Device adjustment processing method and apparatus, electronic device, and storage medium

Abstract

The application provides a device adjustment processing method and device, an electronic device, a storage medium and a computer program product, and relates to the technical field of Internet of Things. The method comprises the following steps: acquiring monitoring data; predicting the working condition of a target function based on the monitoring data to obtain corresponding target attribute data; the target attribute data comprises attribute data that influences the working condition of the target function; based on the target attribute data, target adjustment data having a corresponding relationship with the target attribute data is found; and if the actual working condition of the target function does not meet a set condition, the target function of the target device is adjusted according to the target adjustment data. The application solves the problem that the working condition of an intelligent device does not meet an expected working state in related technologies.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and more specifically, to a device regulation and processing method, apparatus, electronic device, storage medium, and computer program product. Background Technology

[0002] With the rapid development of IoT technology, various smart devices are entering people's lives. Users can enjoy various smart services by deploying smart devices under the IoT framework. For example, smart devices can detect events occurring in a space and then execute corresponding device control operations when a target event is detected.

[0003] However, smart devices are susceptible to environmental changes and may not wake up in time when a target event occurs, leading to missed or false alarms. Understandably, this could cause the smart device to fail to detect the target event or incorrectly determine that it has occurred. Keeping the smart device in a wake-up state for extended periods could also cause abnormal power consumption.

[0004] As can be seen from the above, the problem of smart devices not performing as expected still needs to be addressed. Summary of the Invention

[0005] This application provides a device adjustment and processing method, apparatus, electronic device, and storage medium, which can solve the problem in related technologies where the working state of intelligent devices does not meet expectations. The technical solutions are as follows:

[0006] According to one aspect of this application, a device adjustment processing method includes: acquiring monitoring data; the monitoring data being data detected when a target device operates a target function; predicting the operating status of the target function based on the monitoring data to obtain corresponding target attribute data; the target attribute data including attribute data affecting the operating status of the target function; searching for target adjustment data that has a corresponding relationship with the target attribute data based on the target attribute data; the corresponding relationship being used to describe different attribute data and their corresponding device adjustment data of the target device; the target adjustment data being used to adjust the operating status of the target function; and if the actual operating status of the target function does not meet set conditions, adjusting the target function of the target device according to the target adjustment data.

[0007] According to one aspect of this application, a device adjustment processing apparatus includes: a data acquisition module for acquiring monitoring data; the monitoring data being data detected when a target device operates a target function; a data prediction module for predicting the operating status of the target function based on the monitoring data to obtain corresponding target attribute data; the target attribute data including attribute data affecting the operating status of the target function; a data search module for searching for target adjustment data that has a corresponding relationship with the target attribute data; the corresponding relationship is used to describe different attribute data and their corresponding device adjustment data for the target device; the target adjustment data is used to adjust the operating status of the target function; and a device adjustment module for adjusting the target function of the target device according to the target adjustment data if the actual operating status of the target function does not meet set conditions.

[0008] In an exemplary embodiment, the data prediction module is further configured to input the monitoring data into a wake-up model to predict the working status of the target function based on the monitoring data; the device adjustment processing apparatus further includes a wake-up model construction module, which is further configured to acquire sample data; the sample data includes sample monitoring data and its corresponding different sample attribute data; assign corresponding weights to the sample monitoring data and each of the sample attribute data; and establish a wake-up model based on the sample monitoring data and its corresponding weights and each of the sample attribute data and its corresponding weights.

[0009] In an exemplary embodiment, the wake-up model construction module is further configured to determine the triggering conditions of a set event and the working conditions of the target function; determine whether the working conditions of the target function meet the set conditions based on the triggering conditions; and, if the working conditions do not meet the set conditions, perform supervised learning on the wake-up model based on the working conditions to adjust the sensitivity of the wake-up model in outputting the target attribute data.

[0010] In an exemplary embodiment, the wake-up model construction module is further configured to, when the set event is triggered, increase the sensitivity of the wake-up model in outputting target attribute data if the target function is not woken up.

[0011] In an exemplary embodiment, the wake-up model construction module is further configured to reduce the sensitivity of the wake-up model in outputting target attribute data if the target function is woken up when the set event is not triggered.

[0012] In an exemplary embodiment, the wake-up model construction module is further configured to acquire historical trigger data and historical monitoring data; the historical trigger data includes historical triggering situations of a set event; input the historical monitoring data into the wake-up model to obtain the predicted working status of the target function; compare the deviation between the historical triggering situation and the predicted working status, and perform supervised learning of the wake-up model based on the deviation.

[0013] In an exemplary embodiment, the data lookup module is further configured to obtain a target data table, which stores the correspondence between different attribute data and different device adjustment data; based on the target attribute data, the module searches the target data table for device adjustment data corresponding to the target attribute data to obtain the target adjustment data.

[0014] In an exemplary embodiment, the equipment adjustment processing apparatus is further configured to generate a correspondence between different attribute data and their corresponding target equipment adjustment data through a relationship prediction model; the equipment adjustment processing apparatus further includes a relationship prediction model construction module, which is configured to acquire sample attribute data; determine a prior distribution for the sample attribute data based on the objective of predicting the corresponding target adjustment data using the sample attribute data, and construct an objective function based on the sample attribute data; wherein the prior distribution is used to constrain the prediction result of the relationship prediction model; calculate the posterior distribution of the sample attribute data based on the prior distribution and the objective function; and establish the relationship between different attribute data and different equipment adjustment data based on the posterior distribution to obtain the relationship prediction model.

[0015] In one exemplary embodiment, the target adjustment data includes a set restart time; the device adjustment module is further configured to control the target device to restart at the set restart time, so that the restarted target device wakes up the target function.

[0016] According to one aspect of this application, an electronic device includes at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, implements the device regulation processing method as described above.

[0017] According to one aspect of this application, a storage medium having a computer program stored thereon, which, when executed by one or more processors, implements the device regulation processing method as described above.

[0018] According to one aspect of this application, a computer program product includes a computer program that, when executed by one or more processors, implements the device regulation processing method as described above.

[0019] The beneficial effects of the technical solution provided in this application are:

[0020] In the above technical solution, the working status of the target function under the current conditions can be predicted by monitoring data, and the corresponding target attribute data can be obtained. Then, the target attribute data can be used to find the corresponding device adjustment data to obtain the corresponding target adjustment data. Thus, when the actual working status of the target function does not meet the set conditions, the target function can be adjusted using the target adjustment data so that the adjusted target function works more effectively under the conditions monitored by the monitoring data. This effectively solves the problem in related technologies where the working status of intelligent devices does not meet the expected working state. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram based on the implementation environment involved in this application;

[0023] Figure 2 This is a hardware structure diagram of an electronic device according to an exemplary embodiment;

[0024] Figure 3 This is a flowchart illustrating a device adjustment processing method according to an exemplary embodiment;

[0025] Figure 4 yes Figure 2 The steps for constructing the relationship prediction model in the corresponding embodiment are shown in a flowchart of one embodiment;

[0026] Figure 5a and Figure 5b This is a schematic diagram illustrating the specific implementation of a device adjustment and processing method in an application scenario;

[0027] Figure 6 This is a structural block diagram of a device adjustment and processing apparatus according to an exemplary embodiment;

[0028] Figure 7 This is a structural block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0030] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this disclosure means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0031] As mentioned earlier, smart devices are susceptible to environmental changes and may not be able to be woken up in time when the target event occurs, resulting in missed and false alarms.

[0032] Specifically, missed detections typically occur when the target device fails to respond to a pre-set event in a timely manner. For example, in the ultrasonic monitoring function of a smart door lock, if a target (such as a user) is within the device's monitoring range, but the device fails to detect its presence due to environmental interference (such as noise, other signal interference) or insufficient sensitivity, a missed detection occurs. This situation may affect the normal operation of the device (such as failure to unlock in time) and degrade the user experience.

[0033] False alarms typically occur when the target device responds incorrectly to a non-target event. For example, ultrasonic monitoring may misinterpret the presence of a target under certain environmental factors (such as wind, vibration, temperature changes, etc.).

[0034] As can be seen from the above, there is still a defect in the relevant technologies where the working condition of smart devices does not meet expectations.

[0035] Therefore, the device adjustment and processing method provided in this application can effectively improve the working status of intelligent devices. Accordingly, the device adjustment and processing method is applicable to device adjustment and processing devices, which can be deployed on electronic devices. The electronic devices can be computer devices configured with the von Neumann architecture, such as desktop computers, laptops, servers, etc.; the electronic devices can also be intelligent devices with central control functions.

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0037] Figure 1 This is a schematic diagram of an implementation environment involved in device regulation processing. This implementation environment includes at least a user terminal 110, a smart device 130, a server 170, and network equipment. Figure 1 In this context, network devices include gateway 150 and router 190, but this is not intended to be a specific limitation.

[0038] The user terminal 110, which can also be considered as a user terminal or terminal, can deploy (or install) the client associated with the smart device 130. This user terminal 110 can be an electronic device such as a smartphone, tablet, laptop, desktop computer, smart control panel, or other device with display and control functions, and is not limited here.

[0039] The client, associated with the smart device 130, is essentially where the user registers an account and configures the smart device 130. For example, the configuration includes adding a device identifier to the smart device 130, so that when the client runs on the user terminal 110, it can provide the user with functions such as device display and device control of the smart device 130. This client can be in the form of an application or a web page. Correspondingly, the interface for displaying the device on the client can be in the form of a program window or a web page, and there is no limitation here.

[0040] Smart device 130 is deployed in gateway 150 and communicates with gateway 150 through its own configured communication module, thereby being controlled by gateway 150. It should be understood that smart device 130 generally refers to one of multiple smart devices 130. This application embodiment only uses smart device 130 as an example; that is, this application embodiment does not limit the number or type of smart devices deployed in gateway 150. In one application scenario, smart device 130 is deployed in gateway 150 by accessing it through a local area network. The process of smart device 130 accessing gateway 150 through a local area network includes: gateway 150 first establishes a local area network, and smart device 130 joins the local area network established by gateway 150 by connecting to it. This local area network includes, but is not limited to, ZIGBEE or Bluetooth. Among them, the smart device 130 can be a smart printer, smart fax machine, smart camera, smart air conditioner, smart door lock, smart light, or a human body sensor, door and window sensor, temperature and humidity sensor, water immersion sensor, natural gas alarm, smoke alarm, wall switch, wall socket, wireless switch, wireless wall sticker switch, cube controller, curtain motor, millimeter wave radar, etc., equipped with a communication module.

[0041] The interaction between user terminal 110 and smart device 130 can be achieved through a local area network (LAN) or a wide area network (WAN). In one application scenario, user terminal 110 establishes a wired or wireless communication connection with gateway 150 via router 190, such as Wi-Fi, allowing user terminal 110 and gateway 150 to be deployed on the same LAN, thus enabling user terminal 110 to interact with smart device 130 via the LAN path. In another application scenario, user terminal 110 establishes a wired or wireless communication connection with gateway 150 via server 170, such as 2G, 3G, 4G, 5G, or Wi-Fi, allowing user terminal 110 and gateway 150 to be deployed on the same WAN, thus enabling user terminal 110 to interact with smart device 130 via the WAN path.

[0042] The server-side 170 can also be considered as the cloud, cloud platform, platform side, server side, etc. This server-side 170 can be a single server, a server cluster consisting of multiple servers, or a cloud computing center consisting of multiple servers, in order to better provide backend services to a massive number of user terminals 110. For example, backend services include equipment adjustment and processing services.

[0043] In one application scenario, the target device can be a smart device 130. The server 170 acquires the data detected when the smart device 130 is running the target function, i.e., monitoring data. Based on the monitoring data, the server predicts the working status of the target function and obtains the corresponding target attribute data. Based on the target attribute data, the server finds the target adjustment data that corresponds to the target attribute data. Furthermore, if the actual working status of the target function of the smart device 130 does not meet the set conditions, the server adjusts the target function of the smart device 130 according to the target adjustment data.

[0044] Of course, in other application scenarios, the device adjustment process completed by the user terminal 110 can also be implemented by the smart device 130. The central control module of the smart device 130 predicts the working status of the target function based on the monitoring data and obtains the corresponding target attribute data. Based on the target attribute data, it searches for target adjustment data that has a corresponding relationship with the target attribute data, and adjusts the target function according to the target adjustment data when the actual working status of the target function does not meet the set conditions.

[0045] Please see Figure 2 , Figure 2 This is a hardware structure diagram of an electronic device according to an exemplary embodiment. This electronic device is suitable for... Figure 1 The server-side configuration 170 in the implementation environment is shown.

[0046] It should be noted that this electronic device is merely an example adapted to this application and should not be construed as providing any limitation on the scope of use of this application. Furthermore, this electronic device should not be interpreted as requiring or depending on any specific feature. Figure 2 One or more components of the exemplary electronic device 200 shown.

[0047] The hardware structure of electronic device 200 can vary significantly due to differences in configuration or performance, such as... Figure 2 As shown, the electronic device 200 includes: a power supply 210, an interface 230, at least one memory 250, and at least one central processing unit (CPU) 270.

[0048] Specifically, power supply 210 is used to provide operating voltage for various hardware devices on electronic device 200.

[0049] Interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. For example, to perform... Figure 1 The diagram illustrates the interaction between the smart device 130 and the server 170 in the implementation environment.

[0050] Of course, in other examples adapted in this application, interface 230 may further include at least one serial-to-parallel conversion interface 233, at least one input / output interface 235, and at least one USB interface 237, etc. Figure 2 As shown, this does not constitute a specific limitation.

[0051] The memory 250 serves as a carrier for resource storage and can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored on it include the operating system 251, application programs 253, and data 255, etc., and the storage method can be temporary storage or permanent storage.

[0052] The operating system 251 is used to manage and control the various hardware devices and application programs 253 on the electronic device 200, so as to enable the central processing unit 270 to perform calculations and processing on the massive data 255 in the memory 250. It can be Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0053] Application 253 is a computer program formed by computer-readable instructions based on operating system 251 to perform at least one specific task, and may include at least one module ( Figure 2 (Not shown), each module can contain corresponding computer-readable instructions. For example, the device adjustment processing device can be considered as an application program 253 deployed on electronic device 200.

[0054] Data 255 can be photos, pictures, etc. stored on a disk, or monitoring data, equipment adjustment data, etc., stored in memory 250.

[0055] The central processing unit 270 may include one or more processors and is configured to communicate with the memory 250 via at least one communication bus to read computer programs stored in the memory 250, thereby performing calculations and processing on massive amounts of data 255 stored in the memory 250. For example, the device adjustment processing method may be completed by the central processing unit 270 reading the application program 253 stored in the memory 250.

[0056] Furthermore, this application can also be implemented through hardware circuits or a combination of hardware circuits and software. Therefore, the implementation of this application is not limited to any specific hardware circuit, software, or combination thereof.

[0057] Please see Figure 3 This application provides a device adjustment processing method, which is applicable to electronic devices. For example, the electronic device may be... Figure 1 The server-side 170 shown in the implementation environment can also be... Figure 1The diagram shows intelligent devices 130, gateways 150, etc., in the implementation environment. The hardware structure of this electronic device can be as follows: Figure 2 As shown.

[0058] In the following method embodiments, for ease of description, the execution subject of each step of the method is an electronic device, but this does not constitute a specific limitation.

[0059] like Figure 3 As shown, the method may include the following steps:

[0060] Step 310: Obtain monitoring data.

[0061] The monitoring data refers to the data detected when the target device is performing the target function. The target device refers to an intelligent device with the target function, which can be a monitoring function, such as the ultrasonic monitoring function of a smart door lock, without being specifically limited here.

[0062] For example, taking a smart door lock as the target device, the target function can be an ultrasonic function. Then, the monitoring data is the data detected when the smart door lock runs the ultrasonic monitoring function. It can include at least one of the following data: the wake-up time when the ultrasonic monitoring function is woken up, the frequency, power, pulse width, distance, angle, orientation, and the amount of received bounce signal, etc., without limitation.

[0063] Step 330: Based on the monitoring data, predict the working status of the target function to obtain the corresponding target attribute data.

[0064] Among them, target attribute data includes attribute data that affects the working condition of the target function. In other words, target attribute data can describe the working condition of the target device in performing the target function.

[0065] First, it should be noted that the target attribute data is predicted based on key factors reflected in the monitoring data (such as signal strength, distance, and angle). The target attribute data can affect the working status of the target function, such as whether the target device can effectively identify the target and whether it can accurately start the corresponding operation.

[0066] For example, the wake-up time in the monitoring data may be related to the response time of the target device to a certain target, and the amount of received bounce signal may be related to the recognition accuracy or response speed of the target device, and so on.

[0067] Regarding the working status of the target function, it can refer to the overall operating status of the target device when performing the target function. The monitoring data can reflect the performance of the target device under the target function, such as whether the target device can trigger and complete the target function normally, the accuracy of the output of the target device when performing the target function, the deviation range from the expected result, etc., which are not limited here.

[0068] Regarding prediction, statistical methods or machine learning techniques can be used to map monitoring data to target attribute data in order to predict the working status of target functions based on monitoring data; no specific limitations are specified here.

[0069] It should be noted that target attribute data can be considered as the ideal working state of a target function. In other words, target attribute data describes the optimal or expected performance that the target function should achieve when the target device operates under specific conditions. Specifically, target attribute data reflects the capabilities or conditions required for the target function in its ideal state to ensure that the target device can effectively and accurately complete its predetermined tasks.

[0070] Step 350: Based on the target attribute data, find the target adjustment data that corresponds to the target attribute data.

[0071] The correspondence relationship describes different attribute data and their corresponding target device adjustment data. The device adjustment data can be data used to adjust the target device; specifically, it may include at least one of the target device's sensitivity, threshold parameters, signal strength, etc., without further specific limitations. Target adjustment data is device adjustment data that corresponds to the target attribute data and can be used to adjust the operation of the target function.

[0072] It is understandable that adjusting the target function using target adjustment data can enable the target function to work more effectively under specific conditions, that is, to work more effectively under the conditions monitored by the monitoring data.

[0073] Taking the target device as a smart door lock and the target function as ultrasonic monitoring as an example, the target attribute data includes ultrasonic frequency, orientation, received and reflected signal amount, distance, angle and other attribute data. Based on the target attribute data, the target adjustment data is found. The target adjustment data includes setting the ultrasonic frequency, power and pulse width for the ultrasonic monitoring function so that the ultrasonic module works as expected.

[0074] Step 370: If the actual working condition of the target function does not meet the set conditions, then adjust the target function of the target device according to the target adjustment data.

[0075] Among them, the set conditions can be the basic rules for evaluating the performance of the target function, used to determine whether the target function meets the expected working state in actual work.

[0076] Specifically, the setting conditions can be whether the target function can quickly and accurately identify the target, or the response time of the target function, etc. There are no restrictions here. It should be understood that the configuration of the setting conditions is related to the target function of the target device.

[0077] For example, if the target device is a smart door lock and the target function is ultrasonic monitoring, then the expectation for this ultrasonic monitoring function is that within a certain area, it can detect the target more quickly and trigger the corresponding operation (e.g., unlocking, waking up the peephole camera). In this scenario, if the target has already manually triggered the operation, but the ultrasonic monitoring function has not yet detected the target, then it indicates that the actual operation of the ultrasonic monitoring function does not meet the set conditions. The ultrasonic detection function refers to the ability of a smart door lock, such as emitting ultrasonic waves and receiving their reflected signals, to perceive the presence, movement, or distance changes of targets within a real-time area.

[0078] It should be noted that if the actual operation of the target function does not meet the set conditions, that is, if it does not meet the expected operating state, in other words, the configuration of the target function is not adapted to the conditions monitored by the monitoring data. Furthermore, as mentioned earlier, adjusting the target function using target adjustment data can enable the target function to work more effectively under specific conditions. Based on this, the target adjustment data can be used to adjust the conditions of the target function, thereby enabling the adjusted target function to work more effectively under the conditions monitored by the monitoring data.

[0079] Continuing with the previous example, if the target has already been manually triggered, but the ultrasonic monitoring function has not yet detected the target, then the target adjustment data can include the ultrasonic frequency of the ultrasonic monitoring function. The ultrasonic frequency can optimize the detection range and accuracy of the ultrasonic monitoring function. If the target is close but not detected, the frequency can be increased (e.g., from 40kHz to 60kHz) to improve sensitivity. The target adjustment data can also include ultrasonic power, which can increase the ultrasonic signal strength to overcome environmental interference. The ultrasonic power can be increased (e.g., from 80dB to 100dB) to enhance signal reflection. The target adjustment data can also include pulse width, which can optimize the transmission time and echo quality of the ultrasonic signal. Wider pulses are suitable for long-distance detection, while narrower pulses are suitable for high-resolution detection.

[0080] Through the above process, the working status of the target function under the current conditions can be predicted by monitoring data, and the corresponding target attribute data can be obtained. Then, the corresponding device adjustment data can be found using the target attribute data to obtain the corresponding target adjustment data. Thus, when the actual working status of the target function does not meet the set conditions, the target function can be adjusted using the target adjustment data so that the adjusted target function works more effectively under the conditions monitored by the monitoring data, thereby solving the problem that the working status of smart devices does not meet the expected working state.

[0081] In one exemplary embodiment, the target adjustment data includes a set restart time; the method may further include: adjusting the target function of the target device according to the target adjustment data, including: controlling the target device to restart at the set restart time, so that the restarted target device wakes up the target function.

[0082] Setting a restart time refers to the set restart time for the target device. When the set restart time is reached, the target device is controlled to restart, so that the restarted target device wakes up the target function and ensures that the target function of the target device works normally.

[0083] Taking a smart door lock as an example, smart door locks are susceptible to environmental changes, leading to missed and false alarms. This can result in the inability to detect people or the detection of people even when no one is present, causing abnormal power consumption and making it impossible to accurately determine if someone is at the door. Therefore, restarting the smart door lock can restore the normal operation of modules related to the ultrasonic monitoring function, enabling them to handle abnormal states, adapt to environmental changes, and update configurations.

[0084] Regarding setting the restart time, as mentioned earlier, the monitoring data can include the wake-up time of the target function. Therefore, the working status of the target function can be predicted based on the wake-up time to obtain the corresponding target attribute data, thereby determining when to restart the target device and thus obtaining the set restart time.

[0085] One possible implementation involves obtaining the historical wake-up times of the target function, analyzing these historical wake-up times to determine the past usage patterns of the target function, and then configuring and setting the restart time for the target device based on these past usage patterns.

[0086] The monitoring data may include historical wake-up times of the target function. For example, based on the historical wake-up times of the ultrasonic monitoring function, the module related to the ultrasonic monitoring function on the target device can be proactively restarted one minute in advance (the specific timing can be adjusted based on the user's daily wake-up patterns). The historical wake-up time of the ultrasonic monitoring function can be adjusted to one minute in advance, taking into account the product's battery life requirements. This is because there are instances where the module fails to start softly, so a hard restart can be performed one minute in advance to ensure the ultrasonic module functions properly.

[0087] Through the above process, by utilizing the set restart time in the target adjustment data, the target device is controlled to restart at the set restart time to ensure the normal operation of the target function, improve the working status of the target function, and thus solve the problem that the working status of the smart device does not meet the expected working status.

[0088] In one exemplary embodiment, the method may further include inputting monitoring data into a wake-up model to predict the effectiveness of the monitoring data on the target function.

[0089] The process of constructing the above-mentioned wake-up model may include the following steps: acquiring sample data; assigning corresponding weights to sample monitoring data and each sample attribute data; and establishing a wake-up model based on the sample monitoring data and its corresponding weights, and each sample attribute data and its corresponding weights.

[0090] The wake-up model refers to a model that has the ability to predict the corresponding target attribute data based on different monitoring data.

[0091] The sample data includes sample monitoring data and its corresponding different sample attribute data.

[0092] First, it should be noted that sample monitoring data can be the data detected by the target device each time it runs the target function. Furthermore, by using different sample monitoring data as independent variables, sample attribute data is obtained; in other words, sample attribute data belongs to sample monitoring data.

[0093] Regarding weight allocation, it can be understood that different sample monitoring data and sample attribute data have different degrees of influence / importance on the working status of the target function. Therefore, corresponding weights can be assigned to them according to the degree of influence or importance of the sample monitoring data and sample attribute data.

[0094] Based on this, a wake-up model can be established based on sample monitoring data and corresponding weights, as well as the attribute data of each sample and corresponding weights.

[0095] In one possible implementation, the wake-up model construction process includes: collecting the wake-up time, ultrasonic frequency, power, pulse width, distance, angle, azimuth, and received echo signal quantity for each instance of wake-up by the ultrasonic function; processing this data to obtain sample monitoring data and sample attribute data; then using different sample attribute data as independent variables, such as sound wave frequency, azimuth, received echo signal quantity, distance, and angle; and finally using a weighted multinomial regression model to establish the wake-up model. The sample data can be represented as (x... i ,y i ), where x i = (f, θ, d, s, ...) contains information such as frequency, angle, distance, and signal strength, respectively, and y can be 0 or 1. The wake-up model can be expressed as:

[0096]

[0097] Here, w represents different attribute weights (which can be initially set to 1 / N). Different weights are assigned to the sample attribute data according to their importance, so that the wake-up model can better adapt to the data.

[0098] After the wake-up model is built, the monitoring data can be input into the wake-up model to predict the working status of the target function under the conditions corresponding to the monitoring data, thereby obtaining the corresponding target attribute data.

[0099] Under the above embodiments, a wake-up model is constructed using sample data, thereby allowing monitoring data to be input into the wake-up model to predict the working status of the target function based on the monitoring data, making the predicted target monitoring data more accurate.

[0100] In an exemplary embodiment, the method may further include: determining the triggering condition of the set event and the working condition of the target function; determining the triggering condition of the set event and the working condition of the target function; judging whether the working condition of the target function meets the set conditions based on the triggering condition; and, if the working condition does not meet the set conditions, performing supervised learning on the wake-up model based on the working condition to adjust the sensitivity of the wake-up model in outputting target attribute data.

[0101] The set conditions are used to determine whether the target device can be triggered normally and complete the target function based on the triggering situation. For example, the set condition is that when the target enters the 1-meter range, the unlock must be triggered within 200ms, or the set condition is that when the target enters the 1-meter range, the number of times the unlock is not triggered within 200ms cannot exceed 3 times, etc. There are no restrictions here.

[0102] Regarding the setting event, it refers to the event that needs to be monitored by the target function of the target device. In other words, the setting event is related to the target function and can reflect whether the working status of the target function meets the expected working status.

[0103] For example, if the target device is a smart door lock, its target function could be ultrasonic monitoring, and the set event could be unlocking. Specifically, by running the ultrasonic monitoring function, when the target appears within a certain range, the ultrasonic monitoring function needs to detect the target's presence and call the camera module to identify the target, thereby deciding whether to control unlocking. Furthermore, if the target has already manually completed the unlocking operation, but the ultrasonic monitoring module has not yet been activated, meaning the sensitivity of the output target attribute data may be too low, causing the ultrasonic monitoring function to fail to respond in time, then the working state of the ultrasonic monitoring function can be indicated as not meeting expectations.

[0104] Furthermore, based on the triggering of the set events and the working status of the target function, the output of the wake-up model is adjusted to optimize the sensitivity of the output target attribute data.

[0105] Specifically, sensitivity refers to the response characteristics of the wake-up model to input monitoring data. By adjusting the wake-up model parameters (such as weights), the generation of target attribute data can be affected. In other words, adjusting the wake-up model's sensitivity to input monitoring data when triggering the target function means that high sensitivity means that even small changes in monitoring data can be quickly captured and trigger a response, while low sensitivity means that larger changes in monitoring data are required to trigger a response. Secondly, the target attribute data output by the wake-up model (such as the amount of received reflected signal and the rate of signal change) is the basis for waking up the target function. Sensitivity adjustment can change the thresholds or weights of these output target attribute data to adapt to different triggering conditions and specific scenarios or needs.

[0106] It is understandable that a wake-up model can integrate various monitoring data (such as ultrasonic signals, camera visual data, environmental noise, etc.) to comprehensively determine whether the target function needs to be woken up. Furthermore, the wake-up model can be trained through supervised learning, thereby dynamically adjusting the target attribute data based on historical monitoring data to make the sensitivity adapt to different scenarios and user needs.

[0107] For example, to determine if the smart lock is using its ultrasonic monitoring function before the door is opened from the outside, if it is, it's normal. If it's not, the wake-up model needs improvement. The sensitivity of the wake-up model's output target attribute data needs to be minimized so that even a slight change in the monitored environment triggers the ultrasonic monitoring function. Furthermore, if the number of door openings is far less than the number of times the ultrasonic monitoring function needs to be activated, it indicates that the wake-up model's output target attribute data is too sensitive. In this case, the ultrasonic wake-up function should only be activated when the received bounce signal is at its maximum.

[0108] Specifically, there are three possible adjustments to the above-mentioned supervised learning process:

[0109] ①Missing detection: When the user successfully opens the door, the ultrasonic monitoring function is not activated. At this time, the target attribute data of the wake-up model output [received reflected signal quantity] is adjusted to high sensitivity to ensure that the target function can be activated even if the environmental changes are small.

[0110] ②Normal: The ultrasonic monitoring function is successfully activated when the user successfully opens the door, and no adjustment is required at this time.

[0111] ③ False detection: The number of times the user opens the door is far less than the number of times the ultrasonic monitoring function is woken up. In this case, the target attribute data of the wake-up model output [received reflected signal quantity] is adjusted to a low sensitivity to avoid frequent wake-up due to minor environmental changes (such as wind blowing grass or changes in light).

[0112] Through the above process, by adjusting the sensitivity of the target attribute data output by the wake-up model and combining it with supervised learning, the working efficiency and accuracy of the target function can be effectively improved. This not only reduces false triggers but also ensures timely response to set events, thereby improving the intelligence level of the device and the user experience.

[0113] In an exemplary embodiment, the above method may further include: if the target function is not awakened when the set event is triggered, increasing the sensitivity of the target attribute data output by the wake-up model.

[0114] It is understandable that if the target function is not awakened, it means that the sensitivity of the target attribute data output by the wake-up model is low. For example, the target attribute data output by the wake-up model (such as the amount of received reflected signal, the rate of signal change, etc.) may be lower than the trigger threshold, resulting in the target function not being awakened.

[0115] Therefore, it is necessary to improve the sensitivity of the target attribute data output by the wake-up model so that the target function can be woken up before the set event is triggered.

[0116] Through the above embodiments, the failure of the target function to be woken up can indicate that the wake-up model is unable to output the target attribute data required to trigger the target function. By adjusting the sensitivity of the wake-up model in outputting the target attribute data, it is possible to better match the actual scenario requirements and optimize system performance.

[0117] In an exemplary embodiment, the above method may further include: if the target function is awakened when the set event is not triggered, reducing the sensitivity of the target attribute data output by the wake-up model.

[0118] It's understandable that if a target function is activated even when the event is not triggered, it could indicate that the target attribute data output by the activation model is overly sensitive, causing the target function to be triggered when it shouldn't be. Therefore, reducing the sensitivity of the target attribute data output by the activation model can reduce false activations.

[0119] By reducing sensitivity through the above process, the model can more strictly screen trigger conditions, avoid unnecessary wake-up operations, avoid overly frequent or meaningless wake-up operations, save energy and improve system stability.

[0120] In an exemplary embodiment, after establishing the wake-up model, the above method may further include: acquiring historical trigger data and historical monitoring data; inputting the historical monitoring data into the wake-up model to obtain the predicted working status of the target function; comparing the deviation between the historical trigger status and the predicted working status, and performing supervised learning of the wake-up model based on the deviation.

[0121] Among them, historical trigger data includes the historical triggering of the set event, and historical monitoring data can be the data detected by the target device each time or within a certain period of time when the target function is run.

[0122] It is understandable that the wake-up model can predict the working status of the target function. If historical trigger data indicates that the set event has occurred, but the predicted working status indicates that the target function has not been woken up at this time, or if the set event has not occurred but the predicted working status indicates that the target function has been woken up, it means that the wake-up model prediction is inaccurate.

[0123] Therefore, the wake-up model can be adjusted through supervised learning according to the type of deviation (missed detection, false detection, etc.). For missed detection (i.e., the target function is not woken up when the set event occurs), the wake-up model can be optimized by increasing its sensitivity to the monitoring data. For false detection (i.e., the target function is falsely woken up when the set event has not occurred), the wake-up model can be optimized by decreasing its sensitivity to the monitoring data.

[0124] Through the above process, by analyzing the discrepancy between historical triggering conditions and predicted working conditions, supervised learning of the wake-up model can be achieved based on the discrepancy, thereby optimizing the wake-up model and making the target attribute data output by the wake-up model more accurate.

[0125] In an exemplary embodiment, step 350 may further include the following steps: obtaining a target data table; and based on the target attribute data, searching for the device adjustment data corresponding to the target attribute data in the target data table to obtain the target adjustment data.

[0126] The target data table stores the correspondence between different attribute data and different device adjustment data.

[0127] For example, the fields of the target data table can include attribute data and corresponding equipment adjustment data. By reading the information in the target data table, the equipment adjustment data corresponding to different attribute data in the corresponding environment can be quickly obtained. It should be noted that the target data table stores attribute data and corresponding equipment adjustment data through fields, which has good scalability. When adding new environmental conditions or equipment functions, only a new record needs to be added to the target data table, without the need for large-scale modifications to the existing system.

[0128] In addition, designing corresponding query algorithms or interfaces can enable fast searching of target data tables and extracting device adjustment data in different environments, reducing processing latency.

[0129] In one possible implementation, different attribute data can be input into the relationship prediction model, and the predicted equipment adjustment data can be output, thereby generating a target data table based on the attribute data and the corresponding equipment adjustment data.

[0130] It should be noted that by dynamically collecting real-time attribute data and device adjustment effects, the target data table can be continuously updated to maintain optimal performance in different environments.

[0131] Under the above embodiments, by searching the target data table, the corresponding device adjustment data can be quickly located based on the input target attribute data, reducing the complexity of real-time calculation, improving the response speed, and enabling the system to quickly adjust the target function in a dynamic environment.

[0132] Please see Figure 4 In an exemplary embodiment, the above method may further include generating a correspondence between different attribute data and the corresponding device adjustment data of the target device through a relation prediction model.

[0133] Specifically, the process of constructing a relationship prediction model may include the following steps:

[0134] Step 610: Obtain sample attribute data.

[0135] Sample attribute data can be historical attribute data.

[0136] Step 630: Based on the prediction of the target adjustment data corresponding to the sample attribute data, determine the prior distribution of the sample attribute data, and construct the objective function based on the sample attribute data.

[0137] The prior distribution is used to predict the results of the constraint relationship prediction model.

[0138] First, it should be noted that the prior distribution reflects the initial hypothetical relationship between the sample attribute data and the target regulation data. The objective function is used to measure the deviation between the model prediction results and the actual regulation data. The prediction results are the equipment regulation data inferred from the input sample attribute data, while the actual regulation data are the real equipment regulation data obtained directly from historical records or experiments.

[0139] In one possible implementation, the objective function can be a likelihood function, which describes the degree of agreement between the sample attribute data and the device adjustment data.

[0140] Step 650: Calculate the posterior distribution of the sample attribute data based on the prior distribution and the objective function.

[0141] The posterior distribution can be used to update the relationship prediction model's understanding of the parameters. One possible implementation is to calculate the posterior distribution of the sample attribute data based on the prior distribution and the objective function according to Bayes' theorem, without making any limitations here.

[0142] Step 670: Based on the posterior distribution, establish the relationship between different attribute data and different device adjustment data to obtain the relationship prediction model.

[0143] Specifically, based on the posterior distribution, fitting the relationship curve between sample attribute data and equipment adjustment data can be achieved through regression methods (such as linear regression, multinomial regression) or nonparametric methods (such as Gaussian process regression), thereby obtaining a relationship prediction model.

[0144] Through the combination of the above embodiments, an accurate mapping between attribute data and device adjustment data can be established, thereby constructing an accurate relationship prediction model. In practical applications, by inputting attribute data into the relationship prediction model, the corresponding target adjustment data can be quickly predicted, thereby supporting the adaptive adjustment of smart devices. In addition, the output of the relationship prediction model (the correspondence between attribute data and device adjustment data) can be stored as a target data table for easy retrieval and application in the future.

[0145] Figure 5a and Figure 5bThis is a schematic diagram illustrating the specific implementation of a device adjustment and processing method in an application scenario.

[0146] First, it should be noted that the device adjustment and processing method of this application can be used for passive detection of smart door locks, such as ultrasonic waves, radar, thermal sensors, to detect the situation outside the door and passively trigger events, such as facial recognition, loitering detection, stranger recognition warning, lock picking, etc.

[0147] When a target approaches the ultrasonic detection range of the smart door lock, the smart door lock's peephole camera will be activated to perform pedestrian detection, facial recognition, etc. If a pedestrian is detected or the pedestrian's facial data is recognized, corresponding automation can be selectively performed. For example, if a resident's family member is identified, the lock can be automatically unlocked; if a stranger is identified, an alert or video recording can be performed.

[0148] In one possible implementation, combining Figure 5a The ultrasonic monitoring function of the smart door lock is explained, such as... Figure 5a As shown, the device adjustment and processing method in this application scenario includes the following steps:

[0149] Step 801: Obtain monitoring data from the smart door lock.

[0150] Step 803: Input the monitoring data into the wake-up model to predict the working status of the ultrasonic monitoring function based on the monitoring data, and obtain the target attribute data.

[0151] Step 805: Obtain the target data table.

[0152] Step 807: Based on the target attribute data, search for the equipment adjustment data corresponding to the target attribute data in the target data table to obtain the target adjustment data.

[0153] It should be noted that the target data table is designed to store the correspondence between device adjustment data and target attribute data. That is, different attribute data are input into the relationship prediction model, and the predicted device adjustment data is output. Thus, the target data table is generated based on the attribute data and the corresponding device adjustment data.

[0154] In step 809, based on the historical wake-up time of the ultrasonic monitoring function, the ultrasonic monitoring function is actively restarted 1 minute in advance.

[0155] The historical wake-up time of the ultrasonic function can be combined with the product battery life requirements of the smart door lock. For example, it can be adjusted to 1 minute in advance. The reason for the need for a manual restart is that there may be cases where the module fails to start softly. Therefore, a hard restart can be performed 1 minute in advance to ensure that the ultrasonic function works normally.

[0156] Step 811: If the ultrasonic monitoring function does not meet the set conditions after the user completes the unlocking operation, the ultrasonic monitoring function of the smart door lock is adjusted according to the target adjustment data.

[0157] In another possible implementation, combine Figure 5b The ultrasonic monitoring function of the smart door lock is explained, such as... Figure 5b As shown, the device adjustment and processing method in this application scenario includes the following steps:

[0158] First, data is collected on historical data regarding each instance of wake-up via ultrasound, including wake-up time, ultrasound frequency, power, pulse width, distance, angle, azimuth, and received echo signal. This data is then processed to obtain sample monitoring data and sample attribute data. Different sample attribute data are then used as independent variables, such as sound wave frequency, azimuth, received echo signal, distance, and angle. Based on this sample monitoring data and sample attribute data, a wake-up model can be established, specifically using a weighted multinomial regression model.

[0159] Specifically, different weights can be assigned to each data point based on the importance of the sample attribute data, such as distance, angle > azimuth > received bounce signal quantity, and wake-up time, to allow the model to better adapt to the data. Secondly, appropriate prior distributions and likelihood functions can be selected, and then the posterior distribution of the parameters can be calculated using Bayes' theorem. The corresponding parameter estimates can be obtained from the posterior distribution. Providing more accurate and robust parameter estimates, by establishing a model of the "relationship between effective ultrasonic data and attribute parameters," can be used to predict and analyze the ultrasonic wake-up situation of unknown data, providing practical decision support, i.e., determining the optimal ultrasonic frequency, power, and pulse width for different "distances, azimuths, and received bounce signal quantities" after triggering.

[0160] After the wake-up model is built, the monitoring data detected during the current operation of the ultrasonic detection function can be input into the wake-up model to predict the working condition of the ultrasonic monitoring function under the conditions corresponding to the current monitoring data, thereby obtaining the corresponding target attribute data.

[0161] It should be noted that different attribute data can be input into the relationship prediction model, and the output will be the predicted equipment adjustment data, thereby generating a target data table based on the attribute data and the corresponding equipment adjustment data.

[0162] Therefore, a lookup approximation strategy can be used to quickly obtain equipment adjustment data corresponding to different attribute data under the corresponding environment by reading information from the target data table. Of course, corresponding query algorithms or interfaces can be designed, such as low-level, medium-level, and high-level settings, to achieve fast lookup and extraction of equipment adjustment data under different environments from the target data table.

[0163] Furthermore, by analyzing historical wake-up times, the past usage patterns of the ultrasonic detection function are determined, and a restart time can be configured for the smart lock based on these patterns. For example, the ultrasonic module can be proactively restarted one minute in advance based on past wake-up times, specifically tailored to the user's daily wake-up habits. The past wake-up time can be adjusted to take into account product battery life requirements, such as by setting it one minute in advance, to address potential soft-start failures and ensure proper ultrasonic module operation. Simultaneously, outdoor door opening and closing data within a specific time period, corresponding to the user's daily successful outdoor door opening times, are used to supervised learn the ultrasonic wake-up model, continuously optimizing its sensitivity. This can also be a subsequent feedback adjustment process, aiming to further optimize the trained model through continuous user data feedback and settings.

[0164] Based on this, the activation status of the ultrasonic monitoring function can be determined after the user completes the unlocking operation. There are three possible scenarios:

[0165] 1. Missed detection: The ultrasonic monitoring function was not activated when the user successfully opened the door.

[0166] It should be noted that if the ultrasonic monitoring function is not activated after the user completes the unlocking operation, it means that the sensitivity of the target attribute data output by the wake-up model is low, and the sensitivity of the target attribute data output by the wake-up model needs to be improved.

[0167] 2. Normal: The ultrasonic monitoring function is successfully activated when the user successfully opens the door. No adjustment is required at this time.

[0168] 3. False detection: The number of times the user opens the door is far less than the number of times the ultrasonic monitoring function is activated.

[0169] It should be noted that if the ultrasonic monitoring function is activated after the user completes the unlocking operation, it means that the sensitivity of the target attribute data output by the wake-up model is low, so it is necessary to reduce the sensitivity of the target attribute data output by the wake-up model.

[0170] Of course, adjustments to the ultrasonic monitoring function are necessary to address missed and false detections. Specifically, target adjustment data can include the ultrasonic frequency of the ultrasonic monitoring function. The ultrasonic frequency optimizes the detection range and accuracy. If a missed detection occurs (the target is close but not detected), the frequency can be increased (e.g., from 40kHz to 60kHz) to improve sensitivity. If a false detection occurs, the frequency can be decreased (e.g., from 60kHz to 40kHz) to reduce sensitivity. Target adjustment data can also include ultrasonic power. Ultrasonic power increases the ultrasonic signal strength to overcome environmental interference. Increasing the ultrasonic power (e.g., from 80dB to 100dB) enhances signal reflection. Target adjustment data can also include pulse width. Adjusting the pulse width optimizes the ultrasonic signal transmission time and echo quality. Wider pulses are suitable for long-distance detection, while narrower pulses are suitable for high-resolution detection.

[0171] In this application scenario, based on monitoring data and the prediction results of the wake-up model, it is possible to quickly determine whether the working status of the ultrasonic monitoring function meets expectations. If a set event is not detected normally, the ultrasonic monitoring function can be dynamically adjusted by looking up the target data table and applying target adjustment data. This improves the response speed and accuracy of devices such as smart locks. If the user completes the unlocking operation but the device is not woken up, timely adjustment of the ultrasonic monitoring function using target adjustment data can quickly restore the device to normal operation, preventing user frustration due to sluggish or unresponsive devices.

[0172] Furthermore, the sensitivity has been changed from requiring users to actively set it to allowing for automatic adjustment based on actual usage. This not only improves product power consumption but also avoids false triggering and missed detection.

[0173] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0174] The following are embodiments of the apparatus described in this application, which can be used to execute the equipment adjustment processing method involved in this application. For details not disclosed in the embodiments of the apparatus described in this application, please refer to the method embodiments of the equipment adjustment processing method involved in this application.

[0175] Please see Figure 6 This application provides a device adjustment and processing apparatus 900, including but not limited to: a data acquisition module 910, a data prediction module 930, a data search module 950, and a device adjustment module 970.

[0176] The data acquisition module 910 is used to acquire monitoring data; the monitoring data is the data detected when the target device is running the target function.

[0177] The data prediction module 930 is used to predict the working status of the target function based on monitoring data and obtain the corresponding target attribute data; the target attribute data includes attribute data that affects the working status of the target function;

[0178] The data lookup module 950 is used to find target adjustment data that corresponds to the target attribute data based on the target attribute data; the correspondence is used to describe the equipment adjustment data of different attribute data and their corresponding target equipment; the target adjustment data is used to adjust the working status of the target function.

[0179] The equipment adjustment module 970 is used to adjust the target function of the target equipment according to the target adjustment data if the actual working condition of the target function does not meet the set conditions.

[0180] In an exemplary embodiment, the data prediction module is further configured to input monitoring data into the wake-up model to predict the working status of the target function based on the monitoring data; the equipment adjustment and processing device further includes a wake-up model construction module, which is further configured to acquire sample data; the sample data includes sample monitoring data and its corresponding different sample attribute data; assign corresponding weights to the sample monitoring data and each sample attribute data; and establish a wake-up model based on the sample monitoring data and its corresponding weights and each sample attribute data and its corresponding weights.

[0181] In an exemplary embodiment, the wake-up model construction module is further configured to determine the triggering conditions of the set event and the working conditions of the target function; determine whether the working conditions of the target function meet the set conditions based on the triggering conditions; and perform supervised learning on the wake-up model based on the working conditions to adjust the sensitivity of the wake-up model in outputting target attribute data.

[0182] In one exemplary embodiment, the wake-up model building module is further configured to increase the sensitivity of the wake-up model to output target attribute data if the target function is not woken up when the set event is triggered.

[0183] In one exemplary embodiment, the wake-up model building module is further configured to reduce the sensitivity of the wake-up model in outputting target attribute data if the target function is woken up when the set event is not triggered.

[0184] In an exemplary embodiment, the wake-up model construction module is further configured to acquire historical trigger data and historical monitoring data; the historical trigger data includes the historical triggering status of the set event; input the historical monitoring data into the wake-up model to obtain the predicted working status of the target function; compare the deviation between the historical triggering status and the predicted working status, and perform supervised learning of the wake-up model based on the deviation.

[0185] In one exemplary embodiment, the data lookup module is further configured to obtain a target data table, which stores the correspondence between different attribute data and different device adjustment data; based on the target attribute data, the module searches for the device adjustment data corresponding to the target attribute data in the target data table to obtain the target adjustment data.

[0186] In an exemplary embodiment, the equipment adjustment processing apparatus is further configured to generate a correspondence between different attribute data and their corresponding target equipment adjustment data through a relationship prediction model; the equipment adjustment processing apparatus further includes a relationship prediction model construction module, which is configured to acquire sample attribute data; determine a prior distribution for the sample attribute data based on the target of predicting the corresponding target adjustment data using the sample attribute data, and construct an objective function based on the sample attribute data; wherein the prior distribution is used to constrain the prediction result of the relationship prediction model; calculate the posterior distribution of the sample attribute data based on the prior distribution and the objective function; and establish the relationship between different attribute data and different equipment adjustment data based on the posterior distribution to obtain the relationship prediction model.

[0187] In one exemplary embodiment, the target adjustment data includes a set restart time; the device adjustment module is further configured to control the target device to restart at the set restart time, so that the restarted target device wakes up the target function.

[0188] It should be noted that the equipment adjustment processing device provided in the above embodiments is only illustrated by the division of the above functional modules when performing equipment adjustment processing. In actual applications, the above functions can be assigned to different functional modules as needed. That is, the internal structure of the equipment adjustment processing device will be divided into different functional modules to complete all or part of the functions described above.

[0189] Furthermore, the embodiments of the device adjustment processing apparatus and device adjustment processing method provided in the above embodiments belong to the same concept, and the specific way in which each module performs the operation has been described in detail in the method embodiments, and will not be repeated here.

[0190] Please see Figure 7 This application provides an electronic device 4000, which may include: a desktop computer, a laptop computer, a server, etc.

[0191] exist Figure 7 In this context, the electronic device 4000 includes at least one processor 4001 and at least one memory 4003.

[0192] Data interaction between the processor 4001 and the memory 4003 can be achieved through at least one communication bus 4002. This communication bus 4002 may include a path for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not indicate that there is only one bus or one type of bus.

[0193] Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0194] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0195] The memory 4003 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing computer programs having instruction or data structure forms and accessible by electronic device 400, but not limited to these.

[0196] The memory 4003 stores a computer program, and the processor 4001 can read the computer program stored in the memory 4003 through the communication bus 4002.

[0197] The computer program is executed by one or more processors 4001 to implement the device adjustment processing methods in the above embodiments.

[0198] Furthermore, this application embodiment provides a storage medium storing a computer program, which is executed by one or more processors to implement the device regulation processing method described above.

[0199] This application provides a computer program product, including a computer program that is executed by one or more processors to implement the device regulation processing method described above.

[0200] Compared with related technologies, this solution can predict the working status of the target function under current conditions through monitoring data, obtain corresponding target attribute data, and use the target attribute data to find the corresponding device adjustment data to obtain the corresponding target adjustment data. Thus, when the actual working status of the target function does not meet the set conditions, the target function is adjusted using the target adjustment data, so that the adjusted target function works more effectively under the conditions monitored by the monitoring data, thereby solving the problem of the working status of smart devices not meeting the expected working state.

[0201] Furthermore, by constructing a wake-up model using sample data, monitoring data can be input into the wake-up model to predict the working status of the target function, making the predicted target monitoring data more accurate.

[0202] Furthermore, it can establish an accurate mapping between attribute data and device adjustment data, thereby constructing a precise relationship prediction model. In practical applications, by inputting attribute data into the relationship prediction model, the corresponding target adjustment data can be quickly predicted, thus supporting the adaptive adjustment of smart devices. In addition, the output of the relationship prediction model (the correspondence between attribute data and device adjustment data) can be stored as a target data table for easy retrieval and application later.

[0203] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for adjusting and processing equipment, characterized in that, include: Obtain monitoring data; The monitoring data is the data detected when the target device is performing the target function; Based on the monitoring data, the working status of the target function is predicted to obtain corresponding target attribute data; the target attribute data includes attribute data that affects the working status of the target function; Based on the target attribute data, target adjustment data that corresponds to the target attribute data is found; the correspondence is used to describe the equipment adjustment data of different attribute data and their corresponding target equipment. The target adjustment data is used to adjust the operation of the target function; If the actual working condition of the target function does not meet the set conditions, the target function of the target device shall be adjusted according to the target adjustment data.

2. The method as described in claim 1, characterized in that, The step of predicting the working status of the target function based on the monitoring data to obtain corresponding target attribute data includes: inputting the monitoring data into a wake-up model to predict the working status of the target function based on the monitoring data; The process of constructing the wake-up model includes: Acquire sample data; the sample data includes sample monitoring data and its corresponding different sample attribute data; Assign corresponding weights to the sample monitoring data and each of the sample attribute data; A wake-up model is established based on the sample monitoring data and corresponding weights, and the sample attribute data and corresponding weights.

3. The method as described in claim 2, characterized in that, After adjusting the target function of the target device according to the target adjustment data, the method further includes: Determine the triggering conditions of the set events and the working status of the target function; Based on the triggering conditions, determine whether the working status of the target function meets the set conditions; If the working conditions do not meet the set conditions, supervised learning is performed on the wake-up model based on the working conditions to adjust the sensitivity of the wake-up model in outputting the target attribute data.

4. The method as described in claim 3, characterized in that, When the working conditions do not meet the set conditions, the step of performing supervised learning on the wake-up model based on the working conditions to adjust the sensitivity of the wake-up model in outputting the target attribute data includes: If the target function is not activated when the set event is triggered, the sensitivity of the activation model in outputting target attribute data is increased.

5. The method as described in claim 3, characterized in that, When the working conditions do not meet the set conditions, the step of performing supervised learning on the wake-up model based on the working conditions to adjust the sensitivity of the wake-up model in outputting the target attribute data includes: If the target function is activated when the set event is not triggered, the sensitivity of the target attribute data output by the activation model is reduced.

6. The method as described in claim 3, characterized in that, After establishing the wake-up model, the method further includes: Acquire historical trigger data and historical monitoring data; the historical trigger data includes the historical triggering status of the set event. The historical monitoring data is input into the wake-up model to obtain the predicted working status of the target function; The deviation between the historical triggering conditions and the predicted working conditions is compared, and supervised learning of the wake-up model is performed based on the deviation.

7. The method as described in claim 1, characterized in that, The step of finding target adjustment data that corresponds to the target attribute data based on the target attribute data includes: Obtain the target data table, which stores the correspondence between different attribute data and different device adjustment data; Based on the target attribute data, the device adjustment data corresponding to the target attribute data is searched in the target data table to obtain the target adjustment data.

8. The method as described in claim 1, characterized in that, Before searching for target adjustment data that corresponds to the target attribute data based on the target attribute data, the method further includes: The relationship prediction model generates the correspondence between different attribute data and their corresponding target equipment adjustment data; The process of constructing the relationship prediction model includes: Obtain sample attribute data; Based on the target of predicting the corresponding target adjustment data using the sample attribute data, a prior distribution is determined for the sample attribute data, and a target function is constructed based on the sample attribute data; wherein, the prior distribution is used for the prediction result of the constraint relationship prediction model; Calculate the posterior distribution of the sample attribute data based on the prior distribution and the objective function; Based on the posterior distribution, the relationship between different attribute data and different device adjustment data is established to obtain the relationship prediction model.

9. The method according to any one of claims 1 to 8, characterized in that, The target adjustment data includes the set restart time; Adjusting the target function of the target device according to the target adjustment data includes: At the set restart time, the target device is controlled to restart, so that the restarted target device wakes up the target function.

10. A device for adjusting and processing equipment, characterized in that, include: The data acquisition module is used to acquire monitoring data; The monitoring data is the data detected when the target device is performing the target function; The data prediction module is used to predict the working status of the target function based on the monitoring data to obtain corresponding target attribute data; the target attribute data includes attribute data that affects the working status of the target function; The data lookup module is used to find target adjustment data that has a corresponding relationship with the target attribute data based on the target attribute data; The correspondence is used to describe different attribute data and their corresponding target device adjustment data; The target adjustment data is used to adjust the operation of the target function; The device adjustment module is used to adjust the target function of the target device according to the target adjustment data if the actual working condition of the target function does not meet the set conditions.

11. An electronic device comprising at least one processor and at least one memory, wherein, The memory stores a computer program, characterized in that, when the computer program is executed by the processor, it implements the device adjustment processing method as described in any one of claims 1 to 9.

12. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by one or more processors, it implements the device regulation processing method as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by one or more processors, it implements the device regulation processing method as described in any one of claims 1 to 9.

Images