Home equipment regulation and control method combined with whole house intelligent perception and electronic equipment

Abstract

The invention discloses a home equipment regulation and control method combined with whole-house intelligent perception and electronic equipment, and relates to the technical field of home equipment regulation and control, and the method comprises the steps: carrying out the whole-house environment monitoring according to a sensing monitoring module connected to home equipment, and determining multi-source sensing data; according to the equipment control mode, the intelligent regulation and control module is supervised and trained and initialized; interactively accessing a network protocol of home equipment, and constructing an interaction transfer module; and a strategy is returned to the interaction transfer module to execute equipment protocol form reverse conversion, and the strategy is issued to the corresponding home equipment to perform regulation and control management. The technical problem that in the prior art, due to the fact that data integration is difficult, the intelligent regulation and control capacity is poor and regulation and control are not accurate, reasonable decision making and accurate regulation and control are difficult to conduct by effectively utilizing multi-source sensing data is solved, efficient and intelligent regulation and control management on home equipment is achieved, and the intelligent home control and control system is suitable for popularization and application. And the intelligent level and the precision of home equipment regulation and control management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of home appliance control, and in particular to a home appliance control method and electronic equipment combined with whole-house intelligent sensing. Background Art

[0002] With the rapid development of science and technology, smart home systems are gradually entering people's lives, aiming to create a convenient, comfortable and efficient living environment for users. However, existing smart home technologies still face many challenges in practical applications. From the perspective of sensor data processing, the sensor monitoring modules equipped with various home appliances vary greatly. In order to highlight product features or due to technical standards, different manufacturers have different accuracy, data acquisition frequency and data format of built-in sensor modules. This makes it difficult to integrate multi-source sensor data. The inconsistency and incompleteness of the data make it difficult to fully and accurately reflect the true state of the whole house environment, which greatly limits the scientificity and accuracy of subsequent regulation decisions based on these data. In terms of device control mode, most current smart home systems can only achieve simple control based on multimodal interaction, such as voice commands, mobile phone APP control, etc. However, these interaction methods often rely on user active operation and cannot adapt to complex, changing and dynamic living environments.

[0003] Existing technologies have technical problems in smart homes, such as difficulty in data integration, poor intelligent control capabilities, and inaccurate control, which makes it difficult to effectively use multi-source sensor data for reasonable decision-making and precise control. Summary of the invention

[0004] The present application provides a method and electronic device for controlling home appliances combined with whole-house intelligent sensing, which is used to solve the technical problem in the prior art that smart homes are difficult to integrate data, have poor intelligent control capabilities, and have inaccurate control, making it difficult to effectively use multi-source sensor data for reasonable decision-making and precise control.

[0005] In view of the above problems, the present application provides a home appliance control method and electronic device combined with whole-house intelligent sensing.

[0006] The first aspect of the present application provides a method for controlling home appliances in combination with whole-house intelligent sensing, the method comprising:

[0007] According to the sensor monitoring module connected to the home appliance, the whole house environment is monitored to determine the multi-source sensor data, wherein the sensor monitoring module includes an external sensor module and a built-in sensor module of the home appliance; according to the device control mode, the intelligent control module is supervised and trained and initialized, wherein the device control mode includes a first control based on multimodal interaction and a second control based on automation logic; the network protocol of the home appliance is interactively connected, and an interactive transfer module is constructed by a two-way conversion based on the device protocol form-unified protocol form, wherein one end of the interactive transfer module is connected to the home appliance and the other end is connected to the intelligent control module; control decisions are made on the multi-source sensor data, and control management is performed in response to the home appliance, wherein the multi-source sensor data is transmitted to the interactive transfer module, data fusion under form conversion is performed and transferred to the intelligent control module for control decision, and the form of the device protocol is reversely converted by returning the strategy to the interactive transfer module, and then the control management is decentralized to the corresponding home appliance.

[0008] The second aspect of the present application provides an electronic device, comprising: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement a home appliance control method combined with whole-house intelligent perception.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] According to the sensor monitoring module connected to the home appliance, the whole house environment is monitored to determine the multi-source sensor data; according to the device control mode, the intelligent control module is supervised and trained and initialized; the network protocol of the home appliance is interactively connected to build an interactive transfer module based on the two-way conversion of the device protocol form and the unified protocol form; the control decision is made on the multi-source sensor data, and the control management is performed in response to the home appliance. The technical effect of realizing efficient and intelligent control management of home appliances and improving the intelligence level and accuracy of the control management of home appliances is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a flow chart of a method for controlling home appliances combined with whole-house intelligent sensing provided in an embodiment of the present application;

[0013] Figure 2A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0014] Description of the reference numerals: input device 201 , processor 202 , memory 203 , output device 204 . DETAILED DESCRIPTION

[0015] The present application provides a home appliance control method and electronic equipment combined with whole-house intelligent sensing, which is used to solve the technical problem in the prior art that smart homes are difficult to effectively use multi-source sensor data for reasonable decision-making and precise control due to difficult data integration, poor intelligent control capabilities, and inaccurate control.

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] Embodiment 1, as Figure 1 As shown, the present application provides a method for controlling home appliances combined with whole-house intelligent sensing, the method comprising:

[0018] Step S100: Performing whole-house environment monitoring according to the sensor monitoring module connected to the home appliance to determine multi-source sensor data, wherein the sensor monitoring module includes an external sensor module and a built-in sensor module of the home appliance.

[0019] Specifically, firstly, all access devices in the home environment are comprehensively scanned and identified to accurately locate the sensor monitoring modules they carry. For external sensor modules, they are installed according to strict layout specifications based on the spatial structure and functional zoning of the house. In the open area of ​​the living room, high-precision temperature and humidity sensors and light intensity sensors are installed to ensure that the environmental conditions of the public activity space can be fully and accurately reflected; near the head of the bed and around the windows in the bedroom, sensitive air quality sensors and human infrared sensors are respectively set up to monitor the air quality of the sleeping environment and the activity status of people in real time; above the stove in the kitchen and inside the cabinet, smoke sensors and gas leak sensors are deployed to provide strict protection for kitchen safety. The built-in sensor modules of the home equipment themselves have been integrated into key parts during the production process of the equipment. For example, the temperature and humidity sensing elements inside the smart air conditioner can accurately sense the temperature and humidity changes near the air outlet; the light sensing elements in the smart lighting fixtures can accurately monitor the intensity of the surrounding light; the vibration and current sensors in the motor parts of smart home appliances such as washing machines and refrigerators can effectively feedback the operating stability and energy consumption of the equipment. When in operation, these external and built-in sensor monitoring modules will simultaneously start all-round, uninterrupted monitoring of the entire house environment according to preset time intervals and precise measurement standards. They will collect various types of data, such as temperature data accurate to one decimal place, humidity data accurately presented in percentage form, light intensity accurately quantified in lux, air quality indicators covering the concentration values ​​of various pollutants such as PM2.5, formaldehyde, TVOC, and various parameters of equipment operation, and transmit them to the data processing center through reliable communication links. After preliminary screening, integration and verification by the data processing center, a rich variety of multi-source sensor data was successfully determined. These data will serve as the key basis for subsequent intelligent regulation and control, laying a solid foundation for creating a comfortable, safe and energy-saving home environment.

[0020] Step S200: supervise and train the intelligent control module and initialize it according to the device control mode, wherein the device control mode includes a first control based on multimodal interaction and a second control based on automation logic.

[0021] Specifically, we conduct an in-depth analysis of the device control mode, and integrate interactive technology for the first control based on multimodal interaction, that is, user interactive control. For example, by using a high-precision voice recognition system, which has been trained with a large number of voice samples, it can accurately recognize the voice commands of different users and achieve a high recognition accuracy rate; at the same time, it is equipped with a high-sensitivity gesture recognition sensor, which can accurately capture the user's gestures based on image recognition algorithms and deep learning models, and distinguish the meanings of different gestures, such as waving to turn on or off the device, and sliding gestures to adjust device parameters. For the second control based on automation logic, on the one hand, we focus on the automation control of each device. For example, smart air conditioners continuously monitor the ambient temperature through built-in temperature sensors. When the temperature deviates from the preset comfort range, they automatically start the cooling or heating function according to the pre-set temperature adjustment rules, and can dynamically adjust the wind speed and power according to the temperature changes to achieve adaptive temperature adjustment based on the ambient temperature. On the other hand, we focus on the coordinated automatic adjustment of the interaction between devices, such as the intelligent lighting system and the intelligent curtain system working together. When the light intensity sensor detects that the external light is too strong, the intelligent curtains are automatically closed. At the same time, the intelligent lighting system will automatically adjust the brightness according to the changes in the indoor light to maintain the suitability of the indoor light. On this basis, strict environmental standards are set, and a detailed set of predefined rules is determined through a large amount of actual home environment data. These rules cover the conditions for triggering control, such as how to start the corresponding equipment or adjust the equipment parameters when the temperature reaches a certain threshold or the air quality index exceeds the safe range, as well as the method for determining dimensional amplitude modulation, such as the amplitude of temperature adjustment and the step size of humidity adjustment. A wide range of control samples from different home scenes and different user habits are collected, and the fuzzy decision logic is deeply mined using data mining technology and machine learning algorithms. These logics are closely combined with predefined rules to carry out strict supervised training driven by samples. During the training process, the internal parameters and decision models of the intelligent control module are continuously adjusted, and through repeated iterative optimization, it can accurately generate reasonable control strategies based on the input sensor data and user instructions. Finally, the intelligent control module is initialized based on the user layout information and user preferences. For the layout information of the apartment, the area, orientation, function and other factors of the room are analyzed to determine the initial control parameters of the equipment in different areas. For example, if the living room is large, the initial wind speed and cooling and heating power of the air conditioner may be relatively high; if the bedroom faces the sun, the initial opening and closing degree of the smart curtains and the initial brightness of the smart lighting will be different. At the same time, combined with the preferences expressed by users through questionnaires, usage history records, etc., such as the indoor temperature range that users are accustomed to, favorite light colors and brightness modes, etc., the initial state of the intelligent control module is further personalized to ensure that it can better meet user needs when it is put into use and realize efficient and intelligent home equipment control.

[0022] Step S300: Interactively access the network protocol of the home appliance, and construct an interactive transfer module based on the bidirectional conversion between the device protocol form and the unified protocol form, wherein one end of the interactive transfer module is connected to the home appliance, and the other end is connected to the intelligent control module.

[0023] Specifically, the network protocols used by various home appliances in the home environment are comprehensively sorted out and analyzed. Since the devices produced by different manufacturers have significant differences in the underlying logical design, the network protocols they configure are also different. For example, some well-known home appliance brands use their own developed dedicated network protocols to achieve the unique functions and efficient operation of the devices, but this also leads to compatibility issues with other brands of devices; while some small manufacturers' devices are based on some common but different versions of network protocols, which are insufficient in the stability and security of data transmission. In order to solve this key problem, an interactive transfer module is introduced. When building this module, a set of efficient conversion mechanisms is developed for the network protocols of different devices to achieve two-way conversion from device protocol form to unified protocol form. When receiving data from home devices, the interactive transfer module first identifies the specific network protocol used by the device, and converts the data sent by the device into a unified protocol form according to the established conversion rules through the built-in protocol parser. For the binary-coded protocols used by some devices, the transfer module needs to convert them into universal ASCII codes or other unified data formats, and adjust the timing and frequency of data transmission to meet the specifications of the unified protocol. After the data is analyzed and processed by the intelligent control module, the interactive transfer module plays a key role again. It converts the control instructions generated by the intelligent control module from the unified protocol form back to the device's own protocol form. This reverse conversion process also requires precise operation. The transfer module makes adaptive adjustments based on the characteristics of different devices based on the pre-stored device protocol library and conversion rules. For example, for some devices that require high command response speed, such as smart door locks, the transfer module will optimize the transmission format and timing of the instructions to ensure that the instructions can be quickly and accurately delegated to the device to achieve instant response of the device; while for some complex devices, such as smart home theater systems, the transfer module will perform detailed analysis and encapsulation of the control instructions to ensure that the instructions can correctly drive the various functional modules of the device and achieve accurate control effects. Through such a two-way conversion mechanism, the interactive transfer module successfully connects closely with various home appliances on one end, ensuring smooth upload of device data and accurate reception of control instructions; the other end is firmly connected to the intelligent control module, ensuring efficient transmission and correct processing of data between the two.

[0024] Step S400: Make control decisions on the multi-source sensor data, and perform control management in response to the home appliances, wherein the multi-source sensor data is transmitted to the interactive transit module, data fusion is performed under form conversion, and the data is transferred to the intelligent control module for control decision making, and the strategy is transmitted back to the interactive transit module to perform inverse conversion of the form of the device protocol, and then the data is transferred to the corresponding home appliances for control management.

[0025] Specifically, the multi-source sensor data obtained through the whole house environment monitoring will be accurately transmitted to the interactive transfer module according to the established transmission path. These multi-source sensor data contain rich information from different locations and different types of home appliances, such as temperature and humidity data of each room, light intensity of different areas, and operating status parameters of various home appliances. After receiving the data, the interactive transfer module will immediately start the data fusion program under the form conversion. In view of the diversity of data sources and differences in formats, the transfer module will standardize and deeply integrate the data according to the pre-set fusion rules and algorithms. For example, for temperature data, weighted average calculation may be performed according to the accuracy and calibration of different sensors to obtain a more accurate overall indoor temperature; for light intensity data, the orientation and functional requirements of different rooms will be comprehensively considered to conduct a reasonable summary analysis. After the fusion processing, the integrity and availability of the data are significantly improved, and then it is efficiently transferred to the intelligent control module. With its powerful computing power and complex decision-making logic, the intelligent control module combines the internal pre-trained and set models and rules to conduct a comprehensive and in-depth control decision analysis on the fused sensor data. It will comprehensively consider many factors such as the comfort requirements of the environment, the rational use of energy, and the safety of equipment operation. For example, when it is detected that the temperature in the living room is too high and the humidity is low, the intelligent control module decides to start the cooling and humidification functions of the air conditioner, and accurately adjusts the wind speed and humidification amount of the air conditioner according to the specific deviations of temperature and humidity; when it is found that the light in the bedroom is too strong and affects sleep, it will generate a control strategy to turn off some lights or adjust the opening and closing of the curtains. Once the intelligent control module completes the control decision, the generated strategy will be quickly transmitted back to the interactive transfer module, which will play a key role again and perform the reverse conversion operation of the device protocol. Due to the differences in the device protocols followed by different home appliances, the transfer module needs to accurately identify the protocol type of the target device and convert and encapsulate the control strategy in a format that the device can recognize and accept. Finally, the converted control strategy is accurately delegated to the corresponding home appliance, thereby realizing effective control and management of home appliances and ensuring that the home environment is always in an ideal state of comfort, safety and energy saving.

[0026] In a possible implementation, step S200 further includes:

[0027] Step S210: setting environmental standards and determining a predefined rule set, wherein the predefined rule set is used for control triggering and dimensional amplitude modulation determination.

[0028] Step S220: Acquire control samples, mine fuzzy decision logic, combine the predefined rules, perform sample-driven supervised training, and acquire the intelligent control module.

[0029] Step S230: Initializing the intelligent control module, wherein the initialization method is personalized learning based on apartment layout information and user preferences.

[0030] Specifically, environmental standards are set by taking into account many factors. On the one hand, according to relevant national and industry standards and specifications, such as national standards for indoor air quality, the appropriate range of parameters such as temperature, humidity, and air quality is determined. For example, the comfort range of indoor temperature is set at 22 to 26 degrees Celsius, and the humidity is maintained at 40% to 60%. On the other hand, based on actual home use scenarios and common needs, ideal standards such as light intensity in different time periods are formulated. On this basis, the relationship between these environmental standards and equipment regulation is deeply analyzed to determine the predefined rule set. This rule set specifies in detail the circumstances under which environmental parameters change to trigger the control action of the device, such as when the temperature is higher than 26 degrees Celsius, the air conditioner is started for cooling; at the same time, the dimensional amplitude modulation of the control is clarified, such as the amplitude of each temperature adjustment during air conditioning cooling is 1 degree Celsius, etc., providing a precise guidance framework for subsequent control operations.

[0031] The control samples are collected through various channels, and obtained from the actual operation data of smart homes in different regions, different house types and covering various user behavior habits to form a large-scale sample data set. For example, the indoor environmental parameters (temperature, humidity, light intensity, etc.) in different seasons and different time periods and the corresponding user control operation records of home appliances (air conditioners, lights, curtains, etc.) are collected. For mining fuzzy decision logic, the fuzzy C-means clustering algorithm (FCM) is used. This algorithm divides the sample data into different clusters according to the data characteristics, and each cluster represents a similar control scenario or decision mode. By calculating the membership of the sample data points to each cluster center, the degree of belonging of each data point in different decision modes is determined. For example, for a set of temperature and humidity data and the corresponding air conditioning control operation, the FCM algorithm can identify the user's usual air conditioning temperature setting preference and wind speed adjustment mode within a specific temperature and humidity range. When combining predefined rules for sample-driven supervised training, the back propagation neural network (BP neural network) algorithm is used. The mined fuzzy decision logic and predefined rules are used as the input features of the BP neural network, and the control operation results are used as output labels. The BP neural network predicts the output through forward propagation calculation, compares it with the actual output label, and calculates the error. Then, the weight and bias of the network are adjusted according to the error back propagation, and the optimization is continuously iterated so that the network can accurately generate appropriate control strategies based on the input environmental data and rule information. For example, when a specific temperature, humidity, light intensity and the corresponding predefined control rules are input, the trained BP neural network can output the correct air conditioning temperature adjustment instructions, light brightness adjustment values ​​and curtain opening and closing control signals, etc. After repeated training and verification of a large number of samples, the intelligent control module is finally successfully obtained, which enables it to have efficient and accurate control decision-making capabilities.

[0032] The initialization work of the intelligent control module is fully launched, and the layout information of the apartment is deeply analyzed. For the size of the house, if the area is large, such as a villa apartment of more than 150 square meters, the intelligent control module will appropriately increase the power range of large equipment such as air conditioners during initialization to ensure that the environmental parameters of the entire space can be effectively adjusted; for the number of rooms, it will be classified and set according to the function of each room. For example, the bedroom area will focus on the creation of a sleeping environment. In terms of lighting control, the initial setting is a darker and softer light mode, and the initial value of the air conditioner temperature will be set in the range of 24-26 degrees Celsius, which is suitable for human sleep. In terms of functional zoning, the living room is a public activity area, and the initial brightness of the light will be set relatively high to meet the needs of daily activities. The initial opening and closing degree of the smart curtains may be adjusted according to the orientation and lighting conditions. If it faces the direction of sufficient sunlight, the initial state may be half-open to balance the lighting and shading needs. At the same time, the key factor of user preference is fully considered. User preference information is obtained through the user's preliminary settings in the system, big data analysis of historical usage records, and questionnaires. If the user frequently sets the air conditioner temperature to 22 degrees Celsius in the past, the default temperature of the air conditioner will be set to 22 degrees Celsius during initialization; if the user is accustomed to turning on the specific atmosphere light in the living room from 7 to 10 pm, the light will be automatically turned on during the corresponding time period and set according to the user's previous brightness and color preferences. In addition, for some users with special needs, such as the elderly or children, the system will further adjust the initialization parameters according to their special needs. For rooms where the elderly live, the fluctuation range of the air conditioner temperature will be narrowed to avoid physical discomfort caused by excessive temperature differences, and the light brightness will be appropriately increased to facilitate the activities of the elderly. Through such all-round personalized learning based on apartment layout information and user preferences, the intelligent control module can meet the actual needs of users to the greatest extent at startup, providing users with comfortable and convenient home environment control services.

[0033] In a possible implementation, step S400 further includes:

[0034] Step S410: receiving user interaction information, making a control decision based on the user interaction information, and determining a first control strategy, wherein the user interaction information includes at least one interaction mode.

[0035] Step S420: Determine a second control strategy according to the multi-source sensor data.

[0036] Step S430: Check the first control strategy and the second control strategy. If the difference is less than or equal to a preset control difference, user interaction control is given the first priority and home appliance control management is performed based on the first control strategy.

[0037] Step S440: If it is greater than or equal to the preset control difference, the home appliance control management is performed based on the second control strategy, and feedback indication is given to the user interaction information.

[0038] Specifically, the multimodal interactive receiving mechanism is activated to fully prepare to receive user interactive information. Whether it is a clear voice command from the user, such as "adjust the air conditioner temperature in the living room to 22 degrees", the voice recognition module will quickly capture and convert it into a digital signal; or through touch operations on the screen of the smart device, such as the user sliding on the temperature control interface to select a temperature setting of 20 degrees; or through gestures, such as waving up or down in a specific sensing area to indicate raising or lowering the temperature, it can be accurately perceived. Once these interactive information are received, the intelligent analysis process is immediately started. For the temperature adjustment requirements, combined with the current ambient temperature data, if the current living room temperature is 28 degrees, and the user requires adjustment to 22 degrees, then the amplitude modulation is determined to be reduced by 6 degrees. Then, according to the performance parameters and operating status of the equipment, a detailed program execution logic is planned. For example, a cooling start instruction is first sent to the air conditioner. According to the temperature difference and the cooling power of the air conditioner, the initial wind speed is set to medium. As the temperature gradually approaches the target value, the wind speed is reduced in time to ensure that the temperature drops steadily and the energy consumption is reasonable. Finally, a complete first control strategy is determined to provide accurate guidance for subsequent equipment control.

[0039] The data fusion algorithm is used to integrate multi-source sensor data. For example, for temperature data, the weighted average method is used to assign corresponding weights according to the accuracy and reliability of sensors at different locations to calculate the comprehensive indoor temperature. Assuming that the bedroom temperature sensor has a higher accuracy and the weight is set to 0.6, and the living room temperature sensor has a weight of 0.4, if the bedroom temperature is 23 degrees Celsius and the living room temperature is 26 degrees Celsius, then the comprehensive temperature is 23×0.6+26×0.4=24.2 degrees Celsius. The control requirements are determined by comparing with the preset environmental comfort range. Taking temperature as an example, if the preset comfort temperature range is 22-25 degrees Celsius, when the calculated comprehensive temperature of 24.2 degrees Celsius is higher than the upper limit of 25 degrees Celsius, it is determined that cooling control is required. For equipment control decisions, a rule-based reasoning algorithm is used. For example, for air conditioning control, rules are formulated based on the degree of temperature deviation: if the temperature deviation is between 1-3 degrees Celsius, the air conditioning wind speed is set to low wind speed and the cooling power is 50%; if the deviation is between 3-5 degrees Celsius, the wind speed is adjusted to medium wind speed and the cooling power is 70%; if the deviation is greater than 5 degrees Celsius, the wind speed is set to high wind speed and the cooling power is 90%. When the current temperature of 24.2 degrees Celsius is higher than 25 degrees Celsius and the deviation is less than 3 degrees Celsius, the air conditioning control strategy is determined to adjust the wind speed to low wind speed and set the cooling power to 50%. For humidity control, if the humidity sensor detects that the humidity is 60%, and the comfortable humidity range is 40%-50%, it exceeds the upper limit by 10%. According to the preset rules, when the humidity deviation is between 5%-10%, the dehumidifier is started and the dehumidification intensity is set to medium. For light intensity control, a threshold judgment algorithm is used. If the light sensor detects that the light intensity in a room reaches 800 lux, and the preset upper limit of comfortable light intensity is 500 lux, when it exceeds the threshold, the intelligent curtain motor is controlled to move, so that the curtain is opened to a certain proportion to reduce the light intensity, such as opening to 40%. Through the synergy of the above data fusion, rule-based reasoning, threshold judgment and other algorithms, the second control strategy is accurately determined according to multi-source sensor data to achieve intelligent control of home appliances.

[0040] The first control strategy and the second control strategy are carefully proofread using an accurate comparison algorithm. For example, in terms of temperature control, if the first control strategy is to set the bedroom temperature to 22 degrees Celsius, and the second control strategy is based on the environmental sensor data to obtain a suitable temperature of 21.5 degrees Celsius, the absolute value of the difference between the two is calculated. Assuming that the preset control difference is 0.5 degrees Celsius, in this case the difference is 0.5 degrees Celsius, which satisfies the condition of being less than or equal to the preset control difference. Once it is determined that the condition is met, the principle of user interactive control as the first priority is immediately followed. Then, according to the specific instructions in the first control strategy, the corresponding home appliance control program is started in an orderly manner. For example, for the above temperature control, an instruction is sent to the bedroom air conditioner to make it run according to the set cooling mode and wind speed and other parameters, and the temperature is accurately adjusted to 22 degrees Celsius required by the user. During the entire control process, the operating status of the equipment and the changes in environmental parameters are continuously monitored to ensure the stability and accuracy of the control process, and ultimately to achieve efficient home appliance control management based on user needs, providing users with a comfortable living environment.

[0041] The difference between the first control strategy and the second control strategy is calculated and compared. Once the difference between the two is found to be greater than or equal to the preset control difference, the home appliance control process based on the second control strategy is immediately started. Assuming that the indoor temperature has reached 32 degrees Celsius, the user issues an interactive command to increase the temperature. The second control strategy determines that the air conditioning cooling function should be turned on based on multi-source sensor data and the preset environmental comfort standard, and sets the temperature to 26 degrees Celsius. The second control strategy is executed to send a cooling command to the air-conditioning equipment, adjust parameters such as wind speed and cooling power, so as to quickly reduce the indoor temperature and ensure that the indoor environment is in a comfortable and energy-saving state. At the same time, feedback instructions are given to the user's interactive information in a variety of ways, such as a voice prompt in the smart speaker: "The current indoor temperature is too high. For your comfort and health, the system has automatically executed the cooling operation. Your heating command has not been executed yet." Through feedback, users can clearly understand the system's control decisions, avoid users being confused or repeatedly issuing unreasonable commands due to misunderstandings, and effectively improve the interactive friendliness and control rationality of the smart home system.

[0042] In a possible implementation, step S420 further includes:

[0043] Step S421: converting and fusing the multi-source sensor data by converting from a device protocol format to a unified protocol format to determine fused sensor data.

[0044] Step S422: Based on a predefined rule set, an adjustment trigger decision is made on the fused sensor data, and an adjustment target is determined by decoupling, wherein the adjustment target includes pre-adjusting home equipment-equipment pre-adjustment target.

[0045] Step S423: Based on the adjustment target, an adaptive control decision is made to determine the second control strategy.

[0046] Specifically, the protocol conversion and data fusion mechanism is first started. Since the multi-source sensor data comes from home devices of different types and brands, their data formats and transmission protocols are different. Through the built-in conversion module, the data in the form of these device protocols are converted into a unified protocol form. For example, the smart temperature sensor uses a binary encoding protocol of a specific manufacturer to transmit temperature data, while the smart light sensor uses another text-based protocol. According to the preset conversion rules, they are converted into a common data format, such as the standardized JSON format. After the conversion is completed, the data fusion algorithm is used to process these unified format data. For the temperature data from different rooms, the weighted average method is used for fusion. Weights are assigned according to the accuracy and location importance of the sensor, so as to obtain more accurate indoor comprehensive temperature data; for data such as light intensity and humidity, similar methods are also used for fusion, and finally the fused sensor data is determined to provide comprehensive and accurate basic information for subsequent regulation.

[0047] The fused sensor data is deeply analyzed according to the pre-set rule sets. These rule sets are based on a large amount of experimental data and professional environmental knowledge, covering the correlation between changes in different environmental parameters and the regulation of home appliances. When the fused sensor data shows that the indoor temperature is higher than the preset upper limit of the comfort temperature and the humidity is also beyond the appropriate range, the adjustment decision is triggered according to the rules. Through complex data analysis and logical judgment, the adjustment target is determined by decoupling. For example, it is determined that the pre-adjusted home appliance that needs to adjust the temperature is an air conditioner, and its equipment pre-adjustment target is to reduce the temperature to a comfortable range. At the same time, it is determined that the pre-adjusted home appliance that needs to adjust the humidity is a dehumidifier, and its equipment pre-adjustment target is to reduce the humidity to an appropriate level. The specific regulation tasks and target parameters of each pre-adjusted home appliance are clarified.

[0048] With the determined adjustment target as the core orientation, the adaptive control decision-making process is carried out. For air-conditioning equipment, the control strategies such as the air-conditioning cooling power, wind speed setting and running time are comprehensively determined according to factors such as the difference between the current temperature and the target temperature, the size of the indoor space and the cooling performance parameters of the air-conditioning. If the temperature deviation is large and the indoor space is spacious, set a higher cooling power and a high wind speed to speed up the cooling speed; for the dehumidifier, determine the dehumidification amount and running time according to the degree of humidity deviation and the room area. Through such adaptive control decisions, a scientific and reasonable control strategy is formulated for each pre-adjusted home appliance, and finally a complete second control strategy is determined to achieve efficient and accurate control of home appliances, ensuring that the home environment is always in a comfortable state.

[0049] In a possible implementation, step S422 further includes:

[0050] Step S4221: Make an adjustment trigger decision on the fused sensor data to determine the dimension adjustment requirement, wherein the dimension adjustment requirement includes adjusting dimension-dimensional amplitude modulation.

[0051] Step S4222: traverse the dimensional adjustment requirements, optimize the dimensional adjustment requirements allocation of homologous home appliances based on energy consumption minimization and space constraints, and determine the demand decoupling sequence, wherein each dimensional adjustment requirement corresponds to at least one pre-adjusted home appliance.

[0052] Step S4223: Based on the home appliance affiliation, the demand decoupling sequence is integrated to determine the adjustment target.

[0053] Specifically, a comprehensive and detailed analysis of the fused sensor data is performed. For example, when the fused sensor data shows that the indoor temperature is 28 degrees Celsius, while the preset comfortable temperature range is 22 to 25 degrees Celsius, the humidity is 55%, the comfortable humidity range is 40% to 50%, and the ambient noise reaches 60 decibels, while the suitable quiet environment should be below 40 decibels, according to the difference between these data and the preset standards, it is determined that there are adjustment needs in the three dimensions of temperature, humidity and sound. For the temperature dimension, its adjustment dimension is cooling, and the amplitude modulation is to reduce the temperature by 3 to 6 degrees Celsius; the adjustment direction of the humidity dimension is dehumidification, and the amplitude modulation is to reduce the humidity by 5% to 10%; the sound dimension is noise reduction, and the amplitude modulation is to reduce by about 20 decibels. Next, for the case where the air conditioner can adjust both the temperature and the humidity to a certain extent, an initial allocation is made. Assume that based on the functional characteristics and efficiency of the equipment, it is preliminarily determined that the air conditioner undertakes 70% of the temperature adjustment task and 30% of the humidity adjustment task, and the humidifier or dehumidifier undertakes the remaining humidity adjustment task. Then, further optimization and allocation are carried out based on the principles of minimizing energy consumption and space constraints. For example, if the indoor space is small, the cooling or heating effect of the air conditioner will be more obvious. At this time, the proportion of the air conditioner in temperature regulation will be appropriately increased; if it is found that the dehumidification energy consumption of the air conditioner is high under the current humidity conditions, and the dehumidification efficiency of the dehumidifier is more advantageous in this humidity range, the allocation ratio will be readjusted to increase the proportion of the humidity regulation task of the dehumidifier to ensure that while meeting the regulation needs, the efficient use of energy and the reasonable operation of the equipment are achieved, so as to accurately determine the regulation needs and allocation plans of each dimension, and lay a solid foundation for subsequent regulation decisions.

[0054] A comprehensive traversal of the determined dimensional adjustment requirements is performed. For example, the dimensional adjustment requirements involve multiple aspects such as temperature, humidity and light. For temperature adjustment, there are multiple homologous home appliances that can adjust the temperature, such as air conditioners and electric heaters in different rooms; for humidity adjustment, there are air conditioners with dehumidification functions, independent humidifiers or dehumidifiers; for light adjustment, there are various smart lamps and adjustable curtains. The optimization work is carried out with energy minimization and space constraints as important principles. In terms of energy minimization, the energy consumption of different devices when achieving the same adjustment range is compared. For example, when it is necessary to lower the indoor temperature, the analysis found that the large air conditioner in the living room has high cooling efficiency and relatively low energy consumption, while the small electric heater in the bedroom has high energy consumption in cooling mode. At this time, more temperature adjustment tasks will be assigned to the living room air conditioner first. At the same time, considering the space constraint factor, if a certain area is small and a lot of furniture is placed, the operation of large equipment may be hindered, so the use of such equipment will be reduced in this area. For example, in the study, due to limited space, it is not suitable to use a large air humidifier for a long time. Instead, small, portable and low-space-requirement equipment is given priority. Based on these considerations, the dimensional adjustment requirements of the same-source home appliances are allocated and optimized. For the humidity adjustment requirements, assuming that the humidity needs to be reduced by a certain amount, the dehumidification energy consumption, efficiency of the air conditioner and the performance of the independent dehumidifier are comprehensively evaluated. If the air conditioner is in the current operating state, additional dehumidification will greatly increase energy consumption, and the independent dehumidifier has low energy consumption and can complete the task efficiently, most of the humidity adjustment tasks will be assigned to the independent dehumidifier. Through such an optimization process, at least one pre-adjusted home appliance is determined for each dimensional adjustment requirement, and this information is organized into a demand decoupling sequence. This sequence clearly shows the pre-adjusted home appliances corresponding to each dimensional adjustment requirement, as well as key information such as the proportion of adjustment tasks they each undertake, providing a clear and reasonable basis for subsequent regulation decisions, ensuring that the regulation of home appliances can not only meet the environmental regulation requirements, but also achieve the optimization of energy consumption and space utilization.

[0055] The optimized and apportioned demand decoupling sequence is integrated based on the home appliance attribution. Since the pre-adjusted home appliances and task allocations corresponding to the adjustment requirements of each dimension have been clearly defined in the demand decoupling sequence, it is necessary to further sort out this information according to the attributes such as the area to which the home appliances belong, functional classification, etc. Assuming that in a multi-room residential scenario, the demand decoupling sequence shows that the air conditioner in the living room undertakes certain temperature and humidity adjustment tasks, and the air conditioner in bedroom 1, the electric heater in bedroom 2, and the air purifier placed independently in the living room also undertake the adjustment work of the corresponding dimensions. First, the adjustment tasks of the relevant equipment in the living room are grouped into one group according to the room, and the equipment adjustment tasks of bedroom 1 and bedroom 2 are grouped into two other groups. In the equipment group in the same room, the synergistic relationship between the equipment is comprehensively considered. For example, the air conditioner and air purifier in the living room are responsible for the adjustment of different dimensions respectively, but they may affect each other's energy consumption and adjustment effect during operation. Through the preset algorithm, it is analyzed how to make these two devices work together to reduce the interference between the equipment while ensuring the achievement of the adjustment target and optimize the overall energy consumption. For example, when the air conditioner is cooling, if the wind speed of the air purifier is set too high, it will affect the cooling effect of the air conditioner. The wind speed of the air purifier should be adjusted according to the actual situation. Then, the adjustment tasks are integrated again according to the functional categories of home appliances. For all devices responsible for temperature adjustment, their target temperature, adjustment time, adjustment range and other information are planned in a unified manner to ensure that the temperature adjustment of the entire living space is coordinated and consistent. Similarly, similar integration operations are performed for devices that adjust other dimensions such as humidity and light. After this series of integration steps, a clear, definite and operational adjustment target is finally determined. This adjustment target is no longer a set of scattered equipment adjustment instructions, but a comprehensive and systematic adjustment plan formed from the perspective of the entire home environment and comprehensive consideration of various factors, which provides a clear direction and specific task requirements for the precise regulation of subsequent home appliances.

[0056] In a possible implementation, step S400 further includes:

[0057] Step S450: determining a static adjustment target and a dynamic adjustment target for the adjustment target.

[0058] Step S460: Identify the static adjustment target, make parameter control adjustment decisions, and determine the static target strategy.

[0059] Step S470: Identify the dynamic adjustment target, make parameter adjustment decisions and path planning, and determine the dynamic target strategy, wherein the path planning constraints are performed based on the apartment layout information.

[0060] Step S480: Integrate the static target strategy and the dynamic target strategy as the second control strategy.

[0061] Specifically, the determined regulation targets are classified based on the equipment's operating characteristics and regulation requirements. For example, equipment such as air conditioners and humidifiers, whose regulation is mainly to continuously and stably adjust environmental parameters, are static regulation targets; while equipment such as sweeping robots, whose working process involves movement and dynamic operations, are classified as dynamic regulation targets.

[0062] Quickly scan and identify various static adjustment targets, including smart air conditioners, lighting fixtures, humidifiers, dehumidifiers, and fresh air systems. Through the built-in communication module, the operating status parameters of each device are obtained, such as the set temperature, actual room temperature, operating mode, wind speed level, and energy efficiency ratio of the smart air conditioner; the brightness, color temperature, and opening status of the smart lighting fixture; the water level, humidification amount, and working mode of the humidifier. Combined with multi-source sensor data, the current environmental conditions are deeply analyzed. If the indoor temperature is 28°C and the comfortable temperature range is 22-25°C, it is clear that the temperature needs to be lowered; if the humidity is 35%, which is lower than the comfortable range of 40%-60%, it is determined that the humidity needs to be increased. Subsequently, the parameter control adjustment decision is made. On the one hand, according to the preset rule base, when the temperature deviation is 1-3°C, the smart air conditioner will be set to low wind speed cooling mode, and the temperature will be adjusted to 25°C to cool down in an energy-saving way; if the deviation exceeds 3°C, the wind speed and cooling power will be increased to quickly cool down. When the humidity is 5%-10% below the comfort limit, the humidifier turns on the medium humidification mode; when it is more than 10% below the lower limit, the high humidification mode is turned on. On the other hand, in order to efficiently use energy, the optimization algorithm is used to consider the synergy effect of equipment and the balance of energy consumption. For example, when adjusting the temperature and humidity at the same time, the algorithm analyzes and selects the air conditioner and humidifier to work together to reduce the overall energy consumption. For smart lighting fixtures, according to the time, light intensity and user activity mode, when the outdoor light is strong during the day, its brightness is adjusted to a lower level and the color temperature is adjusted. Through these operations, the static target strategy is finally determined.

[0063] Focus on processing tasks related to dynamic adjustment targets, and quickly identify dynamic adjustment devices such as sweeping robots and window cleaning machines. Taking the sweeping robot as an example, through the connection and communication with the device, obtain its current basic parameters such as power, cleaning mode options, and cleaning efficiency. Then, combine the multi-source sensor data and the preferences set by the user to make parameter control and adjustment decisions. For example, if it is detected that there is a lot of dust in the room and the user sets a deep cleaning preference, set the cleaning mode of the sweeping robot to a strong cleaning mode, and appropriately extend the single cleaning time to ensure the best cleaning effect. In terms of path planning, make full use of the layout information of the house for strict constraints, obtain the floor plan data of the house, and parse out the key information such as the location, size, and placement of furniture in each room. For example, if there is a narrow aisle in the house, the width can only accommodate the sweeping robot, and the robot is planned to pass through the aisle at a slower speed and in a straight line to avoid colliding with the walls on both sides. For areas with dense furniture, such as a living room with many sofas and coffee tables, the robot vacuum cleaner is planned to clean along the edges of the furniture according to the distribution of the furniture, while flexibly avoiding obstacles to ensure efficient completion of the cleaning task without damaging the furniture. By comprehensively considering the parameter control adjustment decision and path planning, a set of scientific and reasonable dynamic target strategies is finally determined to achieve efficient operation of dynamic adjustment equipment in complex home environments.

[0064] Integrate the static target strategy with the dynamic target strategy. Integrate the control strategies of air conditioners, humidifiers and other equipment with the control and path planning strategies of dynamic equipment such as sweeping robots to form a complete and unified control solution. This is the final second control strategy, which provides a detailed operation guide for achieving comprehensive and efficient home environment control.

[0065] In a possible implementation, step S400 further includes:

[0066] Step S490: Combined with the sensor monitoring module, control tracking is performed to determine the control response data; the control response data is identified, a first check is performed based on the response vector difference, a second check is performed based on the response trend deviation, and the control effect is determined; based on the control effect, feedback control management of home appliances is performed.

[0067] Specifically, the control process of home appliances is tracked in all directions with the help of sensor monitoring modules, which are distributed throughout the house and cover various sensors such as temperature, humidity, and light, and can collect environmental data after the equipment is controlled in real time. For example, when the smart air conditioner starts cooling according to the control strategy, the temperature sensor continuously records the change in indoor temperature. This series of data constitutes the control response data.

[0068] The control response data is deeply analyzed. In the first verification stage, the actual control response data is compared with the expected target data by calculating the response vector difference. Assuming that the expected indoor temperature should drop from 30°C to 26°C within one hour, and the actual collected temperature data is 27°C after one hour, the accuracy of the control is judged by calculating the difference between the two (i.e., the response vector difference). In the second verification, pay attention to the response trend bias and analyze whether the change trend of parameters such as temperature and humidity is consistent with expectations. For example, the temperature should show a continuous downward trend. If there is an abnormal situation of a short-term rebound, the response trend bias will be identified. Through these two verification methods, the control effect can be comprehensively determined, and the actual effect of this regulation in improving the home environment can be clearly understood.

[0069] Based on the determined control effect, targeted feedback control management is performed on home appliances. If the control effect shows that the temperature drops too slowly, the cooling power or wind speed of the air conditioner will be adjusted; if the humidity control does not achieve the expected effect, the operating parameters of the humidifier or dehumidifier will be optimized. By continuously making feedback adjustments based on the control effect, it is ensured that home appliances can always create a comfortable and stable living environment for users.

[0070] Embodiment 2: Figure 2 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an implementation of the present invention. Figure 2 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The electronic device is in the form of a general computing device, and its components may include but are not limited to an input device 201, a processor 202, a memory 203, and an output device 204. Among them, the processor 202 may be one or more; the processor 202 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 203, that is, realizing the above-mentioned home appliance control method combined with whole-house intelligent perception.

[0071] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0073] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for controlling home appliances combined with whole-house intelligent sensing, characterized in that: The method comprises: According to the sensor monitoring module connected to the home appliance, the whole house environment is monitored to determine the multi-source sensor data, wherein the sensor monitoring module includes an external sensor module and a built-in sensor module of the home appliance; According to the device control mode, supervise the training of the intelligent control module and initialize it, wherein the device control mode includes a first control based on multimodal interaction and a second control based on automation logic; Interactively access the network protocol of the home device, and construct an interactive transfer module based on the bidirectional conversion of the device protocol form to the unified protocol form, wherein one end of the interactive transfer module is connected to the home device, and the other end is connected to the intelligent control module; The multi-source sensor data is used for control and management, and control and management are performed in response to the home appliances. The multi-source sensor data is transmitted to the interactive transfer module, data fusion is performed under form conversion, and the data is transferred to the intelligent control module for control and management. The strategy is transmitted back to the interactive transfer module to perform a reverse conversion of the form of the device protocol, and the data is transferred to the corresponding home appliances for control and management.

2. The method for controlling home appliances combined with whole-house intelligent sensing according to claim 1, characterized in that: The supervised training of the intelligent control module and initialization thereof include: Setting environmental standards and determining a predefined rule set, wherein the predefined rule set is used to perform control triggering and dimensional amplitude modulation determination; Acquire control samples, mine fuzzy decision logic, combine the predefined rules, perform sample-driven supervised training, and acquire the intelligent control module; The intelligent control module is initialized, wherein the initialization method is personalized learning based on apartment layout information and user preferences.

3. The method for controlling home appliances combined with whole-house intelligent sensing according to claim 1, characterized in that: Making a control decision on the multi-source sensor data and performing control management in response to the home device includes: receiving user interaction information, making a control decision based on the user interaction information, and determining a first control strategy, wherein the user interaction information includes at least one interaction mode; Determining a second control strategy according to the multi-source sensor data; Proofreading the first control strategy and the second control strategy, if the difference is less than or equal to a preset control difference, taking user interaction control as the first priority, and performing control management of the home appliance based on the first control strategy; If it is greater than or equal to the preset control difference, the home appliance control management is performed based on the second control strategy, and feedback indication is given to the user interaction information.

4. The method for controlling home appliances combined with whole-house intelligent sensing as claimed in claim 3, characterized in that: Determining a second control strategy according to the multi-source sensor data includes: Convert and fuse the multi-source sensor data by converting the device protocol form into a unified protocol form, and determine the fused sensor data; Based on a predefined rule set, the fused sensor data is adjusted to trigger a decision, and an adjustment target is determined by decoupling, wherein the adjustment target includes a pre-adjustment home device-device pre-adjustment target; Guided by the regulation target, an adaptive regulation decision is made to determine the second regulation strategy.

5. The method for controlling home appliances combined with whole-house intelligent sensing as claimed in claim 4, characterized in that: Decoupling determines the regulation objectives, including: Making adjustment trigger decisions on the fused sensor data to determine dimension adjustment requirements, wherein the dimension adjustment requirements include adjusting dimension-dimensional amplitude modulation; Traversing the dimensional adjustment requirements, optimizing the allocation of dimensional adjustment requirements of homologous home appliances based on energy consumption minimization and space constraints, and determining a demand decoupling sequence, wherein each dimensional adjustment requirement corresponds to at least one pre-adjusted home appliance; Based on the home appliance ownership, the demand decoupling sequence is integrated to determine the adjustment target.

6. The method for controlling home appliances combined with whole-house intelligent sensing according to claim 4, characterized in that: Home equipment includes static home equipment and dynamic home equipment: For the adjustment target, determining a static adjustment target and a dynamic adjustment target; Identify the static adjustment target, make parameter control adjustment decisions, and determine the static target strategy; Identify the dynamic adjustment target, make parameter adjustment decisions and path planning, and determine the dynamic target strategy, wherein the path planning constraints are performed based on the apartment layout information; The static target strategy and the dynamic target strategy are integrated as the second regulation strategy.

7. The method for controlling home appliances combined with whole-house intelligent sensing according to claim 1, characterized in that: After responding to the regulation and management of home devices, it includes: Combined with the sensor monitoring module, control tracking is performed to determine control response data; Identify the control response data, perform a first check based on the response vector difference, perform a second check based on the response trend deviation, and determine the control effect; Based on the control effect, feedback control management of household equipment is performed.

8. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the home appliance control method combined with whole-house intelligent sensing as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

Images