Device control correction method and device, electronic device, and readable storage medium

Abstract

The application discloses a device control correction method and device, electronic equipment and readable storage medium, and belongs to the technical field of device control. The method comprises the following steps: in a preset scene, after a scene execution instruction corresponding to the preset scene is sent to a target home device, trigger condition information of the scene execution instruction and running state information of the target home device are acquired; the trigger condition information and the running state information are input into a preset evaluation model, and deviation degree information of the target home device executing the scene execution instruction is output; when the deviation degree information is greater than a preset deviation threshold, the deviation reason of the target home device is determined; and the target correction instruction of the target home device is generated according to the deviation reason. Through the embodiment of the application, the dynamic deviation degree information is determined by using the preset evaluation model, and then the instruction correction of the home device is realized based on the deviation degree information.

Description

Technical Field

[0001] This application belongs to the field of equipment control technology, and specifically relates to a correction method, device, electronic device, and readable storage medium for equipment control. Background Technology

[0002] Currently, automatic correction of smart home scenarios is mainly achieved through condition judgment mechanisms linked by static rules or preset modes, as well as scene triggering logic based on fixed condition combinations or event sequences.

[0003] However, the above correction scheme suffers from the problem of relying on a single static rule condition, making it difficult to achieve accurate equipment control correction. Summary of the Invention

[0004] The purpose of this application is to provide a correction method for device control that can solve the problem of single static rule condition judgment for device correction.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows:

[0006] In a first aspect, embodiments of this application provide a method for correcting device control, the method comprising:

[0007] In a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the trigger condition information of the scenario execution command and the operating status information of the target home device are obtained;

[0008] The triggering condition information and running status information are input into a preset evaluation model, and the deviation information of the target home device from the execution of the scene execution command is output.

[0009] When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the target home appliance is determined;

[0010] Based on the cause of the deviation, a target correction instruction is generated for the target home appliance.

[0011] Optionally, the step of inputting the trigger condition information and operating status information into a preset evaluation model and outputting the deviation information of the target home device from the execution of the scene execution command includes:

[0012] Input the triggering condition information and running status information into the preset evaluation model;

[0013] In the evaluation model, the device state weight, time decay factor, and spatial correlation factor are determined based on the triggering condition information and the operating status information.

[0014] Based on the device state weight, the time decay factor, and the spatial correlation factor, the deviation information of the target home device from the execution of the scene execution command is determined;

[0015] Output the deviation information.

[0016] Optionally, determining the deviation information of the target home device from the scene execution command based on the device state weight, the time decay factor, and the spatial correlation factor includes:

[0017] The deviation information of the target home device from the execution of the scene execution command is calculated according to the device state weight, the time decay factor, and the spatial correlation factor using a preset formula, wherein the preset formula is as follows:

[0018] D = Σ(W_device×F_time×F_space);

[0019] D represents the deviation information, W_devic represents the device state weight, F_time represents the time decay factor, and F_space represents the spatial correlation factor.

[0020] Optionally, determining the cause of deviation of the target home appliance when the deviation information is greater than a preset deviation threshold includes:

[0021] When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the target home appliance is determined through multi-source arbitration.

[0022] Optionally, when the deviation information is greater than a preset deviation threshold, determining the cause of the deviation of the target home appliance through multi-source arbitration includes:

[0023] When the deviation information is greater than a preset deviation threshold, the device hardware status information of the target home device is obtained;

[0024] The cause of the deviation is determined based on the device hardware status information.

[0025] Optionally, when the deviation information is greater than a preset deviation threshold, determining the cause of the deviation of the target home appliance through multi-source arbitration includes:

[0026] When the deviation information is greater than a preset deviation threshold, the environmental information of the target home device is obtained;

[0027] The cause of the deviation is determined based on the environmental information.

[0028] Optionally, when the deviation information is greater than a preset deviation threshold, determining the cause of the deviation of the target home appliance through multi-source arbitration includes:

[0029] When the deviation information is greater than a preset deviation threshold, the behavioral habit database corresponding to the target user is obtained;

[0030] The reasons for deviations are determined based on the aforementioned behavioral habit database.

[0031] Optionally, when the deviation information is greater than a preset deviation threshold, determining the cause of the deviation of the target home appliance through multi-source arbitration includes:

[0032] A primary correction instruction is generated based on the cause of the deviation;

[0033] The intervention level is determined based on the initial correction instruction and the preset user policy library;

[0034] The target corrective instructions for the target home appliance are determined according to the intervention level.

[0035] Optionally, it also includes:

[0036] The target correction command is sent to the target user's application for controlling the target home appliance;

[0037] Upon receiving a confirmation message from the target user confirming the execution of the target correction instruction, the target correction instruction is sent to the target home appliance to cause the target home appliance to execute the target correction instruction.

[0038] Secondly, embodiments of this application provide a device for correcting equipment control, the device comprising:

[0039] The information acquisition module is used to obtain the triggering condition information of the scene execution command and the operating status information of the target home device after sending the scene execution command corresponding to the preset scene to the target home device in a preset scene.

[0040] The deviation information determination module is used to input the trigger condition information and the running status information into a preset evaluation model and output the deviation information of the target home device in response to the scene execution command.

[0041] The deviation cause determination module is used to determine the deviation cause of the target home appliance when the deviation information is greater than a preset deviation threshold.

[0042] The target correction instruction determination module is used to generate a target correction instruction for the target home appliance based on the cause of deviation.

[0043] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0044] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0045] In this embodiment, in a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the triggering condition information of the scenario execution command and the operating status information of the target home device are obtained; the triggering condition information and the operating status information are input into a preset evaluation model, and the deviation information of the target home device from the scenario execution command is output; when the deviation information is greater than a preset deviation threshold, the deviation cause of the target home device is determined; and a target correction command for the target home device is generated based on the deviation cause. This realizes the determination of dynamic deviation information using a preset evaluation model, and then the correction of the home device's command based on the deviation information. Attached Figure Description

[0046] Figure 1 This is a schematic flowchart illustrating the steps of a device control correction method according to an embodiment of this application;

[0047] Figure 2 This is a schematic flowchart illustrating the steps of a device control correction method according to an embodiment of this application;

[0048] Figure 3 This is a schematic diagram showing the structure of a device control correction device according to an embodiment of this application;

[0049] Figure 4 This illustrates an electronic device according to an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0052] The correction of device control provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0053] Currently, automatic correction of smart home scenarios can be achieved through condition judgment mechanisms linked by static rules or preset modes, as well as scene triggering logic based on fixed condition combinations or event sequences.

[0054] For example, in practical applications, a smart home scene control method based on multi-condition judgment can set the condition judgment criteria as single satisfaction and full satisfaction. Single satisfaction means execution occurs if any one condition is met; full satisfaction means execution occurs if all conditions are met. Corresponding actions are set based on different judgment results. This allows for flexible and adaptable control of the smart home system, enabling adjustments based on user needs. The advantage of introducing multi-condition judgment is that it can adapt to changes in the actual situation without user intervention.

[0055] In this embodiment, an evaluation model can be pre-trained based on the triggering condition information and actual operation information of the home device. This evaluation model can calculate the deviation information during the execution process of the home device. Then, when the home device receives a scene execution command in a certain scenario, the deviation information can be dynamically evaluated by inputting the triggering condition information and operation status information corresponding to the scene execution command into the evaluation model. When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the home device can be determined, and a target correction command for the target home device can be generated based on the cause of the deviation.

[0056] Reference Figure 1 The diagram illustrates a step-by-step flowchart of a device control correction method according to an embodiment of this application. The method includes:

[0057] Step 101: In a preset scenario, after sending the scenario execution command corresponding to the preset scenario to the target home device, obtain the trigger condition information of the scenario execution command and the operating status information of the target home device;

[0058] In practical applications, preset scenarios can be associated with home appliance control scenarios. Preset scenarios can be determined by analyzing sensor data obtained from multiple sensor devices connected to the home host. For example, data captured by a camera showing the living room door is closed, as well as the door status information fed back to the home host from the living room door, can determine that the current scenario is an "away from home" scenario.

[0059] In practical applications, the control of home devices varies depending on the preset scenario. After determining the preset scenario, the scene execution instruction corresponding to the preset scenario can be determined based on the current preset scenario. The scene execution instruction is the execution instruction set for the home device, that is, the instruction that the home host expects the home device to execute.

[0060] After the home host issues a scene command, it can obtain the trigger condition information of the scene execution command. The trigger condition information can include the specific content that the home device needs to perform in the preset scene. After issuing the scene command, the home host can also monitor the operating status information of the target home device. By monitoring the operating status information, it can determine the execution status of the target home device in response to the received scene execution command.

[0061] For example, when an "away from home" scenario is detected, the corresponding scenario execution command may include turning off indoor lighting and air conditioning equipment. Thus, the scenario execution command for turning off indoor lighting and air conditioning equipment is sent to the indoor lighting and air conditioning equipment.

[0062] After receiving the scene execution command, the indoor lighting and air conditioning equipment can provide feedback on their real-time status.

[0063] Step 102: Input the trigger condition information and running status information into a preset evaluation model, and output the deviation information of the target home device in executing the scene execution command;

[0064] After obtaining the trigger condition information and the running status information, the trigger condition information and the running status information can be input into the preset evaluation model. The evaluation model is used to calculate the execution deviation of the target home device scene execution command, that is, to evaluate the deviation between the trigger condition information and the running status information (deviation information).

[0065] In practical applications, multiple home devices can be pre-collected with the expected scene execution instructions and triggering conditions in different preset scenarios, as well as the operating status information of the home devices after receiving the scene execution instructions. The above data can then be used as training data to train the evaluation model. The input data of the evaluation model are the triggering condition information and the operating status information, and the output data is the deviation information.

[0066] In this embodiment, the deviation information is output by inputting the trigger condition information corresponding to the scene execution command and the operating status information of the target home device into the evaluation model.

[0067] In one embodiment of this application, the home host can configure the evaluation model locally or in the cloud. When the home host configures the evaluation model locally, it can directly call the evaluation model to perform deviation evaluation. When the home host configures the evaluation model in the cloud, it can call the evaluation model in the cloud to perform deviation evaluation.

[0068] In practical applications, the process of evaluating deviation using a preset evaluation model is as follows: the trigger condition information and operating status information are input into the preset evaluation model; in the evaluation model, the device status weight, time decay factor, and spatial correlation factor can be determined based on the trigger condition information and operating status information, and then the deviation information of the target home device in executing the scene execution command can be determined based on the device status weight, the time decay factor, and the spatial correlation factor; the deviation information is then output.

[0069] Among them, the weight of device status can be dynamically adjusted according to the importance of the target home device, such as security camera weight > lighting (importance of privacy and security), and the device weight can be dynamically adjusted by the vertical failure rate.

[0070] Time decay factor (F_time): F_time = e^(-k·t) (where t is the deviation duration and k is the decay coefficient). The longer the deviation of the device's operating state from its actual operating state, the lower the reliability. When the trigger condition information does not match the operating state information, a device control deviation is determined. The deviation duration t can be determined through continuously monitored operating state information and trigger condition information. The decay coefficient is a constant and can be set according to the actual scenario. The time decay factor can then be calculated based on the deviation duration t and the decay coefficient k.

[0071] Spatial correlation factor (F_space): Used to determine the reasonableness of device execution state deviations by locating the distance between the user and the device. Specifically, the home gateway can obtain the distance information between the current user and the target home device, and determine whether the trigger condition information and the running status information match. When the trigger condition information and the running status information do not match, a deviation is determined, and then the spatial correlation factor can be set based on the distance information. For example, if the user is 5 kilometers away from home but the air conditioner is on → correlation factor F_space = 0.1.

[0072] In one embodiment of this application, determining the deviation information of the target home device from the scene execution command based on the device state weight, the time decay factor, and the spatial correlation factor includes:

[0073] The deviation information of the target home device from the execution of the scene execution command is calculated according to the device state weight, the time decay factor, and the spatial correlation factor using a preset formula, wherein the preset formula is as follows:

[0074] D = Σ(W_device×F_time×F_space);

[0075] D represents the deviation information, W_devic represents the device state weight, F_time represents the time decay factor, and F_space represents the spatial correlation factor.

[0076] In this embodiment, a dynamic credibility assessment model can be created. This model can compare the scene triggering conditions with the actual device status in real time, and quantify the inconsistency between the device's operating status and the scene execution requirements through a spatiotemporal weight matrix. The dynamic credibility assessment model can calculate the deviation between the scene triggering conditions and the actual execution result from multiple dimensions, including the scene running device weight, the scene execution time dynamic decay factor, and the user's distance from the device spatial dynamic decay factor. This allows for a more intelligent identification and judgment of whether the device's operating status after scene execution meets the scene requirements. Thus, it enables more intelligent identification and judgment of whether the device is operating normally after scene execution by calculating the deviation between the scene triggering conditions and the actual execution result through multi-dimensional parameters.

[0077] Step S103: When the deviation information is greater than a preset deviation threshold, determine the cause of the deviation of the target home appliance;

[0078] After determining the deviation information through the evaluation model, the deviation information can be compared with a preset deviation threshold. When the deviation information exceeds the preset deviation threshold, the cause of the deviation of the target home appliance can be determined. The cause of the deviation is that the target home appliance failed to execute the scene execution instructions, resulting in a mismatch between the target home appliance's operating status information and the expected scene execution instruction structure.

[0079] Step S104: Generate a target correction instruction for the target home appliance based on the cause of deviation.

[0080] After determining the cause of the deviation, target correction instructions can be generated for the target home appliances according to the different causes of deviation.

[0081] In one embodiment of this application, the process of generating a target correction instruction can be as follows: the home host generates a primary correction instruction based on the cause of deviation, wherein the primary correction instruction can be used to correct the target home device, and then the intervention level can be determined based on the initial correction instruction and a preset user policy library; wherein the intervention level is used to represent the degree of interference, and then the target correction instruction for the target home device can be determined according to the intervention level.

[0082] The intervention level in this embodiment can be set as follows:

[0083] (1) Intervention Level 1, not implemented:

[0084] The user is notified via an asynchronous message queue, but the execution thread is not triggered. This intervention only notifies the user and logs the information, without intervening in device operation. It is suitable for situations where device operation is of low importance and has little impact on the execution of the scenario. For example, in a home sleep scenario, if the air purifier is detected to start with a 10-minute delay, the user is only notified and the information is logged, but no intervention is performed on device operation.

[0085] (2) Intervention Level 2, Confirm Implementation:

[0086] After generating the control command, to prevent accidental activation, the user needs to be notified for secondary confirmation before execution. This is suitable for operating energy and security equipment where a balance between safety and efficiency is required. For example, if the system detects that the user is at home in the living room but the room's air conditioner has been left on for an extended period, it can ask the user whether they wish to turn off the air conditioner or switch it to energy-saving mode.

[0087] (3) Intervention level 3, automatic execution:

[0088] After generating control commands, the commands respond instantly through the local policy library on the edge nodes, making it suitable for security or life-saving scenarios where response delays may lead to accidents. For example, in a nighttime sleep scenario, if millimeter-wave radar detects an elderly person falling while using the toilet at night, the system immediately responds and executes an emergency rescue scenario (quickly turning on all the lights in the house, sending warning messages to users inside the house, and sharing health data, etc.).

[0089] As shown in Table 1, this is an example of a user intervention scenario permission hierarchy in an embodiment of this application:

[0090]

[0091] Table 1

[0092] In one embodiment of this application, the home host can also send the target correction instruction to the application used by the target user to control the target home device; upon receiving a confirmation message from the target user to confirm the execution of the target correction instruction, the home host sends the target correction instruction to the target home device so that the target home device executes the target correction instruction.

[0093] In practical applications, after generating the target correction instruction, the user can be made aware of the correction process by sending a confirmation, and the user can decide whether the target correction instruction needs to be applied.

[0094] In this embodiment, in a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the triggering condition information of the scenario execution command and the operating status information of the target home device are obtained; the triggering condition information and the operating status information are input into a preset evaluation model, and the deviation information of the target home device from the scenario execution command is output; when the deviation information is greater than a preset deviation threshold, the deviation cause of the target home device is determined; and a target correction command for the target home device is generated based on the deviation cause. This realizes the determination of dynamic deviation information using a preset evaluation model, and then the correction of the home device's command based on the deviation information.

[0095] It should be noted that the device control correction method provided in this application embodiment can be executed by a device control correction device, or a control module within that device control correction device for executing the loading device control correction method. This application embodiment uses the execution of the loading device control correction method by a device control correction device as an example to illustrate the device control correction method provided in this application embodiment.

[0096] Reference Figure 2 The diagram illustrates a step-by-step flowchart of another device control correction method according to an embodiment of this application, the method comprising:

[0097] Step S201: In a preset scenario, after sending the scenario execution command corresponding to the preset scenario to the target home device, obtain the trigger condition information of the scenario execution command and the operating status information of the target home device;

[0098] In practical applications, preset scenarios can be associated with home appliance control scenarios. Preset scenarios can be determined by analyzing sensor data obtained from multiple sensor devices connected to the home host. For example, data captured by a camera showing the living room door is closed, as well as the door status information fed back to the home host from the living room door, can determine that the current scenario is an "away from home" scenario.

[0099] In practical applications, the control of home devices varies depending on the preset scenario. After determining the preset scenario, the scene execution instruction corresponding to the preset scenario can be determined based on the current preset scenario. The scene execution instruction is the execution instruction set for the home device, that is, the instruction that the home host expects the home device to execute.

[0100] After the home host issues a scene command, it can obtain the trigger condition information of the scene execution command. The trigger condition information can include the specific content that the home device needs to perform in the preset scene. After issuing the scene command, the home host can also monitor the operating status information of the target home device. By monitoring the operating status information, it can determine the execution status of the target home device in response to the received scene execution command.

[0101] For example, when an "away from home" scenario is detected, the corresponding scenario execution command may include turning off indoor lighting and air conditioning equipment. Thus, the scenario execution command for turning off indoor lighting and air conditioning equipment is sent to the indoor lighting and air conditioning equipment.

[0102] After receiving the scene execution command, the indoor lighting and air conditioning equipment can provide feedback on their real-time status.

[0103] Step S202: Input the trigger condition information and running status information into a preset evaluation model, and output the deviation information of the target home device in executing the scene execution command;

[0104] After obtaining the trigger condition information and the running status information, the trigger condition information and the running status information can be input into the preset evaluation model. The evaluation model is used to calculate the execution deviation of the target home device scene execution command, that is, to evaluate the deviation between the trigger condition information and the running status information (deviation information).

[0105] In practical applications, multiple home devices can be pre-collected with the expected scene execution instructions and triggering conditions in different preset scenarios, as well as the operating status information of the home devices after receiving the scene execution instructions. The above data can then be used as training data to train the evaluation model. The input data of the evaluation model are the triggering condition information and the operating status information, and the output data is the deviation information.

[0106] In this embodiment, the deviation information is output by inputting the trigger condition information corresponding to the scene execution command and the operating status information of the target home device into the evaluation model.

[0107] In one embodiment of this application, the home host can configure the evaluation model locally or in the cloud. When the home host configures the evaluation model locally, it can directly call the evaluation model to perform deviation evaluation. When the home host configures the evaluation model in the cloud, it can call the evaluation model in the cloud to perform deviation evaluation.

[0108] In practical applications, the process of evaluating deviation using a preset evaluation model is as follows: the trigger condition information and operating status information are input into the preset evaluation model; in the evaluation model, the device status weight, time decay factor, and spatial correlation factor can be determined based on the trigger condition information and operating status information, and then the deviation information of the target home device in executing the scene execution command can be determined based on the device status weight, the time decay factor, and the spatial correlation factor; the deviation information is then output.

[0109] Among them, the weight of device status can be dynamically adjusted according to the importance of the target home device, such as security camera weight > lighting (importance of privacy and security), and the device weight can be dynamically adjusted by the vertical failure rate.

[0110] Time decay factor (F_time): F_time = e^(-k·t) (where t is the deviation duration and k is the decay coefficient). The longer the deviation of the device's operating state from its actual operating state, the lower the reliability. When the trigger condition information does not match the operating state information, a device control deviation is determined. The deviation duration t can be determined through continuously monitored operating state information and trigger condition information. The decay coefficient is a constant and can be set according to the actual scenario. The time decay factor can then be calculated based on the deviation duration t and the decay coefficient k.

[0111] Spatial correlation factor (F_space): Used to determine the reasonableness of device execution state deviations by locating the distance between the user and the device. Specifically, the home gateway can obtain the distance information between the current user and the target home device, and determine whether the trigger condition information and the running status information match. When the trigger condition information and the running status information do not match, a deviation is determined, and then the spatial correlation factor can be set based on the distance information. For example, if the user is 5 kilometers away from home but the air conditioner is on → correlation factor F_space = 0.1.

[0112] In one embodiment of this application, determining the deviation information of the target home device from the scene execution command based on the device state weight, the time decay factor, and the spatial correlation factor includes:

[0113] The deviation information of the target home device from the execution of the scene execution command is calculated according to the device state weight, the time decay factor, and the spatial correlation factor using a preset formula, wherein the preset formula is as follows:

[0114] D = Σ(W_device×F_time×F_space);

[0115] D represents the deviation information, W_devic represents the device state weight, F_time represents the time decay factor, and F_space represents the spatial correlation factor.

[0116] In this embodiment of the application, a dynamic credibility assessment model can be created. This model can compare the scene triggering conditions with the actual device status in real time, and quantify the inconsistency between the device's operating status and the scene execution requirements through a spatiotemporal weight matrix. The dynamic credibility assessment model can calculate the deviation between the scene triggering conditions and the actual execution result from multiple dimensions, including the scene running device weight, the scene execution time dynamic decay factor, and the user's distance from the device spatial dynamic decay factor. This allows for a more intelligent identification and judgment of whether the device's operating status after scene execution meets the scene requirements. Thus, it enables more intelligent identification and judgment of whether the device is operating normally after scene execution by calculating the deviation between the scene triggering conditions and the actual execution result through multi-dimensional parameters.

[0117] Step S203: When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the target home appliance is determined by multi-source arbitration.

[0118] When the deviation information exceeds a preset deviation threshold, the cause of the deviation of the target home appliance can be determined through multi-source arbitration. Multi-source arbitration involves analyzing the causes of deviation from multiple levels that could lead to the deviation of the target home appliance.

[0119] In one embodiment of this application, the home host can perform arbitration analysis at the device level. Therefore, when the deviation information is greater than a preset deviation threshold, the specific process of determining the deviation cause of the target home device through multi-source arbitration can be as follows: when the deviation information is greater than the preset deviation threshold, the device hardware status information of the target home device can be obtained. The device hardware status information may include any one or more of the following: device operating status, device energy consumption, and fault codes. Then, the deviation cause can be determined based on the device hardware status information.

[0120] For example, analyzing the hardware status of the equipment can identify physical anomalies such as relay jamming, temperature controller failure, or module failure.

[0121] In one embodiment of this application, the home host can perform arbitration analysis from the environmental level. Therefore, the specific process of determining the cause of deviation of the target home device through multi-source arbitration when the deviation information is greater than a preset deviation threshold can be as follows: when the deviation information is greater than the preset deviation threshold, the environmental information of the target home device is obtained. The environmental information may include multi-sensor data such as temperature and humidity, and human infrared data. The cause of deviation can then be determined based on the environmental information. For example, it can identify abnormal device operation caused by sudden environmental changes (such as false intrusion detection, false alarm of kitchen fumes, or failure to close windows during heavy rain).

[0122] In one embodiment of this application, the home host can perform arbitration analysis from the user level. Therefore, the specific process of determining the deviation cause of the target home device through multi-source arbitration when the deviation information is greater than a preset deviation threshold can be as follows: when the deviation information is greater than the preset deviation threshold, obtain the behavioral habit database corresponding to the target user; and determine the deviation cause based on the behavioral habit database.

[0123] Among these features, the behavior habit database is generated based on users' daily behavior. Decision suggestions are generated based on this database, such as prioritizing turning on all the lights in the house instead of just the bathroom light when an elderly person falls. Another example is when the air conditioner fails to respond to temperature adjustment commands after a user triggers a sleep scene.

[0124] In practical applications, arbitration analysis can be conducted by combining equipment, environmental, and user perspectives to determine the causes of deviations. By comprehensively arbitrating from multiple levels, a more complete understanding of the causes of deviations can be obtained, thereby achieving more accurate equipment control and correction.

[0125] Table 2 shows the processing logic of a multi-source arbitration decision engine:

[0126]

[0127] Table 2

[0128] The following analysis of equipment control correction is based on specific scenario examples:

[0129] (1) Scenario Example 1:

[0130] Scene trigger: The user activates the "sleep scene" (preset conditions: living room lights off + air conditioner set to 26℃).

[0131] Phenomenon detected: The air conditioner is not responding to the temperature adjustment command (it continues to run at 20℃).

[0132] Deviation calculation:

[0133] ① Equipment weight: Air conditioner = 0.8 (high energy consumption equipment);

[0134] ② Time factor: 30-minute timeout → attenuation coefficient = 0.6;

[0135] ③ Spatial factor: No one in the bedroom → Correlation coefficient = 0.3;

[0136] → Deviation = 0.8 × 0.6 × 0.3 = 0.144 (> threshold 0.1);

[0137] Multi-source arbitration decision-making:

[0138] Equipment level: No fault codes for the air conditioner → hardware problems ruled out.

[0139] Environmental layer: Bedroom temperature 28℃ → Cooling is required (reasonable demand).

[0140] User level: User history records show that the temperature is often manually adjusted to 24℃ → generate suggestion "Delay correction: Adjust to 24℃ after 1 hour".

[0141] Substitute the user's policy library and find that the user has set "Air conditioning temperature correction requires confirmation". Execute the intervention level "Confirm Execution" and push the command to the user for confirmation via the APP.

[0142] (2) Scenario Example 2:

[0143] Self-correction of false alarms in security systems (false alarms from living room window sensors);

[0144] Scene trigger: Triggered when the user activates the away mode (preset conditions: home monitoring is turned on, door and window sensors are working and detecting whether doors and windows are closed in real time).

[0145] Phenomenon detection: The door and window sensor falsely reported "living room window not closed" (when it was actually closed).

[0146] Deviation calculation:

[0147] ① Equipment weight: Door and window sensor = 0.7 (medium-risk equipment);

[0148] ②Time factor: False alarm lasting 5 minutes → attenuation coefficient = 0.8;

[0149] ③ Spatial factor: User is 3km away from home → Correlation coefficient = 0.2;

[0150] → Deviation = 0.7 × 0.8 × 0.2 = 0.112 (> threshold 0.1).

[0151] Multi-source arbitration decision-making:

[0152] Equipment level: No fault codes for the sensor → rule out hardware faults.

[0153] Environment layer: Camera visually identifies window closure status → marks it as "environmental evidence conflict".

[0154] User level: Historical records show that the sensor has ≥3 false alarms per month → generate a "block false alarms" suggestion.

[0155] Substitute the user policy library to determine that the fault does not affect the execution of commands in normal scenarios. Set the user intervention scenario level to "do not execute", automatically update the sensor status to "calibrating" and block the sensor alarm, push the log to the cloud, display "living room sensor false alarm" on the user's APP, and provide automatic blocking records of sensor false alarms.

[0156] In this embodiment, when the operating status of devices attached to a user's execution scenario deviates from the established pattern, a distributed chain of evidence is generated at the device layer (device energy consumption, device fault codes, etc.), the environment layer (multi-sensor fusion data within the environment), and the user layer (user historical correction records, user status recognition, etc.) to achieve multi-source cross-decision evaluation. This overcomes the limitations of single-layer decision logic that directly generates instructions based on a preset rule base. Consequently, after identifying a deviation between the user's execution scenario and the actual operating status of the devices, a multi-source arbitration decision logic control mechanism can quickly determine the cause of the problem and generate a solution.

[0157] Step S204: Generate a target correction instruction for the target home appliance based on the cause of deviation.

[0158] In this embodiment, in a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the triggering condition information of the scenario execution command and the operating status information of the target home device are obtained; the triggering condition information and the operating status information are input into a preset evaluation model, and the deviation information of the target home device from the scenario execution command is output; when the deviation information is greater than a preset deviation threshold, the deviation cause of the target home device is determined through multi-source arbitration; the target correction command of the target home device is generated according to the deviation cause, thereby realizing the determination of dynamic deviation information using a preset evaluation model, and then realizing the command correction of the home device based on the deviation information.

[0159] Reference Figure 3 The diagram shows a structural schematic of another device-controlled correction apparatus according to an embodiment of this application, the apparatus comprising:

[0160] The information acquisition module 301 is used to obtain the trigger condition information of the scene execution instruction and the operating status information of the target home device after sending the scene execution instruction corresponding to the preset scene to the target home device in a preset scene.

[0161] The deviation information determination module 302 is used to input the trigger condition information and the running status information into a preset evaluation model and output the deviation information of the target home device in the execution of the scene execution command;

[0162] The deviation cause determination module 303 is used to determine the deviation cause of the target home appliance when the deviation information is greater than a preset deviation threshold.

[0163] The target correction instruction determination module 304 is used to generate a target correction instruction for the target home appliance based on the cause of deviation.

[0164] In one embodiment of this application, the deviation information determination module 302 may include:

[0165] The model input submodule is used to input the triggering condition information and running status information into a preset evaluation model;

[0166] The data processing submodule is used to determine the device state weight, time decay factor, and spatial correlation factor based on the trigger condition information and operating status information in the evaluation model.

[0167] The deviation information determination submodule is used to determine the deviation information of the target home device from the execution of the scene execution command based on the device state weight, the time decay factor and the spatial correlation factor;

[0168] The deviation information determination submodule is used to output the deviation information.

[0169] In one embodiment of this application, the deviation information determination submodule may include:

[0170] The deviation determination unit is used to calculate the deviation information of the target home device from the execution of the scene execution command by using the device state weight, the time decay factor, and the spatial correlation factor according to a preset formula, wherein the preset formula is as follows:

[0171] D = Σ(W_device×F_time×F_space);

[0172] D represents the deviation information, W_devic represents the device state weight, F_time represents the time decay factor, and F_space represents the spatial correlation factor.

[0173] In one embodiment of this application, the deviation cause determination module 303 may include:

[0174] The deviation cause determination submodule is used to determine the deviation cause of the target home appliance through multi-source arbitration when the deviation information is greater than a preset deviation threshold.

[0175] In one embodiment of this application, the deviation cause determination submodule includes:

[0176] The device hardware status acquisition unit is used to acquire the device hardware status information of the target home device when the deviation information is greater than a preset deviation threshold.

[0177] The deviation cause determination unit is used to determine the deviation cause based on the device hardware status information.

[0178] In one embodiment of this application, the deviation cause determination submodule may include:

[0179] An environmental information acquisition unit is used to acquire environmental information of the target home appliance when the deviation information is greater than a preset deviation threshold.

[0180] The deviation cause determination unit is used to determine the deviation cause based on the environmental information.

[0181] In one embodiment of this application, the deviation cause determination submodule may include:

[0182] The behavior habit database acquisition unit is used to acquire the behavior habit database corresponding to the target user when the deviation information is greater than a preset deviation threshold.

[0183] The deviation cause determination unit is used to determine the deviation cause based on the behavior habit database.

[0184] In one embodiment of this application, the method includes:

[0185] A primary correction instruction generation unit is used to generate a primary correction instruction based on the cause of the deviation.

[0186] An intervention level determination unit is used to determine the intervention level based on the initial correction instruction and a preset user policy library;

[0187] Target correction instructions are generated to determine the target home appliance based on the intervention level.

[0188] In one embodiment of this application, the target correction instruction determination module 304 may include:

[0189] The sending submodule is used to send the target correction instruction to the application used by the target user to control the target home device;

[0190] The instruction execution module is configured to send the target correction instruction to the target home device when it receives a confirmation message from the target user confirming the execution of the target correction instruction, so that the target home device executes the target correction instruction.

[0191] In this embodiment, in a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the triggering condition information of the scenario execution command and the operating status information of the target home device are obtained; the triggering condition information and the operating status information are input into a preset evaluation model, and the deviation information of the target home device from the scenario execution command is output; when the deviation information is greater than a preset deviation threshold, the deviation cause of the target home device is determined; and a target correction command for the target home device is generated based on the deviation cause. This realizes the determination of dynamic deviation information using a preset evaluation model, and then the correction of the home device's command based on the deviation information.

[0192] The device control correction method in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0193] The device control correction device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0194] The device control correction device provided in this application embodiment can achieve Figures 1 to 2 The various processes implemented by the device control correction device in the method embodiment will not be described again here to avoid repetition.

[0195] In this embodiment, in a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the triggering condition information of the scenario execution command and the operating status information of the target home device are obtained; the triggering condition information and the operating status information are input into a preset evaluation model, and the deviation information of the target home device from the scenario execution command is output; when the deviation information is greater than a preset deviation threshold, the deviation cause of the target home device is determined; and a target correction command for the target home device is generated based on the deviation cause. This realizes the determination of dynamic deviation information using a preset evaluation model, and then the correction of the home device's command based on the deviation information.

[0196] Reference Figure 4 This application also provides an electronic device 100, including a processor 110, a memory 109, and a program or instructions stored in the memory 109 and executable on the processor 110. When the program or instructions are executed by the processor 110, they implement the various processes of the above method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0197] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0198] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0199] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0200] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0201] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0202] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for correcting equipment control, characterized in that, Applied to a home console, the method includes: In a preset scenario, after the scenario execution command corresponding to the preset scenario is sent to the target home device, the trigger condition information of the scenario execution command and the operating status information of the target home device are obtained; The triggering condition information and the running status information are input into a preset evaluation model, and the deviation information of the target home device from the execution of the scene execution command is output. When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the target home appliance is determined; Generate a target correction instruction for the target home appliance based on the cause of the deviation; The step of inputting the triggering condition information and the running status information into a preset evaluation model and outputting the deviation information of the target home device from the scene execution command includes: The triggering condition information and the running status information are input into a preset evaluation model; In the evaluation model, the device state weight, time decay factor, and spatial correlation factor are determined based on the triggering condition information and the operating status information. Based on the device state weight, the time decay factor, and the spatial correlation factor, the deviation information of the target home device from the execution of the scene execution command is determined; Output the deviation information.

2. The method according to claim 1, characterized in that, The step of determining the deviation information of the target home device from the scene execution command based on the device state weight, the time decay factor, and the spatial correlation factor includes: The deviation information of the target home device from the execution of the scene execution command is calculated according to the device state weight, the time decay factor, and the spatial correlation factor using a preset formula, wherein the preset formula is as follows: D = Σ(W_device×F_time×F_space); D represents the deviation information, W_devic represents the device state weight, F_time represents the time decay factor, and F_space represents the spatial correlation factor.

3. The method according to claim 1, characterized in that, When the deviation information is greater than a preset deviation threshold, determining the cause of the deviation of the target home appliance includes: When the deviation information is greater than a preset deviation threshold, the cause of the deviation of the target home appliance is determined through multi-source arbitration.

4. The method according to claim 3, characterized in that, When the deviation information is greater than a preset deviation threshold, the method of determining the cause of deviation of the target home appliance through multi-source arbitration includes: When the deviation information is greater than a preset deviation threshold, the device hardware status information of the target home device is obtained; The cause of the deviation is determined based on the device hardware status information.

5. The method according to claim 3, characterized in that, When the deviation information is greater than a preset deviation threshold, the method of determining the cause of deviation of the target home appliance through multi-source arbitration includes: When the deviation information is greater than a preset deviation threshold, the environmental information of the target home device is obtained; The cause of the deviation is determined based on the environmental information.

6. The method according to claim 3, characterized in that, When the deviation information is greater than a preset deviation threshold, the method of determining the cause of deviation of the target home appliance through multi-source arbitration includes: When the deviation information is greater than a preset deviation threshold, the behavioral habit database corresponding to the target user is obtained; The reasons for deviations are determined based on the aforementioned behavioral habit database.

7. The method according to claim 1, characterized in that, The step of generating the target correction instruction for the target home appliance based on the cause of deviation includes: A primary correction instruction is generated based on the cause of the deviation; The intervention level is determined based on the primary correction instructions and the preset user policy library; The target corrective instructions for the target home appliance are determined according to the intervention level.

8. The method according to claim 1, characterized in that, Also includes: The target correction command is sent to the target user's application for controlling the target home appliance; Upon receiving a confirmation message from the target user confirming the execution of the target correction instruction, the target correction instruction is sent to the target home appliance to cause the target home appliance to execute the target correction instruction.

9. A correction device for equipment control, characterized in that, For use with home consoles, the device includes: The information acquisition module is used to obtain the triggering condition information of the scene execution command and the operating status information of the target home device after sending the scene execution command corresponding to the preset scene to the target home device in a preset scene. The deviation information determination module is used to input the trigger condition information and the running status information into a preset evaluation model and output the deviation information of the target home device in response to the scene execution command. The deviation cause determination module is used to determine the deviation cause of the target home appliance when the deviation information is greater than a preset deviation threshold. A target correction instruction determination module is used to generate a target correction instruction for the target home appliance based on the cause of deviation. The deviation information determination module includes: The model input submodule is used to input the triggering condition information and running status information into a preset evaluation model; The data processing submodule is used to determine the device state weight, time decay factor, and spatial correlation factor based on the trigger condition information and operating status information in the evaluation model. The deviation information determination submodule is used to determine the deviation information of the target home device from the execution of the scene execution command based on the device state weight, the time decay factor and the spatial correlation factor; The deviation information determination submodule is used to output the deviation information.

10. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the correction method for device control as claimed in any one of claims 1 to 8.

11. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the device control correction method as described in any one of claims 1 to 8.

Images