order of the time windows, a second sequence of data is established according to the corresponding triggering times of the second sample sensing terminal in each of the time windows;

[0024] The second sequence data is input into the neural network to be optimized, and the neighbor relationship between the first sample sensing terminal and the second sample sensing terminal is predicted by the neural network to obtain a second prediction result; the second prediction result is used to indicate that the neural network predicts that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal or the second sample sensing terminal is not an adjacent terminal of the first sample sensing terminal;

[0025] Determining a training loss value according to the second prediction result and the label data;

[0026] According to the loss value, the parameters of the neural network are updated to obtain a trained neural network.

[0027] Furthermore, in one embodiment of the present application, the tag data is determined by the following steps:

[0028] Detecting whether a target object can directly reach the second sample sensing terminal from the first sample sensing terminal;

[0029] If the target object can directly reach the second sample sensing terminal from the first sample sensing terminal, it is determined that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal.

[0030] Further, in one embodiment of the present application, determining the loss value of training according to the second prediction result and the label data includes:

[0031] According to the second prediction result and the label data, a loss value of training is determined by a cross entropy loss function.

[0032] Further, in an embodiment of the present application, predicting the neighbor relationship between the first sensing terminal and the second sensing terminal by the neural network to obtain a first prediction result includes:

[0033] Predicting the neighbor relationship between the first sensing terminal and the second sensing terminal by using the neural network to obtain a probability result that the second sensing terminal is a neighbor terminal of the first sensing terminal;

[0034] According to the probability result, a first prediction result is determined.

[0035] Further, in one embodiment of the present application, the time window is determined by:

[0036] Obtaining distance data between adjacent sensing terminals;

[0037] Determine the time taken for a person to move between adjacent sensing terminals based on the distance data;

[0038] The time window is determined according to the moving time.

[0039] On the other hand, an embodiment of the present application provides an intelligent linkage control device for a lighting system, the system comprising:

[0040] A collection unit, used to collect sensing data of each sensing terminal within a predetermined time period;

[0041] A first query unit, configured to query, according to the sensing data, each first time node at which the first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals;

[0042] A second query unit is used to query whether a second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes according to the sensing data, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal;

[0043] An establishing unit, configured to establish first sequence data according to the order of the time windows and the corresponding triggering times of the second sensing terminal in each of the time windows;

[0044] a prediction unit, configured to input the first sequence data into a trained neural network, and predict the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal;

[0045] A processing unit is used to perform linkage control on the second lighting terminal based on the state of the first lighting terminal according to the first prediction result; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

[0046] On the other hand, an embodiment of the present application provides an electronic device, including:

[0047] at least one processor;

[0048] at least one memory for storing at least one program;

[0049] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned intelligent linkage control method for a lighting system.

[0050] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned intelligent linkage control method of a lighting system.

[0051] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0052] The embodiments of the present application disclose an intelligent linkage control method, device, equipment and storage medium for a lighting system, which collects sensing data of each sensing terminal within a predetermined time period; based on the sensing data, queries each first time node at which a first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals; based on the sensing data, queries whether a second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes, and counts the corresponding triggering times of the second sensing terminal within each of the time windows according to the query results; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal; according to the sorting of the time windows, the first sensing terminal is counted according to the sorting of the first sensing terminals. The first sequence data is established based on the corresponding triggering times of the two sensing terminals in each of the time windows; the first sequence data is input into the trained neural network, and the adjacent relationship between the first sensing terminal and the second sensing terminal is predicted by the neural network to obtain a first prediction result; the first prediction result is used to characterize that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or that the second sensing terminal is not an adjacent terminal of the first sensing terminal; according to the first prediction result, the second lighting terminal is controlled in linkage based on the state of the first lighting terminal; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal. This method can intelligently adjust the adjacent lamps that need to be linked during sensing through historical sensing data, achieve the best balance between lighting effect and energy saving, and replace the manual setting of the linkage of adjacent lamps, which not only reduces labor costs, but also can achieve better lighting effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A schematic diagram of an implementation environment of an intelligent linkage control method for a lighting system provided in an embodiment of the present application;

[0055] Figure 2 A schematic diagram of a flow chart of an intelligent linkage control method for a lighting system provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of the structure of an intelligent linkage control device for a lighting system provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0059] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0061] At present, all walks of life have carried out energy-saving transformation of lighting. One of the transformations is energy saving based on intelligent control, that is, turning on, off or dimming lamps based on sensing. In order to save energy, one strategy is to disperse the lighting, that is, the power of a single or a single group of lamps that sense people or cars is reduced, and it will not be very bright, and the lighting range is limited. However, if people or cars move quickly, the sensing may not be timely, resulting in a decrease in the lighting experience. Therefore, in this case, linkage control is generally used, that is, when a single lamp senses someone, the adjacent lamps are also turned on.

[0062] In the current related technologies, in most cases, lights that require linkage need to be manually set up, which is not only labor-intensive but also coarse in control granularity, and can easily lead to reduced power consumption or lighting experience. For example, in a specific place, it is necessary to determine the adjacent terminals associated with each sensing terminal. This adjacent terminal relationship is one-way. For example, a person may move from sensing terminal A to sensing terminal B without passing through other sensing terminals. In this case, B is the adjacent terminal of A, or the adjacent terminal of A is B, but if a person rarely moves from B to A, then A is not the adjacent terminal of B. It can be seen that due to the complexity of the adjacent terminal situation, it currently relies more on manual labor. When a place is carrying out the construction of intelligent lighting, construction personnel are required to configure the adjacent terminals associated with each sensing terminal. The shortcomings of this implementation mainly include the following points:

[0063] 1. The granularity that can be configured manually is generally coarse, which can easily cause lighting blind spots or excessive lighting;

[0064] 2. If the location has changed, reconfiguration is required;

[0065] 3. Due to the tide of people flow over time, one configuration may not be effective;

[0066] 4. The effects of manual configuration lack verification and are difficult to improve.

[0067] Although some manufacturers are studying movement judgment based on location information, judging the movement direction and speed of people or objects in real time, so as to turn on several adjacent lamps in the direction of movement in advance. This does not require manual configuration of the linkage relationship between adjacent lamps, and it is real-time linkage, which seems very smart. However, in actual applications, it is found that this real-time calculation requires very accurate sensing and positioning information, which is not only very costly, but also has limited accuracy, especially when multiple people or objects move at the same time. As a result, users have invested a lot of money to purchase high-level sensing and positioning equipment, and invested a lot of time to enter the preset data required for calculations such as the position of lamps, but the lighting experience is still very poor, not as good as manual configuration.

[0068] In view of this, an embodiment of the present application provides an intelligent linkage control method for a lighting system. The method can use historical sensing data to intelligently adjust adjacent lamps that need to be linked during sensing, thereby achieving an optimal balance between lighting effect and energy saving, replacing the manual setting of the linkage of adjacent lamps, which not only reduces labor costs but also achieves better lighting effects.

[0069] Before introducing and illustrating the intelligent linkage control method of the lighting system in the embodiment of the present application, the lighting system involved in the embodiment of the present application is first introduced.

[0070] Reference Figure 1 , Figure 1 A schematic diagram of the composition of a lighting system provided in an embodiment of the present application is shown. In the lighting system, the main hardware and software entities involved include a data collection terminal, a data mining module, a sensing terminal and a lighting terminal. Among them, these terminals and modules can interact with each other through data to realize the intelligent linkage control method provided in the embodiment of the present application. Specifically, in the embodiment of the present application, each lighting terminal is set corresponding to a sensing terminal, the sensing terminal can be used to detect and sense the human body or moving objects, so as to report the sensing event, and the lighting terminal is used for lighting; the data collection terminal can be used to store the sensing event, and the data mining module can mine the stored sensing event data, so as to facilitate the conclusion of which sensing terminals (lighting terminals) are adjacent, and the data collection terminal sends the linkage neighbor group configuration. Subsequently, when the sensing terminal senses the human body or moving object, the automatic control of the adjacent lighting terminals can be realized according to the linkage neighbor group configuration sent.

[0071] A communication connection can be established between the terminal and the module through a wireless network or a wired network. The wireless network or wired network uses standard communication technology and / or protocols, and the network can be set to the Internet, or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network. Moreover, the above-mentioned hardware and software entities can use the same communication connection mode or different communication connection modes, and this application does not make specific restrictions on this.

[0072] Of course, it is understandable that Figure 1 The implementation environment in the present application is only some optional application scenarios of the intelligent linkage control method of the lighting system provided in the embodiment of the present application, and the actual application is not fixed. Figure 1 The hardware and software environment shown.

[0073] Below, in combination with the introduction of the aforementioned implementation environment, an intelligent linkage control method for a lighting system provided in an embodiment of the present application is introduced and explained.

[0074] Please refer to Figure 2 , Figure 2 : is a schematic diagram of an intelligent linkage control method for a lighting system provided in an embodiment of the present application, and the intelligent linkage control method for a lighting system includes but is not limited to:

[0075] Step 210: Collect sensing data from each sensing terminal within a predetermined time period;

[0076] Step 220: querying each first time node at which the first sensing terminal triggers sensing according to the sensing data; wherein the first sensing terminal is any sensing terminal among all the sensing terminals;

[0077] Step 230: query, based on the sensing data, whether a second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal;

[0078] Step 240: Establishing first sequence data according to the order of the time windows and the corresponding triggering times of the second sensing terminal in each of the time windows;

[0079] Step 250: input the first sequence data into a trained neural network, and predict the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal;

[0080] Step 260: According to the first prediction result, the second lighting terminal is linked and controlled based on the state of the first lighting terminal; wherein the first lighting terminal is a lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is a lighting terminal corresponding to the second sensing terminal.

[0081] In an embodiment of the present application, an intelligent linkage control method for a lighting system is provided, which can intelligently adjust adjacent lamps that need to be linked during sensing through historical sensing data, thereby achieving an optimal balance between lighting effect and energy saving, replacing the manual setting of the linkage of adjacent lamps, which not only reduces labor costs but also achieves better lighting effects.

[0082] In an embodiment of the present application, sensing data of each sensing terminal is collected within a predetermined time period. These sensing terminals may include sensors, cameras or other devices, and the present application does not limit their specific types. Here, sensing data refers to the signal generated when the sensing terminal senses a human body or a moving object. Based on the sensing data, the various time nodes at which the sensing terminal triggers sensing can be queried and determined. In an embodiment of the present application, any one of the sensing terminals is selected as an example for illustration, and the sensing terminal is recorded as the first sensing terminal, and the time node at which the first sensing terminal triggers sensing is recorded as the first time node.

[0083] After obtaining the first time node, it is possible to query each other sensing terminal whether it triggers sensing after the first time node based on the sensing data. In the embodiment of the present application, any sensing terminal except the first sensing terminal among all sensing terminals is recorded as a second sensing terminal. For each second sensing terminal, when detecting whether it triggers sensing after the first time node, a specified number of time windows can be defined after each first time node. The duration of each time window is fixedly set and can be set between 50-200 milliseconds. The present application does not limit the specific duration of the time window. Then, it is possible to query whether the second sensing terminal triggers sensing in each time window, thereby determining the corresponding number of triggers of the second sensing terminal in each time window. For example, assuming that a total of 10 time windows are set, for each first time node, statistics are counted whether the second sensing terminal triggers sensing in the 10 time windows after the first time node. If triggered, it is accumulated once. After counting all the first time nodes, the corresponding number of triggers of the second sensing terminal in each time window can be obtained.

[0084] In an embodiment of the present application, after obtaining the number of triggers corresponding to the second sensing terminal in each of the time windows, the first sequence data can be established according to the order of the time windows and the number of triggers corresponding to the second sensing terminal in each of the time windows. For example, assume that 5 time windows are set and there are 3 first time nodes in total. The number of triggers corresponding to the second sensing terminal in the 5 time windows is 2 times, 4 times, 4 times, 1 time, and 0 times, respectively, then the first sequence data (2, 4, 4, 1, 0) can be established. Then, the first sequence data can be input into a trained neural network, and the adjacent relationship between the first sensing terminal and the second sensing terminal is predicted by the neural network to obtain a prediction result, which is recorded as the first prediction result. The first prediction result is used to characterize that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or that the second sensing terminal is not an adjacent terminal of the first sensing terminal.

[0085] In the embodiment of the present application, after obtaining the first prediction result, linkage control of the lighting terminal can be implemented according to the first prediction result. For example, when the first sensing terminal and the second sensing terminal are in an adjacent relationship, and the second sensing terminal is an adjacent terminal of the first sensing terminal, linkage control of the second lighting terminal can be performed based on the state of the first lighting terminal. Here, the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

[0086] The intelligent linkage control method of the lighting system in the embodiment of the present application can intelligently adjust the adjacent lamps that need to be linked during sensing through historical sensing data, thereby achieving the optimal balance between lighting effect and energy saving, replacing the manual setting of the linkage of adjacent lamps, which not only reduces labor costs but also achieves better lighting effects.

[0087] Specifically, in some embodiments, inputting the first sequence data into a trained neural network includes:

[0088] According to the predetermined time period, querying the corresponding target neural network;

[0089] The first sequence data is input into the trained target neural network.

[0090] In the embodiment of the present application, since the use of the lighting system may have time period characteristics. Therefore, a corresponding neural network can be set for each time period. For example, different neural network models can be corresponding to rush hours and normal times. By implementing relevant predictions through the corresponding neural network, the prediction accuracy can be improved, thereby facilitating efficient and accurate control of the lighting terminal. Specifically, in the embodiment of the present application, the target neural network that needs to be used currently can be queried and determined based on the correspondence between the predetermined time period and the neural network, and then the first sequence data can be input into the trained target neural network.

[0091] Specifically, in some embodiments, the neural network is trained by the following steps:

[0092] Acquire sample sensing data and label data of each sample sensing terminal; wherein the label data is used to characterize the real result of the neighbor relationship between the sample sensing terminals;

[0093] According to the sample sensing data, query each second time node at which the first sample sensing terminal triggers sensing; wherein the first sample sensing terminal is any sensing terminal among all the sample sensing terminals;

[0094] According to the sample sensing data, query whether the second sample sensing terminal triggers sensing within a specified number of time windows after each of the second time nodes, and count the corresponding triggering times of the second sample sensing terminal in each of the time windows according to the query result; wherein the second sample sensing terminal is any sensing terminal among all the sample sensing terminals except the first sample sensing terminal;

[0095] According to the order of the time windows, a second sequence of data is established according to the corresponding triggering times of the second sample sensing terminal in each of the time windows;

[0096] The second sequence data is input into the neural network to be optimized, and the neighbor relationship between the first sample sensing terminal and the second sample sensing terminal is predicted by the neural network to obtain a second prediction result; the second prediction result is used to indicate that the neural network predicts that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal or the second sample sensing terminal is not an adjacent terminal of the first sample sensing terminal;

[0097] Determining a training loss value according to the second prediction result and the label data;

[0098] According to the loss value, the parameters of the neural network are updated to obtain a trained neural network.

[0099] In the embodiment of the present application, before the neural network is used, it is generally necessary to train it so that it can achieve better performance. Specifically, when training the neural network, batches of training data and label data can be obtained. In the embodiment of the present application, the training data is the sample sensing data of each sample sensing terminal, and the label data is used to characterize the true result of the adjacent relationship between the sample sensing terminals. In a manner similar to the above, based on the sample sensing data, a prediction can be made through the neural network to be optimized to determine the adjacent relationship between the first sample sensing terminal and the second sample sensing terminal, and a prediction result can be obtained, which is recorded as the second prediction result in the embodiment of the present application. Then, based on the second detection result and the label data, the loss value of the training can be determined, and the size of the loss value can be used to measure the accuracy of the model. Therefore, the parameters of the model can be updated according to the loss value to obtain a trained neural network.

[0100] It should be noted that for an artificial intelligence model, the accuracy of its prediction can be measured by a loss function (LossFunction), which is defined on a single (group) of training data and is used to measure the prediction error of a training data. During actual training, a training data set has a lot of training data, such as the embodiment of the present application includes multiple groups of sample image data. Therefore, a cost function (Cost Function) is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction error of all training data, which can better measure the prediction effect of the model. There are many types of commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can all be used as loss functions of machine learning models, which will not be elaborated one by one here. In the embodiment of the present application, a cross entropy loss function can be selected.

[0101] In the embodiment of the present application, the parameter update of the neural network can be carried out in a cyclic iteration manner. That is, after updating the parameters of a round of neural networks, the neural network with updated parameters is continued to be used for prediction, a new loss value is determined, and then the parameters of the neural network are updated again. This cycle is repeated until the pre-set conditions for the end of training are met, and the training can be considered to be completed, and a trained neural network is obtained. The conditions for the end of training can be set according to actual needs, and this application does not limit this.

[0102] In the embodiment of the present application, for the tag data, it can be detected whether the target object can directly reach the second sample sensing terminal from the first sample sensing terminal. If yes, the tag data can record that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal. Conversely, if no, the tag data can record that the second sample sensing terminal is not an adjacent terminal of the first sample sensing terminal.

[0103] In the embodiment of the present application, there is no limitation on the structure of the neural network, which can be set according to actual needs. For example, a structure of two fully connected (including relu) plus a decision tree (such as XGBoost) can be used.

[0104] For the output mode of the neural network, it can output a probability result. For example, the neighboring relationship between the first sensing terminal and the second sensing terminal is predicted by the neural network, and the probability result that the second sensing terminal is an adjacent terminal of the first sensing terminal is obtained. Then, the probability result can be compared with a preset threshold value, where the threshold value can be set to 0.35-0.8. The larger the threshold value, the more energy-saving it is, and the smaller the threshold value, the better the lighting effect is. If the probability result is greater than or equal to the preset threshold value, it is considered that the second sensing terminal is an adjacent terminal of the first sensing terminal. If the probability result is less than the preset threshold value, it is considered that the second sensing terminal is not an adjacent terminal of the first sensing terminal.

[0105] In some embodiments, the time window is determined by:

[0106] Obtaining distance data between adjacent sensing terminals;

[0107] Determine the time taken for a person to move between adjacent sensing terminals based on the distance data;

[0108] The time window is determined according to the moving time.

[0109] In the embodiment of the present application, the time window can be set based on the distance data between adjacent sensing terminals and the moving speed of the person to determine the time taken for the person to move between adjacent sensing terminals. Then, the time window can be set to 2-4 times the moving time, and the present application does not limit the specific multiple.

[0110] The adjacent terminal configuration generated in the embodiment of the present application can be verified and optimized. The specific verification method is that after the configuration is applied for a period of time, the sensing data during this period is obtained, and the same method is used for mining. The mining result is compared with the previous configuration to verify the accuracy and coverage of the configuration. According to the difference, manual intervention or intelligent fine-tuning can be used to achieve optimization.

[0111] Reference Figure 3 , an intelligent linkage control device for a lighting system proposed in an embodiment of the present application comprises:

[0112] The collecting unit 310 is used to collect sensing data of each sensing terminal within a predetermined time period;

[0113] A first query unit 320 is configured to query, according to the sensing data, each first time node at which the first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals;

[0114] A second query unit 330 is used to query, according to the sensing data, whether the second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal;

[0115] An establishing unit 340 is configured to establish first sequence data according to the order of the time windows and the corresponding triggering times of the second sensing terminal in each of the time windows;

[0116] The prediction unit 350 is used to input the first sequence data into a trained neural network, and predict the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal;

[0117] The processing unit 360 is used to perform linkage control on the second lighting terminal based on the state of the first lighting terminal according to the first prediction result; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

[0118] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0119] Reference Figure 4 , an embodiment of the present application provides an electronic device, including:

[0120] at least one processor 410;

[0121] At least one memory 420, used to store at least one program;

[0122] When at least one program is executed by at least one processor 410, the at least one processor 410 implements an intelligent linkage control method for a lighting system.

[0123] Similarly, the contents of the above method embodiments are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0124] The embodiment of the present application also provides a computer-readable storage medium, which stores a program executable by the processor 410. The program executable by the processor 410 is used to execute the above-mentioned intelligent linkage control method of a lighting system when executed by the processor 410.

[0125] Similarly, the contents of the above method embodiments are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0126] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0127] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0128] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0129] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0130] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0131] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0132] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0133] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0134] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Technical personnel familiar with the field can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. An intelligent linkage control method for a lighting system, characterized in that: The lighting system comprises a plurality of lighting terminals and a plurality of sensing terminals, each of the lighting terminals corresponds to one of the sensing terminals; the method comprises: Collecting sensing data from each sensing terminal within a predetermined time period; According to the sensing data, query each first time node at which the first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals; According to the sensing data, query whether the second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal; According to the order of the time windows, a first sequence of data is established according to the corresponding triggering times of the second sensing terminal in each of the time windows; Inputting the first sequence data into a trained neural network, predicting the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal; According to the first prediction result, the second lighting terminal is linked and controlled based on the state of the first lighting terminal; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

2. The intelligent linkage control method of a lighting system according to claim 1, characterized in that: The step of inputting the first sequence data into a trained neural network comprises: According to the predetermined time period, querying the corresponding target neural network; The first sequence data is input into the trained target neural network.

3. The intelligent linkage control method for a lighting system according to claim 1, characterized in that: The neural network is trained by the following steps: Acquire sample sensing data and label data of each sample sensing terminal; wherein the label data is used to characterize the real result of the neighbor relationship between the sample sensing terminals; According to the sample sensing data, query each second time node at which the first sample sensing terminal triggers sensing; wherein the first sample sensing terminal is any sensing terminal among all the sample sensing terminals; According to the sample sensing data, query whether the second sample sensing terminal triggers sensing within a specified number of time windows after each of the second time nodes, and count the corresponding triggering times of the second sample sensing terminal in each of the time windows according to the query result; wherein the second sample sensing terminal is any sensing terminal among all the sample sensing terminals except the first sample sensing terminal; According to the order of the time windows, a second sequence of data is established according to the corresponding triggering times of the second sample sensing terminal in each of the time windows; The second sequence data is input into the neural network to be optimized, and the neighbor relationship between the first sample sensing terminal and the second sample sensing terminal is predicted by the neural network to obtain a second prediction result; the second prediction result is used to indicate that the neural network predicts that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal or the second sample sensing terminal is not an adjacent terminal of the first sample sensing terminal; Determining a training loss value according to the second prediction result and the label data; According to the loss value, the parameters of the neural network are updated to obtain a trained neural network.

4. The intelligent linkage control method for a lighting system according to claim 3, characterized in that: The tag data is determined by the following steps: Detecting whether a target object can directly reach the second sample sensing terminal from the first sample sensing terminal; If the target object can directly reach the second sample sensing terminal from the first sample sensing terminal, it is determined that the second sample sensing terminal is an adjacent terminal of the first sample sensing terminal.

5. The intelligent linkage control method of a lighting system according to claim 3, characterized in that: The step of determining the loss value of training according to the second prediction result and the label data includes: According to the second prediction result and the label data, a loss value of training is determined by a cross entropy loss function.

6. The intelligent linkage control method for a lighting system according to claim 1, characterized in that: The predicting the neighbor relationship between the first sensing terminal and the second sensing terminal by using the neural network to obtain a first prediction result includes: Predicting the neighbor relationship between the first sensing terminal and the second sensing terminal by using the neural network to obtain a probability result that the second sensing terminal is a neighbor terminal of the first sensing terminal; According to the probability result, a first prediction result is determined.

7. An intelligent linkage control method for a lighting system according to any one of claims 1 to 6, characterized in that: The time window is determined by: Obtaining distance data between adjacent sensing terminals; Determine the time taken for a person to move between adjacent sensing terminals based on the distance data; The time window is determined according to the moving time.

8. An intelligent linkage control device for a lighting system, characterized in that: The lighting system comprises a plurality of lighting terminals and a plurality of sensing terminals, each lighting terminal corresponds to one sensing terminal; the device comprises: A collection unit, used to collect sensing data of each sensing terminal within a predetermined time period; A first query unit, configured to query, according to the sensing data, each first time node at which the first sensing terminal triggers sensing; wherein the first sensing terminal is any sensing terminal among all the sensing terminals; A second query unit is used to query whether a second sensing terminal triggers sensing within a specified number of time windows after each of the first time nodes according to the sensing data, and count the corresponding triggering times of the second sensing terminal in each of the time windows according to the query result; wherein the second sensing terminal is any sensing terminal among all the sensing terminals except the first sensing terminal; An establishing unit, configured to establish first sequence data according to the order of the time windows and the corresponding triggering times of the second sensing terminal in each of the time windows; a prediction unit, configured to input the first sequence data into a trained neural network, and predict the neighbor relationship between the first sensing terminal and the second sensing terminal through the neural network to obtain a first prediction result; the first prediction result is used to indicate that the neural network predicts that the second sensing terminal is an adjacent terminal of the first sensing terminal or the second sensing terminal is not an adjacent terminal of the first sensing terminal; A processing unit is used to perform linkage control on the second lighting terminal based on the state of the first lighting terminal according to the first prediction result; wherein the first lighting terminal is the lighting terminal corresponding to the first sensing terminal, and the second lighting terminal is the lighting terminal corresponding to the second sensing terminal.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the intelligent linkage control method for a lighting system as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement an intelligent linkage control method for a lighting system as described in any one of claims 1 to 7 when executed by the processor.

Images