Home device control method, cloud platform, device, medium and program product

Abstract

The application provides a kind of home equipment control method, cloud platform, equipment, medium and program product, method includes: determining the current control success rate prediction value and control rate threshold range of target control equipment;If control success rate prediction value meets control rate threshold range, then issue control command to target control equipment;If control success rate prediction value does not meet control rate threshold range, then issue control command to target control equipment and at least one auxiliary control equipment.The home equipment control method provided by the application can directly issue control command to target control equipment when control success rate prediction value is within threshold range, and when control success rate prediction value is not within threshold range, control command is not only issued to target control equipment but also to auxiliary control equipment, to avoid target control equipment from not receiving control command, and to issue control command to target control equipment through auxiliary control equipment as much as possible, to improve the reliability of equipment control.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a method for controlling home devices, a cloud platform, devices, media, and software products. Background Technology

[0002] With the development of smart homes, users are installing more and more smart devices in their homes. When cloud platforms control these devices, the long-term connection between the devices and the platform may be unstable, leading to occasional control failures and impacting the user experience. In scenarios with high control requirements, such as emergency situations like automatically retracting a clothes rack during rain or opening windows in case of a gas leak, the demands for successful control are particularly high, requiring a robust mechanism to ensure effective management.

[0003] Existing methods for controlling home appliances often employ cloud-based control. This involves the client sending control signals to a cloud server, which then receives and uses these signals to control the corresponding home appliances. While this is a common method, a significant drawback is its high failure rate. Sometimes, a device may appear online in the cloud but not actually be online, and sending a control command to that device individually is likely to fail. Summary of the Invention

[0004] This invention provides a home appliance control method, cloud platform, device, medium, and program product to solve the problem that home appliance control methods in the prior art are prone to failure.

[0005] In a first aspect, the present invention provides a method for controlling home appliances, comprising: Based on home device management data, determine the current predicted success rate and control rate threshold range of the target control device; If the predicted control success rate meets the control rate threshold range, a control command is sent to the target control device. If the predicted control success rate does not meet the control rate threshold range, the control command is sent to the target control device and at least one auxiliary control device; the auxiliary control device is used to send the control command to the target control device.

[0006] In one embodiment, determining the predicted success rate of current control of a target device based on home device management data includes: Based on home device management data, obtain the characteristic parameters of the target control device; The characteristic parameters of the target control device are input into the device control rate prediction model to obtain the current control success rate prediction value of the target control device output by the device control rate prediction model; the device control rate prediction model is obtained by training the model based on the sample characteristic parameters and their corresponding sample control success rates.

[0007] In one embodiment, determining the current control rate threshold range for a target control device based on home device management data includes: Based on the household device management data, determine the historical management data of the target control device; Perform trend analysis on the historical control data to obtain the trend analysis results of the successful control of the target control equipment; Based on the trend analysis results and their preset weights, update the baseline value of the control success rate of the target control device. Based on the updated control success rate benchmark and the preset floating value, the current control rate threshold range of the target control device is determined.

[0008] In one embodiment, the baseline value for the control success rate of the target control device is determined in the following manner: Based on the home device management data, obtain the number of commands successfully managed by the target control device and the total number of commands managed by the target control device within a historical time period; The baseline value of the control success rate of the target control device is obtained by dividing the number of instructions successfully controlled by the target control device by the total number of instructions controlled by the target control device.

[0009] In one embodiment, the number of auxiliary control devices is determined in the following manner: Select the first device that is currently online from the remaining control devices; the remaining control devices are the home devices belonging to the same intranet other than the target control device. Select the second devices corresponding to the top k largest predicted control success rates from each of the first devices; The number of auxiliary control devices is determined based on each of the second devices and its predicted control success rate.

[0010] In one embodiment, determining the number of auxiliary control devices based on each of the second devices and its predicted control success rate includes: The second devices are sorted from largest to smallest according to their predicted control success rate, resulting in a sorted set of third devices. Based on the predicted success rate of the target control device and the predicted success rate of the first and third devices, calculate the probability value of successful control of at least one device. If the probability value meets the control rate threshold range, then the first and third devices are identified as auxiliary control devices; If the probability value does not meet the control rate threshold range, the next third device is updated to the first third device, and the step of calculating the probability value of control success of at least one device is iteratively executed based on the control success rate prediction value of the target control device and the control success rate prediction value of the first third device, until the probability value meets the control rate threshold range, and the number of auxiliary control devices is obtained.

[0011] Secondly, the present invention also provides a cloud platform, comprising: The determination module is used to determine the current predicted success rate and control rate threshold range of the target control device based on home device management data; The first issuing module is used to issue a control command to the target control device if the predicted control success rate meets the control rate threshold range. The second sending module is used to send the control command to the target control device and at least one auxiliary control device if the predicted control success rate does not meet the control rate threshold range; the auxiliary control device is used to send the control command to the target control device.

[0012] Thirdly, the present invention provides an electronic device, the electronic device including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the above-described home device control methods.

[0013] Fourthly, the present invention also provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the above-described home device control methods.

[0014] Fifthly, the present invention also provides a computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein the computer program, when executed by the processor, implements the steps of any of the above-described home device control methods.

[0015] The home device control method, cloud platform, device, medium, and program products provided by this invention predict the current control success rate of the target control device based on the home device management data held by the cloud platform. Simultaneously, it dynamically adjusts the current control success rate threshold range. When the predicted control success rate is within the threshold range, control commands can be directly sent to the target control device in a stable control scenario. However, when the predicted control success rate is outside the threshold range, in an unstable control scenario, control commands are sent not only to the target control device but also to an auxiliary control device. This ensures that the control commands are successfully sent to the auxiliary control device as much as possible, preventing the target control device from failing to receive them, and allowing the auxiliary control device to then send the commands back to the target control device. This maximizes the chances that the device can receive and respond to the control commands, thereby improving the reliability and accuracy of home device control and enhancing the user experience. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the home appliance control method provided by the present invention.

[0018] Figure 2 This is a schematic diagram of the network topology of the smart home devices provided by the present invention.

[0019] Figure 3 This is a schematic diagram of the core processing flow on the platform side provided by the present invention.

[0020] Figure 4 This is an example flowchart of the home device control method provided by the present invention.

[0021] Figure 5 This is a schematic diagram of the cloud platform provided by the present invention.

[0022] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0024] The terms "first," "second," etc., used in this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein.

[0025] The following is combined with Figures 1-6 This invention describes the home appliance control method, cloud platform, device, medium, and program products provided by the present invention.

[0026] Combination Figure 1 , Figure 1 This is a flowchart illustrating the home appliance control method provided by the present invention.

[0027] like Figure 1 As shown, the method includes the following: Step 101: Based on home device management data, determine the current predicted success rate and control rate threshold range of the target control device; Step 102: If the predicted control success rate meets the control rate threshold range, then a control command is sent to the target control device; Step 103: If the predicted control success rate does not meet the control rate threshold range, then the control command is sent to the target control device and at least one auxiliary control device; the auxiliary control device is used to send the control command to the target control device.

[0028] It should be noted that the home device control method provided in this embodiment of the invention is implemented based on a cloud platform. The cloud platform plays a crucial role in the smart home field, serving as the core hub for controlling smart home devices. In other words, by utilizing Internet of Things (IoT) technology, various smart devices within the home are connected to the cloud platform, allowing users to remotely control these devices via the internet. For example... Figure 2 As shown, Figure 2This is a network topology diagram of home smart devices provided by the present invention. This network topology mainly illustrates a home intranet environment. Various smart devices form a home local area network (LAN) environment through a smart home gateway or smart router. The LAN devices are interconnected. Various smart devices and the cloud platform have connection channels, and each smart device is directly connected to the cloud platform. Each smart device has a built-in software module that enables it to be controlled by the cloud platform.

[0029] In the home device control method provided in this embodiment of the invention, the cloud platform has a built-in algorithm process for control scenarios with high control requirements: the cloud platform filters out other devices belonging to the same intranet as the target control device, and sends control commands not only to the target control device but also to the other devices on the intranet. Therefore, this embodiment of the invention uses the cloud platform as the execution subject to describe the home device control method.

[0030] The following specific content can be combined with Figure 3 , Figure 3 This is a schematic diagram of the core processing flow on the platform side provided by the present invention.

[0031] Specifically, cloud platforms possess powerful data processing and storage capabilities, enabling them to collect and store massive amounts of data generated by smart home devices and analyze this data. Therefore, leveraging the advantages of cloud platform data, they control home device management data, including management data for various smart devices within the home.

[0032] When a user selects to control a target device in their home based on the current scenario, the user issues a control command through their user terminal. This control command is transmitted to the cloud platform via the internet. The cloud platform parses the control command, identifies the target device to be controlled, and executes the following home device control methods based on a built-in new algorithm.

[0033] The cloud platform acquires home device management data, further filters out the management data of target control devices from the acquired home device management data, and performs data processing and feature extraction on the management data of target control devices to achieve model training and prediction, as well as dynamic threshold calculation. Furthermore, based on the model prediction results and dynamic threshold calculation results, the platform completes decision execution and feedback.

[0034] Understandably, the cloud platform processes and extracts features based on the management data of the target control device, predicts the current management success rate of the target control device through a model, and calculates the current management rate threshold range of the target control device through dynamic thresholds.

[0035] Furthermore, the cloud platform compares the predicted control success rate from the model with the currently dynamically calculated control rate threshold range.

[0036] If the predicted success rate of the control is within the control rate threshold range, it indicates that the success rate of the current control target device is relatively high. The cloud platform can directly issue control commands to the target control device. After the target control device receives the control command issued by the cloud platform, it will respond to the control command, perform the corresponding operation, generate feedback information and report it to the cloud platform, and then inform the user that the corresponding operation has been completed through the cloud platform.

[0037] If the predicted success rate of control does not meet the control rate threshold, it indicates that the success rate of the current target control device is low. To ensure that the target control device receives the control command as much as possible, the cloud platform not only sends the control command to the target control device but also sends it to at least one auxiliary control device. After receiving the control command from the cloud platform, the auxiliary control device performs internal calculations to determine whether the control command is relevant to itself. If it determines that the control command is relevant to the target control device, it sends the control command to the target control device via the intranet. When the target control device receives the control command from the cloud platform and / or the auxiliary control device, it responds to the control command, performs the corresponding operation, generates feedback information, reports it to the cloud platform, and then informs the user that the corresponding operation has been completed through the cloud platform.

[0038] Throughout the process, the target control device may receive multiple control commands related to itself, but these control commands are all for the same operation. Therefore, once an operation is executed, other control commands related to itself can be executed separately.

[0039] The home device control method provided by this invention predicts the current control success rate of the target control device based on home device management data held by a cloud platform. Simultaneously, it dynamically adjusts the current control success rate threshold range. When the predicted control success rate is within the threshold range, control commands can be directly sent to the target control device in a stable control scenario. However, when the predicted control success rate is outside the threshold range, in an unstable control scenario, control commands are sent not only to the target control device but also to an auxiliary control device. This ensures that the control commands are successfully sent to the auxiliary control device as much as possible, preventing the target control device from failing to receive them. The auxiliary control device then forwards the control commands to the target control device, maximizing the chances that the device can receive and respond to the control commands. This improves the reliability and accuracy of home device control and enhances the user experience.

[0040] In some embodiments, based on the home device management data in step 101, determining the current management success rate prediction value of the target control device specifically includes: Based on home device management data, obtain the characteristic parameters of the target control device; The characteristic parameters of the target control device are input into the device control rate prediction model to obtain the current control success rate prediction value of the target control device output by the device control rate prediction model; the device control rate prediction model is obtained by training the model based on the sample characteristic parameters and their corresponding sample control success rates.

[0041] Specifically, the cloud platform filters out the control data of the target control device from the acquired home device control data, and obtains the characteristic parameters of the target control device based on the control data of the target control device.

[0042] The characteristic parameters of the target control device are categorized into three types: important characteristic parameters, secondary characteristic parameters, and other characteristic parameters. Each category has a different proportion in the model prediction. Generally speaking, the weight of important characteristic parameters > the weight of secondary characteristic parameters > the weight of other characteristic parameters. Specifically, important characteristic parameters include, but are not limited to, device online status, historical control success rate, and the network status of the user's home router; secondary characteristic parameters include, but are not limited to, continuous online duration, device type, average response time, device location, and average control success rate of devices in the same community; other characteristic parameters include, but are not limited to, device age, device location, device version number (devices of the same brand and model may have different performance and reliability), weather factors (different weather conditions, such as heavy rain, may affect device performance), total device usage time (devices with longer usage time may have a higher failure rate), and device usage frequency at different times.

[0043] Furthermore, the cloud platform inputs the characteristic parameters of the target control device into the device control rate prediction model to obtain the current control success rate prediction value of the target control device output by the device control rate prediction model.

[0044] In one embodiment, the equipment control rate prediction model is pre-trained in the following manner: Obtain the sample feature parameters of the sample device, which include important sample feature parameters, secondary sample feature parameters, and other sample feature parameters.

[0045] Furthermore, the important feature parameters, secondary feature parameters, and other feature parameters of the sample are weighted and summed to obtain the sample control success rate. Further, the sample control success rate is determined as the label data of the sample feature parameters.

[0046] The formula is expressed as: Sample control success rate = A × important sample feature parameters + B × secondary sample feature parameters + C × other sample feature parameters.

[0047] Among them, A, B, and C are set with an initial value of 60%, 30%, and 10% based on experience, which can be dynamically adjusted later.

[0048] (1) The important feature parameters of the sample include (for example, each parameter in the important feature parameters of the sample will also be set with a weight, which can be dynamically adjusted): w1=0.2 (online status); w2=0.2 (historical average control success rate); w3=0.2 (Network status of the user's home router).

[0049] (2) The sample secondary feature parameters include (for example, each parameter in the sample secondary feature parameters will also be assigned a weight, which can be dynamically adjusted): w4=0.1 (Device continuous online time); w5=0.1 (average response time); w6=0.1 (Average success rate of network device management in the same community).

[0050] (3) Other feature parameters of the sample (for example, each of the other feature parameters of the sample will also be assigned a weight, which can be dynamically adjusted): w7=0.1 (Equipment age, equipment location, equipment version number, weather factors, total equipment usage time, equipment usage frequency in different time periods, etc.) Using a neural network learning algorithm, combined with the above sample feature parameters, an initial model is constructed.

[0051] Furthermore, the initial model is trained based on the sample feature parameters and their label data, and finally the equipment control rate prediction model is obtained.

[0052] This invention obtains the characteristic parameters of the device, comprehensively considers the multi-dimensional characteristic parameters, uses them as model input data, and predicts the current control success rate of the device through the device control rate prediction model, thereby improving the accuracy of the model prediction.

[0053] In some embodiments, based on home device management data, determining the current control rate threshold range for the target control device includes: Based on the household device management data, determine the historical management data of the target control device; Perform trend analysis on the historical control data to obtain the trend analysis results of the successful control of the target control equipment; Based on the trend analysis results and their preset weights, update the baseline value of the control success rate of the target control device. Based on the updated control success rate benchmark and the preset floating value, the current control rate threshold range of the target control device is determined.

[0054] It should be noted that because the environment and network may change at different times, the control rate threshold range also needs to be dynamically adjusted over time to obtain a more accurate threshold range.

[0055] Specifically, the cloud platform filters the control data of the target control device from the acquired home device control data, and obtains the historical control data of the target control device based on the control data of the target control device.

[0056] Furthermore, the cloud platform uses time series analysis to perform trend analysis on the historical management data of the target control equipment, and obtains trend analysis results of the successful management of the target control equipment.

[0057] If time series analysis shows an upward trend in device control success, it means the device control success rate is improving. In this case, raising the maximum expected success rate threshold is reasonable, as it reflects increased confidence in system performance. By raising the maximum expected success rate threshold, higher targets can be set to drive further system optimization to maintain or enhance the current upward trend.

[0058] Conversely, if time-series analysis shows a declining trend in device control success, it indicates a decreasing success rate and potential problems or challenges that need to be addressed promptly to prevent further performance degradation. In this case, lowering the minimum acceptable success rate threshold can provide a buffer, allowing the system some flexibility as the success rate declines, while also prompting action to identify and address the root causes of the problems.

[0059] Furthermore, the cloud platform determines a trend value based on the trend analysis results. This trend value can be positive (rising) or negative (falling), representing the changing trend of the device control success rate. Based on this trend data and preset weights, the cloud platform updates the baseline value of the control success rate of the target control device.

[0060] The baseline value for the control success rate of the target control equipment can be updated using the following formula: in, This is the updated baseline value for control success rate; This is the original baseline value for control success rate; It is a trend value determined by trend analysis results, used to measure the changing trend of equipment management success rate; It is the weighting coefficient of the trend analysis results, used to adjust the influence of trend values ​​on the threshold.

[0061] Furthermore, the cloud platform determines the current control rate threshold range of the target control device based on the updated control success rate benchmark value and the preset floating value, wherein the preset floating value is set according to the actual situation.

[0062] In other words, the cloud platform adds the updated control success rate benchmark value and the preset floating value to obtain the maximum expected success rate threshold. At the same time, it subtracts the updated control success rate benchmark value and the preset floating value to obtain the minimum acceptable success rate threshold. Furthermore, based on the calculated minimum acceptable success rate threshold and maximum expected success rate threshold, the current control rate threshold range of the target control device is defined.

[0063] The formula for calculating the minimum acceptable success rate threshold is: ; The formula for calculating the maximum expected success rate threshold is: ; in, It is a pre-defined fluctuation range used to account for fluctuations in the success rate; Therefore, the current control rate threshold range for the target control equipment is: .

[0064] This invention, through its platform's self-learning algorithm logic, can dynamically calculate the threshold range for issuing and adjusting the reliability control commands of smart homes. The threshold range, adjusted in real time according to changes in the network environment, is more accurate, making the predicted success rate of the target control device more flexible and accurate when compared with the threshold range.

[0065] Based on the above, the benchmark value for the control success rate of the target control device is determined in the following way: Based on the home device management data, obtain the number of commands successfully managed by the target control device and the total number of commands managed by the target control device within a historical time period; The baseline value of the control success rate of the target control device is obtained by dividing the number of instructions successfully controlled by the target control device by the total number of instructions controlled by the target control device.

[0066] Specifically, the cloud platform filters the control data of the target control device based on the acquired home device control data, and obtains the number of commands successfully controlled by the target control device and the total number of commands controlled by the target control device within a historical time period based on the control data of the target control device. The historical time period can be selected according to the actual situation.

[0067] Furthermore, the cloud platform divides the number of commands successfully controlled by the target control device by the total number of commands controlled by the target control device to obtain the baseline value of the control success rate of the target control device.

[0068] The formula for calculating the baseline value of the control success rate of the target control equipment is as follows: Control success rate benchmark (S) = Number of successfully controlled instructions / Total number of controlled instructions.

[0069] This invention calculates a baseline value for the success rate of device control based on the successful control of devices within a historical time period. This baseline is used as a benchmark for dynamic threshold calculation, which helps to adjust the threshold range in real time and ensures that an accurate threshold range is calculated in a changing usage environment.

[0070] In some embodiments, the number of auxiliary control devices, based on step 103, is determined in the following manner: Select the first device that is currently online from the remaining control devices; the remaining control devices are the home devices belonging to the same intranet other than the target control device. Select the second devices corresponding to the top k largest predicted control success rates from each of the first devices; The number of auxiliary control devices is determined based on each of the second devices and its predicted control success rate.

[0071] It's important to note that when the cloud platform sends control commands to the target control device via auxiliary control devices, the number and specific auxiliary control devices to be sent to are determined internally by the cloud platform before the commands are executed. The selection of auxiliary control devices involves choosing from the remaining control devices within the same home network, excluding the target control device.

[0072] Specifically, the cloud platform selects the first device that is currently online from among the other control devices, which means that when selecting auxiliary control devices, priority is given to devices that are currently online.

[0073] Furthermore, the cloud platform obtains the predicted control success rate of each first device. The method for obtaining the predicted control success rate of the first device is the same as that for obtaining the predicted control success rate of the target control device. The characteristic parameters are obtained and input into the device control rate prediction model for prediction, and the predicted control success rate of each first device can be obtained. The specific process will not be elaborated here. Moreover, the execution order of predicting the control success rate of each first device through the model is not limited to this step.

[0074] Furthermore, the cloud platform compares the predicted control success rates of each first device and selects the top k largest predicted control success rates based on the comparison results, where k is set according to the actual situation.

[0075] Furthermore, the cloud platform identifies the second device corresponding to the top k largest predicted control success rates as the second device, indicating that when selecting auxiliary control devices, it is also necessary to prioritize devices with higher control success rates.

[0076] In an exceptional case, if the predicted success rates of the control of the kth and k+1th first devices are the same, the first device that has most recently reported data to the cloud platform will be selected and classified as the second device.

[0077] Furthermore, the cloud platform determines the number of auxiliary control devices based on each secondary device and its predicted control success rate.

[0078] This invention first selects devices that are online and have a high success rate of control as candidates for auxiliary control devices. Then, it calculates the probability value of the cloud platform successfully controlling at least one device using these candidate devices and their predicted control success rates. When the calculated probability value is within a threshold range, the success rate of sending control commands to the target control device can be increased. This ensures that the device can receive control commands as much as possible, thereby improving the reliability and accuracy of home device control and enhancing the user experience.

[0079] Based on the above, determining the number of auxiliary control devices according to each of the second devices and their predicted control success rates specifically includes: The second devices are sorted from largest to smallest according to their predicted control success rate, resulting in a sorted set of third devices. Based on the predicted success rate of the target control device and the predicted success rate of the first and third devices, calculate the probability value of successful control of at least one device. If the probability value meets the control rate threshold range, then the first and third devices are identified as auxiliary control devices; If the probability value does not meet the control rate threshold range, the next third device is updated to the first third device, and the step of calculating the probability value of control success of at least one device is iteratively executed based on the control success rate prediction value of the target control device and the control success rate prediction value of the first third device, until the probability value meets the control rate threshold range, and the number of auxiliary control devices is obtained.

[0080] Specifically, the cloud platform sorts each second device from largest to smallest according to the predicted success rate of control, resulting in multiple sorted third devices.

[0081] Furthermore, the cloud platform calculates the probability value of successful control of at least one device based on the predicted success rate of the target control device and the predicted success rate of the first and third devices.

[0082] The formula for calculating the probability of successful control of at least one device is as follows: Where P is the probability value of successfully controlling at least one device. , ... These are the predicted success rates of controlling n third-party devices.

[0083] For example, if the predicted success rate of controlling target device A is 80%, and the predicted success rate of controlling auxiliary device B is 90%, then if the cloud platform controls both device A and device B simultaneously, the probability that at least one device will be successfully controlled is: That is, a 98% success rate.

[0084] If the calculated probability value is within the control rate threshold range, the cloud platform will identify the first and third devices as auxiliary control devices.

[0085] If the calculated probability value is not within the control rate threshold range, the cloud platform will update the next third device to the first third device, and iteratively execute the step of calculating the probability value of at least one device's successful control based on the predicted control success rate of the target control device and the predicted control success rate of the first third device, until the calculated probability value meets the control rate threshold range. At this point, it is no longer necessary to select auxiliary control devices. It can then be determined which third devices were selected as auxiliary control devices, and thus the number of auxiliary control devices can also be determined.

[0086] This invention first selects devices that are online and have a high success rate of control as candidates for auxiliary control devices. Then, it calculates the probability value of the cloud platform successfully controlling at least one device using these candidate devices, the target control device, and the predicted control success rate of the devices. When the calculated probability value meets the threshold range, the success rate of sending control commands to the target control device can be increased. This ensures that the device can receive the control commands as much as possible, thereby improving the reliability and accuracy of home device control and enhancing the user experience.

[0087] Based on the content of all the above embodiments, combined with Figure 4 , Figure 4 This is an example flowchart of the home device control method provided by the present invention. The following content will describe the overall process of an example.

[0088] S01, the user sends a light-on command to device 3 via the smart home APP.

[0089] S02. After receiving this instruction, the cloud platform performs internal calculations. When it is found that the predicted success rate of device 3 does not meet the control rate threshold, it finds devices 1, 2, 4, etc. that belong to the same home intranet as device 3, and selects device 1 and device 2 as auxiliary control devices according to a certain strategy.

[0090] S03, the cloud platform simultaneously sends a command to device 1, device 2, and device 3 to control device 3 to turn on the light.

[0091] S04. After receiving the instruction, Device 1 and Device 2 perform internal calculations to determine whether the instruction is a control command related to themselves.

[0092] S05, when Device 1 and Device 2 detect a command that is not under their control, they broadcast the command over the intranet.

[0093] S06. Devices 1, 2, and 3 may receive control messages with varying delays, but each message body contains a fixed and relevant serial number. If device 3 receives the command first, it executes the light-on operation; if device 3 receives the broadcast command from device 1 or device 2 first, it also continues to execute the light-on operation. Throughout this process, smart device 3 may receive multiple messages related to itself (the message serial number needs to be determined), but one thing is clear: the command executed is always to turn on the light.

[0094] Once you have executed the command to turn on the light once, you do not need to execute other commands related to turning on the light.

[0095] Note: The types of devices controlled are not limited to turning smart lights on and off. Possible applications include opening and closing smart curtains, turning smart TVs on and off, adjusting smart light colors, and so on. Once a command is executed, other related commands should not be executed again to avoid multiple volume adjustment commands being received and causing repeated adjustments.

[0096] S07, after the smart device 3 finishes turning on the light, it broadcasts feedback that the light has been turned on and also reports it to the cloud platform.

[0097] S08, after receiving the message, the cloud platform will update the device status.

[0098] The cloud platform provided by the present invention is described below. The cloud platform described below can be referred to in correspondence with the home device control method described above.

[0099] Reference Figure 5 , Figure 5 This is a schematic diagram of the cloud platform provided by the present invention.

[0100] The cloud platform includes: The determination module 510 is used to determine the current predicted value of the control success rate and the control rate threshold range of the target control device based on the home device control data.

[0101] The first issuing module 520 is used to issue a control command to the target control device if the predicted control success rate meets the control rate threshold range.

[0102] The second issuing module 530 is used to issue the control command to the target control device and at least one auxiliary control device if the predicted control success rate does not meet the control rate threshold range; the auxiliary control device is used to issue the control command to the target control device.

[0103] The cloud platform provided by this invention predicts the current control success rate of the target device based on the home device management data it possesses. Simultaneously, it dynamically adjusts the current control success rate threshold range. When the predicted control success rate is within the threshold range, control commands can be directly sent to the target device in a stable control scenario. However, when the predicted control success rate is outside the threshold range, in an unstable control scenario, control commands are sent not only to the target device but also to an auxiliary control device. This ensures that the control commands are successfully sent to the auxiliary control device as much as possible, preventing the target device from failing to receive them. The auxiliary control device then forwards the control commands to the target device, maximizing the chances that the device can receive and respond to the control commands. This improves the reliability and accuracy of home device control and enhances the user experience.

[0104] Furthermore, the determining module 510 is also used for: Based on home device management data, obtain the characteristic parameters of the target control device; The characteristic parameters of the target control device are input into the device control rate prediction model to obtain the current control success rate prediction value of the target control device output by the device control rate prediction model; the device control rate prediction model is obtained by training the model based on the sample characteristic parameters and their corresponding sample control success rates.

[0105] Furthermore, the determining module 510 is also used for: Based on the household device management data, determine the historical management data of the target control device; Perform trend analysis on the historical control data to obtain the trend analysis results of the successful control of the target control equipment; Based on the trend analysis results and their preset weights, update the baseline value of the control success rate of the target control device. Based on the updated control success rate benchmark and the preset floating value, the current control rate threshold range of the target control device is determined.

[0106] Furthermore, the cloud platform is also used for: Based on the home device management data, obtain the number of instructions successfully managed by the target control device and the total number of instructions managed by the target control device within the historical time period; The baseline value of the control success rate of the target control device is obtained by dividing the number of instructions successfully controlled by the target control device by the total number of instructions controlled by the target control device.

[0107] Furthermore, the cloud platform is also used for: Select the first device that is currently online from the remaining control devices; the remaining control devices are the home devices belonging to the same intranet other than the target control device. Select the second devices corresponding to the top k largest predicted control success rates from each of the first devices; The number of auxiliary control devices is determined based on each of the second devices and its predicted control success rate.

[0108] Furthermore, the cloud platform is also used for: The second devices are sorted from largest to smallest according to their predicted control success rate, resulting in a sorted set of third devices. Based on the predicted success rate of the target control device and the predicted success rate of the first and third devices, calculate the probability value of successful control of at least one device. If the probability value meets the control rate threshold range, then the first and third devices are identified as auxiliary control devices; If the probability value does not meet the control rate threshold range, the next third device is updated to the first third device, and the step of calculating the probability value of control success of at least one device is iteratively executed based on the control success rate prediction value of the target control device and the control success rate prediction value of the first third device, until the probability value meets the control rate threshold range, and the number of auxiliary control devices is obtained.

[0109] It should be noted that the cloud platform provided by the present invention can execute the home device control method described in any of the above embodiments during actual operation, which will not be elaborated in this embodiment.

[0110] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 6As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a home device control method. This method includes: determining a predicted control success rate and a control rate threshold range for a target control device based on home device management data; if the predicted control success rate meets the control rate threshold range, issuing a control command to the target control device; if the predicted control success rate does not meet the control rate threshold range, issuing the control command to the target control device and at least one auxiliary control device; the auxiliary control device is used to issue the control command to the target control device.

[0111] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a 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 the present invention. 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.

[0112] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the home device control method provided in the above embodiments, the method comprising: determining a current control success rate prediction value and a control rate threshold range of a target control device based on home device control data; if the control success rate prediction value meets the control rate threshold range, issuing a control command to the target control device; if the control success rate prediction value does not meet the control rate threshold range, issuing the control command to the target control device and at least one auxiliary control device; the auxiliary control device being used to issue the control command to the target control device.

[0113] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the home device control method provided in the above embodiments. The method includes: determining a current control success rate prediction value and a control rate threshold range for a target control device based on home device control data; if the control success rate prediction value meets the control rate threshold range, issuing a control command to the target control device; if the control success rate prediction value does not meet the control rate threshold range, issuing the control command to the target control device and at least one auxiliary control device; the auxiliary control device is used to issue the control command to the target control device.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling home appliances, characterized in that, Applied to cloud platforms, including: Based on home device management data, determine the current predicted success rate and control rate threshold range of the target control device; If the predicted control success rate meets the control rate threshold range, a control command is sent to the target control device. If the predicted control success rate does not meet the control rate threshold range, the control command is sent to the target control device and at least one auxiliary control device; the auxiliary control device is used to send the control command to the target control device.

2. The home appliance control method according to claim 1, characterized in that, Based on home device management data, determine the predicted success rate of current control of the target devices, including: Based on home device management data, obtain the characteristic parameters of the target control device; The characteristic parameters of the target control device are input into the device control rate prediction model to obtain the current control success rate prediction value of the target control device output by the device control rate prediction model; the device control rate prediction model is obtained by training the model based on the sample characteristic parameters and their corresponding sample control success rates.

3. The home appliance control method according to claim 1, characterized in that, Based on home device management data, determine the current control rate threshold range for the target control devices, including: Based on the household device management data, determine the historical management data of the target control device; Perform trend analysis on the historical control data to obtain the trend analysis results of the successful control of the target control equipment; Based on the trend analysis results and their preset weights, update the baseline value of the control success rate of the target control device. Based on the updated control success rate benchmark and the preset floating value, the current control rate threshold range of the target control device is determined.

4. The home appliance control method according to claim 3, characterized in that, The baseline value for the control success rate of the target control equipment is determined in the following way: Based on the home device management data, obtain the number of commands successfully managed by the target control device and the total number of commands managed by the target control device within a historical time period; The baseline value of the control success rate of the target control device is obtained by dividing the number of instructions successfully controlled by the target control device by the total number of instructions controlled by the target control device.

5. The home appliance control method according to any one of claims 1-4, characterized in that, The number of auxiliary control devices is determined in the following way: Select the first device that is currently online from the remaining control devices; the remaining control devices are the home devices belonging to the same intranet other than the target control device. Select the second devices corresponding to the top k largest predicted control success rates from each of the first devices; The number of auxiliary control devices is determined based on each of the second devices and its predicted control success rate.

6. The home appliance control method according to claim 5, characterized in that, The step of determining the number of auxiliary control devices based on each of the second devices and its predicted control success rate includes: The second devices are sorted from largest to smallest according to their predicted control success rate, resulting in a sorted set of third devices. Based on the predicted success rate of the target control device and the predicted success rate of the first and third devices, calculate the probability value of successful control of at least one device. If the probability value meets the control rate threshold range, then the first and third devices are identified as auxiliary control devices; If the probability value does not meet the control rate threshold range, the next third device is updated to the first third device, and the step of calculating the probability value of control success of at least one device is iteratively executed based on the control success rate prediction value of the target control device and the control success rate prediction value of the first third device, until the probability value meets the control rate threshold range, and the number of auxiliary control devices is obtained.

7. A cloud platform, characterized in that, include: The determination module is used to determine the current predicted success rate and control rate threshold range of the target control device based on home device management data; The first issuing module is used to issue a control command to the target control device if the predicted control success rate meets the control rate threshold range. The second sending module is used to send the control command to the target control device and at least one auxiliary control device if the predicted control success rate does not meet the control rate threshold range. The auxiliary control device is used to send the control command to the target control device.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the home device control method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, wherein a computer program is stored on the non-transitory computer-readable storage medium, characterized in that, When the computer program is executed by a processor, it implements the steps of the home device control method as described in any one of claims 1 to 6.

10. A computer program product, the computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the home device control method as described in any one of claims 1 to 6.

Images