Voice control method, device, equipment, system, storage medium and program product

Abstract

This application provides a voice control method, apparatus, device, system, storage medium, and program product. On one hand, voice control based on user expectations offers a novel voice control mode. Users can express their personalized needs by conveying their expected physical or emotional feelings, thereby enabling automatic device control. This achieves intelligent and flexible voice control, embodies a technological feel, and satisfies users' personalized needs. On the other hand, by acquiring user feedback, the system can further understand the user's actual intentions. This allows for the modification of control commands to better match the abstract "expected feelings." Furthermore, the system can gradually learn and understand the user's descriptive habits, making control commands more aligned with the user's actual intentions, improving the accuracy of command conversion, and enhancing the user experience.

Description

Technical Field

[0001] This application relates to the field of equipment control, and in particular to a voice control method, apparatus, device, system, storage medium, and program product. Background Technology

[0002] With the development of science and technology and urban construction, voice recognition technology is gradually being applied to all aspects of people's lives. For example, in office buildings, apartments, schools, shopping malls and other places, devices that can be controlled based on voice, such as smart home devices based on voice control, are becoming increasingly popular.

[0003] As smart home devices become more widespread, users' demands for these devices are also gradually increasing. For example, users hope that home devices can be more intelligent and accurately understand their actual control intentions.

[0004] Current home appliance control systems can only control devices based on voice data that expresses precise control intentions. If the acquired voice data does not express precise control intentions, accurate control commands cannot be generated. When controlling devices based on these commands, the user experience is unsatisfactory and diminishes the overall user experience.

[0005] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of this application and facilitating understanding by those skilled in the art. It should not be assumed that these technical solutions are known to those skilled in the art simply because they have been described in the background section of this application. Summary of the Invention

[0006] The inventors discovered that controlling home appliances based on voice data that expresses precise control intentions requires users to speak clear control commands, which places high demands on users and makes control difficult. In addition, when controlling complex scenarios, controlling one or more home appliances based on only one user's voice may fail to accurately understand the user's actual intentions, thus failing to achieve satisfactory results and reducing the user experience.

[0007] To address at least one of the aforementioned problems, embodiments of this application provide a voice control method, apparatus, device, system, storage medium, and program product.

[0008] According to a first aspect of the embodiments of this application, a voice control method is provided, comprising: acquiring first information related to a user's expected feelings generated based on first voice data; generating a first control command for controlling home appliances in a target space based on the first information; acquiring first feedback information from a user; modifying the first control command into a first modified control command based on the first feedback information; and controlling the home appliances based on the first modified control command.

[0009] According to a second aspect of the embodiments of this application, a voice control system is provided, including: a control device and at least one home appliance, wherein the control device controls the home appliance in a target space based on a first modified control instruction, wherein the first modified control instruction is obtained by modifying a first control instruction based on first feedback information from a user, the first control instruction is generated based on first information, and the first information is generated based on first voice data including information related to the user's intent.

[0010] According to a third aspect of the embodiments of this application, a voice control device is provided, comprising: an information acquisition unit that acquires first information related to a user's expected feelings generated based on first voice data; a generation unit that generates a first control command for controlling home appliances in a target space based on the first information; a feedback information acquisition unit that acquires first feedback information from a user; a correction unit that corrects the first control command into a first corrected control command based on the first feedback information; and a control unit that controls the home appliances based on the first corrected control command.

[0011] According to a fourth aspect of the present application, an electronic device is provided, the electronic device comprising: a memory storing a computer program; and a processor executing the computer program to implement the method described in the first aspect of the present application.

[0012] According to a fifth aspect of the present application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect of the present application.

[0013] According to a sixth aspect of the embodiments of this application, a computer program product is provided, which includes a computer program that, when executed by a processor, implements the method described in the first aspect of the embodiments of this application.

[0014] One of the beneficial effects of this application embodiment is that: for a first control command generated based on first information related to the user's expected feelings, the user's first feedback information on the first control command is obtained, the first control command is corrected based on the first feedback information to obtain a first corrected control command, and the home equipment is controlled based on the first corrected control command.

[0015] On the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their physical or mental expectations. This enables automatic control of devices, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting users' personalized needs.

[0016] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0017] Furthermore, a control command database can be used to generate the first control command based on the first information. This allows for convenient and efficient generation of the first control command.

[0018] Furthermore, if a certain index information (i.e., the first index information) in the index information includes the first information, the control instruction corresponding to the first index information is used as the first control instruction. This ensures the reliability of the first control instruction generated from the control instruction database.

[0019] The modified information of a certain index information (i.e., the second index information) in the index information includes the first information, and the control instruction corresponding to the second index information is used as the first control instruction. This ensures the reliability of the first control instruction generated from the control instruction database and improves the success rate of generating the first control instruction.

[0020] Based on the similarity between each index and the first information, a third index can be selected, and the control instruction corresponding to the third index can be used as the first control instruction. This ensures the reliability of the first control instruction generated from the control instruction database and improves the success rate of generating the first control instruction.

[0021] Furthermore, if it is impossible to generate a first control command for controlling home appliances within the target space based on the first information, the first feedback information can be directly obtained, and a first corrective control command can be generated based on the first feedback information. This allows for understanding the user's actual intentions, improves the matching degree between control commands and the user's "expected feelings," and enhances control efficiency.

[0022] Furthermore, if the interaction information generated based on the user's second voice data is obtained, it can be confirmed whether the interaction information is the first feedback information in response to the first control command. This allows for a more accurate understanding of the user's control intentions, and consequently, reliable correction of the first control command.

[0023] Furthermore, after generating the first corrected control command based on the first feedback information, the first corrected control command can be stored in the control command database. This allows the system to control home appliances based on the first corrected control command the next time the user expresses the same or similar expectations. Thus, the control commands converted from voice data can be continuously corrected or improved, and the system can learn and understand the user's voice description habits. This enables the system to more accurately capture the user's actual intentions and translate them into appropriate control commands, making the device control scenario more closely match the user's "expectations" and improving the user experience.

[0024] Furthermore, in addition to recording the first information and the corresponding first corrected control instruction in the control instruction database, the first state information of the target space when the first control instruction was generated can also be recorded. Since controlling according to the first corrected control instruction may no longer achieve the user's "expected experience" if the state of the target space changes, by storing the first information, the first corrected control instruction, and the target space's state information in the control instruction database, when the same or similar user description is subsequently obtained, the target space's state information can be used to determine whether to control according to the first corrected control instruction. This ensures the reliability of the executed control instructions and further improves the user experience.

[0025] Furthermore, if interactive information generated based on the user's second voice data is obtained, it can be confirmed whether this interactive information is indeed the second type of information. This allows for a more accurate understanding of the user's control intentions, thereby enabling a more reliable next round of control.

[0026] Furthermore, the control command database can store the first modified control command according to different users. This allows for personalized control needs to be met for different users, further improving the user experience.

[0027] Specific embodiments of this application are disclosed in detail with reference to the following description and accompanying drawings, indicating how the principles of this application can be adopted. It should be understood that the embodiments of this application are not limited in scope. Within the spirit and scope of the appended claims, embodiments of this application include many changes, modifications, and equivalents.

[0028] The feature information described and illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with feature information in other embodiments, or substituted for feature information in other embodiments.

[0029] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, whole, step, or component, but does not exclude the presence or addition of one or more other features, wholes, steps, or components. Attached Figure Description

[0030] Many aspects of this application can be better understood by referring to the following accompanying drawings. The components in the drawings are not drawn to scale, but are only intended to illustrate the principles of this application. Corresponding portions in the drawings may be enlarged or reduced for ease of illustration and description of certain parts of this application. Elements and features described in one drawing or embodiment of this application may be combined with elements and features shown in one or more other drawings or embodiments. Furthermore, similar reference numerals in the drawings denote corresponding components in several drawings and can be used to indicate corresponding components used in more than one embodiment.

[0031] In the attached diagram:

[0032] Figure 1 This is a schematic diagram of a voice control method according to an embodiment of this application;

[0033] Figure 2 This is another schematic diagram of the voice control method according to an embodiment of this application;

[0034] Figure 3 This is a schematic diagram of a voice control system according to an embodiment of this application;

[0035] Figure 4 This is a configuration diagram of the voice control system used in the control method of this application embodiment;

[0036] Figure 5 This is a schematic diagram of a voice control device according to an embodiment of this application;

[0037] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0038] The preferred embodiments of this application will now be described with reference to the accompanying drawings.

[0039] Example 1

[0040] Embodiment 1 of this application provides a voice control method.

[0041] Figure 1 This is a schematic diagram of a voice control method according to an embodiment of this application. Figure 1 As shown, the method includes:

[0042] Step 101: Obtain first information related to the user's expected feelings, generated based on the first voice data;

[0043] Step 102: Generate a first control command for controlling home appliances within the target space based on the first information;

[0044] Step 103: Obtain the user's first feedback information, and modify the first control command into a first modified control command based on the first feedback information; and

[0045] Step 104: Control home appliances based on the first correction control command.

[0046] According to the above embodiments, for a first control command generated based on first information related to the user's expected feelings, first feedback information from the user regarding the first control command is obtained, the first control command is corrected based on the first feedback information to obtain a first corrected control command, and the home appliances are controlled based on the first corrected control command.

[0047] On the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their physical or mental expectations. This enables automatic control of devices, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting users' personalized needs.

[0048] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0049] The voice control method of this application is not only applicable to home scenarios, such as residences and apartments, but also to commercial or public scenarios such as office buildings, shopping malls, schools, and factories. This application does not limit the application scenarios of the voice control method.

[0050] The voice control method of this application embodiment is used to control home devices. The home devices in this application embodiment can be various devices deployed in various application scenarios such as home scenarios, commercial scenarios or public scenarios to adjust the indoor environment or meet user needs. This application embodiment does not limit the types of home devices.

[0051] The voice control method of this application embodiment can control home appliances in a target space, that is, the target space is an indoor space that serves as the target for environmental regulation.

[0052] The target space in this application embodiment may include one or more indoor spaces, such as a living room, bedroom, kitchen, bathroom, etc.

[0053] In some embodiments, home appliances may be smart home appliances, such as air handling equipment and smart devices.

[0054] For example, smart devices include at least one of smart speakers, smart display devices, smart switches, smart curtains, smart lighting devices, sensors, and smart pet devices.

[0055] In some embodiments, the air handling unit affects the indoor space within the target space.

[0056] For example, at least one air handling unit is installed in the target space. In some embodiments, indoor units are installed in each indoor space within the target space, or indoor units are installed in some indoor spaces within the target space.

[0057] For example, air handling equipment can be associated with indoor spaces in a target space. For instance, the correspondence between air handling equipment and indoor spaces can be determined through the binding information of the air handling equipment.

[0058] In some embodiments, the air handling unit may not be installed in the target space's interior space, but it may still affect the target space's interior space. For example, a fresh air unit with its main unit installed above the ceiling.

[0059] In some embodiments, the air handling equipment includes at least one of an indoor unit, a humidifier, a dehumidifier, a fresh air system, an air purifier, a fragrance component, a floor heating system, and a valve assembly.

[0060] In addition, air handling equipment can also be called air conditioning equipment.

[0061] In some embodiments, the indoor unit is an indoor unit in an air handling system that includes air handling equipment, and the air handling system may include a commercial air conditioning system or a residential air conditioning system.

[0062] In some embodiments, an air conditioning system may include at least one set of outdoor units and at least one indoor unit connected to each set of outdoor units. That is, an air conditioning system may include one or more sets of outdoor units, each set of outdoor units including at least one outdoor unit; for each set of outdoor units, the set of outdoor units is connected to at least one indoor unit.

[0063] For example, an air conditioning system includes an outdoor unit and an indoor unit connected to the outdoor unit.

[0064] For example, an air conditioning system includes an outdoor unit and at least two indoor units connected to the outdoor unit.

[0065] For example, an air conditioning system includes at least two outdoor units and at least two indoor units connected to the at least two outdoor units.

[0066] For example, a group of outdoor units and at least one indoor unit connected to the group of outdoor units constitute a refrigerant system, or multiple groups of outdoor units and at least one indoor unit connected to the multiple groups of outdoor units respectively constitute multiple refrigerant systems. Thus, an air conditioning system may include one refrigerant system or multiple refrigerant systems.

[0067] In some embodiments, the outdoor unit and the indoor unit can be air conditioning equipment of various models, types, forms, and capacities. For example, the indoor unit can be in the form of four-sided air outlet, two-sided air outlet, duct unit, floor air outlet, or skirting board air outlet, etc.; the outdoor unit can be in the form of single fan top air outlet, dual fan top air outlet, single fan front air outlet, or dual fan front air outlet, etc.

[0068] In some embodiments, the fresh air equipment includes at least one of a fresh air handling device, a total heat exchange device (e.g., with or without internal circulation function), and a ventilation device (e.g., with or without internal circulation function).

[0069] In some embodiments, at least one of the humidifying device and the dehumidifying device is disposed on the output side of the fresh air device to humidify or dehumidify the air output by the fresh air device, for example, to humidify or dehumidify the air output by the fresh air device, and to introduce the humidified or dehumidified air into the indoor space. For example, at least one of the humidifying device and the dehumidifying device has a heat exchanger that can operate as an evaporator.

[0070] In some embodiments, the underfloor heating system is connected to the outdoor unit via refrigerant piping, and to the indoor underfloor heating radiator piping via underfloor heating water piping. For example, the outdoor unit and the underfloor heating system form an air-source heat pump water heater, utilizing heat from the air and the operation of the compressor to heat water. The underfloor heating system may include a water-heat exchange unit, where refrigerant from the outdoor unit's compressor enters the unit via refrigerant piping to exchange heat with the water, thereby heating the water. The heated water is then introduced into the indoor underfloor heating radiator piping via the underfloor heating water piping to provide heating for the indoor space. In some embodiments, the outdoor unit and the underfloor heating system are separate units, or they are integrated.

[0071] In some embodiments, the valve assembly includes at least one of an air valve and a floor heating valve.

[0072] In some embodiments, the air valve for controlling the air volume of the indoor space is, for example, an air valve for controlling the amount of air supplied to the indoor space by the air supply device. For example, when the external circulation function of the total heat exchanger is turned on, the air valve for controlling the air volume of the indoor space can control the air volume of the outdoor air introduced into the indoor space; when the internal circulation function of the total heat exchanger is turned on, the air valve for controlling the air volume of the indoor space can control the air volume of the indoor air introduced into the indoor space.

[0073] In some embodiments, the floor heating valve is used to control the opening and closing of the inlet and outlet pipes in the floor heating system.

[0074] In some embodiments, the voice data used to generate control commands in step 101 can be obtained from a local device.

[0075] In some embodiments, the local device includes at least one of a controller (also known as a control device), an indoor air conditioning unit, a smart device, and a user terminal.

[0076] In some embodiments, the controller includes at least one of a central controller, a wired controller, and a remote controller.

[0077] In some embodiments, the central controller and the wired controller are fixed controllers, for example, fixed to a wall in an indoor space.

[0078] In some embodiments, the central controller may be installed in multiple indoor spaces, that is, the central controller is configured to correspond to all or part of the indoor spaces.

[0079] This allows for the full utilization of various devices as local devices for voice data acquisition, improving the utilization rate of local devices, thereby reducing the cost of voice data acquisition and improving the efficiency and flexibility of voice data processing.

[0080] In some embodiments, smart devices include at least one of smart speakers, smart display devices, smart switches, smart curtains, smart lighting devices, sensors (e.g., air sensors, temperature sensors, humidity sensors, etc.), and smart pet devices.

[0081] In some embodiments, voice data may be acquired through a first local device, and the voice data may be an audio signal.

[0082] For example, the audio signal can be directly acquired by the first local device, or it can be acquired by the second local device and then sent to the first local device. For instance, the centralized controller can act as the first local device to directly acquire the audio signal, or an indoor air conditioning unit or smart device can act as the second local device to acquire the audio signal and then send the acquired audio data to the centralized controller, which is acting as the first local device. This application does not limit the method of acquiring voice data.

[0083] For example, after a user enables the voice control function of a first local device (e.g., a centralized controller), voice monitoring is activated to acquire the monitored voice data. Another example is that the first local device (e.g., the centralized controller) has a control interface that interacts with the user, allowing the user to perform related operations through the interface.

[0084] In some embodiments, the scope of the activated voice monitoring is a target space. Voice monitoring is activated after user confirmation before it can be performed on the target space. For example, the user can confirm or set the settings in the control interface of the central controller to activate the voice monitoring and voice control functions. Alternatively, the user can also set the scope of voice monitoring in the control interface.

[0085] In addition, the scope of the activated voice monitoring may not be the target space or may not be limited to the target space. For example, if the user is currently in the living room and wants to control the home appliances in the bedroom, then the target space is the bedroom, and the scope of the activated voice monitoring includes the living room, or includes both the living room and the bedroom.

[0086] In some embodiments, the voice data includes first information related to the user's expected feelings.

[0087] In the embodiments of this application, "user's expected feeling" refers to an abstract description of the feeling that the user expects to experience.

[0088] In some embodiments, "expected" means that the user is willing or wants to obtain it.

[0089] In some embodiments, the sensation may include at least one of a bodily sensation and a mood sensation.

[0090] In some embodiments, bodily sensation refers to the body's perception of the environment, which may be associated with at least one of scene, location, weather, season, and time. Examples include "a summer breeze," "the West Lake in April," "the refreshing feeling after the rain," and "a mountain after a fresh rain."

[0091] In some embodiments, mood refers to at least one of the feelings and emotions evoked about things or people. For example, "the taste of love," "longing like the wind," or "the feeling of a sunny young man."

[0092] In this way, recognition can be performed on the voice data based on the aforementioned content of "user's expected feelings".

[0093] For example, the first information may include a first category of information related to the user's expectations and a second category of information related to the user's feelings.

[0094] The first category of information may include first descriptive information expressing an expectation or desire, such as first keywords. For example, "I want," "I expect," "I hope," "I want," "I think," "I need," "give me," "help me," "I hope," etc. Or, the first descriptive information may include sentences or phrases that have the meaning of "expectation or desire," such as "It would be great if I could..." "It feels so good to...," etc.

[0095] The second category of information may include a second descriptive information expressing feelings. This second descriptive information may not include descriptive information related to home appliances or control commands. That is, the second category of descriptive information to be identified is an abstract description of feelings, rather than control commands for the appliances. The second descriptive information may include, for example, second keywords such as "April," "summer," or "sunny day," or it may include sentences or phrases with the meaning of "feeling," such as "after a rain in the empty mountains" or "the taste of love."

[0096] In this way, by abstracting the user's "expectations and feelings," it is possible to achieve automatic control that reflects the user's actual control intentions, further enhancing the intelligence and technological feel of voice control and improving the user experience.

[0097] The second descriptive information expressing a feeling may include at least one of a third descriptive information expressing a physical sensation and a fourth descriptive information expressing a mood. Specifically, the third descriptive information expressing a physical sensation includes at least one of scene, location, weather, season, and time, while the fourth descriptive information expressing a mood includes at least one of subjective experience and emotion.

[0098] In some embodiments, the first information can be obtained in various ways in step 101. For example, one way is to generate the first information based on the first voice data, and another way is to receive the first information generated by another device. This application does not impose specific limitations on this.

[0099] In some embodiments, the first information can be generated in various ways. For example, a first category of information and a second category of information can be identified in the voice data; when the voice data contains both first category of information and second category of information, the information obtained by combining the first category of information and the second category of information is used as the first information. This application does not specifically limit the method of identifying the first category of information and the second category of information in the voice data. For example, the voice data can be converted into text data, and the first category of information and the second category of information can be identified in the text data. Thus, the relevant information of "expected feeling" can be identified simply and quickly. Alternatively, the first category of information and the second category of information can be identified in the voice data by sound wave matching. For example, sound wave matching can be performed on the voice data, matching the sound waves of the voice data with preset sound wave data. If the match is successful, the first category of information and the second category of information in the voice data can be determined, thereby enabling the identification of the relevant information of "expected feeling" without recognizing the content of the voice data, reducing the risk of user privacy leakage.

[0100] In some embodiments, in step 102, a first control instruction may be generated based on the first information in various ways.

[0101] For example, based on the first information, the environmental parameters that need to be adjusted and the target values ​​of the environmental parameters can be determined, and a first control command can be generated based on the determined environmental parameters that need to be adjusted, the target values ​​of the environmental parameters, and the home appliances used to adjust the environmental parameters.

[0102] This application is not limited to this. For example, after determining the environmental parameters that need to be adjusted and the target value of the environmental parameters based on the first information, it can also determine whether the control based on the home appliances in the target space can adjust the environmental parameters in the target space to the target value based on the capabilities of the home appliances in the target space; and if it is determined that the environmental parameters in the target space can be adjusted to the target value, control instructions for the home appliances are generated based on the environmental parameters, the target value of the environmental parameters and the home appliances used to adjust the environmental parameters, etc.

[0103] In this way, when controlling the device based on first information related to the user's expected feelings, the system determines whether it is possible to adjust the environmental parameters in the target space to the target value based on the first information and the target value of the environmental parameters, and based on the capabilities of the home appliances in the target space. If it is determined that it is possible, the system performs the corresponding control, thereby taking into account the capabilities of the devices actually deployed on site to execute control that conforms to the actual situation.

[0104] In some embodiments, environmental parameters may include at least one of the following parameters: air quality parameter, light parameter, sound parameter, and odor parameter. For example, environmental parameters may be adjusted by at least one home appliance deployed within the target space.

[0105] For example, air quality parameters include at least one of the following: temperature, humidity, carbon dioxide concentration, fine particulate matter (e.g., PM2.5) concentration, inhalable particulate matter (e.g., PM10) concentration, volatile organic compound (VOC) concentration, indoor total organic matter (TVOC) concentration, nitrogen oxide concentration, ozone concentration, wind speed, and wind direction. Air quality parameters can be regulated by air handling equipment (e.g., at least one of indoor units, humidifiers, dehumidifiers, fresh air systems, air purifiers, fragrance diffusers, and underfloor heating systems) and cleaning equipment (e.g., robotic vacuum cleaners) within the target space.

[0106] For example, lighting parameters include at least one of the following: light intensity, color, direction, and range. Lighting parameters can be adjusted by lighting equipment, curtains, etc., within the target space.

[0107] For example, sound parameters include sound volume and sound content. These sound parameters can be adjusted by audio-visual devices within the target space, such as smart speakers and smart TVs.

[0108] For example, odor parameters include the various types of odors in the air and their concentrations. These odor parameters can be adjusted, for example, by fragrance components within the target space.

[0109] In some embodiments, the environmental parameters that need to be adjusted and the target values ​​of those environmental parameters can be determined in various ways based on first information related to the user's expected feelings.

[0110] In some embodiments, first information or a question based on the first information can be input into a first model, which then outputs environmental parameters matching the first information and their target values. For example, the first model is a big data model, an AI question-answering model, or an AI search engine.

[0111] For example, if the "first information" is "a gentle breeze in the shade in summer", and the big data model is input with "a gentle breeze in the shade in summer", the big data model will output "temperature 26 degrees, no direct sunlight, wind force level 1".

[0112] For example, if the "first information" is "West Lake in April", and the AI ​​question-answering model is input with "What are the air parameters of West Lake in April", the AI ​​question-answering model will output "Temperature 18-20 degrees, humidity 70-80%, wind force 1-2".

[0113] For example, if the "first information" is "the taste of love", and you input "how to create the taste of love" into the AI ​​question-answering model, the AI ​​question-answering model will output "temperature 22-25 degrees, soft lighting, play light music".

[0114] In some embodiments, it can be determined whether the control based on the home appliances in the target space can adjust the environmental parameter in the target space to the target value, based on the capabilities of the home appliances in the target space.

[0115] For example, as mentioned above, if the "first information" is "a cool breeze in the shade during summer", the environmental parameters output by the big data model are "temperature 26 degrees, no direct sunlight, wind force level 1". The target space is a bedroom, which is equipped with an air conditioner that can adjust the temperature and wind force, smart curtains and smart lighting equipment. Therefore, it has the ability to adjust the environmental parameters in the target space to the target value.

[0116] For example, as mentioned above, in the case where the "first information" is "the West Lake in April", the environmental parameters output by the artificial intelligence question answering model are "temperature 18-20 degrees, humidity 70-80%, wind force 1-2". The target space is the living room, which is equipped with an air conditioner that can adjust the temperature, humidity and wind force, and also has a humidifier that can adjust the humidity. Therefore, it has the ability to adjust the environmental parameters in the target space to the target value.

[0117] For example, as mentioned above, when the "first information" is "the taste of love", the environmental parameters output by the AI ​​question-answering model are "temperature 22-25 degrees, soft lighting, playing light music". The target space is the living room. However, the living room is only equipped with air conditioning and cannot automatically adjust the lighting and play light music. Therefore, it does not have the ability to adjust the environmental parameters in the target space to the target value.

[0118] In some embodiments, when it is determined that the environmental parameter within the target space can be adjusted to the target value, a first control command for the home appliance can be generated in various ways based on the environmental parameter, the target value of the environmental parameter, and the home appliance used to adjust the environmental parameter.

[0119] In some embodiments, environmental parameters, target values ​​of the environmental parameters, and home appliances used to adjust the environmental parameters can be input into a second model, which then outputs a first control command. For example, the second model is a trained deep learning model.

[0120] For example, as mentioned above, for the case where the "first information" is "a cool breeze in the shade during summer", the environmental parameters output by the big data model are "temperature 26 degrees, no direct sunlight, wind force level 1". The first control command generated by the second model is "adjust the air conditioner temperature to 26 degrees, adjust the air volume to low, and close the sheer curtains in the curtains". In addition, based on the detection results of the user's location, the control command can also include instructions for adjusting the air conditioner's airflow direction.

[0121] For example, as mentioned above, for the case where the "first information" is "West Lake in April", the environmental parameters output by the AI ​​question-answering model are "temperature 18-20 degrees, humidity 70-80%, wind force 1-2". The first control command generated by the second model is "adjust the air conditioner temperature to 20 degrees, adjust the air volume to low, and adjust the target humidity of the humidifier to 70%". In addition, based on the detection results of the user's location, the control command can also include instructions for adjusting the air conditioner's airflow direction.

[0122] In some embodiments, a control instruction database can be pre-stored, and a first control instruction can be generated based on first information using this database. The control instruction database may include index information related to the user's expected experience and the corresponding control instructions. This allows for convenient and efficient generation of the first control instruction.

[0123] Table 1 is a schematic diagram of the control instruction database. As shown in Table 1, the control instruction database includes index information I related to the user's expected feelings and control instructions C corresponding to the index information.

[0124] Table 1

[0125] Index Information I Control command C I1 "Summer Breeze" C1 "Cooling at 27℃, with low fan speed" ... …

[0126] As shown in Table 1, the index information I1 is "summer breeze", and the corresponding control instruction C is to "cool to 27°C and turn on breeze".

[0127] In some embodiments, if a certain index information (i.e., the first index information) in the index information includes the first information, the control instruction corresponding to the first index information is used as the first control instruction. This ensures the reliability of the first control instruction generated from the control instruction database.

[0128] For example, the first information is "summer breeze". As shown in Table 1, the index information I1 in the control instruction database includes this first information. Therefore, the control instruction C1 "cooling to 27°C, turn on breeze" corresponding to the index information I1 is taken as the first control instruction corresponding to the first information.

[0129] In some embodiments, if none of the index information in the index information includes the first information, and the modified information of a certain index information (i.e., the second index information) in the index information includes the first information, the control instruction corresponding to the second index information is used as the first control instruction.

[0130] Therefore, the reliability of the first control command generated from the control command database can be guaranteed, and the success rate of generating the first control command can be improved.

[0131] For example, the control instruction database may also store one or more variant information I' of index information I, which may be information with a similar or related meaning to index information I.

[0132] For example, Table 2 is another illustration of a control instruction database. As shown in Table 2, the control instruction database includes index information I related to the user's expected feelings, variant information I' of index information I, and control instructions C corresponding to the index information.

[0133] Table 2

[0134]

[0135] Among them, the index information I1 is "summer breeze", the corresponding variant information I1' is "summer breeze", "summer breeze", etc., and the corresponding control command C is "cooling to 27°C, turn on low wind".

[0136] When the first information is "summer breeze", the modified information I1' of the index information I1 includes the first information. Therefore, the control command C1 "cooling to 27°C, turn on breeze" corresponding to the index information I1 is taken as the first control command corresponding to the first information.

[0137] In some embodiments, the deformation information may be preset by the user or set through interaction with the user; or generated by a natural language processing-based model. This application does not limit the method of obtaining deformation information.

[0138] Taking the transformation information set through user interaction as an example:

[0139] The first information is "summer breeze," as shown in Table 1. Index information I does not include this first information, or, as shown in Table 2, neither index information I nor variant information I' includes this first information. In this case, information similar to the first information can be selected from the index information in Table 1 or the index information and variant information in Table 2, and this information can be displayed to the user. For example, index information I1 can be selected as the information similar to the first information, and the user can be interacted with based on index information I1, asking, "Is it 'summer breeze'?" If the user confirms yes, the control command C1 corresponding to index information I1, "cool to 27°C, turn on low speed," is used as the first control command corresponding to the first information, and this first information is added to variant information I1.

[0140] In some embodiments, if none of the index information in the index information includes the first information, a third index information can be selected based on the similarity between each index information and the first information, and the control instruction corresponding to the third index information can be used as the first control instruction.

[0141] Therefore, the reliability of the first control command generated from the control command database can be guaranteed, and the success rate of generating the first control command can be improved.

[0142] The specific method for determining the similarity between the index information and the first information can be found in relevant technologies, and will not be elaborated upon in this application.

[0143] In some embodiments, the third index information may be the index information with the highest similarity to the first information.

[0144] For example, the first information is "summer breeze". Index information I does not include the first information. However, the similarity between index information I1 and the first information is higher than that between other index information and the first information. Therefore, the control instruction C1 "cooling to 27°C, turn on breeze" corresponding to index information I1 can be used as the first control instruction corresponding to the first information.

[0145] In some embodiments, in step 103, first feedback information from the user can be obtained, and the first control command can be modified into a first modified control command based on the first feedback information.

[0146] For example, after generating a first control command based on the first information and before controlling the home appliances according to the first control command, the user's first feedback information is obtained in order to confirm whether the first control command matches the user's "expected feeling", that is, whether the user's "expected feeling" can be achieved after controlling the home appliances according to the first control command.

[0147] If the user agrees to the first control instruction, the home appliances are controlled according to the first control instruction; if the user does not agree to the first control instruction, the first control instruction is modified into a first modified control instruction based on the user's first feedback information, and the home appliances are controlled according to the first modified control instruction.

[0148] This application is not limited to this; it can also obtain the user's first feedback information during the process of controlling home appliances according to the first control command. In other words, after generating the first control command, the home appliances can be run for a period of time based on the first control command. In this way, the user can intuitively judge whether the first control command matches the "expected feeling" based on the effect of the trial run, which facilitates the user's subsequent operation and feedback.

[0149] If the user approves of the trial operation results, the home appliances will continue to be controlled according to the first control command; if the user does not approve of the trial operation results, the first control command will be modified into a first modified control command based on the user's first feedback information, and the home appliances will be controlled according to the first modified control command.

[0150] Furthermore, during the process of controlling home appliances according to the first corrective control command, user feedback information can also be received, and the first corrective control command can be corrected based on the feedback information in order to more reliably achieve the user's "expected feeling".

[0151] In some embodiments, after generating the first control command, in step 103, if interactive information generated based on the user's second voice data is obtained, it can be confirmed whether the user's interactive information is the first feedback information in response to the first control command.

[0152] For example, after a user expresses their desired feeling, the user realizes that their description is problematic, or the user's desired feeling changes. In this case, the interaction information is not a feedback to the first control instruction related to the previous desired feeling, but a new control intention that is different from the previous desired feeling.

[0153] Therefore, by confirming whether the user's interaction information is the first feedback information in response to the first control command, the user's control intention can be understood more accurately, and the control command can be reliably corrected.

[0154] In some embodiments, if it is confirmed that the interaction information is first feedback information in response to the first control command, the first control command is modified into a first modified control command based on the first feedback information.

[0155] If it is confirmed that the interactive information is not the first feedback information for the first control command, for example, if the interactive information is used to distinguish a new control intention from the first information, the interactive information can be used as the new first information and step 102 can be re-executed, or the interactive information can be used as the second information described later and step 105 or step 108 described later can be executed.

[0156] In some embodiments, it can be confirmed in various ways whether the interactive information is the first feedback information in response to the first control command.

[0157] For example, confirmation can be obtained through user interaction. For instance, after receiving user interaction information, a confirmation message can be read aloud, displayed, or pushed to the user to confirm whether the interaction information is a response to the first control command.

[0158] For example, confirmation can be based on the time of receiving user interaction information. For instance, if user interaction information is received within a preset time period from the start of the control operation according to a first control command, this interaction information can be considered feedback information regarding the first control command.

[0159] In some embodiments, initial user feedback can be obtained through interaction with the user. This interaction can include voice interaction, push notifications, etc.

[0160] For example, the aforementioned local device can be used to verbally broadcast information related to the first control command to the user. The local device can also receive the user's voice input to generate first feedback information.

[0161] For example, information related to the first control command can be pushed to the user through a local device with display capabilities, as mentioned above. The user's input information can be obtained through this local device to generate first feedback information. This application does not limit the specific method of obtaining the first feedback information.

[0162] In some embodiments, a first correction control instruction can be generated based on first feedback information in various ways. For example, at least one of the following can be generated based on the first feedback information: first correction information for correcting an environmental parameter that needs to be adjusted, or second correction information for correcting a target value of the environmental parameter. Based on at least one of the first correction information and the second correction information, the first control instruction is corrected into a first correction control instruction.

[0163] The first feedback information may include instructions to adjust environmental parameters or target values, such as "turn the temperature up a little", "adjust the humidity to 40%", "turn the fan speed to the minimum", etc., or it may include information indicating the user's current feelings, such as "it's a little hot", "it's too bright", "it's too stuffy", etc.

[0164] In some embodiments, first correction information can be generated based on first feedback information in various ways.

[0165] Taking the first feedback information, which includes instructions to adjust environmental parameters, as an example:

[0166] When the first feedback information includes instructions to adjust environmental parameters, the first correction information can be generated directly based on the first feedback information.

[0167] For example, if the instruction message is "turn the temperature up slightly", then the first correction message is "indoor temperature"; if the instruction message is "turn the fan speed to the minimum", then the first correction message is "operating fan speed"; and so on.

[0168] Taking the first feedback information, which includes information indicating the user's current feelings, as an example:

[0169] When the first feedback information includes information representing the user's current feelings, first correction information can be generated based on the correspondence between the pre-stored feelings and environmental parameters.

[0170] For example, the environmental parameter corresponding to the feeling "it's a bit hot" is "indoor temperature"; the environmental parameters corresponding to the feeling "it's too stuffy" are "indoor humidity" and "carbon dioxide concentration"; and so on.

[0171] In some embodiments, second correction information can be generated based on the first feedback information in various ways.

[0172] Taking the first feedback information, which includes instructions to adjust the target value, as an example:

[0173] If the first feedback information includes numerical information of the target value, the second correction information can be generated directly based on that numerical information.

[0174] For example, if the instruction in the first feedback information is "adjust humidity to 40%", then the second correction information is "40%"; if the instruction is "turn the fan speed to minimum", then the second correction information is "minimum fan speed"; if the temperature target value of the first control command is 20℃, and the instruction in the first feedback information is "increase the temperature by 2℃", then the second correction information is "22℃"; and so on.

[0175] If the first feedback information does not include numerical information of the target value, but includes a correction trend of the target value, then the second correction information can be determined based on the correction trend.

[0176] For example, the instruction in the first feedback message is "increase the airflow," meaning that the target value of the environmental parameter "airflow" is being corrected to "increase" the airflow. If the "airflow" in the first control command is "low," the second correction message could be to increase the airflow to "medium."

[0177] Furthermore, the second correction information can also be determined based on this correction trend and the first state information of the target space. This allows for the determination of target values ​​for environmental parameters by combining the actual state of the target space, which helps improve the reliability and accuracy of the target values.

[0178] In some embodiments, the first state information of the target space may include at least one of the following: device information, environmental parameters, seasonal information, time information, geographical location information, user information, and energy-saving information of the target space.

[0179] The device information may include the capability information of the home appliances (first home appliances) included in the target space. This allows the target value to be set within the capability range of the home appliances, ensuring the executability of control commands.

[0180] Environmental parameters can include at least one of the following: air quality parameters, light parameters, sound parameters, and odor parameters within the target space. Therefore, target values ​​can be set based on the current environmental parameters to ensure user comfort. Furthermore, since different environmental parameters can correspond to different home appliances, when control commands are associated with multiple home appliances, corresponding target values ​​can be set according to different environmental parameters.

[0181] For details regarding environmental parameters, please refer to the aforementioned content; further explanation will not be provided here.

[0182] User information may include at least one of the following: user attribute information, status information, and usage habit information within the target space. Therefore, by combining the current user information within the target space, the target value can be set to a value that matches the user, thereby ensuring user comfort and enabling personalized settings.

[0183] User attributes may include at least one of the following: user's gender, age, nationality, region, etc.

[0184] A user's status can include at least one of the following: awake or asleep, healthy or sick, emotional state, etc.

[0185] Energy-saving information may include at least one of the following: the operating power, operating time, operating mode, number of devices, and device type of the home appliances associated with the control command. Therefore, target values ​​can be set based on the energy consumption information of the furniture and appliances in the current target space, thereby ensuring the energy efficiency of the control commands.

[0186] Taking the first feedback information, which includes information indicating the user's current feelings, as an example:

[0187] Since the perceived information in the first feedback information does not include the numerical information of the target value, the correction trend of the target value can be determined based on the perceived information, and the second correction information can be determined based on the correction trend.

[0188] For example, the correspondence between perceived information and correction trends can be stored in advance, and the correction trend of the target value can be determined based on the correspondence.

[0189] For example, the corrective trend for the perceived information "it's a bit hot" is "lower indoor temperature"; the environmental parameters for the perceived information "it's too stuffy" are "lower indoor humidity" and "lower carbon dioxide concentration"; and so on.

[0190] Furthermore, after determining the correction trend of the target value based on this perceived information, a second correction information can also be determined based on this correction trend and the first state information of the target space. This allows for the determination of the target value of the environmental parameters by combining the actual state of the target space, which helps improve the reliability and accuracy of the target value.

[0191] In some embodiments, when determining the second correction information based on the correction trend, other information in the first feedback information may also be considered.

[0192] For example, the second correction information can be related to the number of first feedback information pieces that show the same correction trend within a preset time period.

[0193] For example, in the process of controlling home appliances according to the first control command, the more times the user indicates the first feedback information with the same correction trend within a preset time period, the greater the adjustment range of the second correction information can be.

[0194] For example, if the first feedback information includes correction level information, the second correction information can also be determined based on the correction level information.

[0195] For example, consider two different first feedback messages: F1 is "Turn the temperature up a little" and "It's a bit cold," while F2 is "Turn the temperature up a bit more" and "It's too cold." Since F1 and F2 include different levels of correction ("slightly" and "a bit," "a bit more" and "too cold"), the corresponding second correction messages can be different. For instance, the adjustment range of the second correction message for F2 might be larger than that for F1.

[0196] In some embodiments, if it is impossible to generate a first control command for controlling home appliances in the target space based on the first information, the first feedback information can be obtained directly, and a first correction control command can be generated based on the first feedback information.

[0197] This allows us to understand the user's actual intentions, improve the match between control commands and the user's "expected feelings," and increase control efficiency.

[0198] For example, if the index information in the control instruction database does not include the first information, or the variant information of the index information does not include the first information, or the similarity between the index information and the first information is lower than a preset similarity threshold, the first feedback information is directly obtained, and the first correction control instruction is generated based on the first feedback information.

[0199] In some embodiments, after generating a first corrected control command based on the first feedback information, the first corrected control command can be stored in a control command database so that when the user expresses the same or similar expectations again, the home appliances can be controlled according to the first corrected control command. This allows for continuous correction and improvement of control commands converted from voice data, learning and understanding the user's voice description habits, enabling the system to more accurately capture the user's actual intentions and convert them into appropriate control commands. This makes the device control scenario more closely resemble the user's "expectations," improving the user experience.

[0200] For example, such as Figure 1 As shown, the voice control method may further include:

[0201] Step 105: Record the first information and the corresponding first correction control command in the control command database; and

[0202] Step 106: Obtain second information related to the user's expected feelings generated based on the second voice data. If the second information is included in the first information or a variant of the first information, control the home appliances according to the first correction control command corresponding to the first information.

[0203] This allows for the rapid and accurate determination of the user's actual intent and the execution of corresponding controls, further enhancing the user experience.

[0204] In some embodiments, similar to the first feedback information, in step 106, if interaction information generated based on the user's second voice data is obtained, it can be confirmed whether the user's interaction information is the second information. This allows for a more accurate understanding of the user's control intentions, and thus enables a reliable new round of control.

[0205] In some embodiments, it can be confirmed in various ways whether the interactive information is the second information.

[0206] For example, confirmation can be obtained through user interaction. For instance, after receiving user interaction information, a confirmation message can be read aloud, displayed, or pushed to the user to confirm whether the interaction information is the second piece of information.

[0207] For example, confirmation can be based on the time when the user's interaction information is received. For instance, during control operations according to a first control command, if a user's interaction information is received after a preset time period from the start of the control, this interaction information can be considered the second piece of information.

[0208] For example, confirmation can be made based on the number of times the same or similar user interaction information is received. For instance, in multiple control processes, if the same or similar first information is obtained, and the same or similar user interaction information is received repeatedly during the control process based on the control command corresponding to that first information, then the interaction information is likely feedback information in response to that control command; if the interaction information appears only once or a few times, then the interaction information is likely second information.

[0209] For example, a user's desired feeling is "wanting to breathe fresh air," and the corresponding control command is "turn on the fresh air." During the control process based on this command, the user instructs "reduce humidity."

[0210] If, during multiple attempts to control the "start fresh air" function based on the user's desire for "fresh air," the user repeatedly requests to "reduce humidity," then it's highly likely that the "reduce humidity" instruction is a response to the "start fresh air" function.

[0211] If, in multiple attempts to "start fresh air" based on the desire for "fresh air," only one instruction to "reduce humidity" is received, then "reduce humidity" is likely to correspond to a new control intention.

[0212] In some embodiments, in addition to recording the first information and the first corrective control instruction corresponding to the first information in the control instruction database, the first state information of the target space when the first control instruction is generated may also be recorded accordingly.

[0213] If control is still performed according to the first correction control command when the state of the target space changes, it may no longer be possible to achieve the user's "expected feeling".

[0214] By storing the first information, the first corrective control command, and the target space's state information in a corresponding manner in the control command database, when the same or similar user description is subsequently obtained again, the target space's state information can be used to determine whether to perform control according to the first corrective control command. This ensures the reliability of the executed control commands and further improves the user experience.

[0215] For example, such as Figure 1 As shown, the voice control method may further include:

[0216] Step 107: Record the first information, the first corrective control instruction corresponding to the first information, and the first state information of the target space when the first corrective control instruction is generated in the control instruction database;

[0217] Step 108: Obtain second information related to the user's expected feelings generated based on the second voice data. If the second information is included in the first information or a variant of the first information, and the difference between the current second state information and the first state information of the target space is less than a preset threshold, control the home appliances according to the first correction control command corresponding to the first information; or, if the second information is included in the first information or a variant of the first information, and the difference between the current second state information and the first state information of the target space is greater than a preset threshold, generate a second control command based on the second information, obtain the user's second feedback information, correct the second control command to a second correction control command based on the second feedback information, and control the home appliances according to the second correction control command.

[0218] The specific content of the second state information can be found in the aforementioned first state information.

[0219] In some embodiments, the first status information recorded in the control command database may include all available status information. This allows for detailed recording of status information, enabling accurate determination of the appropriateness of the first corrective control command based on this information.

[0220] Alternatively, the first status information recorded in the control command database may include status information associated with the first corrective control command. This allows for targeted recording of status information, reduces the amount of data in the control command database, and simplifies the control process.

[0221] The status information associated with the first corrective control command can be determined in various ways. For example, it can be determined based on environmental parameters related to the first corrective control command. For example, the status information associated with the first corrective control command may include the capability information of home appliances in the target space used to adjust the environmental parameters, environmental parameters of the target space related to the environmental parameters, current seasonal information, time information, geographical location information, user information in the target space, or energy-saving information of home appliances in the target space used to adjust the environmental parameters.

[0222] For example, the first corrective control command is "cooling to 26°C, silent operation". The status information corresponding to this first corrective control command may include: air conditioner capacity information, current indoor temperature, current outdoor temperature, current season, current user indoors, air conditioner operating power, etc.

[0223] In some embodiments, different first state information recorded in the control instruction database may have different priorities. In step 108, the degree of difference between the current second state information and the first state information of the target space can be determined according to the priority of the first state information.

[0224] In some embodiments, the first modified control instruction can be stored in the control instruction database according to different users. This allows for personalized control needs to be met for different users, further improving the user experience.

[0225] For example, the control instruction database has user data tables created by user. These user data tables store the first information corresponding to the first control instruction and the information corresponding to the first corrective control instruction.

[0226] In addition, the user data table can also store the first information corresponding to the first control command, the first correction control command, and the first state information of the target space.

[0227] For example, the control instruction database includes a user data table and a control instruction table. The user data table stores the first information and the first corrected control instruction, while the control instruction table stores index information and the first control instruction.

[0228] After obtaining the second information generated based on the second voice data, the second information is matched with the first information in the user data table. If the second information is included in the first information or a variant of the first information, the home appliances are controlled according to the first correction control command corresponding to the first information.

[0229] If the second information is not included in the first information or a variation of the first information, the second information is matched with the control instruction table, and control instructions are generated based on the matching result.

[0230] In some embodiments, the method may further include: notifying the user of the speech recognition results, for example, notifying the user of first information identified from the speech data that relates to the user's desired feeling. For example, notifying the user "You just mentioned wanting a cool breeze in the shade of summer."

[0231] In some embodiments, notifications may be sent to users through one or more of the following methods: display, broadcast, push notification, etc.

[0232] For example, the speech recognition results can be displayed through a local device with display capabilities, which can be displayed as text. The local device with display capabilities includes, but is not limited to, one or more of a central controller, a smart TV, and a smart screen.

[0233] For example, the speech recognition results can be broadcast through a local device with voice broadcasting capabilities. Such local devices include, but are not limited to, one or more of a central controller, a smart TV, and a smart speaker.

[0234] For example, the speech recognition results can be notified to the user by pushing a message to the user's mobile device.

[0235] In some embodiments, the method may further include: notifying the user of the control result, for example, notifying the user of information about the completion of control based on "first information related to the user's expected feelings", such as "the air conditioner temperature has been adjusted to 26 degrees, the air volume has been adjusted to low, and the curtains in the curtains have been closed, based on your request for a cool breeze in the shade during the summer".

[0236] In some embodiments, notifications may be sent to users through one or more of the following methods: display, broadcast, push notification, etc.

[0237] For example, the control results can be displayed through a local device with display capabilities, and these results can be displayed via text. Local devices with display capabilities include, but are not limited to, one or more of a central controller, a smart TV, and a smart screen.

[0238] For example, control results can be broadcast through a local device with voice broadcasting capabilities. Such local devices include, but are not limited to, one or more of a central controller, a smart TV, and a smart speaker.

[0239] For example, notifications of control results can be sent to users' mobile devices by pushing messages to them.

[0240] In some embodiments, the method may further include: engaging in voice interaction with a user, for example, engaging in voice interaction with a user when it is determined that the generated control commands are inaccurate or unreasonable.

[0241] For example, voice interaction with users can be achieved through local devices with voice broadcasting and data acquisition capabilities. These local devices include, but are not limited to, one or more of a central controller, a smart TV, and a smart speaker.

[0242] Figure 2 This is another schematic diagram of the voice control method according to an embodiment of this application. For example... Figure 2 As shown, the method includes:

[0243] Step 201: Obtain information related to the user's expectations and feelings generated based on the voice data;

[0244] Step 202: Based on the pre-stored control instruction database, determine whether the generated information is recorded in the user data table; if the result is "yes", proceed to step 203; otherwise, proceed to step 204.

[0245] Step 203: Generate control commands based on the user data table, and control home appliances according to the control commands;

[0246] Step 204: Based on the pre-stored control instruction database, determine whether the generated information is recorded in the control instruction table; if the result is "yes", proceed to step 205; otherwise, proceed to step 209.

[0247] Step 205: Generate control commands based on the control command table;

[0248] Step 206: Interact with the user and obtain their feedback;

[0249] Step 207: Correct the control commands based on the feedback information, and control the home appliances according to the corrected control commands;

[0250] Step 208: Store the generated information and the corrected control instructions in the user's user data table;

[0251] Step 209: Interact with the user and obtain their feedback;

[0252] Step 210: Generate control commands based on the feedback information, and control home appliances according to the control commands;

[0253] Step 211: Store the generated information and control instructions in the user's user data table.

[0254] It is worth noting that the above figures are merely illustrative of embodiments of this application, and the application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed (e.g., the operations or steps corresponding to the dashed boxes in the figures). Those skilled in the art can make appropriate modifications based on the above description, and are not limited to the description in the above figures.

[0255] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0256] According to the above embodiments, on the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their expected feelings about their body or mind. This enables automatic control of the device, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting the personalized needs of users.

[0257] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0258] Example 2

[0259] Embodiment 2 of this application provides a voice control system, which corresponds to the method described in Embodiment 1. For details, please refer to the description in Embodiment 1.

[0260] Figure 3 This is a schematic diagram of a voice control system according to an embodiment of this application. Figure 3 As shown, the voice control system 300 includes: a control device 301 and at least one home appliance 302.

[0261] The control device 301 controls the home appliances 302 in the target space based on the first modified control command. The first modified control command is obtained by modifying the first control command according to the user's first feedback information. The first control command is generated based on the first information, which is generated based on the first voice data including information related to the user's intention.

[0262] In some embodiments, such as Figure 3 As shown, the voice control system 300 may also include a server 303.

[0263] In some embodiments, the first correction control command is generated by the control device 301 or by the server 303.

[0264] In some embodiments, the control commands are generated by the control device 301 or by the server 303.

[0265] In some embodiments, the first information is generated by the control device 301, or by the server 303.

[0266] For example, control device 301 generates first information, control device 301 generates first control command based on the first information, control device 301 corrects the first control command to a first corrected control command based on the first feedback information, and control device 301 controls home device 302 based on the first corrected control command.

[0267] For example, control device 301 generates first information, and control device 301 generates first control instruction based on the first information. Server 303 corrects the first control instruction into a first corrected control instruction based on the first feedback information. Control device 301 controls home device 302 based on the first corrected control instruction.

[0268] For example, control device 301 generates first information, server 303 generates first control instruction based on the first information, control device 301 corrects the first control instruction to a first corrected control instruction based on the first feedback information, and control device 301 controls home device 302 based on the first corrected control instruction.

[0269] For example, server 303 generates first information, control device 301 generates first control instruction based on the first information, control device 301 corrects the first control instruction into a first corrected control instruction based on the first feedback information, and control device 301 controls home device 302 based on the first corrected control instruction.

[0270] For example, control device 301 generates first information, server 303 generates first control instruction based on the first information, server 303 corrects the first control instruction into a first corrected control instruction based on the first feedback information, and control device 301 controls home device 302 based on the first corrected control instruction.

[0271] For example, server 303 generates first information, control device 301 generates first control instruction based on the first information, server 303 corrects the first control instruction into a first corrected control instruction based on the first feedback information, and control device 301 controls home device 302 based on the first corrected control instruction.

[0272] For example, server 303 generates first information, server 303 generates first control instruction based on first information, control device 301 corrects the first control instruction to a first corrected control instruction based on first feedback information, and control device 301 controls home device 302 based on the first corrected control instruction.

[0273] For example, server 303 generates first information, server 303 generates first control instruction based on the first information, server 303 modifies the first control instruction into a first modified control instruction based on the first feedback information, and control device 301 controls home device 302 based on the first modified control instruction.

[0274] When generating the first information based on the voice data, the voice data can be acquired by the control device 301 or by other devices in the system 300.

[0275] In some embodiments, the control device may include at least one of a central controller, a wired controller, and a remote controller, wherein the central controller and the wired controller are also referred to as fixed controllers, which are fixedly installed on the wall of an indoor space.

[0276] In some embodiments, the central controller may be located within the indoor space in various ways.

[0277] For example, centralized controllers are set up in various spaces and can control the home appliances in the space where the centralized controller is located. For example, a first centralized controller is set up in the living room, a second centralized controller is set up in the bedroom, and a third centralized controller is set up in the kitchen. The first centralized controller can control the home appliances in the living room, the second centralized controller can control the home appliances in the bedroom, and the third centralized controller can control the home appliances in the kitchen.

[0278] For example, centralized controllers are set up in each space and can control the home appliances in all spaces. For instance, a first centralized controller is set up in the living room, a second centralized controller is set up in the bedroom, and a third centralized controller is set up in the kitchen. The first, second, and third centralized controllers can all control the home appliances in the living room, bedroom, and kitchen.

[0279] For example, a centralized controller can be installed in a specific space and control all home appliances in that space. Additionally, wired controllers can be installed in other spaces outside the designated central controller to control the appliances within those spaces. For instance, a centralized controller in the living room can control all home appliances in the living room, bedrooms, and kitchen; wired controllers can be installed in the bedrooms and kitchen to control the appliances in those spaces respectively.

[0280] This application is not limited to this; the control device may also include a gateway device. In some embodiments, the gateway device can control at least one home appliance according to control commands. For example, the gateway device can control all the home appliances in the voice control system, thereby enabling centralized control of home appliances by connecting home appliances in different spaces through a single gateway device. This application is not limited to this; the gateway device can control some of the home appliances in the voice control system. For example, when there are many home appliances in the voice control system, multiple gateway devices can be set up to control all the home appliances in the voice control system through multiple gateway devices.

[0281] In some embodiments, home appliances can be jointly controlled by a central controller and a gateway device. This allows for the inclusion of multiple control devices (e.g., a gateway device and a central controller) within the voice control system, thereby improving the reliability and fault tolerance of voice control.

[0282] In some embodiments, home devices may be smart home devices. For details regarding home devices, please refer to the relevant description in Embodiment 1, which will not be repeated here.

[0283] The specific processing procedures for each of the above devices can be found in the relevant descriptions in Example 1, and will not be repeated here.

[0284] Figure 4 This is a schematic diagram of a voice control system used in the control method of this application embodiment. Figure 4 As shown, the voice control system 100 includes one or more home appliances 110, user terminal 120, central controller 131, gateway device 132, router 140, Internet 150, and first server 161, second server 162, etc.

[0285] In some embodiments, home appliance 110 may be a smart home appliance, for example, home appliances include at least one of air handling equipment and smart devices. The air handling equipment includes at least one of indoor unit, humidifier, dehumidifier, fresh air system, air purifier, fragrance unit, underfloor heating system, and valve assembly. The smart devices include at least one of smart speaker, smart display device, smart switch, smart curtain, smart lighting device, sensor, and smart pet device.

[0286] In some embodiments, the user terminal 120 may be, for example, a user's smartphone, smart wearable device, or other terminal device with voice functionality.

[0287] In some embodiments, such as Figure 4 As shown, the home appliances 110-1 to 110-5 are centrally controlled by the central controller 131 or the gateway device 132.

[0288] In some embodiments, the central controller 131 is a controller with centralized control functions. For example, the central controller 131 can control multiple or various types of home appliances. The central controller 131 can be a fixed controller, for example, the central controller can be fixed in a preset location (e.g., a wall). The central controller 131 can receive user voice data and control at least one home appliance through the control commands corresponding to the voice data.

[0289] For example, the central controller 131 may include a voice input unit for receiving user voice data. The central controller 131 may also include a voice output unit for broadcasting voice data. Furthermore, the central controller 131 may also have a display screen.

[0290] In some embodiments, gateway device 132 is a gateway with centralized control functionality. Gateway device 132 can receive control commands corresponding to voice data sent from the network, and control at least one home appliance through these control commands.

[0291] In addition, in this embodiment, the central controller 131 and the gateway device 132 can also control home appliances through control commands corresponding to non-voice data.

[0292] In some embodiments, home appliance 110 can connect to and communicate with central controller 131 or gateway device 132 in various ways.

[0293] To distinguish between different connection or communication methods, such as Figure 4 As shown, home appliances 110 include multiple sets of home appliances 110-1, 110-2, 110-3, 110-4, and 110-5.

[0294] In some embodiments, home appliance 110-1 is connected to central controller 131 and gateway device 132 via wired connection. For example, home appliance 110-1 includes at least one of an outdoor air conditioner unit, an indoor air conditioner unit, a fresh air system, and a floor heating system. In addition, the indoor air conditioner unit can be connected to an air quality sensor and a wired controller, and the floor heating system can be connected to the wired controller.

[0295] In some embodiments, home device 110-2 is connected to central controller 131 and gateway device 132 via Wi-Fi. For example, home device 110-2 includes at least one of a home wall-mounted air conditioner, a wall-mounted / cabinet-style display unit, a humidification unit, a dehumidification unit, a smart pet device (e.g., a watchdog unit), and a sleep sensor.

[0296] In some embodiments, home device 110-3 is connected to central controller 131 via Bluetooth or Zigbee. For example, home device 110-3 includes at least one of smart curtains (e.g., motorized curtains, roller blinds) and smart lighting devices (e.g., dimmer lights).

[0297] In some embodiments, home appliances 110-4 are connected to a central controller 131 via a wired connection. For example, home appliances 110-4 include at least one of smart curtains (e.g., motorized curtains, roller blinds), smart lighting devices (e.g., ceiling lights), and floor heating valves.

[0298] In some embodiments, home device 110-5 is connected to gateway device 132 via Wi-Fi. For example, home device 110-5 is directly connected to gateway device 132 via Wi-Fi, or home device 110-5 is connected to router 140 via Wi-Fi, and then connected to gateway device 132 via router 140. Home device 110-5 is, for example, an indoor air sensor.

[0299] In some embodiments, the home appliance may also include Figure 4 Devices not shown, such as smart speakers, smart TVs, etc., can be connected wirelessly or wired to at least one of the central controller 131 and the gateway device 132.

[0300] In some embodiments, the control modes for home appliances include voice control modes and non-voice control modes (e.g., user-operated control modes).

[0301] In some embodiments, the voice control modes include an online voice control mode via the Internet and a local voice control mode implemented locally.

[0302] For example, in an online voice control mode via the internet, user terminal 120 sends the collected voice data to first server 161 via router 140 and internet 150. First server 161 recognizes the voice device, obtains corresponding text data or control parameters, and sends the text data or control parameters to second server 162. Second server 162 generates corresponding control commands based on the text data or control parameters and sends them to gateway device 132 via internet 150 and router 140. Gateway device 132 then controls the relevant home appliances according to the control commands. Alternatively, second server 162 sends control commands via internet 150 and router 140 to central controller 131, which then controls the relevant home appliances according to the control commands. Furthermore, the functions of first server 161 and second server 162 can also be performed by a single server; this embodiment does not limit this.

[0303] Alternatively, in the online voice control mode via the internet, the central controller 131 can collect voice data, transmit it through the router 140, and then via the internet 150 to the first server 161. The subsequent processing is similar to the process described above. Thus, the central controller 131 enables control of home appliances in the online voice control mode.

[0304] For example, in local voice control mode, voice data can be acquired by local devices. For instance, the central controller 131 collects voice data, recognizes the voice device, obtains corresponding text data or control parameters, generates corresponding control commands based on the text data or control parameters, and then controls the relevant home appliances according to the control commands.

[0305] According to the above embodiments, for a first control command generated based on first information related to the user's expected feelings, first feedback information from the user regarding the first control command is obtained, the first control command is corrected based on the first feedback information to obtain a first corrected control command, and the home appliances are controlled based on the first corrected control command.

[0306] On the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their physical or mental expectations. This enables automatic control of devices, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting users' personalized needs.

[0307] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0308] Example 3

[0309] Embodiment 3 of this application provides a voice control device. This voice control device corresponds to the voice control method described in Embodiment 1, and the specific details can be found in Embodiment 1.

[0310] Figure 5 This is a schematic diagram of a voice control device according to an embodiment of this application. Figure 5 As shown, the device 500 includes an information acquisition unit 501, a generation unit 502, a feedback information acquisition unit 503, a correction unit 504, and a control unit 505.

[0311] Specifically, the information acquisition unit 501 acquires first information related to the user's expected feelings generated based on the first voice data; the generation unit 502 generates a first control command for controlling home appliances in the target space based on the first information; the feedback information acquisition unit 503 acquires the user's first feedback information; the correction unit 504 corrects the first control command into a first corrected control command based on the first feedback information; and the control unit 505 controls the home appliances based on the first corrected control command.

[0312] The specific functions of each of the above units can be found in the relevant steps in Embodiment 1, and will not be repeated here.

[0313] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The voice control device may also include other components or modules, or omit some components or modules (e.g., the components or modules corresponding to the dashed boxes in the figures). For details regarding these components or modules, please refer to related technologies.

[0314] Furthermore, for simplicity, the above figures only exemplify the connection relationships or signal flows between the various components or modules. However, those skilled in the art should understand that various related technologies, such as bus connections, can be employed. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0315] According to the above embodiments, for a first control command generated based on first information related to the user's expected feelings, first feedback information from the user regarding the first control command is obtained, the first control command is corrected based on the first feedback information to obtain a first corrected control command, and the home appliances are controlled based on the first corrected control command.

[0316] On the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their physical or mental expectations. This enables automatic control of devices, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting users' personalized needs.

[0317] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0318] Example 4

[0319] Embodiment 4 of this application provides an electronic device. The steps executed by the processor of this electronic device correspond to all or part of the steps of the voice control method described in Embodiment 1, and the specific details can be found in the description of Embodiment 1.

[0320] Figure 6 This is a schematic diagram illustrating the configuration of an electronic device according to an embodiment of this application. Figure 6 As shown, electronic device 600 may include processor 610 and memory 620; memory 620 is coupled to processor 610. It is worth noting that this figure is exemplary; other types of structures may be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0321] In one embodiment, the processor 610 may be configured to: acquire first information related to a user's expected feelings generated based on first voice data; generate a first control instruction for controlling home appliances in a target space based on the first information; acquire first feedback information from the user; modify the first control instruction into a first modified control instruction based on the first feedback information; and control the home appliances based on the first modified control instruction.

[0322] like Figure 6As shown, the electronic device 600 may also include: a communication module 630, an input unit 640, a display 650, a speaker 660, a microphone 670, and a power supply 680. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 6 All components shown; in addition, the electronic device 600 may also include Figure 6 For components not shown, please refer to relevant technologies.

[0323] like Figure 6 As shown, processor 610, sometimes also referred to as controller or operation control, may include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of various components of electronic device 600.

[0324] The memory 620 may be, for example, one or more of a cache, flash memory, hard drive, removable medium, volatile memory, non-volatile memory, or other suitable means. It can store various types of data, and also programs for executing related information. The processor 610 can execute the program stored in the memory 620 to perform information storage or processing, etc. The functions of other components are similar to those in existing systems and will not be described further here. The components of the electronic device 600 can be implemented using dedicated hardware, firmware, software, or a combination thereof without departing from the scope of the invention.

[0325] According to the above embodiments, for a first control command generated based on first information related to the user's expected feelings, first feedback information from the user regarding the first control command is obtained, the first control command is corrected based on the first feedback information to obtain a first corrected control command, and the home appliances are controlled based on the first corrected control command.

[0326] On the one hand, voice control based on user expectations provides a novel voice control mode. Users are not limited to using specific control commands or describing their current physical state, but can express their personalized needs by expressing their physical or mental expectations. This enables automatic control of devices, thereby reducing the threshold and difficulty for users to control home appliances, realizing the intelligence and flexibility of voice control, reflecting the technological feel of voice control, and meeting users' personalized needs.

[0327] On the other hand, by obtaining user feedback, we can further understand the user's actual intentions. As a result, we can revise the control instructions to better match the abstract "expected feelings". Furthermore, we can gradually learn to understand the user's descriptive habits, making the control instructions more in line with the user's actual intentions, improving the accuracy of the conversion of control instructions, and enhancing the user experience.

[0328] This application also provides a computer-readable program, wherein when the program is executed, the program causes the computer to perform the voice control method described in this application.

[0329] This application also provides a computer-readable storage medium storing a computer program that causes a computer to execute the voice control method described in this application.

[0330] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the voice control method described in this application.

[0331] The apparatus and methods described above in the embodiments of this application can be implemented in hardware or in combination with software. This application relates to a computer-readable program that, when executed by a logic component, enables the logic component to implement the apparatus or constituent parts described above, or to implement the various methods or steps described above.

[0332] This application also relates to storage media for storing the above programs, such as hard disks, magnetic disks, optical disks, DVDs, flash memory, etc.

[0333] It should be noted that the limitations on each step involved in this application are not considered as limiting the order of steps, provided that they do not affect the implementation of the specific solution. The steps listed first can be performed first, later, or even simultaneously. As long as the solution can be implemented, they should be considered to fall within the scope of protection of this application.

[0334] The present application has been described above with reference to specific embodiments. However, those skilled in the art should understand that these descriptions are exemplary and not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on its spirit and principles, and these modifications and variations are also within the scope of the present application.

Claims

1. A voice control method, characterized by, The method includes: Obtain first information related to the user's expected feelings, generated based on the first voice data; Based on the first information, a first control command is generated for controlling home appliances within the target space; Obtain the user's first feedback information, and modify the first control command into a first modified control command based on the first feedback information; and The home appliances are controlled based on the first corrected control command.

2. The method according to claim 1, characterized in that, The first control instruction is generated based on a control instruction database, wherein the control instruction database includes index information related to the user's expected feelings and control instructions corresponding to the index information.

3. The method according to claim 2, characterized in that, If the first index information in the index information includes the first information, the control instruction corresponding to the first index information shall be used as the first control instruction. or When the modified information of the second index information in the index information includes the first information, the control instruction corresponding to the second index information is used as the first control instruction; or Based on the similarity between each index information and the first information, a third index information is selected, and the control instruction corresponding to the third index information is used as the first control instruction.

4. The method according to claim 3, characterized in that, The deformation information is preset by the user; or... The deformation information is set through interaction with the user; or... The deformation information is generated using a natural language processing-based model.

5. The method of claim 2, wherein, The method further includes: The first information and the first correction control instruction corresponding to the first information are recorded in the control instruction database; Acquire second information related to the user's expected feelings, generated based on the second voice data; and When the second information is included in the first information or a variation of the first information, the home appliance is controlled according to the first corrected control instruction corresponding to the first information.

6. The method of claim 2, wherein, The method further includes: The control instruction database records the first information, the first corrective control instruction corresponding to the first information, and the first state information of the target space when the first corrective control instruction is generated; Acquire second information related to the user's expected feelings, generated based on the second voice data; and If the second information is included in the first information or a variation of the first information, and the difference between the current second state information and the first state information of the target space is less than a preset threshold, the home appliance is controlled according to the first correction control command corresponding to the first information; or When the second information is included in the first information or a variation of the first information, and the difference between the current second state information of the target space and the first state information is greater than a preset threshold, a second control instruction is generated based on the second information, the user's second feedback information is obtained, the second control instruction is corrected into a second corrected control instruction based on the second feedback information, and the home device is controlled based on the second corrected control instruction.

7. The method according to claim 6, characterized in that, The first status information or the second status information includes at least one of the following: device information, environmental parameters, seasonal information, time information, geographical location information, user information, and energy-saving information of the target space.

8. The method according to claim 7, characterized in that, The device information includes: capability information of the first home appliances included in the target space; or The environmental parameters include at least one of the following: air quality parameters, light parameters, sound parameters, and odor parameters within the target space; or The user information includes at least one of the following: user attribute information, status information, and usage habit information within the target space; or The energy-saving information includes at least one of the following: the operating power, operating time, operating mode, number of devices, and device type of the home appliances associated with the control command.

9. The method of claim 1, wherein, Based on the first feedback information, the first control command is modified into a first modified control command, including: Based on the first feedback information, at least one of the following information is generated: first correction information for correcting the environmental parameter that needs to be adjusted, or second correction information for correcting the target value of the environmental parameter; and Based on at least one of the first correction information and the second correction information, the first control instruction is corrected to a first corrected control instruction.

10. The method according to claim 9, characterized in that, If the first feedback information includes numerical information of the target value, the second correction information is determined based on the numerical information.

11. The method according to claim 9, characterized in that, If the first feedback information includes correction trend information but does not include numerical information of the target value, the second correction information is determined based on the correction trend information, or based on the correction trend information and the first state information of the target space.

12. The method according to claim 11, characterized in that, The second correction information is related to the number of first feedback information entries that show the same correction trend within a preset time period; or If the first feedback information includes correction degree information, the second correction information is also determined based on the correction degree information.

13. The method according to claim 1, characterized in that, The first feedback information includes: feedback information obtained before control is performed according to the first control instruction, and feedback information obtained during control is performed according to the first control instruction.

14. The method of claim 1, wherein, The method further includes: If it is impossible to generate a first control command for controlling home appliances in the target space based on the first information, the first feedback information is directly obtained, and a first correction control command is generated based on the first feedback information.

15. A voice control system, characterized by The system includes a control device and at least one home appliance. The control device controls the home appliances in the target space based on a first corrected control command, wherein the first corrected control command is obtained by correcting a first control command based on the user's first feedback information, and the first control command is generated based on first information, which is generated based on first voice data including information related to the user's intent.

16. The system according to claim 15, characterized in that, The first correction control command is generated by the control device or by the server in the system.

17. A voice control device, comprising: The device includes: An information acquisition unit acquires first information related to the user's expected feelings, generated based on the first voice data. The generation unit generates a first control command for controlling home appliances in the target space based on the first information. The feedback information acquisition unit acquires the user's initial feedback information. The correction unit corrects the first control command to a first corrected control command based on the first feedback information; and The control unit controls the home appliances based on the first corrective control command.

18. An electronic device, characterized in that, The electronic device includes: Memory, which stores computer programs; and A processor that, when executing the computer program, implements the method described in any one of claims 1-14.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-14.

20. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-14.

Images