A method, system, device and medium for classifying an internet of things luminaire

Abstract

The application discloses a kind of classification methods, systems, devices and media of internet of things lamps, wherein the method obtains the sensing dataset of several internet of things lamps, the sensing dataset includes several trigger time stamps;Interval feature extraction is carried out on all the sensing dataset, to obtain the feature dataset of each internet of things lamps;Feature mining is carried out on all the feature dataset, to obtain the lamp supplementary feature of each internet of things lamps;All the feature dataset and the lamp supplementary feature are input into the trained lamp classification model for classification, to obtain the several lamp classification results output by the trained lamp classification model, each lamp classification result corresponds to an internet of things lamps.The method can effectively reduce the time required for internet of things lamps classification, improve classification efficiency, and improve the fine granularity of internet of things lamps classification.The application relates to the technical field of internet of things platform.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method, system, device, and medium for classifying IoT lighting fixtures. Background Technology

[0002] With the continuous development of IoT technology, a large number of IoT lighting fixtures are being used in various industries, and the classification of IoT lighting fixtures has become one of the key focuses of relevant practitioners.

[0003] Currently, the relevant technologies usually classify IoT lighting fixtures in application scenarios manually through remote control or other control devices. This method requires high time costs, has low classification efficiency, and the classification granularity is relatively coarse.

[0004] Therefore, the problems existing in the current technology still need to be solved and optimized. Summary of the Invention

[0005] To address at least one of the aforementioned technical problems, this application provides a method, system, device, and medium for classifying IoT lighting fixtures. This method can effectively reduce the time required for classifying IoT lighting fixtures, improve classification efficiency, and enhance the granularity of IoT lighting fixture classification.

[0006] According to a first aspect of this application, a method for classifying Internet of Things (IoT) lighting fixtures is provided, comprising:

[0007] Acquire a sensor dataset of several IoT lighting fixtures, wherein the sensor dataset includes several trigger timestamps;

[0008] Interval features are extracted from all the sensor datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis.

[0009] Feature mining is performed on all the aforementioned feature datasets to obtain supplementary features for each of the IoT lighting fixtures;

[0010] All the feature datasets and the supplementary features of the lamps are input into the trained lamp classification model for classification, and several lamp classification results are obtained from the trained lamp classification model. Each lamp classification result corresponds to one of the IoT lamps.

[0011] In some embodiments, the step of performing interval feature extraction on all the sensor datasets to obtain the feature dataset for each IoT lighting fixture includes:

[0012] Cooling-off period analysis is performed on all the aforementioned sensing datasets to obtain cooling-off period data, which is used to characterize the minimum trigger time interval threshold for each of the aforementioned IoT lighting fixtures;

[0013] Based on the cooling period data, all the sensor datasets are updated to obtain several first intermediate datasets;

[0014] Trigger feature extraction is performed on all the first intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

[0015] In some embodiments, the step of performing interval feature extraction on all the sensor datasets to obtain the feature dataset for each IoT lighting fixture includes:

[0016] Cooling-off period analysis is performed on all the sensor datasets to obtain cooling-off period data for each IoT lamp. The cooling-off period data is used to characterize the minimum trigger time interval threshold of the corresponding IoT lamp.

[0017] Based on each cooling period data, the corresponding sensing dataset is updated to obtain several second intermediate datasets;

[0018] Trigger feature extraction is performed on all the second intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

[0019] In some embodiments, trigger feature extraction is performed on all third intermediate datasets to obtain a feature dataset for each of the IoT lighting fixtures, including:

[0020] Obtain several time intervals;

[0021] Based on all the time intervals, the interval trigger count analysis is performed on all the third intermediate datasets to obtain the total number of lamp triggers corresponding to each time interval. The third intermediate dataset is either the first intermediate dataset or the second intermediate dataset.

[0022] Based on the total number of times all the lamps are triggered, all the time intervals are filtered to obtain the target interval, which is the time interval corresponding to the largest total number of lamp triggers among all the time intervals;

[0023] Based on the target interval, interval feature statistics are performed on the corresponding third intermediate dataset to obtain the feature dataset.

[0024] In some embodiments, the step of performing interval feature statistics on the corresponding third intermediate dataset according to the target interval to obtain the feature dataset includes:

[0025] Based on the target interval, the third intermediate dataset is filtered by timestamps to obtain a timestamp sequence, which includes several trigger timestamps within the target interval;

[0026] Perform time interval analysis on the timestamp sequence to obtain a time interval sequence;

[0027] The feature dataset is obtained by counting the number of occurrences of the time interval sequence.

[0028] In some embodiments, the step of performing feature mining on all the feature datasets to obtain supplementary features for each of the IoT lighting fixtures includes:

[0029] Obtain a fourth intermediate dataset and several fifth intermediate datasets, wherein the fourth intermediate dataset is any one of the feature datasets, and the fifth intermediate dataset is any one of the feature datasets other than the fourth intermediate dataset.

[0030] Based on the fourth intermediate dataset, all the fifth intermediate datasets are filtered for related data to obtain several sixth intermediate datasets. The sixth intermediate dataset is any one of the top several fifth intermediate datasets that are associated with the fourth intermediate dataset and have the highest frequency distribution. The frequency distribution is used to characterize the trigger frequency of the second light fixture that is associated with the first light fixture within a preset time range before and after the first light fixture is triggered. The first light fixture is any one of the IoT light fixtures, and the second light fixture is any one of the IoT light fixtures other than the first light fixture.

[0031] Based on the fourth intermediate dataset, interval feature analysis is performed on all the sixth intermediate datasets to obtain the supplementary features of the lamps.

[0032] In some embodiments, the trained lighting classification model is obtained through the following steps:

[0033] Obtain training data for lighting fixtures labeled with their categories;

[0034] The lighting training data is input into the initialized lighting classification model for training, and the classification training result corresponding to the lighting training data is obtained.

[0035] Based on the classification training results, the parameters of the initialized lighting classification model are updated to obtain the trained lighting classification model.

[0036] According to a second aspect of this application, a classification system for Internet of Things (IoT) lighting fixtures is provided, comprising:

[0037] The first processing unit is used to acquire a sensing dataset of several Internet of Things (IoT) lighting fixtures, wherein the sensing dataset includes several trigger timestamps;

[0038] The second processing unit is used to extract interval features from all the sensing datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis.

[0039] The third processing unit is used to perform feature mining on all the feature datasets to obtain supplementary features for each of the IoT lighting fixtures;

[0040] The fourth processing unit is used to input all the feature datasets and the supplementary features of the lamps into the trained lamp classification model for classification, and to obtain several lamp classification results output by the trained lamp classification model, each lamp classification result corresponding to one of the IoT lamps.

[0041] According to a third aspect of this application, a computer device is provided, comprising:

[0042] At least one processor;

[0043] At least one memory for storing at least one program;

[0044] When the at least one program is executed by the at least one processor, the at least one processor performs the method as described above.

[0045] According to a fourth aspect of this application, a computer-readable storage medium is provided, wherein a processor-executable program is stored, the processor-executable program being used, when executed by the processor, to implement the method as described above.

[0046] The beneficial effects of the technical solutions provided in this application are:

[0047] This application provides a method, system, device, and medium for classifying IoT lighting fixtures. The method involves acquiring a plurality of sensor datasets for several IoT lighting fixtures, each dataset including several trigger timestamps. Interval features are extracted from all the sensor datasets to obtain a feature dataset for each IoT lighting fixture. This feature dataset includes several interval frequency features for each IoT lighting fixture, each interval frequency feature representing the frequency of occurrence of a trigger interval time based on adjacent trigger timestamps on a time axis. Feature mining is performed on all the feature datasets to obtain supplementary features for each IoT lighting fixture. All the feature datasets and the supplementary features are then input into a trained lighting fixture classification model for classification, resulting in several lighting fixture classification results output by the trained model. Each classification result corresponds to one IoT lighting fixture. This method, by inputting the feature datasets and supplementary features of each IoT lighting fixture into the lighting fixture classification model, classifies the multi-dimensional features of the IoT lighting fixtures using the model. This effectively reduces the time required for classification, improves the efficiency of IoT lighting fixture classification, and enhances the fine-grainedness of lighting fixture classification. Attached Figure Description

[0048] Figure 1 A schematic diagram of a network framework for an Internet of Things (IoT) application scenario provided in this application embodiment;

[0049] Figure 2 A flowchart illustrating a method for classifying IoT lighting fixtures provided in an embodiment of this application;

[0050] Figure 3 A detailed flowchart illustrating the first step S220 provided in this application embodiment;

[0051] Figure 4 A detailed flowchart illustrating the second step S220 provided in this application embodiment;

[0052] Figure 5 A detailed flowchart illustrating the trigger feature extraction process is provided for an embodiment of this application.

[0053] Figure 6 A detailed flowchart of step S540 provided for an embodiment of this application;

[0054] Figure 7 A detailed flowchart of step S230 provided for an embodiment of this application;

[0055] Figure 8 A flowchart illustrating a trained lighting classification model provided for an embodiment of this application;

[0056] Figure 9 A schematic diagram of the framework of a classification system for IoT lighting fixtures provided in an embodiment of this application;

[0057] Figure 10 This is a structural block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0058] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0059] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is 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 commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0061] Currently, the relevant technologies usually classify IoT lighting fixtures in application scenarios manually through remote control or other control devices. This method requires high time costs, has low classification efficiency, and the classification granularity is relatively coarse.

[0062] Furthermore, some related technologies analyze the positional relationships between various IoT lighting fixtures in an application scenario and classify or control the fixtures based on these relationships. This method only classifies and controls the fixtures from a spatial perspective, failing to comprehensively capture the complex information of each IoT lighting fixture in the application scenario. The classification results are often inaccurate, with coarse-grained classification. Additionally, this method requires collecting or analyzing the positional relationships between various IoT lighting fixtures. In practical applications, due to the large number of IoT lighting fixtures, this method requires significant computational resources, resulting in unsatisfactory efficiency in IoT lighting fixture classification.

[0063] It should be noted that the aforementioned related technologies are only used to assist in understanding the technical solutions of this application and do not mean that they belong to the publicly disclosed prior art.

[0064] In view of this, embodiments of this application provide a method, system, device, and medium for classifying IoT lighting fixtures. The method extracts interval features from the sensor datasets of all IoT lighting fixtures. Specifically, it performs interval feature statistics on the analyzed and filtered sensor datasets based on target intervals. This allows it to capture, from a global perspective, the most important feature intervals for all IoT lighting fixtures in the application scenario, as well as the interval frequency characteristics of each IoT lighting fixture within that interval. Furthermore, the method performs feature mining on the feature datasets of each IoT lighting fixture. Specifically, through correlation data filtering and interval feature analysis, it can capture the trigger time feature information of each IoT lighting fixture in the application scenario from a local perspective. The obtained supplementary lighting fixture features and feature datasets are then input into a lighting fixture classification model. This allows the model to classify based on inputs containing more comprehensive and complex information, effectively improving the accuracy of lighting fixture classification results, increasing the granularity of lighting fixture classification, and improving the efficiency of IoT lighting fixture classification.

[0065] This application provides a method, system, device, and medium for classifying IoT lighting fixtures, which can be specifically described through the following embodiments. First, a method for classifying IoT lighting fixtures in this application is described.

[0066] The IoT lighting classification method provided in this application can be applied to specific IoT application scenarios such as smart parking lighting systems, smart home lighting systems, smart hospital lighting systems, and smart learning lighting systems. In these IoT application scenarios, IoT service providers can use the method provided in this application to automatically classify all IoT lighting devices within the application scenario, facilitating subsequent operation and control of the IoT lighting devices. This method can effectively reduce the time required for classification, improve the efficiency of IoT lighting device classification, and increase the granularity of lighting device classification.

[0067] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0068] Reference Figure 1 and Figure 2 , Figure 2 This is a flowchart illustrating a classification method for IoT lighting fixtures provided in an embodiment of this application. The classification method includes, but is not limited to, steps S210 to S240:

[0069] Step S210: Obtain a sensing dataset of several IoT lighting fixtures, wherein the sensing dataset includes several trigger timestamps;

[0070] In this embodiment, a sensor dataset of several IoT lamps in IoT application scenarios such as smart parking lot lighting systems and smart shopping mall lighting systems can be obtained; specifically, this sensor dataset can be obtained from the sensing terminals in the lighting system within a certain time period, based on each IoT lamp (i.e., Figure 1 The trigger timestamps of the lighting terminals in the system are collected and transmitted to the server (i.e., the lighting terminals in the system). Figure 1 The data is obtained from the data collection terminal in the middle.

[0071] Step S220: Extract interval features from all the sensor datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis.

[0072] In this embodiment of the application, the interval feature extraction can be the number of occurrences of several different trigger interval times in each sensing dataset, thereby obtaining a feature set of several interval frequency features for each IoT lamp, denoted as the feature dataset.

[0073] Reference Figure 3 In some embodiments, the step of performing interval feature extraction on all the sensor datasets to obtain the feature dataset for each IoT lighting fixture includes:

[0074] S310. Perform a cooling period analysis on all the sensor datasets to obtain cooling period data, which is used to characterize the minimum trigger time interval threshold for each of the IoT lights.

[0075] S320. Based on the cooling period data, update all the sensing datasets to obtain several first intermediate datasets;

[0076] S330. Perform trigger feature extraction on all the first intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

[0077] In this embodiment, the interval feature extraction can first involve performing a cooling-off period analysis on all sensing datasets to obtain the minimum trigger time interval threshold corresponding to all sensing datasets, denoted as cooling-off period data. The cooling-off period data is the same for each IoT lighting fixture. This cooling-off period analysis can be performed by extracting the minimum trigger time interval of each sensing dataset and calculating the minimum trigger time interval threshold by averaging all minimum trigger time intervals. Alternatively, the cooling-off period analysis can also be performed by extracting the minimum trigger time interval of each sensing dataset and determining the maximum value among all minimum trigger time intervals as the minimum trigger time interval.

[0078] Understandably, for any given sensing dataset, data updates can involve deleting trigger timestamps that are repeatedly triggered during the cooldown period. Specifically, this can be achieved by calculating the trigger time interval between two adjacent trigger timestamps on the timeline and comparing this interval with the cooldown period data. If the trigger time interval is greater than or equal to the cooldown period data, the two adjacent trigger timestamps can be retained; or, if the trigger time interval is less than the cooldown period data, the latter trigger timestamp can be deleted, and the former can be retained. The remaining trigger timestamps in the sensing dataset are processed similarly, ultimately yielding the first intermediate dataset corresponding to the sensing dataset.

[0079] Reference Figure 4 In some embodiments, the step of performing interval feature extraction on all the sensor datasets to obtain the feature dataset for each IoT lighting fixture includes:

[0080] Step S410: Perform a cooling period analysis on all the sensor datasets to obtain cooling period data for each IoT lamp. The cooling period data is used to characterize the minimum trigger time interval threshold of the corresponding IoT lamp.

[0081] Step S420: Update the corresponding sensing dataset according to each cooling period data to obtain several second intermediate datasets;

[0082] Step S430: Perform trigger feature extraction on all the second intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

[0083] In this embodiment, the cooling-off period analysis can be performed by calculating the minimum trigger time interval threshold for each sensing dataset. Specifically, it can be calculated based on the three sigma (3σ) principle. For example, trigger time intervals smaller than the difference between the mean of the sensing dataset and several times the standard deviation can be deleted to obtain the cooling-off period data corresponding to each IoT device. The acquisition of the second intermediate dataset is similar to the acquisition of the first intermediate dataset, and can be simply deduced by analogy. This application will not elaborate further here.

[0084] Reference Figure 5 Furthermore, trigger feature extraction is performed on all third intermediate datasets to obtain the feature dataset for each IoT lighting fixture, including:

[0085] Step S510: Obtain several time intervals;

[0086] Step S520: Based on all the time intervals, perform interval trigger count analysis on all the third intermediate datasets to obtain the total number of lamp triggers corresponding to each time interval. The third intermediate dataset is either the first intermediate dataset or the second intermediate dataset.

[0087] Step S530: Based on the total number of times all the lamps are triggered, all the time intervals are filtered to obtain the target interval, which is the time interval corresponding to the largest total number of lamp triggers among all the time intervals;

[0088] In this embodiment of the application, the time interval can be a period of time such as weekly, daily, every three hours, or hourly. In this embodiment of the application, the third intermediate dataset is used as the first intermediate dataset as an example. The interval trigger count analysis can be to count the total number of trigger timestamps of all sensing datasets in each time interval, thereby obtaining the total number of times the lamps are triggered in each time interval for all sensing datasets.

[0089] Understandably, interval filtering can compare the total number of light triggers in each time interval and determine the time interval corresponding to the largest total number of light triggers as the target interval. The content of the third intermediate dataset being the second intermediate dataset is consistent with the aforementioned situation where the third intermediate dataset was the first intermediate dataset.

[0090] Step S540: Based on the target interval, perform interval feature statistics on the corresponding third intermediate dataset to obtain the feature dataset.

[0091] Reference Figure 6 Furthermore, the step of performing interval feature statistics on the corresponding third intermediate dataset based on the target interval to obtain the feature dataset includes:

[0092] Step S610: Based on the target interval, the third intermediate dataset is filtered by timestamps to obtain a timestamp sequence, which includes several trigger timestamps within the target interval;

[0093] Step S620: Perform time interval analysis on the timestamp sequence to obtain a time interval sequence;

[0094] Step S630: Count the number of occurrences of the time interval sequence to obtain the feature dataset.

[0095] In this embodiment of the application, for any third intermediate dataset of an IoT lighting device, timestamp filtering can be performed to select several trigger timestamps within a target interval from the third intermediate dataset of the IoT lighting device, denoted as a timestamp sequence. Interval analysis can be performed by sequentially calculating the trigger time interval between two adjacent trigger timestamps in the timestamp sequence, thereby obtaining the time interval sequence. .

[0096] It is understandable that for time interval sequences They may have the same trigger time interval, for example, trigger time interval and trigger time interval The occurrences may be the same; therefore, frequency analysis can be a statistical analysis of the number of times the same triggering time intervals occur in the time interval sequence, and the number of occurrences of each different triggering time interval is used as a statistical feature (i.e., the frequency feature of the intervals), thereby obtaining a feature dataset.

[0097] Step S230: Perform feature mining on all the feature datasets to obtain supplementary features for each IoT lighting fixture;

[0098] In this embodiment of the application, local features between feature datasets can be mined from all feature datasets to obtain supplementary features for each IoT lighting fixture.

[0099] Reference Figure 7 In some embodiments, the step of performing feature mining on all the feature datasets to obtain supplementary features for each of the IoT lighting fixtures includes:

[0100] Step S710: Obtain a fourth intermediate dataset and several fifth intermediate datasets, wherein the fourth intermediate dataset is any one of the feature datasets, and the fifth intermediate dataset is any one of the feature datasets other than the fourth intermediate dataset.

[0101] Step S720: Based on the fourth intermediate dataset, perform associated data filtering on all the fifth intermediate datasets to obtain several sixth intermediate datasets. The sixth intermediate dataset is any one of the top several fifth intermediate datasets that are associated with the fourth intermediate dataset and have the highest frequency distribution. The frequency distribution is used to characterize the trigger frequency of the second light fixture that is associated with the first light fixture within a preset time range before and after the first light fixture is triggered. The first light fixture is any one of the IoT light fixtures, and the second light fixture is any one of the IoT light fixtures other than the first light fixture.

[0102] Step S730: Based on the fourth intermediate dataset, perform interval feature analysis on all the sixth intermediate datasets to obtain the supplementary features of the lamps.

[0103] In this embodiment, the feature dataset of any one IoT lighting device can be designated as the fourth intermediate dataset, and the feature datasets of the remaining IoT lighting devices can be designated as the fifth intermediate dataset. Association data filtering can analyze the frequency distribution relationship between the fourth intermediate dataset and each fifth intermediate dataset, and designate the fifth intermediate dataset with the highest associated frequency distribution as the sixth intermediate dataset. Specifically, for the fourth intermediate dataset and any fifth intermediate dataset, the frequency distribution relationship between them can be obtained by measuring the data distribution between the trigger time interval of the fourth intermediate dataset and the trigger time interval of the fifth intermediate dataset.

[0104] For example, for any one light fixture Based on this lamp The feature dataset (i.e., the fourth intermediate dataset) determines the lamp. Lighting trigger time sequence representation ,in, For lighting fixtures The nth trigger timestamp; then, based on the lamp... The time series representation of the lamp trigger and all fifth intermediate datasets for the lamp Within a certain time range (e.g., t seconds) before and after each trigger, the frequency distribution of the linked triggering lights is statistically analyzed to obtain the correlation between the triggering lights and the triggering frequency distribution. Several related light fixtures were identified; then, by sorting the frequency distributions obtained statistically from largest to smallest, several fifth intermediate datasets with high frequency distributions and associations with the fourth intermediate dataset were obtained. (The light fixture...) The frequency distribution can be expressed as:

[0105]

[0106] in, For lighting fixtures The function representation of the frequency distribution; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency . For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For lighting fixtures Trigger timestamp When triggered, the linked lights and its trigger frequency ; For the first A single IoT lighting fixture m represents the total number of IoT lighting fixtures; IoT lighting fixtures The total number of trigger timestamps.

[0107] Understandably, since each light fixture is often triggered multiple times within a certain period of time, the light fixture... The trigger frequency of a specific lamp, obtained from statistics on a given trigger timestamp, is often greater than or equal to 2, with a few exceptions where the trigger frequency is 0 or 1. Furthermore, when obtaining the lamp's... After analyzing the frequency distribution of the lamps, it is easy to determine the lamps associated with that lamp. Several lamps that are related and have a high frequency distribution, for example, this lamp can be... At each trigger timestamp, the luminaire with the highest trigger frequency in the linkage triggering is identified as the associated luminaire with a high frequency distribution; alternatively, the luminaire can also be... At each trigger timestamp, several lamps with a low trigger frequency are excluded, and the remaining lamps are identified as associated lamps with a high frequency distribution. This will not be elaborated further in this application.

[0108] It should be noted that after obtaining all the sixth intermediate datasets of the fourth intermediate dataset, the average triggering time interval corresponding to the fourth intermediate dataset can be calculated based on several triggering time intervals in the fourth intermediate dataset and / or all the sixth intermediate datasets, and is denoted as the lamp supplementary feature.

[0109] Step S240: Input all the feature datasets and the supplementary features of the lamps into the trained lamp classification model for classification, and obtain several lamp classification results output by the trained lamp classification model, each lamp classification result corresponding to one IoT lamp.

[0110] In this embodiment of the application, for any IoT lighting fixture's feature dataset and supplementary features, the feature dataset and supplementary features of the IoT lighting fixture can be input into a pre-trained lighting fixture classification model. The lighting fixture classification model can then classify the IoT lighting fixture into its category, thereby obtaining the classification result of the IoT lighting fixture.

[0111] Reference Figure 8 In some embodiments, the trained lighting classification model is obtained through the following steps:

[0112] Step S810: Obtain lighting training data with lighting category labels;

[0113] Step S820: Input the lighting training data into the initialized lighting classification model for training, and obtain the classification training result corresponding to the lighting training data;

[0114] Step S830: Based on the classification training results, update the parameters of the initialized lighting classification model to obtain the trained lighting classification model.

[0115] In this embodiment of the application, the lighting fixture classification model can be a time-series classification model built based on the Transformer network architecture. The lighting fixture classification model includes an encoding layer and a fully connected layer, wherein the encoding layer is used to extract input data features, and the fully connected layer is used to map class probabilities.

[0116] Specifically, the lighting training data can be fed into the lighting classification model to obtain the classification training result output by the lighting classification model. The target loss value of the classification training result can be calculated based on the loss function (such as multi-class cross-entropy). The lighting classification model can then be backpropagated and updated using the target loss value to obtain the trained lighting classification model.

[0117] Figure 9 A system block diagram of a classification system for IoT lighting fixtures provided in this application embodiment includes:

[0118] The first processing unit 901 is used to acquire a sensing dataset of several Internet of Things (IoT) lamps, wherein the sensing dataset includes several trigger timestamps;

[0119] The second processing unit 902 is used to extract interval features from all the sensing datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis.

[0120] The third processing unit 903 is used to perform feature mining on all the feature datasets to obtain supplementary features for each of the IoT lighting fixtures;

[0121] The fourth processing unit 904 is used to input all the feature datasets and the supplementary features of the lamps into the trained lamp classification model for classification, and obtain several lamp classification results output by the trained lamp classification model, each lamp classification result corresponding to one IoT lamp.

[0122] It is worth mentioning that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0123] Figure 10 A schematic diagram of the structure of a computer device provided in this application embodiment includes:

[0124] At least one processor 980;

[0125] At least one memory 920 is used to store at least one program;

[0126] When the at least one program is executed by the at least one processor 980, the at least one processor 980 performs the method as described in the foregoing embodiments.

[0127] This application also provides a computer-readable storage medium storing a processor-executable program, which, when executed by the processor 980, is used to implement the methods described in the foregoing embodiments.

[0128] Figure 10 Specifically, computer equipment can be either a user terminal or a server.

[0129] This application uses a computer device as a user terminal as an example, as detailed below:

[0130] like Figure 10 As shown, the computer device 900 may include an RF (Radio Frequency) circuit 910, a memory 920 including one or more computer-readable storage media, an input unit 930, a display unit 940, a sensor 950, an audio circuit 960, a WiFi module 970, a processor 980 including one or more processing cores, and a power supply 990, among other components. Those skilled in the art will understand that... Figure 10 The device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0131] The RF circuit 910 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 980 for processing; additionally, it transmits uplink data to the base station. Typically, the RF circuit 910 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. Furthermore, the RF circuit 910 can also communicate wirelessly with networks and other devices. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0132] The memory 920 can be used to store software programs and modules. The processor 980 executes various functional applications and data processing by running the software programs and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device 900 (such as audio data, telephone directory, etc.). In addition, the memory 920 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 920 may also include a memory controller to provide access to the memory 920 by the processor 980 and the input unit 930. Although Figure 10 The RF circuit 910 is shown, but it is understood that it is not a necessary component of the computer device 900 and can be omitted as needed without changing the nature of the invention.

[0133] The input unit 930 can be used to receive input digital or character information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, the input unit 930 may include a touch-sensitive surface 932 and other input devices 931. The touch-sensitive surface 932, also known as a touch display screen or touchpad, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch-sensitive surface 932), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 932 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 980, and can receive and execute commands from the processor 980. In addition, the touch-sensitive surface 932 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 932, the input unit 930 may also include other input devices 931. Specifically, other input devices 931 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0134] Display unit 940 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of computer device 900. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Display unit 940 may include display panel 941, optionally configured as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, touch-sensitive surface 932 may cover display panel 941. When touch-sensitive surface 932 detects a touch operation on or near it, it transmits the information to processor 980 to determine the type of touch event. Subsequently, processor 980 provides corresponding visual output on display panel 941 according to the type of touch event. Although in Figure 10 In this embodiment, the touch-sensitive surface 932 and the display panel 941 are implemented as two separate components to realize input and output functions. However, in some embodiments, the touch-sensitive surface 932 and the display panel 941 can be integrated to realize input and output functions.

[0135] The computer device 900 may also include at least one sensor 950, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 941 according to the ambient light level, and the proximity sensor can turn off the display panel 941 and / or backlight when the computer device 900 is moved to the ear. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometers, taps), etc. Other sensors that the computer device 900 may also be equipped with, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0136] Audio circuitry 960, speaker 961, and microphone 962 provide an audio interface between the user and computer device 900. Audio circuitry 960 converts received audio data into electrical signals, which are then transmitted to speaker 961, where they are converted into sound signals for output. Conversely, microphone 962 converts collected sound signals into electrical signals, which are received by audio circuitry 960, converted back into audio data, and then processed by processor 980 before being transmitted via RF circuitry 910 to another control device, or output to memory 920 for further processing. Audio circuitry 960 may also include an earphone jack to facilitate communication between peripheral headphones and computer device 900.

[0137] Computer device 900 can transmit information with the wireless transmission module set up on the battle equipment via WiFi module 970.

[0138] The processor 980 is the control center of the computer device 900. It connects various parts of the control device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 920, and by calling data stored in the memory 920, it performs various functions of the computer device 900 and processes data, thereby providing overall monitoring of the control device. Optionally, the processor 980 may include one or more processing cores; optionally, the processor 980 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may also not be integrated into the processor 980.

[0139] The computer device 900 also includes a power supply 990 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 980 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 990 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0140] Although not shown, the computer device 900 may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0141] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the methods described in the foregoing embodiments.

[0142] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatuses.

[0143] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0145] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0147] If the integrated unit is implemented as 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 this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0148] The step numbers in the above method embodiments are set only for ease of explanation and do not limit the order of the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0149] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for classifying IoT lighting fixtures, characterized in that, include: Acquire a sensor dataset of several IoT lighting fixtures, wherein the sensor dataset includes several trigger timestamps; Interval features are extracted from all the sensor datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis. Feature mining is performed on all the aforementioned feature datasets to obtain supplementary features for each of the IoT lighting fixtures; All the feature datasets and the supplementary features of the lamps are input into the trained lamp classification model for classification, and several lamp classification results are obtained from the trained lamp classification model. Each lamp classification result corresponds to one of the IoT lamps. The step of performing feature mining on all the aforementioned feature datasets to obtain supplementary features for each of the IoT lighting fixtures includes: Obtain a fourth intermediate dataset and several fifth intermediate datasets, wherein the fourth intermediate dataset is any one of the feature datasets, and the fifth intermediate dataset is any one of the feature datasets other than the fourth intermediate dataset. Based on the fourth intermediate dataset, all the fifth intermediate datasets are filtered for related data to obtain several sixth intermediate datasets. The sixth intermediate dataset is any one of the top several fifth intermediate datasets that are associated with the fourth intermediate dataset and have the highest frequency distribution. The frequency distribution is used to characterize the trigger frequency of the second light fixture that is associated with the first light fixture within a preset time range before and after the first light fixture is triggered. The first light fixture is any one of the IoT light fixtures, and the second light fixture is any one of the IoT light fixtures other than the first light fixture. Based on the fourth intermediate dataset, interval feature analysis is performed on all the sixth intermediate datasets to obtain the supplementary features of the lamps.

2. The method according to claim 1, characterized in that, The step of performing interval feature extraction on all the aforementioned sensing datasets to obtain the feature dataset for each of the IoT lighting fixtures includes: Cooling-off period analysis is performed on all the aforementioned sensing datasets to obtain cooling-off period data, which is used to characterize the minimum trigger time interval threshold for each of the aforementioned IoT lighting fixtures; Based on the cooling period data, all the sensor datasets are updated to obtain several first intermediate datasets; Trigger feature extraction is performed on all the first intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

3. The method according to claim 1, characterized in that, The step of performing interval feature extraction on all the aforementioned sensing datasets to obtain the feature dataset for each of the IoT lighting fixtures includes: Cooling-off period analysis is performed on all the sensor datasets to obtain cooling-off period data for each IoT lamp. The cooling-off period data is used to characterize the minimum trigger time interval threshold of the corresponding IoT lamp. Based on each cooling period data, the corresponding sensing dataset is updated to obtain several second intermediate datasets; Trigger feature extraction is performed on all the second intermediate datasets to obtain the feature dataset for each of the IoT lighting fixtures.

4. The method according to claim 2 or 3, characterized in that, Trigger feature extraction is performed on all third intermediate datasets to obtain the feature dataset for each IoT lighting fixture, including: Obtain several time intervals; Based on all the time intervals, the interval trigger count analysis is performed on all the third intermediate datasets to obtain the total number of lamp triggers corresponding to each time interval. The third intermediate dataset is either the first intermediate dataset or the second intermediate dataset. Based on the total number of times all the lamps are triggered, all the time intervals are filtered to obtain the target interval, which is the time interval corresponding to the largest total number of lamp triggers among all the time intervals; Based on the target interval, interval feature statistics are performed on the corresponding third intermediate dataset to obtain the feature dataset.

5. The method according to claim 4, characterized in that, The step of performing interval feature statistics on the corresponding third intermediate dataset based on the target interval to obtain the feature dataset includes: Based on the target interval, the third intermediate dataset is filtered by timestamps to obtain a timestamp sequence, which includes several trigger timestamps within the target interval; Perform time interval analysis on the timestamp sequence to obtain a time interval sequence; The feature dataset is obtained by counting the number of occurrences of the time interval sequence.

6. The method according to claim 1, characterized in that, The frequency distribution is represented as follows: in, IoT lighting fixtures The function representation of the frequency distribution; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; IoT lighting fixtures Trigger timestamp When triggered, the IoT lighting fixtures are linked to it. and its trigger frequency ; For the first A single IoT lighting fixture m represents the total number of IoT lighting fixtures; IoT lighting fixtures The total number of trigger timestamps.

7. A classification system for Internet of Things (IoT) lighting fixtures, characterized in that, include: The first processing unit is used to acquire a sensing dataset of several Internet of Things (IoT) lighting fixtures, wherein the sensing dataset includes several trigger timestamps; The second processing unit is used to extract interval features from all the sensing datasets to obtain a feature dataset for each IoT lamp. The feature dataset includes several interval frequency features of the IoT lamp. Each interval frequency feature is used to characterize the number of times the trigger interval time of the IoT lamp occurs. The trigger interval time is obtained based on the trigger timestamps that are adjacent on the time axis. The third processing unit is used to perform feature mining on all the feature datasets to obtain supplementary features for each of the IoT lighting fixtures; The fourth processing unit is used to input all the feature datasets and the supplementary features of the lamps into the trained lamp classification model for classification, and to obtain several lamp classification results output by the trained lamp classification model, each lamp classification result corresponding to one of the IoT lamps; The step of performing feature mining on all the aforementioned feature datasets to obtain supplementary features for each of the IoT lighting fixtures includes: Obtain a fourth intermediate dataset and several fifth intermediate datasets, wherein the fourth intermediate dataset is any one of the feature datasets, and the fifth intermediate dataset is any one of the feature datasets other than the fourth intermediate dataset. Based on the fourth intermediate dataset, all the fifth intermediate datasets are filtered for related data to obtain several sixth intermediate datasets. The sixth intermediate dataset is any one of the top several fifth intermediate datasets that are associated with the fourth intermediate dataset and have the highest frequency distribution. The frequency distribution is used to characterize the trigger frequency of the second light fixture that is associated with the first light fixture within a preset time range before and after the first light fixture is triggered. The first light fixture is any one of the IoT light fixtures, and the second light fixture is any one of the IoT light fixtures other than the first light fixture. Based on the fourth intermediate dataset, interval feature analysis is performed on all the sixth intermediate datasets to obtain the supplementary features of the lamps.

8. 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 performs the method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images